Add all 5 deployments solution for testing

.github/workflows/main.yml

@@ -1,35 +0,0 @@
-name: Discord GitHub Notifications
-
-on:
-  issues:
-    types: [opened]
-  issue_comment:
-    types: [created]
-  pull_request:
-    types: [opened]
-  discussion:
-    types: [created]
-
-jobs:
-  notify-discord:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Set webhook based on event type
-        id: set-webhook
-        run: |
-          if [ "${{ github.event_name }}" == "discussion" ]; then
-            echo "webhook=${{ secrets.DISCORD_DISCUSSIONS_WEBHOOK }}" >> $GITHUB_OUTPUT
-          else
-            echo "webhook=${{ secrets.DISCORD_WEBHOOK }}" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Discord Notification
-        uses: Ilshidur/action-discord@master
-        env:
-          DISCORD_WEBHOOK: ${{ steps.set-webhook.outputs.webhook }}
-        with:
-          args: |
-            ${{ github.event_name == 'issues' && format('📣 New issue created: **{0}** by {1} - {2}', github.event.issue.title, github.event.issue.user.login, github.event.issue.html_url) || 
-            github.event_name == 'issue_comment' && format('💬 New comment on issue **{0}** by {1} - {2}', github.event.issue.title, github.event.comment.user.login, github.event.comment.html_url) ||
-            github.event_name == 'pull_request' && format('🔄 New PR opened: **{0}** by {1} - {2}', github.event.pull_request.title, github.event.pull_request.user.login, github.event.pull_request.html_url) || 
-            format('💬 New discussion started: **{0}** by {1} - {2}', github.event.discussion.title, github.event.discussion.user.login, github.event.discussion.html_url) }}

.gitignore

@@ -255,6 +255,3 @@ continue_config.json
 
 .llm.env
 .private/
-
-CLAUDE_MONITOR.md
-CLAUDE.md

CHANGELOG.md

@@ -5,39 +5,6 @@ All notable changes to Crawl4AI will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## Version 0.5.0.post5 (2025-03-14)
-
-### Added
-
-- *(crawler)* Add experimental parameters dictionary to CrawlerRunConfig to support beta features
-- *(tables)* Add comprehensive table detection and extraction functionality with scoring system
-- *(monitor)* Add real-time crawler monitoring system with memory management
-- *(content)* Add target_elements parameter for selective content extraction
-- *(browser)* Add standalone CDP browser launch capability
-- *(schema)* Add preprocess_html_for_schema utility for better HTML cleaning
-- *(api)* Add special handling for single URL requests in Docker API
-
-### Changed
-
-- *(filters)* Add reverse option to URLPatternFilter for inverting filter logic
-- *(browser)* Make CSP nonce headers optional via experimental config
-- *(browser)* Remove default cookie injection from page initialization
-- *(crawler)* Optimize response handling for single-URL processing
-- *(api)* Refactor crawl request handling to streamline processing
-- *(config)* Update default provider to gpt-4o
-- *(cache)* Change default cache_mode from aggressive to bypass in examples
-
-### Fixed
-
-- *(browser)* Clean up browser context creation code
-- *(api)* Improve code formatting in API handler
-
-### Breaking Changes
-
-- WebScrapingStrategy no longer returns 'scraped_html' in its output dictionary
-- Table extraction logic has been modified to better handle thead/tbody structures
-- Default cookie injection has been removed from page initialization
-
 ## Version 0.5.0 (2025-03-02)
 
 ### Added

Dockerfile

@@ -24,7 +24,7 @@ ARG TARGETARCH
 
 LABEL maintainer="unclecode"
 LABEL description="🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & scraper"
-LABEL version="1.0"
+LABEL version="1.0"    
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     build-essential \
@@ -38,7 +38,6 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     libjpeg-dev \
     redis-server \
     supervisor \
-    && apt-get clean \ 
     && rm -rf /var/lib/apt/lists/*
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
@@ -63,13 +62,11 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     libcairo2 \
     libasound2 \
     libatspi2.0-0 \
-    && apt-get clean \ 
     && rm -rf /var/lib/apt/lists/*
 
 RUN if [ "$ENABLE_GPU" = "true" ] && [ "$TARGETARCH" = "amd64" ] ; then \
     apt-get update && apt-get install -y --no-install-recommends \
     nvidia-cuda-toolkit \
-    && apt-get clean \ 
     && rm -rf /var/lib/apt/lists/* ; \
 else \
     echo "Skipping NVIDIA CUDA Toolkit installation (unsupported platform or GPU disabled)"; \
@@ -79,24 +76,16 @@ RUN if [ "$TARGETARCH" = "arm64" ]; then \
     echo "🦾 Installing ARM-specific optimizations"; \
     apt-get update && apt-get install -y --no-install-recommends \
     libopenblas-dev \
-    && apt-get clean \ 
     && rm -rf /var/lib/apt/lists/*; \
 elif [ "$TARGETARCH" = "amd64" ]; then \
     echo "🖥️ Installing AMD64-specific optimizations"; \
     apt-get update && apt-get install -y --no-install-recommends \
     libomp-dev \
-    && apt-get clean \ 
     && rm -rf /var/lib/apt/lists/*; \
 else \
     echo "Skipping platform-specific optimizations (unsupported platform)"; \
 fi
 
-# Create a non-root user and group
-RUN groupadd -r appuser && useradd --no-log-init -r -g appuser appuser
-
-# Create and set permissions for appuser home directory
-RUN mkdir -p /home/appuser && chown -R appuser:appuser /home/appuser
-
 WORKDIR ${APP_HOME}
 
 RUN echo '#!/bin/bash\n\
@@ -114,7 +103,6 @@ fi' > /tmp/install.sh && chmod +x /tmp/install.sh
 
 COPY . /tmp/project/
 
-# Copy supervisor config first (might need root later, but okay for now)
 COPY deploy/docker/supervisord.conf .
 
 COPY deploy/docker/requirements.txt .
@@ -143,31 +131,16 @@ RUN if [ "$INSTALL_TYPE" = "all" ] ; then \
     else \
         pip install "/tmp/project" ; \
     fi
-
+    
 RUN pip install --no-cache-dir --upgrade pip && \
     /tmp/install.sh && \
     python -c "import crawl4ai; print('✅ crawl4ai is ready to rock!')" && \
     python -c "from playwright.sync_api import sync_playwright; print('✅ Playwright is feeling dramatic!')"
+    
+RUN playwright install --with-deps chromium
 
-RUN crawl4ai-setup
-
-RUN playwright install --with-deps
-
-RUN mkdir -p /home/appuser/.cache/ms-playwright \
-    && cp -r /root/.cache/ms-playwright/chromium-* /home/appuser/.cache/ms-playwright/ \
-    && chown -R appuser:appuser /home/appuser/.cache/ms-playwright
-
-RUN crawl4ai-doctor
-
-# Copy application code
 COPY deploy/docker/* ${APP_HOME}/
 
-# Change ownership of the application directory to the non-root user
-RUN chown -R appuser:appuser ${APP_HOME}
-
-# give permissions to redis persistence dirs if used
-RUN mkdir -p /var/lib/redis /var/log/redis && chown -R appuser:appuser /var/lib/redis /var/log/redis
-
 HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
     CMD bash -c '\
     MEM=$(free -m | awk "/^Mem:/{print \$2}"); \
@@ -176,14 +149,8 @@ HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
         exit 1; \
     fi && \
     redis-cli ping > /dev/null && \
-    curl -f http://localhost:11235/health || exit 1'
+    curl -f http://localhost:8000/health || exit 1'
 
 EXPOSE 6379
-# Switch to the non-root user before starting the application
+CMD ["supervisord", "-c", "supervisord.conf"]
-USER appuser
+    
-
-# Set environment variables to ptoduction
-ENV PYTHON_ENV=production 
-
-# Start the application using supervisord
-CMD ["supervisord", "-c", "supervisord.conf"]

JOURNAL.md

@@ -1,108 +0,0 @@
-# Development Journal
-
-This journal tracks significant feature additions, bug fixes, and architectural decisions in the crawl4ai project. It serves as both documentation and a historical record of the project's evolution.
-
-## [2025-04-09] Added MHTML Capture Feature
-
-**Feature:** MHTML snapshot capture of crawled pages
-
-**Changes Made:**
-1. Added `capture_mhtml: bool = False` parameter to `CrawlerRunConfig` class
-2. Added `mhtml: Optional[str] = None` field to `CrawlResult` model
-3. Added `mhtml_data: Optional[str] = None` field to `AsyncCrawlResponse` class
-4. Implemented `capture_mhtml()` method in `AsyncPlaywrightCrawlerStrategy` class to capture MHTML via CDP
-5. Modified the crawler to capture MHTML when enabled and pass it to the result
-
-**Implementation Details:**
-- MHTML capture uses Chrome DevTools Protocol (CDP) via Playwright's CDP session API
-- The implementation waits for page to fully load before capturing MHTML content
-- Enhanced waiting for JavaScript content with requestAnimationFrame for better JS content capture
-- We ensure all browser resources are properly cleaned up after capture
-
-**Files Modified:**
-- `crawl4ai/models.py`: Added the mhtml field to CrawlResult
-- `crawl4ai/async_configs.py`: Added capture_mhtml parameter to CrawlerRunConfig
-- `crawl4ai/async_crawler_strategy.py`: Implemented MHTML capture logic
-- `crawl4ai/async_webcrawler.py`: Added mapping from AsyncCrawlResponse.mhtml_data to CrawlResult.mhtml
-
-**Testing:**
-- Created comprehensive tests in `tests/20241401/test_mhtml.py` covering:
-  - Capturing MHTML when enabled
-  - Ensuring mhtml is None when disabled explicitly
-  - Ensuring mhtml is None by default
-  - Capturing MHTML on JavaScript-enabled pages
-
-**Challenges:**
-- Had to improve page loading detection to ensure JavaScript content was fully rendered
-- Tests needed to be run independently due to Playwright browser instance management
-- Modified test expected content to match actual MHTML output
-
-**Why This Feature:**
-The MHTML capture feature allows users to capture complete web pages including all resources (CSS, images, etc.) in a single file. This is valuable for:
-1. Offline viewing of captured pages
-2. Creating permanent snapshots of web content for archival
-3. Ensuring consistent content for later analysis, even if the original site changes
-
-**Future Enhancements to Consider:**
-- Add option to save MHTML to file
-- Support for filtering what resources get included in MHTML
-- Add support for specifying MHTML capture options
-
-## [2025-04-10] Added Network Request and Console Message Capturing
-
-**Feature:** Comprehensive capturing of network requests/responses and browser console messages during crawling
-
-**Changes Made:**
-1. Added `capture_network_requests: bool = False` and `capture_console_messages: bool = False` parameters to `CrawlerRunConfig` class
-2. Added `network_requests: Optional[List[Dict[str, Any]]] = None` and `console_messages: Optional[List[Dict[str, Any]]] = None` fields to both `AsyncCrawlResponse` and `CrawlResult` models
-3. Implemented event listeners in `AsyncPlaywrightCrawlerStrategy._crawl_web()` to capture browser network events and console messages
-4. Added proper event listener cleanup in the finally block to prevent resource leaks
-5. Modified the crawler flow to pass captured data from AsyncCrawlResponse to CrawlResult
-
-**Implementation Details:**
-- Network capture uses Playwright event listeners (`request`, `response`, and `requestfailed`) to record all network activity
-- Console capture uses Playwright event listeners (`console` and `pageerror`) to record console messages and errors
-- Each network event includes metadata like URL, headers, status, and timing information
-- Each console message includes type, text content, and source location when available
-- All captured events include timestamps for chronological analysis
-- Error handling ensures even failed capture attempts won't crash the main crawling process
-
-**Files Modified:**
-- `crawl4ai/models.py`: Added new fields to AsyncCrawlResponse and CrawlResult
-- `crawl4ai/async_configs.py`: Added new configuration parameters to CrawlerRunConfig
-- `crawl4ai/async_crawler_strategy.py`: Implemented capture logic using event listeners
-- `crawl4ai/async_webcrawler.py`: Added data transfer from AsyncCrawlResponse to CrawlResult
-
-**Documentation:**
-- Created detailed documentation in `docs/md_v2/advanced/network-console-capture.md`
-- Added feature to site navigation in `mkdocs.yml`
-- Updated CrawlResult documentation in `docs/md_v2/api/crawl-result.md`
-- Created comprehensive example in `docs/examples/network_console_capture_example.py`
-
-**Testing:**
-- Created `tests/general/test_network_console_capture.py` with tests for:
-  - Verifying capture is disabled by default
-  - Testing network request capturing
-  - Testing console message capturing
-  - Ensuring both capture types can be enabled simultaneously
-  - Checking correct content is captured in expected formats
-
-**Challenges:**
-- Initial implementation had synchronous/asynchronous mismatches in event handlers
-- Needed to fix type of property access vs. method calls in handlers
-- Required careful cleanup of event listeners to prevent memory leaks
-
-**Why This Feature:**
-The network and console capture feature provides deep visibility into web page activity, enabling:
-1. Debugging complex web applications by seeing all network requests and errors
-2. Security analysis to detect unexpected third-party requests and data flows
-3. Performance profiling to identify slow-loading resources
-4. API discovery in single-page applications
-5. Comprehensive analysis of web application behavior
-
-**Future Enhancements to Consider:**
-- Option to filter captured events by type, domain, or content
-- Support for capturing response bodies (with size limits)
-- Aggregate statistics calculation for performance metrics
-- Integration with visualization tools for network waterfall analysis
-- Exporting captures in HAR format for use with external tools

crawl4ai/__init__.py

@@ -33,12 +33,13 @@ from .content_filter_strategy import (
     LLMContentFilter,
     RelevantContentFilter,
 )
-from .models import CrawlResult, MarkdownGenerationResult, DisplayMode
+from .models import CrawlResult, MarkdownGenerationResult
-from .components.crawler_monitor import CrawlerMonitor
 from .async_dispatcher import (
     MemoryAdaptiveDispatcher,
     SemaphoreDispatcher,
     RateLimiter,
+    CrawlerMonitor,
+    DisplayMode,
     BaseDispatcher,
 )
 from .docker_client import Crawl4aiDockerClient

crawl4ai/__version__.py

@@ -1,2 +1,2 @@
 # crawl4ai/_version.py
-__version__ = "0.5.0.post8"
+__version__ = "0.5.0.post4"

crawl4ai/async_configs.py

@@ -1,7 +1,6 @@
 import os
 from .config import (
     DEFAULT_PROVIDER,
-    DEFAULT_PROVIDER_API_KEY,
     MIN_WORD_THRESHOLD,
     IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD,
     PROVIDER_MODELS,
@@ -15,7 +14,7 @@ from .user_agent_generator import UAGen, ValidUAGenerator  # , OnlineUAGenerator
 from .extraction_strategy import ExtractionStrategy, LLMExtractionStrategy
 from .chunking_strategy import ChunkingStrategy, RegexChunking
 
-from .markdown_generation_strategy import MarkdownGenerationStrategy, DefaultMarkdownGenerator
+from .markdown_generation_strategy import MarkdownGenerationStrategy
 from .content_scraping_strategy import ContentScrapingStrategy, WebScrapingStrategy
 from .deep_crawling import DeepCrawlStrategy
 
@@ -28,10 +27,6 @@ from typing import Any, Dict, Optional
 from enum import Enum
 
 from .proxy_strategy import ProxyConfig
-try:
-    from .browser.models import DockerConfig
-except ImportError:
-    DockerConfig = None
 
 
 def to_serializable_dict(obj: Any, ignore_default_value : bool = False) -> Dict:
@@ -122,25 +117,23 @@ def from_serializable_dict(data: Any) -> Any:
     # Handle typed data
     if isinstance(data, dict) and "type" in data:
         # Handle plain dictionaries
-        if data["type"] == "dict" and "value" in data:
+        if data["type"] == "dict":
             return {k: from_serializable_dict(v) for k, v in data["value"].items()}
 
         # Import from crawl4ai for class instances
         import crawl4ai
 
-        if hasattr(crawl4ai, data["type"]):
+        cls = getattr(crawl4ai, data["type"])
-            cls = getattr(crawl4ai, data["type"])
 
-            # Handle Enum
+        # Handle Enum
-            if issubclass(cls, Enum):
+        if issubclass(cls, Enum):
-                return cls(data["params"])
+            return cls(data["params"])
 
-            if "params" in data:
+        # Handle class instances
-                # Handle class instances
+        constructor_args = {
-                constructor_args = {
+            k: from_serializable_dict(v) for k, v in data["params"].items()
-                    k: from_serializable_dict(v) for k, v in data["params"].items()
+        }
-                }
+        return cls(**constructor_args)
-                return cls(**constructor_args)
 
     # Handle lists
     if isinstance(data, list):
@@ -175,12 +168,6 @@ class BrowserConfig:
                             Default: "chromium".
         headless (bool): Whether to run the browser in headless mode (no visible GUI).
                          Default: True.
-        browser_mode (str): Determines how the browser should be initialized:
-                           "builtin" - use the builtin CDP browser running in background
-                           "dedicated" - create a new dedicated browser instance each time
-                           "cdp" - use explicit CDP settings provided in cdp_url
-                           "docker" - run browser in Docker container with isolation
-                           Default: "dedicated"
         use_managed_browser (bool): Launch the browser using a managed approach (e.g., via CDP), allowing
                                     advanced manipulation. Default: False.
         cdp_url (str): URL for the Chrome DevTools Protocol (CDP) endpoint. Default: "ws://localhost:9222/devtools/browser/".
@@ -197,8 +184,6 @@ class BrowserConfig:
                              Default: None.
         proxy_config (ProxyConfig or dict or None): Detailed proxy configuration, e.g. {"server": "...", "username": "..."}.
                                      If None, no additional proxy config. Default: None.
-        docker_config (DockerConfig or dict or None): Configuration for Docker-based browser automation.
-                                     Contains settings for Docker container operation. Default: None.
         viewport_width (int): Default viewport width for pages. Default: 1080.
         viewport_height (int): Default viewport height for pages. Default: 600.
         viewport (dict): Default viewport dimensions for pages. If set, overrides viewport_width and viewport_height.
@@ -209,7 +194,7 @@ class BrowserConfig:
                                  Default: False.
         downloads_path (str or None): Directory to store downloaded files. If None and accept_downloads is True,
                                       a default path will be created. Default: None.
-        storage_state (str or dict or None): An in-memory storage state (cookies, localStorage).
+        storage_state (str or dict or None): Path or object describing storage state (cookies, localStorage).
                                              Default: None.
         ignore_https_errors (bool): Ignore HTTPS certificate errors. Default: True.
         java_script_enabled (bool): Enable JavaScript execution in pages. Default: True.
@@ -235,7 +220,6 @@ class BrowserConfig:
         self,
         browser_type: str = "chromium",
         headless: bool = True,
-        browser_mode: str = "dedicated",
         use_managed_browser: bool = False,
         cdp_url: str = None,
         use_persistent_context: bool = False,
@@ -244,7 +228,6 @@ class BrowserConfig:
         channel: str = "chromium",
         proxy: str = None,
         proxy_config: Union[ProxyConfig, dict, None] = None,
-        docker_config: Union[DockerConfig, dict, None] = None,
         viewport_width: int = 1080,
         viewport_height: int = 600,
         viewport: dict = None,
@@ -272,8 +255,7 @@ class BrowserConfig:
         host: str = "localhost",
     ):
         self.browser_type = browser_type
-        self.headless = headless or True
+        self.headless = headless
-        self.browser_mode = browser_mode
         self.use_managed_browser = use_managed_browser
         self.cdp_url = cdp_url
         self.use_persistent_context = use_persistent_context
@@ -285,16 +267,6 @@ class BrowserConfig:
             self.chrome_channel = ""
         self.proxy = proxy
         self.proxy_config = proxy_config
-        
-        # Handle docker configuration
-        if isinstance(docker_config, dict) and DockerConfig is not None:
-            self.docker_config = DockerConfig.from_kwargs(docker_config)
-        else:
-            self.docker_config = docker_config
-
-        if self.docker_config:
-            self.user_data_dir = self.docker_config.user_data_dir
-
         self.viewport_width = viewport_width
         self.viewport_height = viewport_height
         self.viewport = viewport
@@ -317,7 +289,6 @@ class BrowserConfig:
         self.sleep_on_close = sleep_on_close
         self.verbose = verbose
         self.debugging_port = debugging_port
-        self.host = host
 
         fa_user_agenr_generator = ValidUAGenerator()
         if self.user_agent_mode == "random":
@@ -330,22 +301,6 @@ class BrowserConfig:
         self.browser_hint = UAGen.generate_client_hints(self.user_agent)
         self.headers.setdefault("sec-ch-ua", self.browser_hint)
 
-        # Set appropriate browser management flags based on browser_mode
-        if self.browser_mode == "builtin":
-            # Builtin mode uses managed browser connecting to builtin CDP endpoint
-            self.use_managed_browser = True
-            # cdp_url will be set later by browser_manager
-        elif self.browser_mode == "docker":
-            # Docker mode uses managed browser with CDP to connect to browser in container
-            self.use_managed_browser = True
-            # cdp_url will be set later by docker browser strategy
-        elif self.browser_mode == "custom" and self.cdp_url:
-            # Custom mode with explicit CDP URL
-            self.use_managed_browser = True
-        elif self.browser_mode == "dedicated":
-            # Dedicated mode uses a new browser instance each time
-            pass
-
         # If persistent context is requested, ensure managed browser is enabled
         if self.use_persistent_context:
             self.use_managed_browser = True
@@ -355,7 +310,6 @@ class BrowserConfig:
         return BrowserConfig(
             browser_type=kwargs.get("browser_type", "chromium"),
             headless=kwargs.get("headless", True),
-            browser_mode=kwargs.get("browser_mode", "dedicated"),
             use_managed_browser=kwargs.get("use_managed_browser", False),
             cdp_url=kwargs.get("cdp_url"),
             use_persistent_context=kwargs.get("use_persistent_context", False),
@@ -364,7 +318,6 @@ class BrowserConfig:
             channel=kwargs.get("channel", "chromium"),
             proxy=kwargs.get("proxy"),
             proxy_config=kwargs.get("proxy_config", None),
-            docker_config=kwargs.get("docker_config", None),
             viewport_width=kwargs.get("viewport_width", 1080),
             viewport_height=kwargs.get("viewport_height", 600),
             accept_downloads=kwargs.get("accept_downloads", False),
@@ -384,15 +337,12 @@ class BrowserConfig:
             text_mode=kwargs.get("text_mode", False),
             light_mode=kwargs.get("light_mode", False),
             extra_args=kwargs.get("extra_args", []),
-            debugging_port=kwargs.get("debugging_port", 9222),
-            host=kwargs.get("host", "localhost"),
         )
 
     def to_dict(self):
-        result = {
+        return {
             "browser_type": self.browser_type,
             "headless": self.headless,
-            "browser_mode": self.browser_mode,
             "use_managed_browser": self.use_managed_browser,
             "cdp_url": self.cdp_url,
             "use_persistent_context": self.use_persistent_context,
@@ -419,17 +369,7 @@ class BrowserConfig:
             "sleep_on_close": self.sleep_on_close,
             "verbose": self.verbose,
             "debugging_port": self.debugging_port,
-            "host": self.host,
         }
-        
-        # Include docker_config if it exists
-        if hasattr(self, "docker_config") and self.docker_config is not None:
-            if hasattr(self.docker_config, "to_dict"):
-                result["docker_config"] = self.docker_config.to_dict()
-            else:
-                result["docker_config"] = self.docker_config
-                
-        return result
 
     def clone(self, **kwargs):
         """Create a copy of this configuration with updated values.
@@ -709,12 +649,6 @@ class CrawlerRunConfig():
         user_agent_generator_config (dict or None): Configuration for user agent generation if user_agent_mode is set.
                                                     Default: None.
 
-        # Experimental Parameters
-        experimental (dict): Dictionary containing experimental parameters that are in beta phase.
-                            This allows passing temporary features that are not yet fully integrated 
-                            into the main parameter set.
-                            Default: None.
-
         url: str = None  # This is not a compulsory parameter
     """
 
@@ -724,7 +658,7 @@ class CrawlerRunConfig():
         word_count_threshold: int = MIN_WORD_THRESHOLD,
         extraction_strategy: ExtractionStrategy = None,
         chunking_strategy: ChunkingStrategy = RegexChunking(),
-        markdown_generator: MarkdownGenerationStrategy = DefaultMarkdownGenerator(),
+        markdown_generator: MarkdownGenerationStrategy = None,
         only_text: bool = False,
         css_selector: str = None,
         target_elements: List[str] = None,
@@ -774,12 +708,10 @@ class CrawlerRunConfig():
         screenshot_wait_for: float = None,
         screenshot_height_threshold: int = SCREENSHOT_HEIGHT_TRESHOLD,
         pdf: bool = False,
-        capture_mhtml: bool = False,
         image_description_min_word_threshold: int = IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD,
         image_score_threshold: int = IMAGE_SCORE_THRESHOLD,
         table_score_threshold: int = 7,
         exclude_external_images: bool = False,
-        exclude_all_images: bool = False,
         # Link and Domain Handling Parameters
         exclude_social_media_domains: list = None,
         exclude_external_links: bool = False,
@@ -789,9 +721,6 @@ class CrawlerRunConfig():
         # Debugging and Logging Parameters
         verbose: bool = True,
         log_console: bool = False,
-        # Network and Console Capturing Parameters
-        capture_network_requests: bool = False,
-        capture_console_messages: bool = False,
         # Connection Parameters
         method: str = "GET",
         stream: bool = False,
@@ -802,8 +731,6 @@ class CrawlerRunConfig():
         user_agent_generator_config: dict = {},
         # Deep Crawl Parameters
         deep_crawl_strategy: Optional[DeepCrawlStrategy] = None,
-        # Experimental Parameters
-        experimental: Dict[str, Any] = None,
     ):
         # TODO: Planning to set properties dynamically based on the __init__ signature
         self.url = url
@@ -867,11 +794,9 @@ class CrawlerRunConfig():
         self.screenshot_wait_for = screenshot_wait_for
         self.screenshot_height_threshold = screenshot_height_threshold
         self.pdf = pdf
-        self.capture_mhtml = capture_mhtml
         self.image_description_min_word_threshold = image_description_min_word_threshold
         self.image_score_threshold = image_score_threshold
         self.exclude_external_images = exclude_external_images
-        self.exclude_all_images = exclude_all_images
         self.table_score_threshold = table_score_threshold
 
         # Link and Domain Handling Parameters
@@ -886,10 +811,6 @@ class CrawlerRunConfig():
         # Debugging and Logging Parameters
         self.verbose = verbose
         self.log_console = log_console
-        
-        # Network and Console Capturing Parameters
-        self.capture_network_requests = capture_network_requests
-        self.capture_console_messages = capture_console_messages
 
         # Connection Parameters
         self.stream = stream
@@ -923,9 +844,6 @@ class CrawlerRunConfig():
 
         # Deep Crawl Parameters
         self.deep_crawl_strategy = deep_crawl_strategy
-        
-        # Experimental Parameters
-        self.experimental = experimental or {}
 
 
     def __getattr__(self, name):
@@ -1004,7 +922,6 @@ class CrawlerRunConfig():
                 "screenshot_height_threshold", SCREENSHOT_HEIGHT_TRESHOLD
             ),
             pdf=kwargs.get("pdf", False),
-            capture_mhtml=kwargs.get("capture_mhtml", False),
             image_description_min_word_threshold=kwargs.get(
                 "image_description_min_word_threshold",
                 IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD,
@@ -1013,7 +930,6 @@ class CrawlerRunConfig():
                 "image_score_threshold", IMAGE_SCORE_THRESHOLD
             ),
             table_score_threshold=kwargs.get("table_score_threshold", 7),
-            exclude_all_images=kwargs.get("exclude_all_images", False),
             exclude_external_images=kwargs.get("exclude_external_images", False),
             # Link and Domain Handling Parameters
             exclude_social_media_domains=kwargs.get(
@@ -1026,9 +942,6 @@ class CrawlerRunConfig():
             # Debugging and Logging Parameters
             verbose=kwargs.get("verbose", True),
             log_console=kwargs.get("log_console", False),
-            # Network and Console Capturing Parameters
-            capture_network_requests=kwargs.get("capture_network_requests", False),
-            capture_console_messages=kwargs.get("capture_console_messages", False),
             # Connection Parameters
             method=kwargs.get("method", "GET"),
             stream=kwargs.get("stream", False),
@@ -1039,8 +952,6 @@ class CrawlerRunConfig():
             # Deep Crawl Parameters
             deep_crawl_strategy=kwargs.get("deep_crawl_strategy"),
             url=kwargs.get("url"),
-            # Experimental Parameters 
-            experimental=kwargs.get("experimental"),
         )
 
     # Create a funciton returns dict of the object
@@ -1106,11 +1017,9 @@ class CrawlerRunConfig():
             "screenshot_wait_for": self.screenshot_wait_for,
             "screenshot_height_threshold": self.screenshot_height_threshold,
             "pdf": self.pdf,
-            "capture_mhtml": self.capture_mhtml,
             "image_description_min_word_threshold": self.image_description_min_word_threshold,
             "image_score_threshold": self.image_score_threshold,
             "table_score_threshold": self.table_score_threshold,
-            "exclude_all_images": self.exclude_all_images,
             "exclude_external_images": self.exclude_external_images,
             "exclude_social_media_domains": self.exclude_social_media_domains,
             "exclude_external_links": self.exclude_external_links,
@@ -1119,8 +1028,6 @@ class CrawlerRunConfig():
             "exclude_internal_links": self.exclude_internal_links,
             "verbose": self.verbose,
             "log_console": self.log_console,
-            "capture_network_requests": self.capture_network_requests,
-            "capture_console_messages": self.capture_console_messages,
             "method": self.method,
             "stream": self.stream,
             "check_robots_txt": self.check_robots_txt,
@@ -1129,7 +1036,6 @@ class CrawlerRunConfig():
             "user_agent_generator_config": self.user_agent_generator_config,
             "deep_crawl_strategy": self.deep_crawl_strategy,
             "url": self.url,
-            "experimental": self.experimental,
         }
 
     def clone(self, **kwargs):
@@ -1165,13 +1071,6 @@ class LLMConfig:
         provider: str = DEFAULT_PROVIDER,
         api_token: Optional[str] = None,
         base_url: Optional[str] = None,
-        temprature: Optional[float] = None,
-        max_tokens: Optional[int] = None,
-        top_p: Optional[float] = None,
-        frequency_penalty: Optional[float] = None,
-        presence_penalty: Optional[float] = None,
-        stop: Optional[List[str]] = None,
-        n: Optional[int] = None,    
     ):
         """Configuaration class for LLM provider and API token."""
         self.provider = provider
@@ -1181,16 +1080,10 @@ class LLMConfig:
             self.api_token = os.getenv(api_token[4:])
         else:
             self.api_token = PROVIDER_MODELS.get(provider, "no-token") or os.getenv(
-                DEFAULT_PROVIDER_API_KEY
+                "OPENAI_API_KEY"
             )
         self.base_url = base_url
-        self.temprature = temprature
+
-        self.max_tokens = max_tokens
-        self.top_p = top_p
-        self.frequency_penalty = frequency_penalty
-        self.presence_penalty = presence_penalty
-        self.stop = stop
-        self.n = n
 
     @staticmethod
     def from_kwargs(kwargs: dict) -> "LLMConfig":
@@ -1198,27 +1091,13 @@ class LLMConfig:
             provider=kwargs.get("provider", DEFAULT_PROVIDER),
             api_token=kwargs.get("api_token"),
             base_url=kwargs.get("base_url"),
-            temprature=kwargs.get("temprature"),
-            max_tokens=kwargs.get("max_tokens"),
-            top_p=kwargs.get("top_p"),
-            frequency_penalty=kwargs.get("frequency_penalty"),
-            presence_penalty=kwargs.get("presence_penalty"),
-            stop=kwargs.get("stop"),
-            n=kwargs.get("n")
         )
 
     def to_dict(self):
         return {
             "provider": self.provider,
             "api_token": self.api_token,
-            "base_url": self.base_url,
+            "base_url": self.base_url
-            "temprature": self.temprature,
-            "max_tokens": self.max_tokens,
-            "top_p": self.top_p,
-            "frequency_penalty": self.frequency_penalty,
-            "presence_penalty": self.presence_penalty,
-            "stop": self.stop,
-            "n": self.n
         }
 
     def clone(self, **kwargs):

crawl4ai/async_crawler_strategy.py

@@ -409,11 +409,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
 
         user_agent = kwargs.get("user_agent", self.user_agent)
         # Use browser_manager to get a fresh page & context assigned to this session_id
-        page, context = await self.browser_manager.get_page(CrawlerRunConfig(
+        page, context = await self.browser_manager.get_page(session_id, user_agent)
-            session_id=session_id,
-            user_agent=user_agent,
-            **kwargs,
-        ))
         return session_id
 
     async def crawl(
@@ -451,17 +447,12 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                 html = f.read()
             if config.screenshot:
                 screenshot_data = await self._generate_screenshot_from_html(html)
-            if config.capture_console_messages:
-                page, context = await self.browser_manager.get_page(crawlerRunConfig=config)
-                captured_console = await self._capture_console_messages(page, url)
-
             return AsyncCrawlResponse(
                 html=html,
                 response_headers=response_headers,
                 status_code=status_code,
                 screenshot=screenshot_data,
                 get_delayed_content=None,
-                console_messages=captured_console,
             )
 
         elif url.startswith("raw:") or url.startswith("raw://"):
@@ -487,7 +478,6 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
     ) -> AsyncCrawlResponse:
         """
         Internal method to crawl web URLs with the specified configuration.
-        Includes optional network and console capturing.
 
         Args:
             url (str): The web URL to crawl
@@ -504,10 +494,6 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
 
         # Reset downloaded files list for new crawl
         self._downloaded_files = []
-        
-        # Initialize capture lists
-        captured_requests = []
-        captured_console = []
 
         # Handle user agent with magic mode
         user_agent_to_override = config.user_agent
@@ -521,12 +507,10 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
         # Get page for session
         page, context = await self.browser_manager.get_page(crawlerRunConfig=config)
 
-        # await page.goto(URL)
-
         # Add default cookie
-        # await context.add_cookies(
+        await context.add_cookies(
-        #     [{"name": "cookiesEnabled", "value": "true", "url": url}]
+            [{"name": "cookiesEnabled", "value": "true", "url": url}]
-        # )
+        )
 
         # Handle navigator overrides
         if config.override_navigator or config.simulate_user or config.magic:
@@ -535,144 +519,9 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
         # Call hook after page creation
         await self.execute_hook("on_page_context_created", page, context=context, config=config)
 
-        # Network Request Capturing
-        if config.capture_network_requests:
-            async def handle_request_capture(request):
-                try:
-                    post_data_str = None
-                    try:
-                        # Be cautious with large post data
-                        post_data = request.post_data_buffer
-                        if post_data:
-                             # Attempt to decode, fallback to base64 or size indication
-                             try:
-                                 post_data_str = post_data.decode('utf-8', errors='replace')
-                             except UnicodeDecodeError:
-                                 post_data_str = f"[Binary data: {len(post_data)} bytes]"
-                    except Exception:
-                        post_data_str = "[Error retrieving post data]"
-
-                    captured_requests.append({
-                        "event_type": "request",
-                        "url": request.url,
-                        "method": request.method,
-                        "headers": dict(request.headers), # Convert Header dict
-                        "post_data": post_data_str,
-                        "resource_type": request.resource_type,
-                        "is_navigation_request": request.is_navigation_request(),
-                        "timestamp": time.time()
-                    })
-                except Exception as e:
-                    if self.logger:
-                        self.logger.warning(f"Error capturing request details for {request.url}: {e}", tag="CAPTURE")
-                    captured_requests.append({"event_type": "request_capture_error", "url": request.url, "error": str(e), "timestamp": time.time()})
-
-            async def handle_response_capture(response):
-                try:
-                    captured_requests.append({
-                        "event_type": "response",
-                        "url": response.url,
-                        "status": response.status,
-                        "status_text": response.status_text,
-                        "headers": dict(response.headers), # Convert Header dict
-                        "from_service_worker": response.from_service_worker,
-                        "request_timing": response.request.timing, # Detailed timing info
-                        "timestamp": time.time()
-                    })
-                except Exception as e:
-                    if self.logger:
-                        self.logger.warning(f"Error capturing response details for {response.url}: {e}", tag="CAPTURE")
-                    captured_requests.append({"event_type": "response_capture_error", "url": response.url, "error": str(e), "timestamp": time.time()})
-
-            async def handle_request_failed_capture(request):
-                 try:
-                    captured_requests.append({
-                        "event_type": "request_failed",
-                        "url": request.url,
-                        "method": request.method,
-                        "resource_type": request.resource_type,
-                        "failure_text": str(request.failure) if request.failure else "Unknown failure",
-                        "timestamp": time.time()
-                    })
-                 except Exception as e:
-                    if self.logger:
-                        self.logger.warning(f"Error capturing request failed details for {request.url}: {e}", tag="CAPTURE")
-                    captured_requests.append({"event_type": "request_failed_capture_error", "url": request.url, "error": str(e), "timestamp": time.time()})
-
-            page.on("request", handle_request_capture)
-            page.on("response", handle_response_capture)
-            page.on("requestfailed", handle_request_failed_capture)
-
-        # Console Message Capturing
-        if config.capture_console_messages:
-            def handle_console_capture(msg):
-                try:
-                    message_type = "unknown"
-                    try:
-                        message_type = msg.type
-                    except:
-                        pass
-                        
-                    message_text = "unknown"
-                    try:
-                        message_text = msg.text
-                    except:
-                        pass
-                        
-                    # Basic console message with minimal content
-                    entry = {
-                        "type": message_type,
-                        "text": message_text,
-                        "timestamp": time.time()
-                    }
-                    
-                    captured_console.append(entry)
-                    
-                except Exception as e:
-                    if self.logger:
-                        self.logger.warning(f"Error capturing console message: {e}", tag="CAPTURE")
-                    # Still add something to the list even on error
-                    captured_console.append({
-                        "type": "console_capture_error", 
-                        "error": str(e), 
-                        "timestamp": time.time()
-                    })
-
-            def handle_pageerror_capture(err):
-                try:
-                    error_message = "Unknown error"
-                    try:
-                        error_message = err.message
-                    except:
-                        pass
-                        
-                    error_stack = ""
-                    try:
-                        error_stack = err.stack
-                    except:
-                        pass
-                        
-                    captured_console.append({
-                        "type": "error",
-                        "text": error_message,
-                        "stack": error_stack,
-                        "timestamp": time.time()
-                    })
-                except Exception as e:
-                    if self.logger:
-                        self.logger.warning(f"Error capturing page error: {e}", tag="CAPTURE")
-                    captured_console.append({
-                        "type": "pageerror_capture_error", 
-                        "error": str(e), 
-                        "timestamp": time.time()
-                    })
-
-            # Add event listeners directly
-            page.on("console", handle_console_capture)
-            page.on("pageerror", handle_pageerror_capture)
-
         # Set up console logging if requested
         if config.log_console:
+
             def log_consol(
                 msg, console_log_type="debug"
             ):  # Corrected the parameter syntax
@@ -713,15 +562,14 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
 
                 try:
                     # Generate a unique nonce for this request
-                    if config.experimental.get("use_csp_nonce", False):
+                    nonce = hashlib.sha256(os.urandom(32)).hexdigest()
-                        nonce = hashlib.sha256(os.urandom(32)).hexdigest()
 
-                        # Add CSP headers to the request
+                    # Add CSP headers to the request
-                        await page.set_extra_http_headers(
+                    await page.set_extra_http_headers(
-                            {
+                        {
-                                "Content-Security-Policy": f"default-src 'self'; script-src 'self' 'nonce-{nonce}' 'strict-dynamic'"
+                            "Content-Security-Policy": f"default-src 'self'; script-src 'self' 'nonce-{nonce}' 'strict-dynamic'"
-                            }
+                        }
-                        )
+                    )
 
                     response = await page.goto(
                         url, wait_until=config.wait_until, timeout=config.page_timeout
@@ -985,18 +833,14 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                 "before_return_html", page=page, html=html, context=context, config=config
             )
 
-            # Handle PDF, MHTML and screenshot generation
+            # Handle PDF and screenshot generation
             start_export_time = time.perf_counter()
             pdf_data = None
             screenshot_data = None
-            mhtml_data = None
 
             if config.pdf:
                 pdf_data = await self.export_pdf(page)
 
-            if config.capture_mhtml:
-                mhtml_data = await self.capture_mhtml(page)
-
             if config.screenshot:
                 if config.screenshot_wait_for:
                     await asyncio.sleep(config.screenshot_wait_for)
@@ -1004,9 +848,9 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                     page, screenshot_height_threshold=config.screenshot_height_threshold
                 )
 
-            if screenshot_data or pdf_data or mhtml_data:
+            if screenshot_data or pdf_data:
                 self.logger.info(
-                    message="Exporting media (PDF/MHTML/screenshot) took {duration:.2f}s",
+                    message="Exporting PDF and taking screenshot took {duration:.2f}s",
                     tag="EXPORT",
                     params={"duration": time.perf_counter() - start_export_time},
                 )
@@ -1029,16 +873,12 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                 status_code=status_code,
                 screenshot=screenshot_data,
                 pdf_data=pdf_data,
-                mhtml_data=mhtml_data,
                 get_delayed_content=get_delayed_content,
                 ssl_certificate=ssl_cert,
                 downloaded_files=(
                     self._downloaded_files if self._downloaded_files else None
                 ),
                 redirected_url=redirected_url,
-                # Include captured data if enabled
-                network_requests=captured_requests if config.capture_network_requests else None,
-                console_messages=captured_console if config.capture_console_messages else None,
             )
 
         except Exception as e:
@@ -1047,15 +887,6 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
         finally:
             # If no session_id is given we should close the page
             if not config.session_id:
-                # Detach listeners before closing to prevent potential errors during close
-                if config.capture_network_requests:
-                    page.remove_listener("request", handle_request_capture)
-                    page.remove_listener("response", handle_response_capture)
-                    page.remove_listener("requestfailed", handle_request_failed_capture)
-                if config.capture_console_messages:
-                    page.remove_listener("console", handle_console_capture)
-                    page.remove_listener("pageerror", handle_pageerror_capture)
-                
                 await page.close()
 
     async def _handle_full_page_scan(self, page: Page, scroll_delay: float = 0.1):
@@ -1218,107 +1049,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
         """
         pdf_data = await page.pdf(print_background=True)
         return pdf_data
-        
-    async def capture_mhtml(self, page: Page) -> Optional[str]:
-        """
-        Captures the current page as MHTML using CDP.
-        
-        MHTML (MIME HTML) is a web page archive format that combines the HTML content 
-        with its resources (images, CSS, etc.) into a single MIME-encoded file.
-        
-        Args:
-            page (Page): The Playwright page object
-            
-        Returns:
-            Optional[str]: The MHTML content as a string, or None if there was an error
-        """
-        try:
-            # Ensure the page is fully loaded before capturing
-            try:
-                # Wait for DOM content and network to be idle
-                await page.wait_for_load_state("domcontentloaded", timeout=5000)
-                await page.wait_for_load_state("networkidle", timeout=5000)
-                
-                # Give a little extra time for JavaScript execution
-                await page.wait_for_timeout(1000)
-                
-                # Wait for any animations to complete
-                await page.evaluate("""
-                    () => new Promise(resolve => {
-                        // First requestAnimationFrame gets scheduled after the next repaint
-                        requestAnimationFrame(() => {
-                            // Second requestAnimationFrame gets called after all animations complete
-                            requestAnimationFrame(resolve);
-                        });
-                    })
-                """)
-            except Error as e:
-                if self.logger:
-                    self.logger.warning(
-                        message="Wait for load state timed out: {error}",
-                        tag="MHTML",
-                        params={"error": str(e)},
-                    )
-            
-            # Create a new CDP session
-            cdp_session = await page.context.new_cdp_session(page)
-            
-            # Call Page.captureSnapshot with format "mhtml"
-            result = await cdp_session.send("Page.captureSnapshot", {"format": "mhtml"})
-            
-            # The result contains a 'data' field with the MHTML content
-            mhtml_content = result.get("data")
-            
-            # Detach the CDP session to clean up resources
-            await cdp_session.detach()
-            
-            return mhtml_content
-        except Exception as e:
-            # Log the error but don't raise it - we'll just return None for the MHTML
-            if self.logger:
-                self.logger.error(
-                    message="Failed to capture MHTML: {error}",
-                    tag="MHTML",
-                    params={"error": str(e)},
-                )
-            return None
 
-    async def _capture_console_messages(
-        self, page: Page, file_path: str
-    ) -> List[Dict[str, Union[str, float]]]:
-        """
-        Captures console messages from the page.
-        Args:
-
-            page (Page): The Playwright page object
-        Returns:
-            List[Dict[str, Union[str, float]]]: A list of captured console messages
-        """
-        captured_console = []
-
-        def handle_console_message(msg):
-            try:
-                message_type = msg.type
-                message_text = msg.text
-
-                entry = {
-                    "type": message_type,
-                    "text": message_text,
-                    "timestamp": time.time(),
-                }
-                captured_console.append(entry)
-            except Exception as e:
-                if self.logger:
-                    self.logger.warning(
-                        f"Error capturing console message: {e}", tag="CAPTURE"
-                    )
-
-        page.on("console", handle_console_message)
-        
-        await page.goto(file_path)
-
-        return captured_console
-        
     async def take_screenshot(self, page, **kwargs) -> str:
         """
         Take a screenshot of the current page.

crawl4ai/async_database.py

@@ -4,15 +4,20 @@ import aiosqlite
 import asyncio
 from typing import Optional, Dict
 from contextlib import asynccontextmanager
-import json  
+import json  # Added for serialization/deserialization
-from .models import CrawlResult, MarkdownGenerationResult, StringCompatibleMarkdown
-import aiofiles
-from .async_logger import AsyncLogger
-
 from .utils import ensure_content_dirs, generate_content_hash
+from .models import CrawlResult, MarkdownGenerationResult, StringCompatibleMarkdown
+# , StringCompatibleMarkdown
+import aiofiles
 from .utils import VersionManager
+from .async_logger import AsyncLogger
 from .utils import get_error_context, create_box_message
 
+# Set up logging
+# logging.basicConfig(level=logging.INFO)
+# logger = logging.getLogger(__name__)
+# logger.setLevel(logging.INFO)
+
 base_directory = DB_PATH = os.path.join(
     os.getenv("CRAWL4_AI_BASE_DIRECTORY", Path.home()), ".crawl4ai"
 )

crawl4ai/async_dispatcher.py

@@ -4,15 +4,17 @@ from .models import (
     CrawlResult,
     CrawlerTaskResult,
     CrawlStatus,
+    DisplayMode,
+    CrawlStats,
     DomainState,
 )
 
-from .components.crawler_monitor import CrawlerMonitor
+from rich.live import Live
-
+from rich.table import Table
-from .types import AsyncWebCrawler
+from rich.console import Console
-
+from rich import box
+from datetime import timedelta, datetime
 from collections.abc import AsyncGenerator
-
 import time
 import psutil
 import asyncio
@@ -22,6 +24,8 @@ from urllib.parse import urlparse
 import random
 from abc import ABC, abstractmethod
 
+from math import inf as infinity
+
 
 class RateLimiter:
     def __init__(
@@ -83,6 +87,201 @@ class RateLimiter:
         return True
 
 
+class CrawlerMonitor:
+    def __init__(
+        self,
+        max_visible_rows: int = 15,
+        display_mode: DisplayMode = DisplayMode.DETAILED,
+    ):
+        self.console = Console()
+        self.max_visible_rows = max_visible_rows
+        self.display_mode = display_mode
+        self.stats: Dict[str, CrawlStats] = {}
+        self.process = psutil.Process()
+        self.start_time = time.time()
+        self.live = Live(self._create_table(), refresh_per_second=2)
+
+    def start(self):
+        self.live.start()
+
+    def stop(self):
+        self.live.stop()
+
+    def add_task(self, task_id: str, url: str):
+        self.stats[task_id] = CrawlStats(
+            task_id=task_id, url=url, status=CrawlStatus.QUEUED
+        )
+        self.live.update(self._create_table())
+
+    def update_task(self, task_id: str, **kwargs):
+        if task_id in self.stats:
+            for key, value in kwargs.items():
+                setattr(self.stats[task_id], key, value)
+            self.live.update(self._create_table())
+
+    def _create_aggregated_table(self) -> Table:
+        """Creates a compact table showing only aggregated statistics"""
+        table = Table(
+            box=box.ROUNDED,
+            title="Crawler Status Overview",
+            title_style="bold magenta",
+            header_style="bold blue",
+            show_lines=True,
+        )
+
+        # Calculate statistics
+        total_tasks = len(self.stats)
+        queued = sum(
+            1 for stat in self.stats.values() if stat.status == CrawlStatus.QUEUED
+        )
+        in_progress = sum(
+            1 for stat in self.stats.values() if stat.status == CrawlStatus.IN_PROGRESS
+        )
+        completed = sum(
+            1 for stat in self.stats.values() if stat.status == CrawlStatus.COMPLETED
+        )
+        failed = sum(
+            1 for stat in self.stats.values() if stat.status == CrawlStatus.FAILED
+        )
+
+        # Memory statistics
+        current_memory = self.process.memory_info().rss / (1024 * 1024)
+        total_task_memory = sum(stat.memory_usage for stat in self.stats.values())
+        peak_memory = max(
+            (stat.peak_memory for stat in self.stats.values()), default=0.0
+        )
+
+        # Duration
+        duration = time.time() - self.start_time
+
+        # Create status row
+        table.add_column("Status", style="bold cyan")
+        table.add_column("Count", justify="right")
+        table.add_column("Percentage", justify="right")
+
+        table.add_row("Total Tasks", str(total_tasks), "100%")
+        table.add_row(
+            "[yellow]In Queue[/yellow]",
+            str(queued),
+            f"{(queued / total_tasks * 100):.1f}%" if total_tasks > 0 else "0%",
+        )
+        table.add_row(
+            "[blue]In Progress[/blue]",
+            str(in_progress),
+            f"{(in_progress / total_tasks * 100):.1f}%" if total_tasks > 0 else "0%",
+        )
+        table.add_row(
+            "[green]Completed[/green]",
+            str(completed),
+            f"{(completed / total_tasks * 100):.1f}%" if total_tasks > 0 else "0%",
+        )
+        table.add_row(
+            "[red]Failed[/red]",
+            str(failed),
+            f"{(failed / total_tasks * 100):.1f}%" if total_tasks > 0 else "0%",
+        )
+
+        # Add memory information
+        table.add_section()
+        table.add_row(
+            "[magenta]Current Memory[/magenta]", f"{current_memory:.1f} MB", ""
+        )
+        table.add_row(
+            "[magenta]Total Task Memory[/magenta]", f"{total_task_memory:.1f} MB", ""
+        )
+        table.add_row(
+            "[magenta]Peak Task Memory[/magenta]", f"{peak_memory:.1f} MB", ""
+        )
+        table.add_row(
+            "[yellow]Runtime[/yellow]",
+            str(timedelta(seconds=int(duration))),
+            "",
+        )
+
+        return table
+
+    def _create_detailed_table(self) -> Table:
+        table = Table(
+            box=box.ROUNDED,
+            title="Crawler Performance Monitor",
+            title_style="bold magenta",
+            header_style="bold blue",
+        )
+
+        # Add columns
+        table.add_column("Task ID", style="cyan", no_wrap=True)
+        table.add_column("URL", style="cyan", no_wrap=True)
+        table.add_column("Status", style="bold")
+        table.add_column("Memory (MB)", justify="right")
+        table.add_column("Peak (MB)", justify="right")
+        table.add_column("Duration", justify="right")
+        table.add_column("Info", style="italic")
+
+        # Add summary row
+        total_memory = sum(stat.memory_usage for stat in self.stats.values())
+        active_count = sum(
+            1 for stat in self.stats.values() if stat.status == CrawlStatus.IN_PROGRESS
+        )
+        completed_count = sum(
+            1 for stat in self.stats.values() if stat.status == CrawlStatus.COMPLETED
+        )
+        failed_count = sum(
+            1 for stat in self.stats.values() if stat.status == CrawlStatus.FAILED
+        )
+
+        table.add_row(
+            "[bold yellow]SUMMARY",
+            f"Total: {len(self.stats)}",
+            f"Active: {active_count}",
+            f"{total_memory:.1f}",
+            f"{self.process.memory_info().rss / (1024 * 1024):.1f}",
+            str(
+                timedelta(
+                    seconds=int(time.time() - self.start_time)
+                )
+            ),
+            f"✓{completed_count} ✗{failed_count}",
+            style="bold",
+        )
+
+        table.add_section()
+
+        # Add rows for each task
+        visible_stats = sorted(
+            self.stats.values(),
+            key=lambda x: (
+                x.status != CrawlStatus.IN_PROGRESS,
+                x.status != CrawlStatus.QUEUED,
+                x.end_time or infinity,
+            ),
+        )[: self.max_visible_rows]
+
+        for stat in visible_stats:
+            status_style = {
+                CrawlStatus.QUEUED: "white",
+                CrawlStatus.IN_PROGRESS: "yellow",
+                CrawlStatus.COMPLETED: "green",
+                CrawlStatus.FAILED: "red",
+            }[stat.status]
+
+            table.add_row(
+                stat.task_id[:8],  # Show first 8 chars of task ID
+                stat.url[:40] + "..." if len(stat.url) > 40 else stat.url,
+                f"[{status_style}]{stat.status.value}[/{status_style}]",
+                f"{stat.memory_usage:.1f}",
+                f"{stat.peak_memory:.1f}",
+                stat.duration,
+                stat.error_message[:40] if stat.error_message else "",
+            )
+
+        return table
+
+    def _create_table(self) -> Table:
+        """Creates the appropriate table based on display mode"""
+        if self.display_mode == DisplayMode.AGGREGATED:
+            return self._create_aggregated_table()
+        return self._create_detailed_table()
+
 
 class BaseDispatcher(ABC):
     def __init__(
@@ -110,7 +309,7 @@ class BaseDispatcher(ABC):
     async def run_urls(
         self,
         urls: List[str],
-        crawler: AsyncWebCrawler,  # noqa: F821
+        crawler: "AsyncWebCrawler",  # noqa: F821
         config: CrawlerRunConfig,
         monitor: Optional[CrawlerMonitor] = None,
     ) -> List[CrawlerTaskResult]:
@@ -121,144 +320,71 @@ class MemoryAdaptiveDispatcher(BaseDispatcher):
     def __init__(
         self,
         memory_threshold_percent: float = 90.0,
-        critical_threshold_percent: float = 95.0,  # New critical threshold
-        recovery_threshold_percent: float = 85.0,  # New recovery threshold
         check_interval: float = 1.0,
         max_session_permit: int = 20,
-        fairness_timeout: float = 600.0,  # 10 minutes before prioritizing long-waiting URLs
+        memory_wait_timeout: float = 300.0,  # 5 minutes default timeout
         rate_limiter: Optional[RateLimiter] = None,
         monitor: Optional[CrawlerMonitor] = None,
     ):
         super().__init__(rate_limiter, monitor)
         self.memory_threshold_percent = memory_threshold_percent
-        self.critical_threshold_percent = critical_threshold_percent
-        self.recovery_threshold_percent = recovery_threshold_percent
         self.check_interval = check_interval
         self.max_session_permit = max_session_permit
-        self.fairness_timeout = fairness_timeout
+        self.memory_wait_timeout = memory_wait_timeout
-        self.result_queue = asyncio.Queue()
+        self.result_queue = asyncio.Queue()  # Queue for storing results
-        self.task_queue = asyncio.PriorityQueue()  # Priority queue for better management
+
-        self.memory_pressure_mode = False  # Flag to indicate when we're in memory pressure mode
-        self.current_memory_percent = 0.0  # Track current memory usage
-        
-    async def _memory_monitor_task(self):
-        """Background task to continuously monitor memory usage and update state"""
-        while True:
-            self.current_memory_percent = psutil.virtual_memory().percent
-            
-            # Enter memory pressure mode if we cross the threshold
-            if not self.memory_pressure_mode and self.current_memory_percent >= self.memory_threshold_percent:
-                self.memory_pressure_mode = True
-                if self.monitor:
-                    self.monitor.update_memory_status("PRESSURE")
-            
-            # Exit memory pressure mode if we go below recovery threshold
-            elif self.memory_pressure_mode and self.current_memory_percent <= self.recovery_threshold_percent:
-                self.memory_pressure_mode = False
-                if self.monitor:
-                    self.monitor.update_memory_status("NORMAL")
-            
-            # In critical mode, we might need to take more drastic action
-            if self.current_memory_percent >= self.critical_threshold_percent:
-                if self.monitor:
-                    self.monitor.update_memory_status("CRITICAL")
-                # We could implement additional memory-saving measures here
-                
-            await asyncio.sleep(self.check_interval)
-    
-    def _get_priority_score(self, wait_time: float, retry_count: int) -> float:
-        """Calculate priority score (lower is higher priority)
-        - URLs waiting longer than fairness_timeout get higher priority
-        - More retry attempts decreases priority
-        """
-        if wait_time > self.fairness_timeout:
-            # High priority for long-waiting URLs
-            return -wait_time
-        # Standard priority based on retries
-        return retry_count
-    
     async def crawl_url(
         self,
         url: str,
         config: CrawlerRunConfig,
         task_id: str,
-        retry_count: int = 0,
     ) -> CrawlerTaskResult:
         start_time = time.time()
         error_message = ""
         memory_usage = peak_memory = 0.0
-        
+
-        # Get starting memory for accurate measurement
-        process = psutil.Process()
-        start_memory = process.memory_info().rss / (1024 * 1024)
-        
         try:
             if self.monitor:
                 self.monitor.update_task(
-                    task_id, 
+                    task_id, status=CrawlStatus.IN_PROGRESS, start_time=start_time
-                    status=CrawlStatus.IN_PROGRESS, 
-                    start_time=start_time,
-                    retry_count=retry_count
                 )
-                
             self.concurrent_sessions += 1
-            
+
             if self.rate_limiter:
                 await self.rate_limiter.wait_if_needed(url)
-                
+
-            # Check if we're in critical memory state
+            process = psutil.Process()
-            if self.current_memory_percent >= self.critical_threshold_percent:
+            start_memory = process.memory_info().rss / (1024 * 1024)
-                # Requeue this task with increased priority and retry count
-                enqueue_time = time.time()
-                priority = self._get_priority_score(enqueue_time - start_time, retry_count + 1)
-                await self.task_queue.put((priority, (url, task_id, retry_count + 1, enqueue_time)))
-                
-                # Update monitoring
-                if self.monitor:
-                    self.monitor.update_task(
-                        task_id,
-                        status=CrawlStatus.QUEUED,
-                        error_message="Requeued due to critical memory pressure"
-                    )
-                
-                # Return placeholder result with requeued status
-                return CrawlerTaskResult(
-                    task_id=task_id,
-                    url=url,
-                    result=CrawlResult(
-                        url=url, html="", metadata={"status": "requeued"}, 
-                        success=False, error_message="Requeued due to critical memory pressure"
-                    ),
-                    memory_usage=0,
-                    peak_memory=0,
-                    start_time=start_time,
-                    end_time=time.time(),
-                    error_message="Requeued due to critical memory pressure",
-                    retry_count=retry_count + 1
-                )
-            
-            # Execute the crawl
             result = await self.crawler.arun(url, config=config, session_id=task_id)
-            
-            # Measure memory usage
             end_memory = process.memory_info().rss / (1024 * 1024)
+
             memory_usage = peak_memory = end_memory - start_memory
-            
+
-            # Handle rate limiting
             if self.rate_limiter and result.status_code:
                 if not self.rate_limiter.update_delay(url, result.status_code):
                     error_message = f"Rate limit retry count exceeded for domain {urlparse(url).netloc}"
                     if self.monitor:
                         self.monitor.update_task(task_id, status=CrawlStatus.FAILED)
-                        
+                    result = CrawlerTaskResult(
-            # Update status based on result
+                        task_id=task_id,
+                        url=url,
+                        result=result,
+                        memory_usage=memory_usage,
+                        peak_memory=peak_memory,
+                        start_time=start_time,
+                        end_time=time.time(),
+                        error_message=error_message,
+                    )
+                    await self.result_queue.put(result)
+                    return result
+
             if not result.success:
                 error_message = result.error_message
                 if self.monitor:
                     self.monitor.update_task(task_id, status=CrawlStatus.FAILED)
             elif self.monitor:
                 self.monitor.update_task(task_id, status=CrawlStatus.COMPLETED)
-                
+
         except Exception as e:
             error_message = str(e)
             if self.monitor:
@@ -266,7 +392,7 @@ class MemoryAdaptiveDispatcher(BaseDispatcher):
             result = CrawlResult(
                 url=url, html="", metadata={}, success=False, error_message=str(e)
             )
-            
+
         finally:
             end_time = time.time()
             if self.monitor:
@@ -276,10 +402,9 @@ class MemoryAdaptiveDispatcher(BaseDispatcher):
                     memory_usage=memory_usage,
                     peak_memory=peak_memory,
                     error_message=error_message,
-                    retry_count=retry_count
                 )
             self.concurrent_sessions -= 1
-            
+
         return CrawlerTaskResult(
             task_id=task_id,
             url=url,
@@ -289,240 +414,116 @@ class MemoryAdaptiveDispatcher(BaseDispatcher):
             start_time=start_time,
             end_time=end_time,
             error_message=error_message,
-            retry_count=retry_count
         )
-        
+
     async def run_urls(
         self,
         urls: List[str],
-        crawler: AsyncWebCrawler,
+        crawler: "AsyncWebCrawler",  # noqa: F821
         config: CrawlerRunConfig,
     ) -> List[CrawlerTaskResult]:
         self.crawler = crawler
-        
+
-        # Start the memory monitor task
-        memory_monitor = asyncio.create_task(self._memory_monitor_task())
-        
         if self.monitor:
             self.monitor.start()
-            
+
-        results = []
-        
         try:
-            # Initialize task queue
+            pending_tasks = []
+            active_tasks = []
+            task_queue = []
+
             for url in urls:
                 task_id = str(uuid.uuid4())
                 if self.monitor:
                     self.monitor.add_task(task_id, url)
-                # Add to queue with initial priority 0, retry count 0, and current time
+                task_queue.append((url, task_id))
-                await self.task_queue.put((0, (url, task_id, 0, time.time())))
-                
-            active_tasks = []
-            
-            # Process until both queues are empty
-            while not self.task_queue.empty() or active_tasks:
-                # If memory pressure is low, start new tasks
-                if not self.memory_pressure_mode and len(active_tasks) < self.max_session_permit:
-                    try:
-                        # Try to get a task with timeout to avoid blocking indefinitely
-                        priority, (url, task_id, retry_count, enqueue_time) = await asyncio.wait_for(
-                            self.task_queue.get(), timeout=0.1
-                        )
-                        
-                        # Create and start the task
-                        task = asyncio.create_task(
-                            self.crawl_url(url, config, task_id, retry_count)
-                        )
-                        active_tasks.append(task)
-                        
-                        # Update waiting time in monitor
-                        if self.monitor:
-                            wait_time = time.time() - enqueue_time
-                            self.monitor.update_task(
-                                task_id, 
-                                wait_time=wait_time,
-                                status=CrawlStatus.IN_PROGRESS
-                            )
-                            
-                    except asyncio.TimeoutError:
-                        # No tasks in queue, that's fine
-                        pass
-                        
-                # Wait for completion even if queue is starved
-                if active_tasks:
-                    done, pending = await asyncio.wait(
-                        active_tasks, timeout=0.1, return_when=asyncio.FIRST_COMPLETED
-                    )
-                    
-                    # Process completed tasks
-                    for completed_task in done:
-                        result = await completed_task
-                        results.append(result)
-                        
-                    # Update active tasks list
-                    active_tasks = list(pending)
-                else:
-                    # If no active tasks but still waiting, sleep briefly
-                    await asyncio.sleep(self.check_interval / 2)
-                    
-                # Update priorities for waiting tasks if needed
-                await self._update_queue_priorities()
-                
-            return results
 
-        except Exception as e:
+            while task_queue or active_tasks:
-            if self.monitor:
+                wait_start_time = time.time()
-                self.monitor.update_memory_status(f"QUEUE_ERROR: {str(e)}")                
+                while len(active_tasks) < self.max_session_permit and task_queue:
-        
+                    if psutil.virtual_memory().percent >= self.memory_threshold_percent:
+                        # Check if we've exceeded the timeout
+                        if time.time() - wait_start_time > self.memory_wait_timeout:
+                            raise MemoryError(
+                                f"Memory usage above threshold ({self.memory_threshold_percent}%) for more than {self.memory_wait_timeout} seconds"
+                            )
+                        await asyncio.sleep(self.check_interval)
+                        continue
+
+                    url, task_id = task_queue.pop(0)
+                    task = asyncio.create_task(self.crawl_url(url, config, task_id))
+                    active_tasks.append(task)
+
+                if not active_tasks:
+                    await asyncio.sleep(self.check_interval)
+                    continue
+
+                done, pending = await asyncio.wait(
+                    active_tasks, return_when=asyncio.FIRST_COMPLETED
+                )
+
+                pending_tasks.extend(done)
+                active_tasks = list(pending)
+
+            return await asyncio.gather(*pending_tasks)
         finally:
-            # Clean up
-            memory_monitor.cancel()
             if self.monitor:
                 self.monitor.stop()
-                
+
-    async def _update_queue_priorities(self):
-        """Periodically update priorities of items in the queue to prevent starvation"""
-        # Skip if queue is empty
-        if self.task_queue.empty():
-            return
-            
-        # Use a drain-and-refill approach to update all priorities
-        temp_items = []
-        
-        # Drain the queue (with a safety timeout to prevent blocking)
-        try:
-            drain_start = time.time()
-            while not self.task_queue.empty() and time.time() - drain_start < 5.0:  # 5 second safety timeout
-                try:
-                    # Get item from queue with timeout
-                    priority, (url, task_id, retry_count, enqueue_time) = await asyncio.wait_for(
-                        self.task_queue.get(), timeout=0.1
-                    )
-                    
-                    # Calculate new priority based on current wait time
-                    current_time = time.time()
-                    wait_time = current_time - enqueue_time
-                    new_priority = self._get_priority_score(wait_time, retry_count)
-                    
-                    # Store with updated priority
-                    temp_items.append((new_priority, (url, task_id, retry_count, enqueue_time)))
-                    
-                    # Update monitoring stats for this task
-                    if self.monitor and task_id in self.monitor.stats:
-                        self.monitor.update_task(task_id, wait_time=wait_time)
-                        
-                except asyncio.TimeoutError:
-                    # Queue might be empty or very slow
-                    break
-        except Exception as e:
-            # If anything goes wrong, make sure we refill the queue with what we've got
-            self.monitor.update_memory_status(f"QUEUE_ERROR: {str(e)}")
-        
-        # Calculate queue statistics
-        if temp_items and self.monitor:
-            total_queued = len(temp_items)
-            wait_times = [item[1][3] for item in temp_items]
-            highest_wait_time = time.time() - min(wait_times) if wait_times else 0
-            avg_wait_time = sum(time.time() - t for t in wait_times) / len(wait_times) if wait_times else 0
-            
-            # Update queue statistics in monitor
-            self.monitor.update_queue_statistics(
-                total_queued=total_queued,
-                highest_wait_time=highest_wait_time,
-                avg_wait_time=avg_wait_time
-            )
-        
-        # Sort by priority (lowest number = highest priority)
-        temp_items.sort(key=lambda x: x[0])
-        
-        # Refill the queue with updated priorities
-        for item in temp_items:
-            await self.task_queue.put(item)
-                
     async def run_urls_stream(
         self,
         urls: List[str],
-        crawler: AsyncWebCrawler,
+        crawler: "AsyncWebCrawler", # noqa: F821
         config: CrawlerRunConfig,
     ) -> AsyncGenerator[CrawlerTaskResult, None]:
         self.crawler = crawler
-        
-        # Start the memory monitor task
-        memory_monitor = asyncio.create_task(self._memory_monitor_task())
-        
         if self.monitor:
             self.monitor.start()
-            
+
         try:
+            active_tasks = []
+            task_queue = []
+            completed_count = 0
+            total_urls = len(urls)
+
             # Initialize task queue
             for url in urls:
                 task_id = str(uuid.uuid4())
                 if self.monitor:
                     self.monitor.add_task(task_id, url)
-                # Add to queue with initial priority 0, retry count 0, and current time
+                task_queue.append((url, task_id))
-                await self.task_queue.put((0, (url, task_id, 0, time.time())))
+
-                
-            active_tasks = []
-            completed_count = 0
-            total_urls = len(urls)
-            
             while completed_count < total_urls:
-                # If memory pressure is low, start new tasks
+                # Start new tasks if memory permits
-                if not self.memory_pressure_mode and len(active_tasks) < self.max_session_permit:
+                while len(active_tasks) < self.max_session_permit and task_queue:
-                    try:
+                    if psutil.virtual_memory().percent >= self.memory_threshold_percent:
-                        # Try to get a task with timeout
+                        await asyncio.sleep(self.check_interval)
-                        priority, (url, task_id, retry_count, enqueue_time) = await asyncio.wait_for(
+                        continue
-                            self.task_queue.get(), timeout=0.1
+
-                        )
+                    url, task_id = task_queue.pop(0)
-                        
+                    task = asyncio.create_task(self.crawl_url(url, config, task_id))
-                        # Create and start the task
+                    active_tasks.append(task)
-                        task = asyncio.create_task(
+
-                            self.crawl_url(url, config, task_id, retry_count)
+                if not active_tasks and not task_queue:
-                        )
+                    break
-                        active_tasks.append(task)
+
-                        
+                # Wait for any task to complete and yield results
-                        # Update waiting time in monitor
-                        if self.monitor:
-                            wait_time = time.time() - enqueue_time
-                            self.monitor.update_task(
-                                task_id, 
-                                wait_time=wait_time,
-                                status=CrawlStatus.IN_PROGRESS
-                            )
-                            
-                    except asyncio.TimeoutError:
-                        # No tasks in queue, that's fine
-                        pass
-                        
-                # Process completed tasks and yield results
                 if active_tasks:
                     done, pending = await asyncio.wait(
                         active_tasks, timeout=0.1, return_when=asyncio.FIRST_COMPLETED
                     )
-                    
                     for completed_task in done:
                         result = await completed_task
-                        
+                        completed_count += 1
-                        # Only count as completed if it wasn't requeued
+                        yield result
-                        if "requeued" not in result.error_message:
-                            completed_count += 1
-                            yield result
-                        
-                    # Update active tasks list
                     active_tasks = list(pending)
                 else:
-                    # If no active tasks but still waiting, sleep briefly
+                    await asyncio.sleep(self.check_interval)
-                    await asyncio.sleep(self.check_interval / 2)
+
-                
-                # Update priorities for waiting tasks if needed
-                await self._update_queue_priorities()
-                
         finally:
-            # Clean up
-            memory_monitor.cancel()
             if self.monitor:
                 self.monitor.stop()
-                
+
 
 class SemaphoreDispatcher(BaseDispatcher):
     def __init__(
@@ -619,7 +620,7 @@ class SemaphoreDispatcher(BaseDispatcher):
 
     async def run_urls(
         self,
-        crawler: AsyncWebCrawler,  # noqa: F821
+        crawler: "AsyncWebCrawler",  # noqa: F821
         urls: List[str],
         config: CrawlerRunConfig,
     ) -> List[CrawlerTaskResult]:
@@ -643,4 +644,4 @@ class SemaphoreDispatcher(BaseDispatcher):
             return await asyncio.gather(*tasks, return_exceptions=True)
         finally:
             if self.monitor:
-                self.monitor.stop()
+                self.monitor.stop()

crawl4ai/async_logger.py

@@ -156,22 +156,9 @@ class AsyncLogger(AsyncLoggerBase):
                 formatted_message = message.format(**params)
 
                 # Then apply colors if specified
-                color_map = {
-                    "green": Fore.GREEN,
-                    "red": Fore.RED,
-                    "yellow": Fore.YELLOW,
-                    "blue": Fore.BLUE,
-                    "cyan": Fore.CYAN,
-                    "magenta": Fore.MAGENTA,
-                    "white": Fore.WHITE,
-                    "black": Fore.BLACK,
-                    "reset": Style.RESET_ALL,
-                }
                 if colors:
                     for key, color in colors.items():
                         # Find the formatted value in the message and wrap it with color
-                        if color in color_map:
-                            color = color_map[color]
                         if key in params:
                             value_str = str(params[key])
                             formatted_message = formatted_message.replace(

crawl4ai/async_webcrawler.py

@@ -4,26 +4,20 @@ import sys
 import time
 from colorama import Fore
 from pathlib import Path
-from typing import Optional, List
+from typing import Optional, List, Generic, TypeVar
 import json
 import asyncio
 
 # from contextlib import nullcontext, asynccontextmanager
 from contextlib import asynccontextmanager
-from .models import (
+from .models import CrawlResult, MarkdownGenerationResult, DispatchResult, ScrapingResult
-    CrawlResult,
-    MarkdownGenerationResult,
-    DispatchResult,
-    ScrapingResult,
-    CrawlResultContainer,
-    RunManyReturn
-)
 from .async_database import async_db_manager
 from .chunking_strategy import *  # noqa: F403
-from .chunking_strategy import IdentityChunking
+from .chunking_strategy import RegexChunking, ChunkingStrategy, IdentityChunking
 from .content_filter_strategy import *  # noqa: F403
-from .extraction_strategy import *  # noqa: F403
+from .content_filter_strategy import RelevantContentFilter
-from .extraction_strategy import NoExtractionStrategy
+from .extraction_strategy import * # noqa: F403
+from .extraction_strategy import NoExtractionStrategy, ExtractionStrategy
 from .async_crawler_strategy import (
     AsyncCrawlerStrategy,
     AsyncPlaywrightCrawlerStrategy,
@@ -37,9 +31,10 @@ from .markdown_generation_strategy import (
 from .deep_crawling import DeepCrawlDecorator
 from .async_logger import AsyncLogger, AsyncLoggerBase
 from .async_configs import BrowserConfig, CrawlerRunConfig
-from .async_dispatcher import *  # noqa: F403
+from .async_dispatcher import * # noqa: F403
 from .async_dispatcher import BaseDispatcher, MemoryAdaptiveDispatcher, RateLimiter
 
+from .config import MIN_WORD_THRESHOLD
 from .utils import (
     sanitize_input_encode,
     InvalidCSSSelectorError,
@@ -49,6 +44,45 @@ from .utils import (
     RobotsParser,
 )
 
+from typing import Union, AsyncGenerator
+
+CrawlResultT = TypeVar('CrawlResultT', bound=CrawlResult)
+# RunManyReturn = Union[CrawlResultT, List[CrawlResultT], AsyncGenerator[CrawlResultT, None]]
+
+class CrawlResultContainer(Generic[CrawlResultT]):
+    def __init__(self, results: Union[CrawlResultT, List[CrawlResultT]]):
+        # Normalize to a list
+        if isinstance(results, list):
+            self._results = results
+        else:
+            self._results = [results]
+
+    def __iter__(self):
+        return iter(self._results)
+
+    def __getitem__(self, index):
+        return self._results[index]
+
+    def __len__(self):
+        return len(self._results)
+
+    def __getattr__(self, attr):
+        # Delegate attribute access to the first element.
+        if self._results:
+            return getattr(self._results[0], attr)
+        raise AttributeError(f"{self.__class__.__name__} object has no attribute '{attr}'")
+
+    def __repr__(self):
+        return f"{self.__class__.__name__}({self._results!r})"
+
+# Redefine the union type. Now synchronous calls always return a container,
+# while stream mode is handled with an AsyncGenerator.
+RunManyReturn = Union[
+    CrawlResultContainer[CrawlResultT],
+    AsyncGenerator[CrawlResultT, None]
+]
+
+
 
 class AsyncWebCrawler:
     """
@@ -161,18 +195,23 @@ class AsyncWebCrawler:
 
         # Decorate arun method with deep crawling capabilities
         self._deep_handler = DeepCrawlDecorator(self)
-        self.arun = self._deep_handler(self.arun)
+        self.arun = self._deep_handler(self.arun)  
 
     async def start(self):
         """
         Start the crawler explicitly without using context manager.
         This is equivalent to using 'async with' but gives more control over the lifecycle.
+
+        This method will:
+        1. Initialize the browser and context
+        2. Perform warmup sequence
+        3. Return the crawler instance for method chaining
+
         Returns:
             AsyncWebCrawler: The initialized crawler instance
         """
         await self.crawler_strategy.__aenter__()
-        self.logger.info(f"Crawl4AI {crawl4ai_version}", tag="INIT")
+        await self.awarmup()
-        self.ready = True
         return self
 
     async def close(self):
@@ -192,6 +231,18 @@ class AsyncWebCrawler:
     async def __aexit__(self, exc_type, exc_val, exc_tb):
         await self.close()
 
+    async def awarmup(self):
+        """
+        Initialize the crawler with warm-up sequence.
+
+        This method:
+        1. Logs initialization info
+        2. Sets up browser configuration
+        3. Marks the crawler as ready
+        """
+        self.logger.info(f"Crawl4AI {crawl4ai_version}", tag="INIT")
+        self.ready = True
+
     @asynccontextmanager
     async def nullcontext(self):
         """异步空上下文管理器"""
@@ -231,10 +282,6 @@ class AsyncWebCrawler:
         Returns:
             CrawlResult: The result of crawling and processing
         """
-        # Auto-start if not ready
-        if not self.ready:
-            await self.start()
-
         config = config or CrawlerRunConfig()
         if not isinstance(url, str) or not url:
             raise ValueError("Invalid URL, make sure the URL is a non-empty string")
@@ -248,7 +295,9 @@ class AsyncWebCrawler:
                     config.cache_mode = CacheMode.ENABLED
 
                 # Create cache context
-                cache_context = CacheContext(url, config.cache_mode, False)
+                cache_context = CacheContext(
+                    url, config.cache_mode, False
+                )
 
                 # Initialize processing variables
                 async_response: AsyncCrawlResponse = None
@@ -278,7 +327,7 @@ class AsyncWebCrawler:
                     # if config.screenshot and not screenshot or config.pdf and not pdf:
                     if config.screenshot and not screenshot_data:
                         cached_result = None
-
+                    
                     if config.pdf and not pdf_data:
                         cached_result = None
 
@@ -310,18 +359,14 @@ class AsyncWebCrawler:
 
                     # Check robots.txt if enabled
                     if config and config.check_robots_txt:
-                        if not await self.robots_parser.can_fetch(
+                        if not await self.robots_parser.can_fetch(url, self.browser_config.user_agent):
-                            url, self.browser_config.user_agent
-                        ):
                             return CrawlResult(
                                 url=url,
                                 html="",
                                 success=False,
                                 status_code=403,
                                 error_message="Access denied by robots.txt",
-                                response_headers={
+                                response_headers={"X-Robots-Status": "Blocked by robots.txt"}
-                                    "X-Robots-Status": "Blocked by robots.txt"
-                                },
                             )
 
                     ##############################
@@ -348,7 +393,7 @@ class AsyncWebCrawler:
                     ###############################################################
                     # Process the HTML content, Call CrawlerStrategy.process_html #
                     ###############################################################
-                    crawl_result: CrawlResult = await self.aprocess_html(
+                    crawl_result : CrawlResult = await self.aprocess_html(
                         url=url,
                         html=html,
                         extracted_content=extracted_content,
@@ -365,11 +410,9 @@ class AsyncWebCrawler:
                     crawl_result.response_headers = async_response.response_headers
                     crawl_result.downloaded_files = async_response.downloaded_files
                     crawl_result.js_execution_result = js_execution_result
-                    crawl_result.mhtml = async_response.mhtml_data
+                    crawl_result.ssl_certificate = (
-                    crawl_result.ssl_certificate = async_response.ssl_certificate
+                        async_response.ssl_certificate
-                    # Add captured network and console data if available
+                    )  # Add SSL certificate
-                    crawl_result.network_requests = async_response.network_requests
-                    crawl_result.console_messages = async_response.console_messages
 
                     crawl_result.success = bool(html)
                     crawl_result.session_id = getattr(config, "session_id", None)
@@ -427,7 +470,7 @@ class AsyncWebCrawler:
                     tag="ERROR",
                 )
 
-                return CrawlResultContainer(
+                return  CrawlResultContainer(
                     CrawlResult(
                         url=url, html="", success=False, error_message=error_message
                     )
@@ -472,14 +515,15 @@ class AsyncWebCrawler:
 
             # Process HTML content
             params = config.__dict__.copy()
-            params.pop("url", None)
+            params.pop("url", None)            
             # add keys from kwargs to params that doesn't exist in params
             params.update({k: v for k, v in kwargs.items() if k not in params.keys()})
 
+            
             ################################
             # Scraping Strategy Execution  #
             ################################
-            result: ScrapingResult = scraping_strategy.scrap(url, html, **params)
+            result : ScrapingResult = scraping_strategy.scrap(url, html, **params)
 
             if result is None:
                 raise ValueError(
@@ -528,10 +572,7 @@ class AsyncWebCrawler:
         self.logger.info(
             message="{url:.50}... | Time: {timing}s",
             tag="SCRAPE",
-            params={
+            params={"url": _url, "timing": int((time.perf_counter() - t1) * 1000) / 1000},
-                "url": _url,
-                "timing": int((time.perf_counter() - t1) * 1000) / 1000,
-            },
         )
 
         ################################
@@ -606,7 +647,7 @@ class AsyncWebCrawler:
     async def arun_many(
         self,
         urls: List[str],
-        config: Optional[CrawlerRunConfig] = None,
+        config: Optional[CrawlerRunConfig] = None, 
         dispatcher: Optional[BaseDispatcher] = None,
         # Legacy parameters maintained for backwards compatibility
         # word_count_threshold=MIN_WORD_THRESHOLD,
@@ -620,8 +661,8 @@ class AsyncWebCrawler:
         # pdf: bool = False,
         # user_agent: str = None,
         # verbose=True,
-        **kwargs,
+        **kwargs
-    ) -> RunManyReturn:
+        ) -> RunManyReturn:
         """
         Runs the crawler for multiple URLs concurrently using a configurable dispatcher strategy.
 
@@ -677,32 +718,37 @@ class AsyncWebCrawler:
 
         def transform_result(task_result):
             return (
-                setattr(
+                    setattr(task_result.result, 'dispatch_result', 
-                    task_result.result,
+                        DispatchResult(
-                    "dispatch_result",
+                            task_id=task_result.task_id,
-                    DispatchResult(
+                            memory_usage=task_result.memory_usage,
-                        task_id=task_result.task_id,
+                            peak_memory=task_result.peak_memory,
-                        memory_usage=task_result.memory_usage,
+                            start_time=task_result.start_time,
-                        peak_memory=task_result.peak_memory,
+                            end_time=task_result.end_time,
-                        start_time=task_result.start_time,
+                            error_message=task_result.error_message,
-                        end_time=task_result.end_time,
+                        )
-                        error_message=task_result.error_message,
+                    ) or task_result.result
-                    ),
                 )
-                or task_result.result
-            )
 
         stream = config.stream
-
+        
         if stream:
-
             async def result_transformer():
-                async for task_result in dispatcher.run_urls_stream(
+                async for task_result in dispatcher.run_urls_stream(crawler=self, urls=urls, config=config):
-                    crawler=self, urls=urls, config=config
-                ):
                     yield transform_result(task_result)
-
             return result_transformer()
         else:
             _results = await dispatcher.run_urls(crawler=self, urls=urls, config=config)
-            return [transform_result(res) for res in _results]
+            return [transform_result(res) for res in _results]    
+
+    async def aclear_cache(self):
+        """Clear the cache database."""
+        await async_db_manager.cleanup()
+
+    async def aflush_cache(self):
+        """Flush the cache database."""
+        await async_db_manager.aflush_db()
+
+    async def aget_cache_size(self):
+        """Get the total number of cached items."""
+        return await async_db_manager.aget_total_count()

crawl4ai/browser_manager.py

@@ -145,60 +145,17 @@ class ManagedBrowser:
 
         # Start browser process
         try:
-            # Use DETACHED_PROCESS flag on Windows to fully detach the process
+            self.browser_process = subprocess.Popen(
-            # On Unix, we'll use preexec_fn=os.setpgrp to start the process in a new process group
+                args, stdout=subprocess.PIPE, stderr=subprocess.PIPE
-            if sys.platform == "win32":
+            )
-                self.browser_process = subprocess.Popen(
+            # Monitor browser process output for errors
-                    args, 
+            asyncio.create_task(self._monitor_browser_process())
-                    stdout=subprocess.PIPE, 
-                    stderr=subprocess.PIPE,
-                    creationflags=subprocess.DETACHED_PROCESS | subprocess.CREATE_NEW_PROCESS_GROUP
-                )
-            else:
-                self.browser_process = subprocess.Popen(
-                    args, 
-                    stdout=subprocess.PIPE, 
-                    stderr=subprocess.PIPE,
-                    preexec_fn=os.setpgrp  # Start in a new process group
-                )
-                
-            # We'll monitor for a short time to make sure it starts properly, but won't keep monitoring
-            await asyncio.sleep(0.5)  # Give browser time to start
-            await self._initial_startup_check()
             await asyncio.sleep(2)  # Give browser time to start
             return f"http://{self.host}:{self.debugging_port}"
         except Exception as e:
             await self.cleanup()
             raise Exception(f"Failed to start browser: {e}")
 
-    async def _initial_startup_check(self):
-        """
-        Perform a quick check to make sure the browser started successfully.
-        This only runs once at startup rather than continuously monitoring.
-        """
-        if not self.browser_process:
-            return
-            
-        # Check that process started without immediate termination
-        await asyncio.sleep(0.5)
-        if self.browser_process.poll() is not None:
-            # Process already terminated
-            stdout, stderr = b"", b""
-            try:
-                stdout, stderr = self.browser_process.communicate(timeout=0.5)
-            except subprocess.TimeoutExpired:
-                pass
-                
-            self.logger.error(
-                message="Browser process terminated during startup | Code: {code} | STDOUT: {stdout} | STDERR: {stderr}",
-                tag="ERROR",
-                params={
-                    "code": self.browser_process.returncode,
-                    "stdout": stdout.decode() if stdout else "",
-                    "stderr": stderr.decode() if stderr else "",
-                },
-            )
-    
     async def _monitor_browser_process(self):
         """
         Monitor the browser process for unexpected termination.
@@ -210,7 +167,6 @@ class ManagedBrowser:
         4. If any other error occurs, log the error message.
 
         Note: This method should be called in a separate task to avoid blocking the main event loop.
-        This is DEPRECATED and should not be used for builtin browsers that need to outlive the Python process.
         """
         if self.browser_process:
             try:
@@ -305,33 +261,22 @@ class ManagedBrowser:
 
         if self.browser_process:
             try:
-                # For builtin browsers that should persist, we should check if it's a detached process
+                self.browser_process.terminate()
-                # Only terminate if we have proper control over the process
+                # Wait for process to end gracefully
-                if not self.browser_process.poll():
+                for _ in range(10):  # 10 attempts, 100ms each
-                    # Process is still running
+                    if self.browser_process.poll() is not None:
-                    self.browser_process.terminate()
+                        break
-                    # Wait for process to end gracefully
+                    await asyncio.sleep(0.1)
-                    for _ in range(10):  # 10 attempts, 100ms each
-                        if self.browser_process.poll() is not None:
-                            break
-                        await asyncio.sleep(0.1)
 
-                    # Force kill if still running
+                # Force kill if still running
-                    if self.browser_process.poll() is None:
+                if self.browser_process.poll() is None:
-                        if sys.platform == "win32":
+                    self.browser_process.kill()
-                            # On Windows we might need taskkill for detached processes
+                    await asyncio.sleep(0.1)  # Brief wait for kill to take effect
-                            try:
-                                subprocess.run(["taskkill", "/F", "/PID", str(self.browser_process.pid)])
-                            except Exception:
-                                self.browser_process.kill()
-                        else:
-                            self.browser_process.kill()
-                        await asyncio.sleep(0.1)  # Brief wait for kill to take effect
 
             except Exception as e:
                 self.logger.error(
                     message="Error terminating browser: {error}",
-                    tag="ERROR", 
+                    tag="ERROR",
                     params={"error": str(e)},
                 )
 
@@ -434,14 +379,7 @@ class BrowserManager:
         sessions (dict): Dictionary to store session information
         session_ttl (int): Session timeout in seconds
     """
-
-    _playwright_instance = None
     
-    @classmethod
-    async def get_playwright(cls):
-        from playwright.async_api import async_playwright
-        cls._playwright_instance = await async_playwright().start()
-        return cls._playwright_instance    
 
     def __init__(self, browser_config: BrowserConfig, logger=None):
         """
@@ -491,12 +429,10 @@ class BrowserManager:
 
         Note: This method should be called in a separate task to avoid blocking the main event loop.
         """
-        if self.playwright is not None:
+        if self.playwright is None:
-            await self.close()
+            from playwright.async_api import async_playwright
-            
-        from playwright.async_api import async_playwright
 
-        self.playwright = await async_playwright().start()
+            self.playwright = await async_playwright().start()
 
         if self.config.cdp_url or self.config.use_managed_browser:
             self.config.use_managed_browser = True
@@ -507,6 +443,19 @@ class BrowserManager:
                 self.default_context = contexts[0]
             else:
                 self.default_context = await self.create_browser_context()
+                # self.default_context = await self.browser.new_context(
+                #     viewport={
+                #         "width": self.config.viewport_width,
+                #         "height": self.config.viewport_height,
+                #     },
+                #     storage_state=self.config.storage_state,
+                #     user_agent=self.config.headers.get(
+                #         "User-Agent", self.config.user_agent
+                #     ),
+                #     accept_downloads=self.config.accept_downloads,
+                #     ignore_https_errors=self.config.ignore_https_errors,
+                #     java_script_enabled=self.config.java_script_enabled,
+                # )
             await self.setup_context(self.default_context)
         else:
             browser_args = self._build_browser_args()
@@ -521,7 +470,6 @@ class BrowserManager:
 
             self.default_context = self.browser
 
-
     def _build_browser_args(self) -> dict:
         """Build browser launch arguments from config."""
         args = [
@@ -660,7 +608,7 @@ class BrowserManager:
                     "name": "cookiesEnabled",
                     "value": "true",
                     "url": crawlerRunConfig.url
-                    if crawlerRunConfig and crawlerRunConfig.url
+                    if crawlerRunConfig
                     else "https://crawl4ai.com/",
                 }
             ]

crawl4ai/browser_profiler.py

@@ -12,10 +12,7 @@ import sys
 import datetime
 import uuid
 import shutil
-import json
+from typing import List, Dict, Optional, Any
-import subprocess
-import time
-from typing import List, Dict, Optional, Any, Tuple
 from colorama import Fore, Style, init
 
 from .async_configs import BrowserConfig
@@ -59,11 +56,6 @@ class BrowserProfiler:
         # Ensure profiles directory exists
         self.profiles_dir = os.path.join(get_home_folder(), "profiles")
         os.makedirs(self.profiles_dir, exist_ok=True)
-        
-        # Builtin browser config file
-        self.builtin_browser_dir = os.path.join(get_home_folder(), "builtin-browser")
-        self.builtin_config_file = os.path.join(self.builtin_browser_dir, "browser_config.json")
-        os.makedirs(self.builtin_browser_dir, exist_ok=True)
     
     async def create_profile(self, 
                             profile_name: Optional[str] = None, 
@@ -555,12 +547,12 @@ class BrowserProfiler:
             else:
                 self.logger.error(f"Invalid choice. Please enter a number between 1 and {exit_option}.", tag="MENU")
 
+
     async def launch_standalone_browser(self, 
                                   browser_type: str = "chromium",
                                   user_data_dir: Optional[str] = None,
                                   debugging_port: int = 9222,
-                                  headless: bool = False,
+                                  headless: bool = False) -> Optional[str]:
-                                  save_as_builtin: bool = False) -> Optional[str]:
         """
         Launch a standalone browser with CDP debugging enabled and keep it running
         until the user presses 'q'. Returns and displays the CDP URL.
@@ -774,201 +766,4 @@ class BrowserProfiler:
         # Return the CDP URL
         return cdp_url
     
-    async def launch_builtin_browser(self, 
-                                 browser_type: str = "chromium",
-                                 debugging_port: int = 9222,
-                                 headless: bool = True) -> Optional[str]:
-        """
-        Launch a browser in the background for use as the builtin browser.
-        
-        Args:
-            browser_type (str): Type of browser to launch ('chromium' or 'firefox')
-            debugging_port (int): Port to use for CDP debugging
-            headless (bool): Whether to run in headless mode
-            
-        Returns:
-            str: CDP URL for the browser, or None if launch failed
-        """
-        # Check if there's an existing browser still running
-        browser_info = self.get_builtin_browser_info()
-        if browser_info and self._is_browser_running(browser_info.get('pid')):
-            self.logger.info("Builtin browser is already running", tag="BUILTIN")
-            return browser_info.get('cdp_url')
-        
-        # Create a user data directory for the builtin browser
-        user_data_dir = os.path.join(self.builtin_browser_dir, "user_data")
-        os.makedirs(user_data_dir, exist_ok=True)
-        
-        # Create managed browser instance
-        managed_browser = ManagedBrowser(
-            browser_type=browser_type,
-            user_data_dir=user_data_dir,
-            headless=headless,
-            logger=self.logger,
-            debugging_port=debugging_port
-        )
-        
-        try:
-            # Start the browser
-            await managed_browser.start()
-            
-            # Check if browser started successfully
-            browser_process = managed_browser.browser_process
-            if not browser_process:
-                self.logger.error("Failed to start browser process.", tag="BUILTIN")
-                return None
-            
-            # Get CDP URL
-            cdp_url = f"http://localhost:{debugging_port}"
-            
-            # Try to verify browser is responsive by fetching version info
-            import aiohttp
-            json_url = f"{cdp_url}/json/version"
-            config_json = None
-            
-            try:
-                async with aiohttp.ClientSession() as session:
-                    for _ in range(10):  # Try multiple times
-                        try:
-                            async with session.get(json_url) as response:
-                                if response.status == 200:
-                                    config_json = await response.json()
-                                    break
-                        except Exception:
-                            pass
-                        await asyncio.sleep(0.5)
-            except Exception as e:
-                self.logger.warning(f"Could not verify browser: {str(e)}", tag="BUILTIN")
-            
-            # Save browser info
-            browser_info = {
-                'pid': browser_process.pid,
-                'cdp_url': cdp_url,
-                'user_data_dir': user_data_dir,
-                'browser_type': browser_type,
-                'debugging_port': debugging_port,
-                'start_time': time.time(),
-                'config': config_json
-            }
-            
-            with open(self.builtin_config_file, 'w') as f:
-                json.dump(browser_info, f, indent=2)
-                
-            # Detach from the browser process - don't keep any references
-            # This is important to allow the Python script to exit while the browser continues running
-            # We'll just record the PID and other info, and the browser will run independently
-            managed_browser.browser_process = None
-                
-            self.logger.success(f"Builtin browser launched at CDP URL: {cdp_url}", tag="BUILTIN")
-            return cdp_url
-            
-        except Exception as e:
-            self.logger.error(f"Error launching builtin browser: {str(e)}", tag="BUILTIN")
-            if managed_browser:
-                await managed_browser.cleanup()
-            return None
-    
-    def get_builtin_browser_info(self) -> Optional[Dict[str, Any]]:
-        """
-        Get information about the builtin browser.
-        
-        Returns:
-            dict: Browser information or None if no builtin browser is configured
-        """
-        if not os.path.exists(self.builtin_config_file):
-            return None
-            
-        try:
-            with open(self.builtin_config_file, 'r') as f:
-                browser_info = json.load(f)
-                
-            # Check if the browser is still running
-            if not self._is_browser_running(browser_info.get('pid')):
-                self.logger.warning("Builtin browser is not running", tag="BUILTIN")
-                return None
-                
-            return browser_info
-        except Exception as e:
-            self.logger.error(f"Error reading builtin browser config: {str(e)}", tag="BUILTIN")
-            return None
-            
-    def _is_browser_running(self, pid: Optional[int]) -> bool:
-        """Check if a process with the given PID is running"""
-        if not pid:
-            return False
-            
-        try:
-            # Check if the process exists
-            if sys.platform == "win32":
-                process = subprocess.run(["tasklist", "/FI", f"PID eq {pid}"], 
-                                         capture_output=True, text=True)
-                return str(pid) in process.stdout
-            else:
-                # Unix-like systems
-                os.kill(pid, 0)  # This doesn't actually kill the process, just checks if it exists
-            return True
-        except (ProcessLookupError, PermissionError, OSError):
-            return False
-            
-    async def kill_builtin_browser(self) -> bool:
-        """
-        Kill the builtin browser if it's running.
-        
-        Returns:
-            bool: True if the browser was killed, False otherwise
-        """
-        browser_info = self.get_builtin_browser_info()
-        if not browser_info:
-            self.logger.warning("No builtin browser found", tag="BUILTIN")
-            return False
-            
-        pid = browser_info.get('pid')
-        if not pid:
-            return False
-            
-        try:
-            if sys.platform == "win32":
-                subprocess.run(["taskkill", "/F", "/PID", str(pid)], check=True)
-            else:
-                os.kill(pid, signal.SIGTERM)
-                # Wait for termination
-                for _ in range(5):
-                    if not self._is_browser_running(pid):
-                        break
-                    await asyncio.sleep(0.5)
-                else:
-                    # Force kill if still running
-                    os.kill(pid, signal.SIGKILL)
-                    
-            # Remove config file
-            if os.path.exists(self.builtin_config_file):
-                os.unlink(self.builtin_config_file)
-                
-            self.logger.success("Builtin browser terminated", tag="BUILTIN")
-            return True
-        except Exception as e:
-            self.logger.error(f"Error killing builtin browser: {str(e)}", tag="BUILTIN")
-            return False
-    
-    async def get_builtin_browser_status(self) -> Dict[str, Any]:
-        """
-        Get status information about the builtin browser.
-        
-        Returns:
-            dict: Status information with running, cdp_url, and info fields
-        """
-        browser_info = self.get_builtin_browser_info()
-        
-        if not browser_info:
-            return {
-                'running': False,
-                'cdp_url': None,
-                'info': None
-            }
-            
-        return {
-            'running': True,
-            'cdp_url': browser_info.get('cdp_url'),
-            'info': browser_info
-        }
 

crawl4ai/cli.py

@@ -20,16 +20,13 @@ from crawl4ai import (
     BrowserConfig, 
     CrawlerRunConfig,
     LLMExtractionStrategy, 
-    LXMLWebScrapingStrategy,
     JsonCssExtractionStrategy,
     JsonXPathExtractionStrategy,
     BM25ContentFilter, 
     PruningContentFilter,
     BrowserProfiler,
-    DefaultMarkdownGenerator,
     LLMConfig
 )
-from crawl4ai.config import USER_SETTINGS
 from litellm import completion
 from pathlib import Path
 
@@ -178,12 +175,8 @@ def show_examples():
     # CSS-based extraction
     crwl https://example.com -e extract_css.yml -s css_schema.json -o json
 
-    # LLM-based extraction with config file
+    # LLM-based extraction
     crwl https://example.com -e extract_llm.yml -s llm_schema.json -o json
-    
-    # Quick LLM-based JSON extraction (prompts for LLM provider first time)
-    crwl https://example.com -j  # Auto-extracts structured data
-    crwl https://example.com -j "Extract product details including name, price, and features"  # With specific instructions
 
 3️⃣  Direct Parameters:
     # Browser settings
@@ -285,7 +278,7 @@ llm_schema.json:
     # Combine configs with direct parameters
     crwl https://example.com -B browser.yml -b "headless=false,viewport_width=1920"
 
-    # Full extraction pipeline with config files
+    # Full extraction pipeline
     crwl https://example.com \\
         -B browser.yml \\
         -C crawler.yml \\
@@ -293,12 +286,6 @@ llm_schema.json:
         -s llm_schema.json \\
         -o json \\
         -v
-        
-    # Quick LLM-based extraction with specific instructions
-    crwl https://amazon.com/dp/B01DFKC2SO \\
-        -j "Extract product title, current price, original price, rating, and all product specifications" \\
-        -b "headless=true,viewport_width=1280" \\
-        -v
 
     # Content filtering with BM25
     crwl https://example.com \\
@@ -340,14 +327,6 @@ For more documentation visit: https://github.com/unclecode/crawl4ai
       - google/gemini-pro
     
     See full list of providers: https://docs.litellm.ai/docs/providers
-    
-    # Set default LLM provider and token in advance
-    crwl config set DEFAULT_LLM_PROVIDER "anthropic/claude-3-sonnet"
-    crwl config set DEFAULT_LLM_PROVIDER_TOKEN "your-api-token-here"
-    
-    # Set default browser behavior
-    crwl config set BROWSER_HEADLESS false  # Always show browser window
-    crwl config set USER_AGENT_MODE random  # Use random user agent
 
 9️⃣ Profile Management:
     # Launch interactive profile manager
@@ -362,32 +341,6 @@ For more documentation visit: https://github.com/unclecode/crawl4ai
     crwl profiles  # Select "Create new profile" option
     # 2. Then use that profile to crawl authenticated content:
     crwl https://site-requiring-login.com/dashboard -p my-profile-name
-
-🔄 Builtin Browser Management:
-    # Start a builtin browser (runs in the background)
-    crwl browser start
-    
-    # Check builtin browser status
-    crwl browser status
-    
-    # Open a visible window to see the browser
-    crwl browser view --url https://example.com
-    
-    # Stop the builtin browser
-    crwl browser stop
-    
-    # Restart with different options
-    crwl browser restart --browser-type chromium --port 9223 --no-headless
-    
-    # Use the builtin browser in your code
-    # (Just set browser_mode="builtin" in your BrowserConfig)
-    browser_config = BrowserConfig(
-        browser_mode="builtin", 
-        headless=True
-    )
-    
-    # Usage via CLI:
-    crwl https://example.com -b "browser_mode=builtin"
 """
     click.echo(examples)
 
@@ -622,307 +575,6 @@ def cli():
     pass
 
 
-@cli.group("browser")
-def browser_cmd():
-    """Manage browser instances for Crawl4AI
-    
-    Commands to manage browser instances for Crawl4AI, including:
-    - status - Check status of the builtin browser
-    - start - Start a new builtin browser
-    - stop - Stop the running builtin browser
-    - restart - Restart the builtin browser
-    """
-    pass
-    
-@browser_cmd.command("status")
-def browser_status_cmd():
-    """Show status of the builtin browser"""
-    profiler = BrowserProfiler()
-    
-    try:
-        status = anyio.run(profiler.get_builtin_browser_status)
-        
-        if status["running"]:
-            info = status["info"]
-            console.print(Panel(
-                f"[green]Builtin browser is running[/green]\n\n"
-                f"CDP URL: [cyan]{info['cdp_url']}[/cyan]\n"
-                f"Process ID: [yellow]{info['pid']}[/yellow]\n"
-                f"Browser type: [blue]{info['browser_type']}[/blue]\n"
-                f"User data directory: [magenta]{info['user_data_dir']}[/magenta]\n"
-                f"Started: [cyan]{time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(info['start_time']))}[/cyan]",
-                title="Builtin Browser Status",
-                border_style="green"
-            ))
-        else:
-            console.print(Panel(
-                "[yellow]Builtin browser is not running[/yellow]\n\n"
-                "Use 'crwl browser start' to start a builtin browser",
-                title="Builtin Browser Status",
-                border_style="yellow"
-            ))
-            
-    except Exception as e:
-        console.print(f"[red]Error checking browser status: {str(e)}[/red]")
-        sys.exit(1)
-        
-@browser_cmd.command("start")
-@click.option("--browser-type", "-b", type=click.Choice(["chromium", "firefox"]), default="chromium", 
-              help="Browser type (default: chromium)")
-@click.option("--port", "-p", type=int, default=9222, help="Debugging port (default: 9222)")
-@click.option("--headless/--no-headless", default=True, help="Run browser in headless mode")
-def browser_start_cmd(browser_type: str, port: int, headless: bool):
-    """Start a builtin browser instance
-    
-    This will start a persistent browser instance that can be used by Crawl4AI
-    by setting browser_mode="builtin" in BrowserConfig.
-    """
-    profiler = BrowserProfiler()
-    
-    # First check if browser is already running
-    status = anyio.run(profiler.get_builtin_browser_status)
-    if status["running"]:
-        console.print(Panel(
-            "[yellow]Builtin browser is already running[/yellow]\n\n"
-            f"CDP URL: [cyan]{status['cdp_url']}[/cyan]\n\n"
-            "Use 'crwl browser restart' to restart the browser",
-            title="Builtin Browser Start",
-            border_style="yellow"
-        ))
-        return
-    
-    try:
-        console.print(Panel(
-            f"[cyan]Starting builtin browser[/cyan]\n\n"
-            f"Browser type: [green]{browser_type}[/green]\n"
-            f"Debugging port: [yellow]{port}[/yellow]\n"
-            f"Headless: [cyan]{'Yes' if headless else 'No'}[/cyan]",
-            title="Builtin Browser Start",
-            border_style="cyan"
-        ))
-        
-        cdp_url = anyio.run(
-            profiler.launch_builtin_browser,
-            browser_type,
-            port,
-            headless
-        )
-        
-        if cdp_url:
-            console.print(Panel(
-                f"[green]Builtin browser started successfully[/green]\n\n"
-                f"CDP URL: [cyan]{cdp_url}[/cyan]\n\n"
-                "This browser will be used automatically when setting browser_mode='builtin'",
-                title="Builtin Browser Start",
-                border_style="green"
-            ))
-        else:
-            console.print(Panel(
-                "[red]Failed to start builtin browser[/red]",
-                title="Builtin Browser Start",
-                border_style="red"
-            ))
-            sys.exit(1)
-            
-    except Exception as e:
-        console.print(f"[red]Error starting builtin browser: {str(e)}[/red]")
-        sys.exit(1)
-        
-@browser_cmd.command("stop")
-def browser_stop_cmd():
-    """Stop the running builtin browser"""
-    profiler = BrowserProfiler()
-    
-    try:
-        # First check if browser is running
-        status = anyio.run(profiler.get_builtin_browser_status)
-        if not status["running"]:
-            console.print(Panel(
-                "[yellow]No builtin browser is currently running[/yellow]",
-                title="Builtin Browser Stop",
-                border_style="yellow"
-            ))
-            return
-            
-        console.print(Panel(
-            "[cyan]Stopping builtin browser...[/cyan]",
-            title="Builtin Browser Stop", 
-            border_style="cyan"
-        ))
-        
-        success = anyio.run(profiler.kill_builtin_browser)
-        
-        if success:
-            console.print(Panel(
-                "[green]Builtin browser stopped successfully[/green]",
-                title="Builtin Browser Stop",
-                border_style="green"
-            ))
-        else:
-            console.print(Panel(
-                "[red]Failed to stop builtin browser[/red]",
-                title="Builtin Browser Stop",
-                border_style="red"
-            ))
-            sys.exit(1)
-            
-    except Exception as e:
-        console.print(f"[red]Error stopping builtin browser: {str(e)}[/red]")
-        sys.exit(1)
-        
-@browser_cmd.command("view")
-@click.option("--url", "-u", help="URL to navigate to (defaults to about:blank)")
-def browser_view_cmd(url: Optional[str]):
-    """
-    Open a visible window of the builtin browser
-    
-    This command connects to the running builtin browser and opens a visible window,
-    allowing you to see what the browser is currently viewing or navigate to a URL.
-    """
-    profiler = BrowserProfiler()
-    
-    try:
-        # First check if browser is running
-        status = anyio.run(profiler.get_builtin_browser_status)
-        if not status["running"]:
-            console.print(Panel(
-                "[yellow]No builtin browser is currently running[/yellow]\n\n"
-                "Use 'crwl browser start' to start a builtin browser first",
-                title="Builtin Browser View",
-                border_style="yellow"
-            ))
-            return
-        
-        info = status["info"]
-        cdp_url = info["cdp_url"]
-        
-        console.print(Panel(
-            f"[cyan]Opening visible window connected to builtin browser[/cyan]\n\n"
-            f"CDP URL: [green]{cdp_url}[/green]\n"
-            f"URL to load: [yellow]{url or 'about:blank'}[/yellow]",
-            title="Builtin Browser View",
-            border_style="cyan"
-        ))
-        
-        # Use the CDP URL to launch a new visible window
-        import subprocess
-        import os
-        
-        # Determine the browser command based on platform
-        if sys.platform == "darwin":  # macOS
-            browser_cmd = ["/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"]
-        elif sys.platform == "win32":  # Windows
-            browser_cmd = ["C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe"]
-        else:  # Linux
-            browser_cmd = ["google-chrome"]
-        
-        # Add arguments
-        browser_args = [
-            f"--remote-debugging-port={info['debugging_port']}",
-            "--remote-debugging-address=localhost",
-            "--no-first-run",
-            "--no-default-browser-check"
-        ]
-        
-        # Add URL if provided
-        if url:
-            browser_args.append(url)
-        
-        # Launch browser
-        try:
-            subprocess.Popen(browser_cmd + browser_args)
-            console.print("[green]Browser window opened. Close it when finished viewing.[/green]")
-        except Exception as e:
-            console.print(f"[red]Error launching browser: {str(e)}[/red]")
-            console.print(f"[yellow]Try connecting manually to {cdp_url} in Chrome or using the '--remote-debugging-port' flag.[/yellow]")
-    
-    except Exception as e:
-        console.print(f"[red]Error viewing builtin browser: {str(e)}[/red]")
-        sys.exit(1)
-
-@browser_cmd.command("restart")
-@click.option("--browser-type", "-b", type=click.Choice(["chromium", "firefox"]), default=None, 
-              help="Browser type (defaults to same as current)")
-@click.option("--port", "-p", type=int, default=None, help="Debugging port (defaults to same as current)")
-@click.option("--headless/--no-headless", default=None, help="Run browser in headless mode")
-def browser_restart_cmd(browser_type: Optional[str], port: Optional[int], headless: Optional[bool]):
-    """Restart the builtin browser
-    
-    Stops the current builtin browser if running and starts a new one.
-    By default, uses the same configuration as the current browser.
-    """
-    profiler = BrowserProfiler()
-    
-    try:
-        # First check if browser is running and get its config
-        status = anyio.run(profiler.get_builtin_browser_status)
-        current_config = {}
-        
-        if status["running"]:
-            info = status["info"]
-            current_config = {
-                "browser_type": info["browser_type"],
-                "port": info["debugging_port"],
-                "headless": True  # Default assumption
-            }
-            
-            # Stop the browser
-            console.print(Panel(
-                "[cyan]Stopping current builtin browser...[/cyan]",
-                title="Builtin Browser Restart", 
-                border_style="cyan"
-            ))
-            
-            success = anyio.run(profiler.kill_builtin_browser)
-            if not success:
-                console.print(Panel(
-                    "[red]Failed to stop current browser[/red]",
-                    title="Builtin Browser Restart",
-                    border_style="red"
-                ))
-                sys.exit(1)
-        
-        # Use provided options or defaults from current config
-        browser_type = browser_type or current_config.get("browser_type", "chromium")
-        port = port or current_config.get("port", 9222)
-        headless = headless if headless is not None else current_config.get("headless", True)
-        
-        # Start a new browser
-        console.print(Panel(
-            f"[cyan]Starting new builtin browser[/cyan]\n\n"
-            f"Browser type: [green]{browser_type}[/green]\n"
-            f"Debugging port: [yellow]{port}[/yellow]\n"
-            f"Headless: [cyan]{'Yes' if headless else 'No'}[/cyan]",
-            title="Builtin Browser Restart",
-            border_style="cyan"
-        ))
-        
-        cdp_url = anyio.run(
-            profiler.launch_builtin_browser,
-            browser_type,
-            port,
-            headless
-        )
-        
-        if cdp_url:
-            console.print(Panel(
-                f"[green]Builtin browser restarted successfully[/green]\n\n"
-                f"CDP URL: [cyan]{cdp_url}[/cyan]",
-                title="Builtin Browser Restart",
-                border_style="green"
-            ))
-        else:
-            console.print(Panel(
-                "[red]Failed to restart builtin browser[/red]",
-                title="Builtin Browser Restart",
-                border_style="red"
-            ))
-            sys.exit(1)
-            
-    except Exception as e:
-        console.print(f"[red]Error restarting builtin browser: {str(e)}[/red]")
-        sys.exit(1)
-
 @cli.command("cdp")
 @click.option("--user-data-dir", "-d", help="Directory to use for browser data (will be created if it doesn't exist)")
 @click.option("--port", "-P", type=int, default=9222, help="Debugging port (default: 9222)")
@@ -1004,19 +656,17 @@ def cdp_cmd(user_data_dir: Optional[str], port: int, browser_type: str, headless
 @click.option("--crawler-config", "-C", type=click.Path(exists=True), help="Crawler config file (YAML/JSON)")
 @click.option("--filter-config", "-f", type=click.Path(exists=True), help="Content filter config file")
 @click.option("--extraction-config", "-e", type=click.Path(exists=True), help="Extraction strategy config file")
-@click.option("--json-extract", "-j", is_flag=False, flag_value="", default=None, help="Extract structured data using LLM with optional description")
 @click.option("--schema", "-s", type=click.Path(exists=True), help="JSON schema for extraction")
 @click.option("--browser", "-b", type=str, callback=parse_key_values, help="Browser parameters as key1=value1,key2=value2")
 @click.option("--crawler", "-c", type=str, callback=parse_key_values, help="Crawler parameters as key1=value1,key2=value2")
 @click.option("--output", "-o", type=click.Choice(["all", "json", "markdown", "md", "markdown-fit", "md-fit"]), default="all")
-@click.option("--output-file", "-O", type=click.Path(), help="Output file path (default: stdout)")
+@click.option("--bypass-cache", is_flag=True, default=True, help="Bypass cache when crawling")
-@click.option("--bypass-cache", "-b", is_flag=True, default=True, help="Bypass cache when crawling")
 @click.option("--question", "-q", help="Ask a question about the crawled content")
 @click.option("--verbose", "-v", is_flag=True)
 @click.option("--profile", "-p", help="Use a specific browser profile (by name)")
 def crawl_cmd(url: str, browser_config: str, crawler_config: str, filter_config: str, 
-           extraction_config: str, json_extract: str, schema: str, browser: Dict, crawler: Dict,
+           extraction_config: str, schema: str, browser: Dict, crawler: Dict,
-           output: str, output_file: str, bypass_cache: bool, question: str, verbose: bool, profile: str):
+           output: str, bypass_cache: bool, question: str, verbose: bool, profile: str):
     """Crawl a website and extract content
     
     Simple Usage:
@@ -1060,65 +710,21 @@ def crawl_cmd(url: str, browser_config: str, crawler_config: str, filter_config:
             crawler_cfg = crawler_cfg.clone(**crawler)
             
         # Handle content filter config
-        if filter_config or output in ["markdown-fit", "md-fit"]:
+        if filter_config:
-            if filter_config:
+            filter_conf = load_config_file(filter_config)
-                filter_conf = load_config_file(filter_config)
-            elif not filter_config and output in ["markdown-fit", "md-fit"]:
-                filter_conf = {
-                    "type": "pruning",
-                    "query": "",
-                    "threshold": 0.48
-                }
             if filter_conf["type"] == "bm25":
-                crawler_cfg.markdown_generator = DefaultMarkdownGenerator(
+                crawler_cfg.content_filter = BM25ContentFilter(
-                    content_filter = BM25ContentFilter(
+                    user_query=filter_conf.get("query"),
-                        user_query=filter_conf.get("query"),
+                    bm25_threshold=filter_conf.get("threshold", 1.0)
-                        bm25_threshold=filter_conf.get("threshold", 1.0)
-                    )
                 )
             elif filter_conf["type"] == "pruning":
-                crawler_cfg.markdown_generator = DefaultMarkdownGenerator(
+                crawler_cfg.content_filter = PruningContentFilter(
-                    content_filter = PruningContentFilter(
+                    user_query=filter_conf.get("query"),
-                        user_query=filter_conf.get("query"),
+                    threshold=filter_conf.get("threshold", 0.48)
-                        threshold=filter_conf.get("threshold", 0.48)
-                    )
                 )
-        
-        # Handle json-extract option (takes precedence over extraction-config)
-        if json_extract is not None:
-            # Get LLM provider and token
-            provider, token = setup_llm_config()
-            
-            # Default sophisticated instruction for structured data extraction
-            default_instruction = """Analyze the web page content and extract structured data as JSON. 
-If the page contains a list of items with repeated patterns, extract all items in an array. 
-If the page is an article or contains unique content, extract a comprehensive JSON object with all relevant information.
-Look at the content, intention of content, what it offers and find the data item(s) in the page.
-Always return valid, properly formatted JSON."""
-            
-            
-            default_instruction_with_user_query = """Analyze the web page content and extract structured data as JSON, following the below instruction and explanation of schema and always return valid, properly formatted JSON. \n\nInstruction:\n\n""" + json_extract
-            
-            # Determine instruction based on whether json_extract is empty or has content
-            instruction = default_instruction_with_user_query if json_extract else default_instruction
-            
-            # Create LLM extraction strategy
-            crawler_cfg.extraction_strategy = LLMExtractionStrategy(
-                llm_config=LLMConfig(provider=provider, api_token=token),
-                instruction=instruction,
-                schema=load_schema_file(schema),  # Will be None if no schema is provided
-                extraction_type="schema", #if schema else "block",
-                apply_chunking=False,
-                force_json_response=True,
-                verbose=verbose,
-            )
-            
-            # Set output to JSON if not explicitly specified
-            if output == "all":
-                output = "json"
                 
-        # Handle extraction strategy from config file (only if json-extract wasn't used)
+        # Handle extraction strategy
-        elif extraction_config:
+        if extraction_config:
             extract_conf = load_config_file(extraction_config)
             schema_data = load_schema_file(schema)
             
@@ -1152,13 +758,6 @@ Always return valid, properly formatted JSON."""
         # No cache
         if bypass_cache:
             crawler_cfg.cache_mode = CacheMode.BYPASS
-
-        crawler_cfg.scraping_strategy = LXMLWebScrapingStrategy()    
-
-        config = get_global_config()
-        
-        browser_cfg.verbose = config.get("VERBOSE", False)
-        crawler_cfg.verbose = config.get("VERBOSE", False)
         
         # Run crawler
         result : CrawlResult = anyio.run(
@@ -1177,31 +776,14 @@ Always return valid, properly formatted JSON."""
             return
         
         # Handle output
-        if not output_file:
+        if output == "all":
-            if output == "all":
+            click.echo(json.dumps(result.model_dump(), indent=2))
-                click.echo(json.dumps(result.model_dump(), indent=2))
+        elif output == "json":
-            elif output == "json":
+            click.echo(json.dumps(json.loads(result.extracted_content), indent=2))
-                print(result.extracted_content)
+        elif output in ["markdown", "md"]:
-                extracted_items = json.loads(result.extracted_content)
+            click.echo(result.markdown.raw_markdown)
-                click.echo(json.dumps(extracted_items, indent=2))
+        elif output in ["markdown-fit", "md-fit"]:
-                
+            click.echo(result.markdown.fit_markdown)
-            elif output in ["markdown", "md"]:
-                click.echo(result.markdown.raw_markdown)
-            elif output in ["markdown-fit", "md-fit"]:
-                click.echo(result.markdown.fit_markdown)
-        else:
-            if output == "all":
-                with open(output_file, "w") as f:
-                    f.write(json.dumps(result.model_dump(), indent=2))
-            elif output == "json":
-                with open(output_file, "w") as f:
-                    f.write(result.extracted_content)
-            elif output in ["markdown", "md"]:
-                with open(output_file, "w") as f:
-                    f.write(result.markdown.raw_markdown)
-            elif output in ["markdown-fit", "md-fit"]:
-                with open(output_file, "w") as f:
-                    f.write(result.markdown.fit_markdown)
             
     except Exception as e:
         raise click.ClickException(str(e))
@@ -1211,120 +793,6 @@ def examples_cmd():
     """Show usage examples"""
     show_examples()
 
-@cli.group("config")
-def config_cmd():
-    """Manage global configuration settings
-    
-    Commands to view and update global configuration settings:
-    - list: Display all current configuration settings
-    - get: Get the value of a specific setting
-    - set: Set the value of a specific setting
-    """
-    pass
-
-@config_cmd.command("list")
-def config_list_cmd():
-    """List all configuration settings"""
-    config = get_global_config()
-    
-    table = Table(title="Crawl4AI Configuration", show_header=True, header_style="bold cyan", border_style="blue")
-    table.add_column("Setting", style="cyan")
-    table.add_column("Value", style="green")
-    table.add_column("Default", style="yellow")
-    table.add_column("Description", style="white")
-    
-    for key, setting in USER_SETTINGS.items():
-        value = config.get(key, setting["default"])
-        
-        # Handle secret values
-        display_value = value
-        if setting.get("secret", False) and value:
-            display_value = "********"
-            
-        # Handle boolean values
-        if setting["type"] == "boolean":
-            display_value = str(value).lower()
-            default_value = str(setting["default"]).lower()
-        else:
-            default_value = str(setting["default"])
-        
-        table.add_row(
-            key,
-            str(display_value),
-            default_value,
-            setting["description"]
-        )
-    
-    console.print(table)
-
-@config_cmd.command("get")
-@click.argument("key", required=True)
-def config_get_cmd(key: str):
-    """Get a specific configuration setting"""
-    config = get_global_config()
-    
-    # Normalize key to uppercase
-    key = key.upper()
-    
-    if key not in USER_SETTINGS:
-        console.print(f"[red]Error: Unknown setting '{key}'[/red]")
-        return
-    
-    value = config.get(key, USER_SETTINGS[key]["default"])
-    
-    # Handle secret values
-    display_value = value
-    if USER_SETTINGS[key].get("secret", False) and value:
-        display_value = "********"
-    
-    console.print(f"[cyan]{key}[/cyan] = [green]{display_value}[/green]")
-    console.print(f"[dim]Description: {USER_SETTINGS[key]['description']}[/dim]")
-
-@config_cmd.command("set")
-@click.argument("key", required=True)
-@click.argument("value", required=True)
-def config_set_cmd(key: str, value: str):
-    """Set a configuration setting"""
-    config = get_global_config()
-    
-    # Normalize key to uppercase
-    key = key.upper()
-    
-    if key not in USER_SETTINGS:
-        console.print(f"[red]Error: Unknown setting '{key}'[/red]")
-        console.print(f"[yellow]Available settings: {', '.join(USER_SETTINGS.keys())}[/yellow]")
-        return
-    
-    setting = USER_SETTINGS[key]
-    
-    # Type conversion and validation
-    if setting["type"] == "boolean":
-        if value.lower() in ["true", "yes", "1", "y"]:
-            typed_value = True
-        elif value.lower() in ["false", "no", "0", "n"]:
-            typed_value = False
-        else:
-            console.print(f"[red]Error: Invalid boolean value. Use 'true' or 'false'.[/red]")
-            return
-    elif setting["type"] == "string":
-        typed_value = value
-        
-        # Check if the value should be one of the allowed options
-        if "options" in setting and value not in setting["options"]:
-            console.print(f"[red]Error: Value must be one of: {', '.join(setting['options'])}[/red]")
-            return
-    
-    # Update config
-    config[key] = typed_value
-    save_global_config(config)
-    
-    # Handle secret values for display
-    display_value = typed_value
-    if setting.get("secret", False) and typed_value:
-        display_value = "********"
-        
-    console.print(f"[green]Successfully set[/green] [cyan]{key}[/cyan] = [green]{display_value}[/green]")
-
 @cli.command("profiles")
 def profiles_cmd():
     """Manage browser profiles interactively
@@ -1344,7 +812,6 @@ def profiles_cmd():
 @click.option("--crawler-config", "-C", type=click.Path(exists=True), help="Crawler config file (YAML/JSON)")
 @click.option("--filter-config", "-f", type=click.Path(exists=True), help="Content filter config file")
 @click.option("--extraction-config", "-e", type=click.Path(exists=True), help="Extraction strategy config file")
-@click.option("--json-extract", "-j", is_flag=False, flag_value="", default=None, help="Extract structured data using LLM with optional description")
 @click.option("--schema", "-s", type=click.Path(exists=True), help="JSON schema for extraction")
 @click.option("--browser", "-b", type=str, callback=parse_key_values, help="Browser parameters as key1=value1,key2=value2")
 @click.option("--crawler", "-c", type=str, callback=parse_key_values, help="Crawler parameters as key1=value1,key2=value2")
@@ -1354,7 +821,7 @@ def profiles_cmd():
 @click.option("--verbose", "-v", is_flag=True)
 @click.option("--profile", "-p", help="Use a specific browser profile (by name)")
 def default(url: str, example: bool, browser_config: str, crawler_config: str, filter_config: str, 
-        extraction_config: str, json_extract: str, schema: str, browser: Dict, crawler: Dict,
+        extraction_config: str, schema: str, browser: Dict, crawler: Dict,
         output: str, bypass_cache: bool, question: str, verbose: bool, profile: str):
     """Crawl4AI CLI - Web content extraction tool
 
@@ -1367,15 +834,7 @@ def default(url: str, example: bool, browser_config: str, crawler_config: str, f
         crwl profiles   - Manage browser profiles for identity-based crawling
         crwl crawl      - Crawl a website with advanced options
         crwl cdp        - Launch browser with CDP debugging enabled
-        crwl browser    - Manage builtin browser (start, stop, status, restart)
-        crwl config     - Manage global configuration settings
         crwl examples   - Show more usage examples
-        
-    Configuration Examples:
-        crwl config list                         - List all configuration settings
-        crwl config get DEFAULT_LLM_PROVIDER     - Show current LLM provider
-        crwl config set VERBOSE true             - Enable verbose mode globally
-        crwl config set BROWSER_HEADLESS false   - Default to visible browser
     """
 
     if example:
@@ -1396,8 +855,7 @@ def default(url: str, example: bool, browser_config: str, crawler_config: str, f
         browser_config=browser_config,
         crawler_config=crawler_config,
         filter_config=filter_config,
-        extraction_config=extraction_config,
+        extraction_config=extraction_config, 
-        json_extract=json_extract,
         schema=schema,
         browser=browser,
         crawler=crawler,

crawl4ai/components/crawler_monitor.py

@@ -1,837 +0,0 @@
-import time
-import uuid
-import threading
-import psutil
-from datetime import datetime, timedelta
-from typing import Dict, Optional, List
-import threading
-from rich.console import Console
-from rich.layout import Layout
-from rich.panel import Panel
-from rich.table import Table
-from rich.text import Text
-from rich.live import Live
-from rich import box
-from ..models import CrawlStatus
-
-class TerminalUI:
-    """Terminal user interface for CrawlerMonitor using rich library."""
-    
-    def __init__(self, refresh_rate: float = 1.0, max_width: int = 120):
-        """
-        Initialize the terminal UI.
-        
-        Args:
-            refresh_rate: How often to refresh the UI (in seconds)
-            max_width: Maximum width of the UI in characters
-        """
-        self.console = Console(width=max_width)
-        self.layout = Layout()
-        self.refresh_rate = refresh_rate
-        self.stop_event = threading.Event()
-        self.ui_thread = None
-        self.monitor = None  # Will be set by CrawlerMonitor
-        self.max_width = max_width
-        
-        # Setup layout - vertical layout (top to bottom)
-        self.layout.split(
-            Layout(name="header", size=3),
-            Layout(name="pipeline_status", size=10),
-            Layout(name="task_details", ratio=1),
-            Layout(name="footer", size=3)  # Increased footer size to fit all content
-        )
-        
-    def start(self, monitor):
-        """Start the UI thread."""
-        self.monitor = monitor
-        self.stop_event.clear()
-        self.ui_thread = threading.Thread(target=self._ui_loop)
-        self.ui_thread.daemon = True
-        self.ui_thread.start()
-        
-    def stop(self):
-        """Stop the UI thread."""
-        if self.ui_thread and self.ui_thread.is_alive():
-            self.stop_event.set()
-            # Only try to join if we're not in the UI thread
-            # This prevents "cannot join current thread" errors
-            if threading.current_thread() != self.ui_thread:
-                self.ui_thread.join(timeout=5.0)
-    
-    def _ui_loop(self):
-        """Main UI rendering loop."""
-        import sys
-        import select
-        import termios
-        import tty
-        
-        # Setup terminal for non-blocking input
-        old_settings = termios.tcgetattr(sys.stdin)
-        try:
-            tty.setcbreak(sys.stdin.fileno())
-            
-            # Use Live display to render the UI
-            with Live(self.layout, refresh_per_second=1/self.refresh_rate, screen=True) as live:
-                self.live = live  # Store the live display for updates
-                
-                # Main UI loop
-                while not self.stop_event.is_set():
-                    self._update_display()
-                    
-                    # Check for key press (non-blocking)
-                    if select.select([sys.stdin], [], [], 0)[0]:
-                        key = sys.stdin.read(1)
-                        # Check for 'q' to quit
-                        if key == 'q':
-                            # Signal stop but don't call monitor.stop() from UI thread
-                            # as it would cause the thread to try to join itself
-                            self.stop_event.set()
-                            self.monitor.is_running = False
-                            break
-                    
-                    time.sleep(self.refresh_rate)
-                    
-                    # Just check if the monitor was stopped
-                    if not self.monitor.is_running:
-                        break
-        finally:
-            # Restore terminal settings
-            termios.tcsetattr(sys.stdin, termios.TCSADRAIN, old_settings)
-    
-    def _update_display(self):
-        """Update the terminal display with current statistics."""
-        if not self.monitor:
-            return
-            
-        # Update crawler status panel
-        self.layout["header"].update(self._create_status_panel())
-        
-        # Update pipeline status panel and task details panel
-        self.layout["pipeline_status"].update(self._create_pipeline_panel())
-        self.layout["task_details"].update(self._create_task_details_panel())
-        
-        # Update footer
-        self.layout["footer"].update(self._create_footer())
-    
-    def _create_status_panel(self) -> Panel:
-        """Create the crawler status panel."""
-        summary = self.monitor.get_summary()
-        
-        # Format memory status with icon
-        memory_status = self.monitor.get_memory_status()
-        memory_icon = "🟢"  # Default NORMAL
-        if memory_status == "PRESSURE":
-            memory_icon = "🟠"
-        elif memory_status == "CRITICAL":
-            memory_icon = "🔴"
-        
-        # Get current memory usage
-        current_memory = psutil.Process().memory_info().rss / (1024 * 1024)  # MB
-        memory_percent = (current_memory / psutil.virtual_memory().total) * 100
-        
-        # Format runtime
-        runtime = self.monitor._format_time(time.time() - self.monitor.start_time if self.monitor.start_time else 0)
-        
-        # Create the status text
-        status_text = Text()
-        status_text.append(f"Web Crawler Dashboard | Runtime: {runtime} | Memory: {memory_percent:.1f}% {memory_icon}\n")
-        status_text.append(f"Status: {memory_status} | URLs: {summary['urls_completed']}/{summary['urls_total']} | ")
-        status_text.append(f"Peak Mem: {summary['peak_memory_percent']:.1f}% at {self.monitor._format_time(summary['peak_memory_time'])}")
-        
-        return Panel(status_text, title="Crawler Status", border_style="blue")
-    
-    def _create_pipeline_panel(self) -> Panel:
-        """Create the pipeline status panel."""
-        summary = self.monitor.get_summary()
-        queue_stats = self.monitor.get_queue_stats()
-        
-        # Create a table for status counts
-        table = Table(show_header=True, box=None)
-        table.add_column("Status", style="cyan")
-        table.add_column("Count", justify="right")
-        table.add_column("Percentage", justify="right")
-        table.add_column("Stat", style="cyan")
-        table.add_column("Value", justify="right")
-        
-        # Calculate overall progress
-        progress = f"{summary['urls_completed']}/{summary['urls_total']}"
-        progress_percent = f"{summary['completion_percentage']:.1f}%"
-        
-        # Add rows for each status
-        table.add_row(
-            "Overall Progress", 
-            progress, 
-            progress_percent,
-            "Est. Completion", 
-            summary.get('estimated_completion_time', "N/A")
-        )
-        
-        # Add rows for each status
-        status_counts = summary['status_counts']
-        total = summary['urls_total'] or 1  # Avoid division by zero
-        
-        # Status rows
-        table.add_row(
-            "Completed", 
-            str(status_counts.get(CrawlStatus.COMPLETED.name, 0)),
-            f"{status_counts.get(CrawlStatus.COMPLETED.name, 0) / total * 100:.1f}%",
-            "Avg. Time/URL",
-            f"{summary.get('avg_task_duration', 0):.2f}s"
-        )
-        
-        table.add_row(
-            "Failed", 
-            str(status_counts.get(CrawlStatus.FAILED.name, 0)),
-            f"{status_counts.get(CrawlStatus.FAILED.name, 0) / total * 100:.1f}%",
-            "Concurrent Tasks",
-            str(status_counts.get(CrawlStatus.IN_PROGRESS.name, 0))
-        )
-        
-        table.add_row(
-            "In Progress", 
-            str(status_counts.get(CrawlStatus.IN_PROGRESS.name, 0)),
-            f"{status_counts.get(CrawlStatus.IN_PROGRESS.name, 0) / total * 100:.1f}%",
-            "Queue Size",
-            str(queue_stats['total_queued'])
-        )
-        
-        table.add_row(
-            "Queued", 
-            str(status_counts.get(CrawlStatus.QUEUED.name, 0)),
-            f"{status_counts.get(CrawlStatus.QUEUED.name, 0) / total * 100:.1f}%",
-            "Max Wait Time",
-            f"{queue_stats['highest_wait_time']:.1f}s"
-        )
-        
-        # Requeued is a special case as it's not a status
-        requeued_count = summary.get('requeued_count', 0)
-        table.add_row(
-            "Requeued", 
-            str(requeued_count),
-            f"{summary.get('requeue_rate', 0):.1f}%",
-            "Avg Wait Time",
-            f"{queue_stats['avg_wait_time']:.1f}s"
-        )
-        
-        # Add empty row for spacing
-        table.add_row(
-            "", 
-            "",
-            "",
-            "Requeue Rate",
-            f"{summary.get('requeue_rate', 0):.1f}%"
-        )
-        
-        return Panel(table, title="Pipeline Status", border_style="green")
-    
-    def _create_task_details_panel(self) -> Panel:
-        """Create the task details panel."""
-        # Create a table for task details
-        table = Table(show_header=True, expand=True)
-        table.add_column("Task ID", style="cyan", no_wrap=True, width=10)
-        table.add_column("URL", style="blue", ratio=3)
-        table.add_column("Status", style="green", width=15)
-        table.add_column("Memory", justify="right", width=8)
-        table.add_column("Peak", justify="right", width=8)
-        table.add_column("Duration", justify="right", width=10)
-        
-        # Get all task stats
-        task_stats = self.monitor.get_all_task_stats()
-        
-        # Add summary row
-        active_tasks = sum(1 for stats in task_stats.values() 
-                          if stats['status'] == CrawlStatus.IN_PROGRESS.name)
-        
-        total_memory = sum(stats['memory_usage'] for stats in task_stats.values())
-        total_peak = sum(stats['peak_memory'] for stats in task_stats.values())
-        
-        # Summary row with separators
-        table.add_row(
-            "SUMMARY", 
-            f"Total: {len(task_stats)}", 
-            f"Active: {active_tasks}",
-            f"{total_memory:.1f}",
-            f"{total_peak:.1f}",
-            "N/A"
-        )
-        
-        # Add a separator
-        table.add_row("—" * 10, "—" * 20, "—" * 10, "—" * 8, "—" * 8, "—" * 10)
-        
-        # Status icons
-        status_icons = {
-            CrawlStatus.QUEUED.name: "⏳",
-            CrawlStatus.IN_PROGRESS.name: "🔄",
-            CrawlStatus.COMPLETED.name: "✅",
-            CrawlStatus.FAILED.name: "❌"
-        }
-        
-        # Calculate how many rows we can display based on available space
-        # We can display more rows now that we have a dedicated panel
-        display_count = min(len(task_stats), 20)  # Display up to 20 tasks
-        
-        # Add rows for each task
-        for task_id, stats in sorted(
-            list(task_stats.items())[:display_count],
-            # Sort: 1. IN_PROGRESS first, 2. QUEUED, 3. COMPLETED/FAILED by recency
-            key=lambda x: (
-                0 if x[1]['status'] == CrawlStatus.IN_PROGRESS.name else 
-                1 if x[1]['status'] == CrawlStatus.QUEUED.name else 
-                2,
-                -1 * (x[1].get('end_time', 0) or 0)  # Most recent first
-            )
-        ):
-            # Truncate task_id and URL for display
-            short_id = task_id[:8]
-            url = stats['url']
-            if len(url) > 50:  # Allow longer URLs in the dedicated panel
-                url = url[:47] + "..."
-                
-            # Format status with icon
-            status = f"{status_icons.get(stats['status'], '?')} {stats['status']}"
-            
-            # Add row
-            table.add_row(
-                short_id,
-                url,
-                status,
-                f"{stats['memory_usage']:.1f}",
-                f"{stats['peak_memory']:.1f}",
-                stats['duration'] if 'duration' in stats else "0:00"
-            )
-        
-        return Panel(table, title="Task Details", border_style="yellow")
-    
-    def _create_footer(self) -> Panel:
-        """Create the footer panel."""
-        from rich.columns import Columns
-        from rich.align import Align
-        
-        memory_status = self.monitor.get_memory_status()
-        memory_icon = "🟢"  # Default NORMAL
-        if memory_status == "PRESSURE":
-            memory_icon = "🟠"
-        elif memory_status == "CRITICAL":
-            memory_icon = "🔴"
-        
-        # Left section - memory status
-        left_text = Text()
-        left_text.append("Memory Status: ", style="bold")
-        status_style = "green" if memory_status == "NORMAL" else "yellow" if memory_status == "PRESSURE" else "red bold"
-        left_text.append(f"{memory_icon} {memory_status}", style=status_style)
-        
-        # Center section - copyright
-        center_text = Text("© Crawl4AI 2025 | Made by UnclecCode", style="cyan italic")
-        
-        # Right section - quit instruction
-        right_text = Text()
-        right_text.append("Press ", style="bold")
-        right_text.append("q", style="white on blue")
-        right_text.append(" to quit", style="bold")
-        
-        # Create columns with the three sections
-        footer_content = Columns(
-            [
-                Align.left(left_text),
-                Align.center(center_text),
-                Align.right(right_text)
-            ],
-            expand=True
-        )
-        
-        # Create a more visible footer panel
-        return Panel(
-            footer_content,
-            border_style="white",
-            padding=(0, 1)  # Add padding for better visibility
-        )
-
-
-class CrawlerMonitor:
-    """
-    Comprehensive monitoring and visualization system for tracking web crawler operations in real-time.
-    Provides a terminal-based dashboard that displays task statuses, memory usage, queue statistics,
-    and performance metrics.
-    """
-    
-    def __init__(
-        self,
-        urls_total: int = 0,
-        refresh_rate: float = 1.0,
-        enable_ui: bool = True,
-        max_width: int = 120
-    ):
-        """
-        Initialize the CrawlerMonitor.
-        
-        Args:
-            urls_total: Total number of URLs to be crawled
-            refresh_rate: How often to refresh the UI (in seconds)
-            enable_ui: Whether to display the terminal UI
-            max_width: Maximum width of the UI in characters
-        """
-        # Core monitoring attributes
-        self.stats = {}  # Task ID -> stats dict
-        self.memory_status = "NORMAL"
-        self.start_time = None
-        self.end_time = None
-        self.is_running = False
-        self.queue_stats = {
-            "total_queued": 0,
-            "highest_wait_time": 0.0,
-            "avg_wait_time": 0.0
-        }
-        self.urls_total = urls_total
-        self.urls_completed = 0
-        self.peak_memory_percent = 0.0
-        self.peak_memory_time = 0.0
-        
-        # Status counts
-        self.status_counts = {
-            CrawlStatus.QUEUED.name: 0,
-            CrawlStatus.IN_PROGRESS.name: 0,
-            CrawlStatus.COMPLETED.name: 0,
-            CrawlStatus.FAILED.name: 0
-        }
-        
-        # Requeue tracking
-        self.requeued_count = 0
-        
-        # Thread-safety
-        self._lock = threading.RLock()
-        
-        # Terminal UI
-        self.enable_ui = enable_ui
-        self.terminal_ui = TerminalUI(
-            refresh_rate=refresh_rate, 
-            max_width=max_width
-        ) if enable_ui else None
-    
-    def start(self):
-        """
-        Start the monitoring session.
-        
-        - Initializes the start_time
-        - Sets is_running to True
-        - Starts the terminal UI if enabled
-        """
-        with self._lock:
-            self.start_time = time.time()
-            self.is_running = True
-            
-            # Start the terminal UI
-            if self.enable_ui and self.terminal_ui:
-                self.terminal_ui.start(self)
-    
-    def stop(self):
-        """
-        Stop the monitoring session.
-        
-        - Records end_time
-        - Sets is_running to False
-        - Stops the terminal UI
-        - Generates final summary statistics
-        """
-        with self._lock:
-            self.end_time = time.time()
-            self.is_running = False
-            
-            # Stop the terminal UI
-            if self.enable_ui and self.terminal_ui:
-                self.terminal_ui.stop()
-    
-    def add_task(self, task_id: str, url: str):
-        """
-        Register a new task with the monitor.
-        
-        Args:
-            task_id: Unique identifier for the task
-            url: URL being crawled
-            
-        The task is initialized with:
-            - status: QUEUED
-            - url: The URL to crawl
-            - enqueue_time: Current time
-            - memory_usage: 0
-            - peak_memory: 0
-            - wait_time: 0
-            - retry_count: 0
-        """
-        with self._lock:
-            self.stats[task_id] = {
-                "task_id": task_id,
-                "url": url,
-                "status": CrawlStatus.QUEUED.name,
-                "enqueue_time": time.time(),
-                "start_time": None,
-                "end_time": None,
-                "memory_usage": 0.0,
-                "peak_memory": 0.0,
-                "error_message": "",
-                "wait_time": 0.0,
-                "retry_count": 0,
-                "duration": "0:00",
-                "counted_requeue": False
-            }
-            
-            # Update status counts
-            self.status_counts[CrawlStatus.QUEUED.name] += 1
-    
-    def update_task(
-        self, 
-        task_id: str, 
-        status: Optional[CrawlStatus] = None,
-        start_time: Optional[float] = None,
-        end_time: Optional[float] = None,
-        memory_usage: Optional[float] = None,
-        peak_memory: Optional[float] = None,
-        error_message: Optional[str] = None,
-        retry_count: Optional[int] = None,
-        wait_time: Optional[float] = None
-    ):
-        """
-        Update statistics for a specific task.
-        
-        Args:
-            task_id: Unique identifier for the task
-            status: New status (QUEUED, IN_PROGRESS, COMPLETED, FAILED)
-            start_time: When task execution started
-            end_time: When task execution ended
-            memory_usage: Current memory usage in MB
-            peak_memory: Maximum memory usage in MB
-            error_message: Error description if failed
-            retry_count: Number of retry attempts
-            wait_time: Time spent in queue
-            
-        Updates task statistics and updates status counts.
-        If status changes, decrements old status count and 
-        increments new status count.
-        """
-        with self._lock:
-            # Check if task exists
-            if task_id not in self.stats:
-                return
-            
-            task_stats = self.stats[task_id]
-            
-            # Update status counts if status is changing
-            old_status = task_stats["status"]
-            if status and status.name != old_status:
-                self.status_counts[old_status] -= 1
-                self.status_counts[status.name] += 1
-                
-                # Track completion
-                if status == CrawlStatus.COMPLETED:
-                    self.urls_completed += 1
-                
-                # Track requeues
-                if old_status in [CrawlStatus.COMPLETED.name, CrawlStatus.FAILED.name] and not task_stats.get("counted_requeue", False):
-                    self.requeued_count += 1
-                    task_stats["counted_requeue"] = True
-            
-            # Update task statistics
-            if status:
-                task_stats["status"] = status.name
-            if start_time is not None:
-                task_stats["start_time"] = start_time
-            if end_time is not None:
-                task_stats["end_time"] = end_time
-            if memory_usage is not None:
-                task_stats["memory_usage"] = memory_usage
-                
-                # Update peak memory if necessary
-                current_percent = (memory_usage / psutil.virtual_memory().total) * 100
-                if current_percent > self.peak_memory_percent:
-                    self.peak_memory_percent = current_percent
-                    self.peak_memory_time = time.time()
-                
-            if peak_memory is not None:
-                task_stats["peak_memory"] = peak_memory
-            if error_message is not None:
-                task_stats["error_message"] = error_message
-            if retry_count is not None:
-                task_stats["retry_count"] = retry_count
-            if wait_time is not None:
-                task_stats["wait_time"] = wait_time
-            
-            # Calculate duration
-            if task_stats["start_time"]:
-                end = task_stats["end_time"] or time.time()
-                duration = end - task_stats["start_time"]
-                task_stats["duration"] = self._format_time(duration)
-    
-    def update_memory_status(self, status: str):
-        """
-        Update the current memory status.
-        
-        Args:
-            status: Memory status (NORMAL, PRESSURE, CRITICAL, or custom)
-            
-        Also updates the UI to reflect the new status.
-        """
-        with self._lock:
-            self.memory_status = status
-    
-    def update_queue_statistics(
-        self,
-        total_queued: int,
-        highest_wait_time: float,
-        avg_wait_time: float
-    ):
-        """
-        Update statistics related to the task queue.
-        
-        Args:
-            total_queued: Number of tasks currently in queue
-            highest_wait_time: Longest wait time of any queued task
-            avg_wait_time: Average wait time across all queued tasks
-        """
-        with self._lock:
-            self.queue_stats = {
-                "total_queued": total_queued,
-                "highest_wait_time": highest_wait_time,
-                "avg_wait_time": avg_wait_time
-            }
-    
-    def get_task_stats(self, task_id: str) -> Dict:
-        """
-        Get statistics for a specific task.
-        
-        Args:
-            task_id: Unique identifier for the task
-            
-        Returns:
-            Dictionary containing all task statistics
-        """
-        with self._lock:
-            return self.stats.get(task_id, {}).copy()
-    
-    def get_all_task_stats(self) -> Dict[str, Dict]:
-        """
-        Get statistics for all tasks.
-        
-        Returns:
-            Dictionary mapping task_ids to their statistics
-        """
-        with self._lock:
-            return self.stats.copy()
-    
-    def get_memory_status(self) -> str:
-        """
-        Get the current memory status.
-        
-        Returns:
-            Current memory status string
-        """
-        with self._lock:
-            return self.memory_status
-    
-    def get_queue_stats(self) -> Dict:
-        """
-        Get current queue statistics.
-        
-        Returns:
-            Dictionary with queue statistics including:
-            - total_queued: Number of tasks in queue
-            - highest_wait_time: Longest wait time
-            - avg_wait_time: Average wait time
-        """
-        with self._lock:
-            return self.queue_stats.copy()
-    
-    def get_summary(self) -> Dict:
-        """
-        Get a summary of all crawler statistics.
-        
-        Returns:
-            Dictionary containing:
-            - runtime: Total runtime in seconds
-            - urls_total: Total URLs to process
-            - urls_completed: Number of completed URLs
-            - completion_percentage: Percentage complete
-            - status_counts: Count of tasks in each status
-            - memory_status: Current memory status
-            - peak_memory_percent: Highest memory usage
-            - peak_memory_time: When peak memory occurred
-            - avg_task_duration: Average task processing time
-            - estimated_completion_time: Projected finish time
-            - requeue_rate: Percentage of tasks requeued
-        """
-        with self._lock:
-            # Calculate runtime
-            current_time = time.time()
-            runtime = current_time - (self.start_time or current_time)
-            
-            # Calculate completion percentage
-            completion_percentage = 0
-            if self.urls_total > 0:
-                completion_percentage = (self.urls_completed / self.urls_total) * 100
-            
-            # Calculate average task duration for completed tasks
-            completed_tasks = [
-                task for task in self.stats.values() 
-                if task["status"] == CrawlStatus.COMPLETED.name and task.get("start_time") and task.get("end_time")
-            ]
-            
-            avg_task_duration = 0
-            if completed_tasks:
-                total_duration = sum(task["end_time"] - task["start_time"] for task in completed_tasks)
-                avg_task_duration = total_duration / len(completed_tasks)
-            
-            # Calculate requeue rate
-            requeue_rate = 0
-            if len(self.stats) > 0:
-                requeue_rate = (self.requeued_count / len(self.stats)) * 100
-            
-            # Calculate estimated completion time
-            estimated_completion_time = "N/A"
-            if avg_task_duration > 0 and self.urls_total > 0 and self.urls_completed > 0:
-                remaining_tasks = self.urls_total - self.urls_completed
-                estimated_seconds = remaining_tasks * avg_task_duration
-                estimated_completion_time = self._format_time(estimated_seconds)
-            
-            return {
-                "runtime": runtime,
-                "urls_total": self.urls_total,
-                "urls_completed": self.urls_completed,
-                "completion_percentage": completion_percentage,
-                "status_counts": self.status_counts.copy(),
-                "memory_status": self.memory_status,
-                "peak_memory_percent": self.peak_memory_percent,
-                "peak_memory_time": self.peak_memory_time,
-                "avg_task_duration": avg_task_duration,
-                "estimated_completion_time": estimated_completion_time,
-                "requeue_rate": requeue_rate,
-                "requeued_count": self.requeued_count
-            }
-    
-    def render(self):
-        """
-        Render the terminal UI.
-        
-        This is the main UI rendering loop that:
-        1. Updates all statistics
-        2. Formats the display
-        3. Renders the ASCII interface
-        4. Handles keyboard input
-        
-        Note: The actual rendering is handled by the TerminalUI class
-        which uses the rich library's Live display.
-        """
-        if self.enable_ui and self.terminal_ui:
-            # Force an update of the UI
-            if hasattr(self.terminal_ui, '_update_display'):
-                self.terminal_ui._update_display()
-    
-    def _format_time(self, seconds: float) -> str:
-        """
-        Format time in hours:minutes:seconds.
-        
-        Args:
-            seconds: Time in seconds
-            
-        Returns:
-            Formatted time string (e.g., "1:23:45")
-        """
-        delta = timedelta(seconds=int(seconds))
-        hours, remainder = divmod(delta.seconds, 3600)
-        minutes, seconds = divmod(remainder, 60)
-        
-        if hours > 0:
-            return f"{hours}:{minutes:02}:{seconds:02}"
-        else:
-            return f"{minutes}:{seconds:02}"
-    
-    def _calculate_estimated_completion(self) -> str:
-        """
-        Calculate estimated completion time based on current progress.
-        
-        Returns:
-            Formatted time string
-        """
-        summary = self.get_summary()
-        return summary.get("estimated_completion_time", "N/A")
-
-
-# Example code for testing
-if __name__ == "__main__":
-    # Initialize the monitor
-    monitor = CrawlerMonitor(urls_total=100)
-    
-    # Start monitoring
-    monitor.start()
-    
-    try:
-        # Simulate some tasks
-        for i in range(20):
-            task_id = str(uuid.uuid4())
-            url = f"https://example.com/page{i}"
-            monitor.add_task(task_id, url)
-            
-            # Simulate 20% of tasks are already running
-            if i < 4:
-                monitor.update_task(
-                    task_id=task_id,
-                    status=CrawlStatus.IN_PROGRESS,
-                    start_time=time.time() - 30,  # Started 30 seconds ago
-                    memory_usage=10.5
-                )
-                
-            # Simulate 10% of tasks are completed
-            if i >= 4 and i < 6:
-                start_time = time.time() - 60
-                end_time = time.time() - 15
-                monitor.update_task(
-                    task_id=task_id,
-                    status=CrawlStatus.IN_PROGRESS,
-                    start_time=start_time,
-                    memory_usage=8.2
-                )
-                monitor.update_task(
-                    task_id=task_id,
-                    status=CrawlStatus.COMPLETED,
-                    end_time=end_time,
-                    memory_usage=0,
-                    peak_memory=15.7
-                )
-                
-            # Simulate 5% of tasks fail
-            if i >= 6 and i < 7:
-                start_time = time.time() - 45
-                end_time = time.time() - 20
-                monitor.update_task(
-                    task_id=task_id,
-                    status=CrawlStatus.IN_PROGRESS,
-                    start_time=start_time,
-                    memory_usage=12.3
-                )
-                monitor.update_task(
-                    task_id=task_id,
-                    status=CrawlStatus.FAILED,
-                    end_time=end_time,
-                    memory_usage=0,
-                    peak_memory=18.2,
-                    error_message="Connection timeout"
-                )
-        
-        # Simulate memory pressure
-        monitor.update_memory_status("PRESSURE")
-        
-        # Simulate queue statistics
-        monitor.update_queue_statistics(
-            total_queued=16,  # 20 - 4 (in progress)
-            highest_wait_time=120.5,
-            avg_wait_time=60.2
-        )
-        
-        # Keep the monitor running for a demonstration
-        print("Crawler Monitor is running. Press 'q' to exit.")
-        while monitor.is_running:
-            time.sleep(0.1)
-            
-    except KeyboardInterrupt:
-        print("\nExiting crawler monitor...")
-    finally:
-        # Stop the monitor
-        monitor.stop()
-        print("Crawler monitor exited successfully.")

crawl4ai/config.py

@@ -4,8 +4,7 @@ from dotenv import load_dotenv
 load_dotenv()  # Load environment variables from .env file
 
 # Default provider, ONLY used when the extraction strategy is LLMExtractionStrategy
-DEFAULT_PROVIDER = "openai/gpt-4o"
+DEFAULT_PROVIDER = "openai/gpt-4o-mini"
-DEFAULT_PROVIDER_API_KEY = "OPENAI_API_KEY"
 MODEL_REPO_BRANCH = "new-release-0.0.2"
 # Provider-model dictionary, ONLY used when the extraction strategy is LLMExtractionStrategy
 PROVIDER_MODELS = {
@@ -93,46 +92,3 @@ SHOW_DEPRECATION_WARNINGS = True
 SCREENSHOT_HEIGHT_TRESHOLD = 10000
 PAGE_TIMEOUT = 60000
 DOWNLOAD_PAGE_TIMEOUT = 60000
-
-# Global user settings with descriptions and default values
-USER_SETTINGS = {
-    "DEFAULT_LLM_PROVIDER": {
-        "default": "openai/gpt-4o",
-        "description": "Default LLM provider in 'company/model' format (e.g., 'openai/gpt-4o', 'anthropic/claude-3-sonnet')",
-        "type": "string"
-    },
-    "DEFAULT_LLM_PROVIDER_TOKEN": {
-        "default": "",
-        "description": "API token for the default LLM provider",
-        "type": "string",
-        "secret": True
-    },
-    "VERBOSE": {
-        "default": False,
-        "description": "Enable verbose output for all commands",
-        "type": "boolean"
-    },
-    "BROWSER_HEADLESS": {
-        "default": True,
-        "description": "Run browser in headless mode by default",
-        "type": "boolean"
-    },
-    "BROWSER_TYPE": {
-        "default": "chromium",
-        "description": "Default browser type (chromium or firefox)",
-        "type": "string",
-        "options": ["chromium", "firefox"]
-    },
-    "CACHE_MODE": {
-        "default": "bypass",
-        "description": "Default cache mode (bypass, use, or refresh)",
-        "type": "string",
-        "options": ["bypass", "use", "refresh"]
-    },
-    "USER_AGENT_MODE": {
-        "default": "default",
-        "description": "Default user agent mode (default, random, or mobile)",
-        "type": "string",
-        "options": ["default", "random", "mobile"]
-    }
-}

crawl4ai/content_scraping_strategy.py

@@ -860,12 +860,6 @@ class WebScrapingStrategy(ContentScrapingStrategy):
         soup = BeautifulSoup(html, parser_type)
         body = soup.body
         base_domain = get_base_domain(url)
-        
-        # Early removal of all images if exclude_all_images is set
-        # This happens before any processing to minimize memory usage
-        if kwargs.get("exclude_all_images", False):
-            for img in body.find_all('img'):
-                img.decompose()
 
         try:
             meta = extract_metadata("", soup)
@@ -1497,13 +1491,6 @@ class LXMLWebScrapingStrategy(WebScrapingStrategy):
             body = doc
 
             base_domain = get_base_domain(url)
-            
-            # Early removal of all images if exclude_all_images is set
-            # This is more efficient in lxml as we remove elements before any processing
-            if kwargs.get("exclude_all_images", False):
-                for img in body.xpath('//img'):
-                    if img.getparent() is not None:
-                        img.getparent().remove(img)
 
             # Add comment removal
             if kwargs.get("remove_comments", False):

crawl4ai/crawlers/google_search/crawler.py

@@ -1,6 +1,6 @@
 from crawl4ai import BrowserConfig, AsyncWebCrawler, CrawlerRunConfig, CacheMode
 from crawl4ai.hub import BaseCrawler
-from crawl4ai.utils import optimize_html, get_home_folder, preprocess_html_for_schema
+from crawl4ai.utils import optimize_html, get_home_folder
 from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
 from pathlib import Path
 import json
@@ -68,8 +68,7 @@ class GoogleSearchCrawler(BaseCrawler):
         home_dir = get_home_folder() if not schema_cache_path else schema_cache_path
         os.makedirs(f"{home_dir}/schema", exist_ok=True)
 
-        # cleaned_html = optimize_html(html, threshold=100)
+        cleaned_html = optimize_html(html, threshold=100)
-        cleaned_html = preprocess_html_for_schema(html) 
 
         organic_schema = None
         if os.path.exists(f"{home_dir}/schema/organic_schema.json"):

crawl4ai/extraction_strategy.py

@@ -5,11 +5,9 @@ from concurrent.futures import ThreadPoolExecutor, as_completed
 import json
 import time
 
-from .prompts import PROMPT_EXTRACT_BLOCKS, PROMPT_EXTRACT_BLOCKS_WITH_INSTRUCTION, PROMPT_EXTRACT_SCHEMA_WITH_INSTRUCTION, JSON_SCHEMA_BUILDER_XPATH, PROMPT_EXTRACT_INFERRED_SCHEMA
+from .prompts import PROMPT_EXTRACT_BLOCKS, PROMPT_EXTRACT_BLOCKS_WITH_INSTRUCTION, PROMPT_EXTRACT_SCHEMA_WITH_INSTRUCTION, JSON_SCHEMA_BUILDER_XPATH
 from .config import (
-    DEFAULT_PROVIDER,
+    DEFAULT_PROVIDER, CHUNK_TOKEN_THRESHOLD,
-    DEFAULT_PROVIDER_API_KEY,
-    CHUNK_TOKEN_THRESHOLD,
     OVERLAP_RATE,
     WORD_TOKEN_RATE,
 )
@@ -36,7 +34,7 @@ from .model_loader import (
     calculate_batch_size
 )
 
-from .types import LLMConfig, create_llm_config
+from .types import LLMConfig
 
 from functools import partial
 import numpy as np
@@ -509,7 +507,6 @@ class LLMExtractionStrategy(ExtractionStrategy):
         word_token_rate=WORD_TOKEN_RATE,
         apply_chunking=True,
         input_format: str = "markdown",
-        force_json_response=False,
         verbose=False,
         # Deprecated arguments
         provider: str = DEFAULT_PROVIDER,
@@ -530,10 +527,9 @@ class LLMExtractionStrategy(ExtractionStrategy):
             overlap_rate: Overlap between chunks.
             word_token_rate: Word to token conversion rate.
             apply_chunking: Whether to apply chunking.
-            input_format: Content format to use for extraction.
-                            Options: "markdown" (default), "html", "fit_markdown"
-            force_json_response: Whether to force a JSON response from the LLM.
             verbose: Whether to print verbose output.
+            usages: List of individual token usages.
+            total_usage: Accumulated token usage.
 
             # Deprecated arguments, will be removed very soon
             provider: The provider to use for extraction. It follows the format <provider_name>/<model_name>, e.g., "ollama/llama3.3".
@@ -544,17 +540,11 @@ class LLMExtractionStrategy(ExtractionStrategy):
         """
         super().__init__( input_format=input_format, **kwargs)
         self.llm_config = llm_config
-        if not self.llm_config:
-            self.llm_config = create_llm_config(
-                provider=DEFAULT_PROVIDER,
-                api_token=os.environ.get(DEFAULT_PROVIDER_API_KEY),
-            )
         self.instruction = instruction
         self.extract_type = extraction_type
         self.schema = schema
         if schema:
             self.extract_type = "schema"
-        self.force_json_response = force_json_response
         self.chunk_token_threshold = chunk_token_threshold or CHUNK_TOKEN_THRESHOLD
         self.overlap_rate = overlap_rate
         self.word_token_rate = word_token_rate
@@ -618,97 +608,64 @@ class LLMExtractionStrategy(ExtractionStrategy):
             variable_values["SCHEMA"] = json.dumps(self.schema, indent=2) # if type of self.schema is dict else self.schema
             prompt_with_variables = PROMPT_EXTRACT_SCHEMA_WITH_INSTRUCTION
 
-        if self.extract_type == "schema" and not self.schema:
-            prompt_with_variables = PROMPT_EXTRACT_INFERRED_SCHEMA
-
         for variable in variable_values:
             prompt_with_variables = prompt_with_variables.replace(
                 "{" + variable + "}", variable_values[variable]
             )
 
+        response = perform_completion_with_backoff(
+            self.llm_config.provider,
+            prompt_with_variables,
+            self.llm_config.api_token,
+            base_url=self.llm_config.base_url,
+            extra_args=self.extra_args,
+        )  # , json_response=self.extract_type == "schema")
+        # Track usage
+        usage = TokenUsage(
+            completion_tokens=response.usage.completion_tokens,
+            prompt_tokens=response.usage.prompt_tokens,
+            total_tokens=response.usage.total_tokens,
+            completion_tokens_details=response.usage.completion_tokens_details.__dict__
+            if response.usage.completion_tokens_details
+            else {},
+            prompt_tokens_details=response.usage.prompt_tokens_details.__dict__
+            if response.usage.prompt_tokens_details
+            else {},
+        )
+        self.usages.append(usage)
+
+        # Update totals
+        self.total_usage.completion_tokens += usage.completion_tokens
+        self.total_usage.prompt_tokens += usage.prompt_tokens
+        self.total_usage.total_tokens += usage.total_tokens
+
         try:
-            response = perform_completion_with_backoff(
+            blocks = extract_xml_data(["blocks"], response.choices[0].message.content)[
-                self.llm_config.provider,
+                "blocks"
-                prompt_with_variables,
-                self.llm_config.api_token,
-                base_url=self.llm_config.base_url,
-                json_response=self.force_json_response,
-                extra_args=self.extra_args,
-            )  # , json_response=self.extract_type == "schema")
-            # Track usage
-            usage = TokenUsage(
-                completion_tokens=response.usage.completion_tokens,
-                prompt_tokens=response.usage.prompt_tokens,
-                total_tokens=response.usage.total_tokens,
-                completion_tokens_details=response.usage.completion_tokens_details.__dict__
-                if response.usage.completion_tokens_details
-                else {},
-                prompt_tokens_details=response.usage.prompt_tokens_details.__dict__
-                if response.usage.prompt_tokens_details
-                else {},
-            )
-            self.usages.append(usage)
-
-            # Update totals
-            self.total_usage.completion_tokens += usage.completion_tokens
-            self.total_usage.prompt_tokens += usage.prompt_tokens
-            self.total_usage.total_tokens += usage.total_tokens
-
-            try:
-                response = response.choices[0].message.content
-                blocks = None
-
-                if self.force_json_response:
-                    blocks = json.loads(response)
-                    if isinstance(blocks, dict):
-                        # If it has only one key which calue is list then assign that to blocks, exampled: {"news": [..]}
-                        if len(blocks) == 1 and isinstance(list(blocks.values())[0], list):
-                            blocks = list(blocks.values())[0]
-                        else:
-                            # If it has only one key which value is not list then assign that to blocks, exampled: { "article_id": "1234", ... }
-                            blocks = [blocks]
-                    elif isinstance(blocks, list):
-                        # If it is a list then assign that to blocks
-                        blocks = blocks
-                else: 
-                    # blocks = extract_xml_data(["blocks"], response.choices[0].message.content)["blocks"]
-                    blocks = extract_xml_data(["blocks"], response)["blocks"]
-                    blocks = json.loads(blocks)
-
-                for block in blocks:
-                    block["error"] = False
-            except Exception:
-                parsed, unparsed = split_and_parse_json_objects(
-                    response.choices[0].message.content
-                )
-                blocks = parsed
-                if unparsed:
-                    blocks.append(
-                        {"index": 0, "error": True, "tags": ["error"], "content": unparsed}
-                    )
-
-            if self.verbose:
-                print(
-                    "[LOG] Extracted",
-                    len(blocks),
-                    "blocks from URL:",
-                    url,
-                    "block index:",
-                    ix,
-                )
-            return blocks
-        except Exception as e:
-            if self.verbose:
-                print(f"[LOG] Error in LLM extraction: {e}")
-            # Add error information to extracted_content
-            return [
-                {
-                    "index": ix,
-                    "error": True,
-                    "tags": ["error"],
-                    "content": str(e),
-                }
             ]
+            blocks = json.loads(blocks)
+            for block in blocks:
+                block["error"] = False
+        except Exception:
+            parsed, unparsed = split_and_parse_json_objects(
+                response.choices[0].message.content
+            )
+            blocks = parsed
+            if unparsed:
+                blocks.append(
+                    {"index": 0, "error": True, "tags": ["error"], "content": unparsed}
+                )
+
+        if self.verbose:
+            print(
+                "[LOG] Extracted",
+                len(blocks),
+                "blocks from URL:",
+                url,
+                "block index:",
+                ix,
+            )
+        return blocks
 
     def _merge(self, documents, chunk_token_threshold, overlap) -> List[str]:
         """
@@ -800,6 +757,8 @@ class LLMExtractionStrategy(ExtractionStrategy):
 #######################################################
 # New extraction strategies for JSON-based extraction #
 #######################################################
+
+
 class JsonElementExtractionStrategy(ExtractionStrategy):
     """
     Abstract base class for extracting structured JSON from HTML content.
@@ -1090,7 +1049,7 @@ class JsonElementExtractionStrategy(ExtractionStrategy):
         schema_type: str = "CSS", # or XPATH
         query: str = None,
         target_json_example: str = None,
-        llm_config: 'LLMConfig' = create_llm_config(),
+        llm_config: 'LLMConfig' = None,
         provider: str = None,
         api_token: str = None,
         **kwargs
@@ -1122,7 +1081,7 @@ class JsonElementExtractionStrategy(ExtractionStrategy):
         # Build the prompt
         system_message = {
             "role": "system", 
-            "content": f"""You specialize in generating special JSON schemas for web scraping. This schema uses CSS or XPATH selectors to present a repetitive pattern in crawled HTML, such as a product in a product list or a search result item in a list of search results. We use this JSON schema to pass to a language model along with the HTML content to extract structured data from the HTML. The language model uses the JSON schema to extract data from the HTML and retrieve values for fields in the JSON schema, following the schema.
+            "content": f"""You specialize in generating special JSON schemas for web scraping. This schema uses CSS or XPATH selectors to present a repetitive pattern in crawled HTML, such as a product in a product list or a search result item in a list of search results. You use this JSON schema to pass to a language model along with the HTML content to extract structured data from the HTML. The language model uses the JSON schema to extract data from the HTML and retrieve values for fields in the JSON schema, following the schema.
 
 Generating this HTML manually is not feasible, so you need to generate the JSON schema using the HTML content. The HTML copied from the crawled website is provided below, which we believe contains the repetitive pattern.
 
@@ -1136,10 +1095,9 @@ Generating this HTML manually is not feasible, so you need to generate the JSON
 In this context, the following items may or may not be present:
 - Example of target JSON object: This is a sample of the final JSON object that we hope to extract from the HTML using the schema you are generating.
 - Extra Instructions: This is optional instructions to consider when generating the schema provided by the user.
-- Query or explanation of target/goal data item: This is a description of what data we are trying to extract from the HTML. This explanation means we're not sure about the rigid schema of the structures we want, so we leave it to you to use your expertise to create the best and most comprehensive structures aimed at maximizing data extraction from this page. You must ensure that you do not pick up nuances that may exist on a particular page. The focus should be on the data we are extracting, and it must be valid, safe, and robust based on the given HTML.
 
-# What if there is no example of target JSON object and also no extra instructions or even no explanation of target/goal data item?
+# What if there is no example of target JSON object?
-In this scenario, use your best judgment to generate the schema. You need to examine the content of the page and understand the data it provides. If the page contains repetitive data, such as lists of items, products, jobs, places, books, or movies, focus on one single item that repeats. If the page is a detailed page about one product or item, create a schema to extract the entire structured data. At this stage, you must think and decide for yourself. Try to maximize the number of fields that you can extract from the HTML.
+In this scenario, use your best judgment to generate the schema. Try to maximize the number of fields that you can extract from the HTML.
 
 # What are the instructions and details for this schema generation?
 {prompt_template}"""
@@ -1156,18 +1114,11 @@ In this scenario, use your best judgment to generate the schema. You need to exa
         }
 
         if query:
-            user_message["content"] += f"\n\n## Query or explanation of target/goal data item:\n{query}"
+            user_message["content"] += f"\n\nImportant Notes to Consider:\n{query}"
         if target_json_example:
-            user_message["content"] += f"\n\n## Example of target JSON object:\n```json\n{target_json_example}\n```"
+            user_message["content"] += f"\n\nExample of target JSON object:\n{target_json_example}"
-
-        if query and not target_json_example:
-            user_message["content"] += """IMPORTANT: To remind you, in this process, we are not providing a rigid example of the adjacent objects we seek. We rely on your understanding of the explanation provided in the above section. Make sure to grasp what we are looking for and, based on that, create the best schema.."""
-        elif not query and target_json_example:
-            user_message["content"] += """IMPORTANT: Please remember that in this process, we provided a proper example of a target JSON object. Make sure to adhere to the structure and create a schema that exactly fits this example. If you find that some elements on the page do not match completely, vote for the majority."""
-        elif not query and not target_json_example:
-            user_message["content"] += """IMPORTANT: Since we neither have a query nor an example, it is crucial to rely solely on the HTML content provided. Leverage your expertise to determine the schema based on the repetitive patterns observed in the content."""
         
-        user_message["content"] += """IMPORTANT: Ensure your schema remains reliable by avoiding selectors that appear to generate dynamically and are not dependable. You want a reliable schema, as it consistently returns the same data even after many page reloads.
+        user_message["content"] += """IMPORTANT: Ensure your schema is reliable, meaning do not use selectors that seem to generate dynamically and are not reliable. A reliable schema is what you want, as it consistently returns the same data even after many reloads of the page.
 
         Analyze the HTML and generate a JSON schema that follows the specified format. Only output valid JSON schema, nothing else.
         """
@@ -1189,6 +1140,7 @@ In this scenario, use your best judgment to generate the schema. You need to exa
         except Exception as e:
             raise Exception(f"Failed to generate schema: {str(e)}")
 
+
 class JsonCssExtractionStrategy(JsonElementExtractionStrategy):
     """
     Concrete implementation of `JsonElementExtractionStrategy` using CSS selectors.

crawl4ai/install.py

@@ -40,55 +40,12 @@ def setup_home_directory():
             f.write("")
 
 def post_install():
-    """
+    """Run all post-installation tasks"""
-    Run all post-installation tasks.
-    Checks CRAWL4AI_MODE environment variable. If set to 'api',
-    skips Playwright browser installation.
-    """
     logger.info("Running post-installation setup...", tag="INIT")
     setup_home_directory()
-
+    install_playwright()
-    # Check environment variable to conditionally skip Playwright install
-    run_mode = os.getenv('CRAWL4AI_MODE')
-    if run_mode == 'api':
-        logger.warning(
-            "CRAWL4AI_MODE=api detected. Skipping Playwright browser installation.",
-            tag="SETUP"
-        )
-    else:
-        # Proceed with installation only if mode is not 'api'
-        install_playwright()
-
     run_migration()
-    # TODO: Will be added in the future
-    # setup_builtin_browser()
     logger.success("Post-installation setup completed!", tag="COMPLETE")
-    
-def setup_builtin_browser():
-    """Set up a builtin browser for use with Crawl4AI"""
-    try:
-        logger.info("Setting up builtin browser...", tag="INIT")
-        asyncio.run(_setup_builtin_browser())
-        logger.success("Builtin browser setup completed!", tag="COMPLETE")
-    except Exception as e:
-        logger.warning(f"Failed to set up builtin browser: {e}")
-        logger.warning("You can manually set up a builtin browser using 'crawl4ai-doctor builtin-browser-start'")
-    
-async def _setup_builtin_browser():
-    try:
-        # Import BrowserProfiler here to avoid circular imports
-        from .browser_profiler import BrowserProfiler
-        profiler = BrowserProfiler(logger=logger)
-        
-        # Launch the builtin browser
-        cdp_url = await profiler.launch_builtin_browser(headless=True)
-        if cdp_url:
-            logger.success(f"Builtin browser launched at {cdp_url}", tag="BROWSER")
-        else:
-            logger.warning("Failed to launch builtin browser", tag="BROWSER")
-    except Exception as e:
-        logger.warning(f"Error setting up builtin browser: {e}", tag="BROWSER")
-        raise
 
 
 def install_playwright():

crawl4ai/models.py

@@ -1,7 +1,6 @@
+from re import U
 from pydantic import BaseModel, HttpUrl, PrivateAttr
 from typing import List, Dict, Optional, Callable, Awaitable, Union, Any
-from typing import AsyncGenerator
-from typing import Generic, TypeVar
 from enum import Enum
 from dataclasses import dataclass
 from .ssl_certificate import SSLCertificate
@@ -29,12 +28,7 @@ class CrawlerTaskResult:
     start_time: Union[datetime, float]
     end_time: Union[datetime, float]
     error_message: str = ""
-    retry_count: int = 0
+
-    wait_time: float = 0.0
-    
-    @property
-    def success(self) -> bool:
-        return self.result.success
 
 class CrawlStatus(Enum):
     QUEUED = "QUEUED"
@@ -42,6 +36,27 @@ class CrawlStatus(Enum):
     COMPLETED = "COMPLETED"
     FAILED = "FAILED"
 
+
+# @dataclass
+# class CrawlStats:
+#     task_id: str
+#     url: str
+#     status: CrawlStatus
+#     start_time: Optional[datetime] = None
+#     end_time: Optional[datetime] = None
+#     memory_usage: float = 0.0
+#     peak_memory: float = 0.0
+#     error_message: str = ""
+
+#     @property
+#     def duration(self) -> str:
+#         if not self.start_time:
+#             return "0:00"
+#         end = self.end_time or datetime.now()
+#         duration = end - self.start_time
+#         return str(timedelta(seconds=int(duration.total_seconds())))
+
+
 @dataclass
 class CrawlStats:
     task_id: str
@@ -52,9 +67,6 @@ class CrawlStats:
     memory_usage: float = 0.0
     peak_memory: float = 0.0
     error_message: str = ""
-    wait_time: float = 0.0
-    retry_count: int = 0
-    counted_requeue: bool = False
 
     @property
     def duration(self) -> str:
@@ -91,11 +103,21 @@ class TokenUsage:
     completion_tokens_details: Optional[dict] = None
     prompt_tokens_details: Optional[dict] = None
 
+
 class UrlModel(BaseModel):
     url: HttpUrl
     forced: bool = False
 
 
+class MarkdownGenerationResult(BaseModel):
+    raw_markdown: str
+    markdown_with_citations: str
+    references_markdown: str
+    fit_markdown: Optional[str] = None
+    fit_html: Optional[str] = None
+
+    def __str__(self):
+        return self.raw_markdown
 
 @dataclass
 class TraversalStats:
@@ -116,16 +138,6 @@ class DispatchResult(BaseModel):
     end_time: Union[datetime, float]
     error_message: str = ""
 
-class MarkdownGenerationResult(BaseModel):
-    raw_markdown: str
-    markdown_with_citations: str
-    references_markdown: str
-    fit_markdown: Optional[str] = None
-    fit_html: Optional[str] = None
-
-    def __str__(self):
-        return self.raw_markdown
-    
 class CrawlResult(BaseModel):
     url: str
     html: str
@@ -137,7 +149,6 @@ class CrawlResult(BaseModel):
     js_execution_result: Optional[Dict[str, Any]] = None
     screenshot: Optional[str] = None
     pdf: Optional[bytes] = None
-    mhtml: Optional[str] = None
     _markdown: Optional[MarkdownGenerationResult] = PrivateAttr(default=None)
     extracted_content: Optional[str] = None
     metadata: Optional[dict] = None
@@ -148,8 +159,6 @@ class CrawlResult(BaseModel):
     ssl_certificate: Optional[SSLCertificate] = None
     dispatch_result: Optional[DispatchResult] = None
     redirected_url: Optional[str] = None
-    network_requests: Optional[List[Dict[str, Any]]] = None
-    console_messages: Optional[List[Dict[str, Any]]] = None
 
     class Config:
         arbitrary_types_allowed = True
@@ -266,40 +275,6 @@ class StringCompatibleMarkdown(str):
     def __getattr__(self, name):
         return getattr(self._markdown_result, name)
 
-CrawlResultT = TypeVar('CrawlResultT', bound=CrawlResult)
-
-class CrawlResultContainer(Generic[CrawlResultT]):
-    def __init__(self, results: Union[CrawlResultT, List[CrawlResultT]]):
-        # Normalize to a list
-        if isinstance(results, list):
-            self._results = results
-        else:
-            self._results = [results]
-
-    def __iter__(self):
-        return iter(self._results)
-
-    def __getitem__(self, index):
-        return self._results[index]
-
-    def __len__(self):
-        return len(self._results)
-
-    def __getattr__(self, attr):
-        # Delegate attribute access to the first element.
-        if self._results:
-            return getattr(self._results[0], attr)
-        raise AttributeError(f"{self.__class__.__name__} object has no attribute '{attr}'")
-
-    def __repr__(self):
-        return f"{self.__class__.__name__}({self._results!r})"
-
-RunManyReturn = Union[
-    CrawlResultContainer[CrawlResultT],
-    AsyncGenerator[CrawlResultT, None]
-]
-
-
 # END of backward compatibility code for markdown/markdown_v2.
 # When removing this code in the future, make sure to:
 # 1. Replace the private attribute and property with a standard field
@@ -312,17 +287,15 @@ class AsyncCrawlResponse(BaseModel):
     status_code: int
     screenshot: Optional[str] = None
     pdf_data: Optional[bytes] = None
-    mhtml_data: Optional[str] = None
     get_delayed_content: Optional[Callable[[Optional[float]], Awaitable[str]]] = None
     downloaded_files: Optional[List[str]] = None
     ssl_certificate: Optional[SSLCertificate] = None
     redirected_url: Optional[str] = None
-    network_requests: Optional[List[Dict[str, Any]]] = None
-    console_messages: Optional[List[Dict[str, Any]]] = None
 
     class Config:
         arbitrary_types_allowed = True
 
+
 ###############################
 # Scraping Models
 ###############################

crawl4ai/prompts.py

@@ -203,62 +203,6 @@ Avoid Common Mistakes:
 Result
 Output the final list of JSON objects, wrapped in <blocks>...</blocks> XML tags. Make sure to close the tag properly."""
 
-PROMPT_EXTRACT_INFERRED_SCHEMA = """Here is the content from the URL:
-<url>{URL}</url>
-
-<url_content>
-{HTML}
-</url_content>
-
-Please carefully read the URL content and the user's request. Analyze the page structure and infer the most appropriate JSON schema based on the content and request.
-
-Extraction Strategy:
-1. First, determine if the page contains repetitive items (like multiple products, articles, etc.) or a single content item (like a single article or page).
-2. For repetitive items: Identify the common pattern and extract each instance as a separate JSON object in an array.
-3. For single content: Extract the key information into a comprehensive JSON object that captures the essential details.
-
-Extraction instructions:
-Return the extracted information as a list of JSON objects. For repetitive content, each object in the list should correspond to a distinct item. For single content, you may return just one detailed JSON object. Wrap the entire JSON list in <blocks>...</blocks> XML tags.
-
-Schema Design Guidelines:
-- Create meaningful property names that clearly describe the data they contain
-- Use nested objects for hierarchical information
-- Use arrays for lists of related items
-- Include all information requested by the user
-- Maintain consistency in property names and data structures
-- Only include properties that are actually present in the content
-- For dates, prefer ISO format (YYYY-MM-DD)
-- For prices or numeric values, extract them without currency symbols when possible
-
-Quality Reflection:
-Before outputting your final answer, double check that:
-1. The inferred schema makes logical sense for the type of content
-2. All requested information is included
-3. The JSON is valid and could be parsed without errors
-4. Property names are consistent and descriptive
-5. The structure is optimal for the type of data being represented
-
-Avoid Common Mistakes:
-- Do NOT add any comments using "//" or "#" in the JSON output. It causes parsing errors.
-- Make sure the JSON is properly formatted with curly braces, square brackets, and commas in the right places.
-- Do not miss closing </blocks> tag at the end of the JSON output.
-- Do not generate Python code showing how to do the task; this is your task to extract the information and return it in JSON format.
-- Ensure consistency in property names across all objects
-- Don't include empty properties or null values unless they're meaningful
-- For repetitive content, ensure all objects follow the same schema
-
-Important: If user specific instruction is provided, then stress significantly on what user is requesting and describing about the schema of end result (if any). If user is requesting to extract specific information, then focus on that and ignore the rest of the content.
-<user_request>
-{REQUEST}
-</user_request>
-
-Result:
-Output the final list of JSON objects, wrapped in <blocks>...</blocks> XML tags. Make sure to close the tag properly.
-
-DO NOT ADD ANY PRE OR POST COMMENTS. JUST RETURN THE JSON OBJECTS INSIDE <blocks>...</blocks> TAGS.
-
-CRITICAL: The content inside the <blocks> tags MUST be a direct array of JSON objects (starting with '[' and ending with ']'), not a dictionary/object containing an array. For example, use <blocks>[{...}, {...}]</blocks> instead of <blocks>{"items": [{...}, {...}]}</blocks>. This is essential for proper parsing.
-"""
 
 PROMPT_FILTER_CONTENT = """Your task is to filter and convert HTML content into clean, focused markdown that's optimized for use with LLMs and information retrieval systems.
 

crawl4ai/types.py

@@ -178,10 +178,4 @@ if TYPE_CHECKING:
         BestFirstCrawlingStrategy as BestFirstCrawlingStrategyType,
         DFSDeepCrawlStrategy as DFSDeepCrawlStrategyType,
         DeepCrawlDecorator as DeepCrawlDecoratorType,
-    )
+    )
-
-
-
-def create_llm_config(*args, **kwargs) -> 'LLMConfigType':
-    from .async_configs import LLMConfig
-    return LLMConfig(*args, **kwargs)

crawl4ai/utils.py

@@ -26,7 +26,7 @@ import cProfile
 import pstats
 from functools import wraps
 import asyncio
-from lxml import etree, html as lhtml
+
 import sqlite3
 import hashlib
 
@@ -1551,7 +1551,7 @@ def extract_xml_tags(string):
     return list(set(tags))
 
 
-def extract_xml_data_legacy(tags, string):
+def extract_xml_data(tags, string):
     """
     Extract data for specified XML tags from a string.
 
@@ -1580,38 +1580,6 @@ def extract_xml_data_legacy(tags, string):
 
     return data
 
-def extract_xml_data(tags, string):
-    """
-    Extract data for specified XML tags from a string, returning the longest content for each tag.
-
-    How it works:
-    1. Finds all occurrences of each tag in the string using regex.
-    2. For each tag, selects the occurrence with the longest content.
-    3. Returns a dictionary of tag-content pairs.
-
-    Args:
-        tags (List[str]): The list of XML tags to extract.
-        string (str): The input string containing XML data.
-
-    Returns:
-        Dict[str, str]: A dictionary with tag names as keys and longest extracted content as values.
-    """
-
-    data = {}
-
-    for tag in tags:
-        pattern = f"<{tag}>(.*?)</{tag}>"
-        matches = re.findall(pattern, string, re.DOTALL)
-        
-        if matches:
-            # Find the longest content for this tag
-            longest_content = max(matches, key=len).strip()
-            data[tag] = longest_content
-        else:
-            data[tag] = ""
-
-    return data
-
 
 def perform_completion_with_backoff(
     provider,
@@ -1680,19 +1648,6 @@ def perform_completion_with_backoff(
                         "content": ["Rate limit error. Please try again later."],
                     }
                 ]
-        except Exception as e:
-            raise e  # Raise any other exceptions immediately
-            # print("Error during completion request:", str(e))
-            # error_message = e.message
-            # return [
-            #     {
-            #         "index": 0,
-            #         "tags": ["error"],
-            #         "content": [
-            #             f"Error during LLM completion request. {error_message}"
-            #         ],
-            #     }
-            # ]
 
 
 def extract_blocks(url, html, provider=DEFAULT_PROVIDER, api_token=None, base_url=None):
@@ -2662,116 +2617,3 @@ class HeadPeekr:
     def get_title(head_content: str):
         title_match = re.search(r'<title>(.*?)</title>', head_content, re.IGNORECASE | re.DOTALL)
         return title_match.group(1) if title_match else None
-
-def preprocess_html_for_schema(html_content, text_threshold=100, attr_value_threshold=200, max_size=100000):
-    """
-    Preprocess HTML to reduce size while preserving structure for schema generation.
-    
-    Args:
-        html_content (str): Raw HTML content
-        text_threshold (int): Maximum length for text nodes before truncation
-        attr_value_threshold (int): Maximum length for attribute values before truncation
-        max_size (int): Target maximum size for output HTML
-        
-    Returns:
-        str: Preprocessed HTML content
-    """
-    try:
-        # Parse HTML with error recovery
-        parser = etree.HTMLParser(remove_comments=True, remove_blank_text=True)
-        tree = lhtml.fromstring(html_content, parser=parser)
-        
-        # 1. Remove HEAD section (keep only BODY)
-        head_elements = tree.xpath('//head')
-        for head in head_elements:
-            if head.getparent() is not None:
-                head.getparent().remove(head)
-        
-        # 2. Define tags to remove completely
-        tags_to_remove = [
-            'script', 'style', 'noscript', 'iframe', 'canvas', 'svg',
-            'video', 'audio', 'source', 'track', 'map', 'area'
-        ]
-        
-        # Remove unwanted elements
-        for tag in tags_to_remove:
-            elements = tree.xpath(f'//{tag}')
-            for element in elements:
-                if element.getparent() is not None:
-                    element.getparent().remove(element)
-        
-        # 3. Process remaining elements to clean attributes and truncate text
-        for element in tree.iter():
-            # Skip if we're at the root level
-            if element.getparent() is None:
-                continue
-                
-            # Clean non-essential attributes but preserve structural ones
-            # attribs_to_keep = {'id', 'class', 'name', 'href', 'src', 'type', 'value', 'data-'}
-
-            # This is more aggressive than the previous version
-            attribs_to_keep = {'id', 'class', 'name', 'type', 'value'}
-
-            # attributes_hates_truncate = ['id', 'class', "data-"]
-
-            # This means, I don't care, if an attribute is too long, truncate it, go and find a better css selector to build a schema
-            attributes_hates_truncate = []
-            
-            # Process each attribute
-            for attrib in list(element.attrib.keys()):
-                # Keep if it's essential or starts with data-
-                if not (attrib in attribs_to_keep or attrib.startswith('data-')):
-                    element.attrib.pop(attrib)
-                # Truncate long attribute values except for selectors
-                elif attrib not in attributes_hates_truncate and len(element.attrib[attrib]) > attr_value_threshold:
-                    element.attrib[attrib] = element.attrib[attrib][:attr_value_threshold] + '...'
-            
-            # Truncate text content if it's too long
-            if element.text and len(element.text.strip()) > text_threshold:
-                element.text = element.text.strip()[:text_threshold] + '...'
-                
-            # Also truncate tail text if present
-            if element.tail and len(element.tail.strip()) > text_threshold:
-                element.tail = element.tail.strip()[:text_threshold] + '...'
-        
-        # 4. Find repeated patterns and keep only a few examples
-        # This is a simplistic approach - more sophisticated pattern detection could be implemented
-        pattern_elements = {}
-        for element in tree.xpath('//*[contains(@class, "")]'):
-            parent = element.getparent()
-            if parent is None:
-                continue
-                
-            # Create a signature based on tag and classes
-            classes = element.get('class', '')
-            if not classes:
-                continue
-            signature = f"{element.tag}.{classes}"
-            
-            if signature in pattern_elements:
-                pattern_elements[signature].append(element)
-            else:
-                pattern_elements[signature] = [element]
-        
-        # Keep only 3 examples of each repeating pattern
-        for signature, elements in pattern_elements.items():
-            if len(elements) > 3:
-                # Keep the first 2 and last elements
-                for element in elements[2:-1]:
-                    if element.getparent() is not None:
-                        element.getparent().remove(element)
-        
-        # 5. Convert back to string
-        result = etree.tostring(tree, encoding='unicode', method='html')
-        
-        # If still over the size limit, apply more aggressive truncation
-        if len(result) > max_size:
-            return result[:max_size] + "..."
-            
-        return result
-    
-    except Exception as e:
-        # Fallback for parsing errors
-        return html_content[:max_size] if len(html_content) > max_size else html_content
-    
-

deploy/aws/Dockerfile

@@ -0,0 +1,137 @@
+FROM python:3.10-slim
+
+# Set build arguments
+ARG APP_HOME=/app
+ARG GITHUB_REPO=https://github.com/unclecode/crawl4ai.git
+ARG GITHUB_BRANCH=next
+ARG USE_LOCAL=False
+ARG CONFIG_PATH=""
+
+ENV PYTHONFAULTHANDLER=1 \
+    PYTHONHASHSEED=random \
+    PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PIP_DISABLE_PIP_VERSION_CHECK=1 \
+    PIP_DEFAULT_TIMEOUT=100 \
+    DEBIAN_FRONTEND=noninteractive \
+    REDIS_HOST=localhost \
+    REDIS_PORT=6379
+
+ARG PYTHON_VERSION=3.10
+ARG INSTALL_TYPE=default
+ARG ENABLE_GPU=false
+ARG TARGETARCH
+
+LABEL maintainer="unclecode"
+LABEL description="🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & scraper"
+LABEL version="1.0"    
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    curl \
+    wget \
+    gnupg \
+    git \
+    cmake \
+    pkg-config \
+    python3-dev \
+    libjpeg-dev \
+    redis-server \
+    supervisor \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libglib2.0-0 \
+    libnss3 \
+    libnspr4 \
+    libatk1.0-0 \
+    libatk-bridge2.0-0 \
+    libcups2 \
+    libdrm2 \
+    libdbus-1-3 \
+    libxcb1 \
+    libxkbcommon0 \
+    libx11-6 \
+    libxcomposite1 \
+    libxdamage1 \
+    libxext6 \
+    libxfixes3 \
+    libxrandr2 \
+    libgbm1 \
+    libpango-1.0-0 \
+    libcairo2 \
+    libasound2 \
+    libatspi2.0-0 \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN if [ "$ENABLE_GPU" = "true" ] && [ "$TARGETARCH" = "amd64" ] ; then \
+    apt-get update && apt-get install -y --no-install-recommends \
+    nvidia-cuda-toolkit \
+    && rm -rf /var/lib/apt/lists/* ; \
+else \
+    echo "Skipping NVIDIA CUDA Toolkit installation (unsupported platform or GPU disabled)"; \
+fi
+
+RUN if [ "$TARGETARCH" = "arm64" ]; then \
+    echo "🦾 Installing ARM-specific optimizations"; \
+    apt-get update && apt-get install -y --no-install-recommends \
+    libopenblas-dev \
+    && rm -rf /var/lib/apt/lists/*; \
+elif [ "$TARGETARCH" = "amd64" ]; then \
+    echo "🖥️ Installing AMD64-specific optimizations"; \
+    apt-get update && apt-get install -y --no-install-recommends \
+    libomp-dev \
+    && rm -rf /var/lib/apt/lists/*; \
+else \
+    echo "Skipping platform-specific optimizations (unsupported platform)"; \
+fi
+
+WORKDIR ${APP_HOME}
+
+RUN git clone --branch ${GITHUB_BRANCH} ${GITHUB_REPO} /tmp/crawl4ai
+
+COPY docker/supervisord.conf .
+COPY docker/requirements.txt .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+RUN if [ "$INSTALL_TYPE" = "all" ] ; then \
+        pip install "/tmp/crawl4ai/[all]" && \
+        python -m nltk.downloader punkt stopwords && \
+        python -m crawl4ai.model_loader ; \
+    elif [ "$INSTALL_TYPE" = "torch" ] ; then \
+        pip install "/tmp/crawl4ai/[torch]" ; \
+    elif [ "$INSTALL_TYPE" = "transformer" ] ; then \
+        pip install "/tmp/crawl4ai/[transformer]" && \
+        python -m crawl4ai.model_loader ; \
+    else \
+        pip install "/tmp/crawl4ai" ; \
+    fi
+    
+RUN pip install --no-cache-dir --upgrade pip && \
+    python -c "import crawl4ai; print('✅ crawl4ai is ready to rock!')" && \
+    python -c "from playwright.sync_api import sync_playwright; print('✅ Playwright is feeling dramatic!')"
+    
+RUN playwright install --with-deps chromium
+
+COPY docker/* ${APP_HOME}/
+RUN if [ -n "$CONFIG_PATH" ] && [ -f "$CONFIG_PATH" ]; then \
+    echo "Using custom config from $CONFIG_PATH" && \
+    cp $CONFIG_PATH /app/config.yml; \
+fi
+
+HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
+    CMD bash -c '\
+    MEM=$(free -m | awk "/^Mem:/{print \$2}"); \
+    if [ $MEM -lt 2048 ]; then \
+        echo "⚠️ Warning: Less than 2GB RAM available! Your container might need a memory boost! 🚀"; \
+        exit 1; \
+    fi && \
+    redis-cli ping > /dev/null && \
+    curl -f http://localhost:8000/health || exit 1'
+
+# EXPOSE 6379
+
+CMD ["supervisord", "-c", "supervisord.conf"]
+    

deploy/aws/deploy-config.yml

@@ -0,0 +1,3 @@
+project_name: PROJECT_NAME
+domain_name: DOMAIN_NAME
+aws_region: AWS_REGION

deploy/aws/deploy.py

@@ -0,0 +1,729 @@
+#!/usr/bin/env python3
+import argparse
+import subprocess
+import sys
+import time
+import json
+import yaml
+import requests
+import os
+
+# Steps for deployment
+STEPS = [
+    "refresh_aws_auth",
+    "fetch_or_create_vpc_and_subnets",
+    "create_ecr_repositories",
+    "create_iam_role",
+    "create_security_groups",
+    "request_acm_certificate",
+    "build_and_push_docker",
+    "create_task_definition",
+    "setup_alb",
+    "deploy_ecs_service",
+    "configure_custom_domain",
+    "test_endpoints"
+]
+
+# Utility function to prompt user for confirmation
+def confirm_step(step_name):
+    while True:
+        response = input(f"Proceed with {step_name}? (yes/no): ").strip().lower()
+        if response in ["yes", "no"]:
+            return response == "yes"
+        print("Please enter 'yes' or 'no'.")
+
+# Utility function to run AWS CLI or shell commands and handle errors
+def run_command(command, error_message, additional_diagnostics=None, cwd="."):
+    try:
+        result = subprocess.run(command, capture_output=True, text=True, check=True, cwd=cwd)
+        return result
+    except subprocess.CalledProcessError as e:
+        with open("error_context.md", "w") as f:
+            f.write(f"{error_message}:\n")
+            f.write(f"Command: {' '.join(command)}\n")
+            f.write(f"Exit Code: {e.returncode}\n")
+            f.write(f"Stdout: {e.stdout}\n")
+            f.write(f"Stderr: {e.stderr}\n")
+            if additional_diagnostics:
+                for diag_cmd in additional_diagnostics:
+                    diag_result = subprocess.run(diag_cmd, capture_output=True, text=True)
+                    f.write(f"\nDiagnostic command: {' '.join(diag_cmd)}\n")
+                    f.write(f"Stdout: {diag_result.stdout}\n")
+                    f.write(f"Stderr: {diag_result.stderr}\n")
+        raise Exception(f"{error_message}: {e.stderr}")
+
+# Utility function to load or initialize state
+def load_state(project_name):
+    state_file = f"{project_name}-state.json"
+    if os.path.exists(state_file):
+        with open(state_file, "r") as f:
+            return json.load(f)
+    return {"last_step": -1}
+
+# Utility function to save state
+def save_state(project_name, state):
+    state_file = f"{project_name}-state.json"
+    with open(state_file, "w") as f:
+        json.dump(state, f, indent=4)
+
+# DNS Check Function
+def check_dns_propagation(domain, alb_dns):
+    try:
+        result = subprocess.run(["dig", "+short", domain], capture_output=True, text=True)
+        if alb_dns in result.stdout:
+            return True
+        return False
+    except Exception as e:
+        print(f"Failed to check DNS: {e}")
+        return False
+
+# Step Functions
+def refresh_aws_auth(project_name, state, config):
+    if state["last_step"] >= 0:
+        print("Skipping refresh_aws_auth (already completed)")
+        return
+    if not confirm_step("Refresh AWS authentication"):
+        sys.exit("User aborted.")
+    run_command(
+        ["aws", "sts", "get-caller-identity"],
+        "Failed to verify AWS credentials"
+    )
+    print("AWS authentication verified.")
+    state["last_step"] = 0
+    save_state(project_name, state)
+
+def fetch_or_create_vpc_and_subnets(project_name, state, config):
+    if state["last_step"] >= 1:
+        print("Skipping fetch_or_create_vpc_and_subnets (already completed)")
+        return state["vpc_id"], state["public_subnets"]
+    if not confirm_step("Fetch or Create VPC and Subnets"):
+        sys.exit("User aborted.")
+    
+    # Fetch AWS account ID
+    result = run_command(
+        ["aws", "sts", "get-caller-identity"],
+        "Failed to get AWS account ID"
+    )
+    account_id = json.loads(result.stdout)["Account"]
+    
+    # Fetch default VPC
+    result = run_command(
+        ["aws", "ec2", "describe-vpcs", "--filters", "Name=isDefault,Values=true", "--region", config["aws_region"]],
+        "Failed to describe VPCs"
+    )
+    vpcs = json.loads(result.stdout).get("Vpcs", [])
+    if not vpcs:
+        result = run_command(
+            ["aws", "ec2", "create-vpc", "--cidr-block", "10.0.0.0/16", "--region", config["aws_region"]],
+            "Failed to create VPC"
+        )
+        vpc_id = json.loads(result.stdout)["Vpc"]["VpcId"]
+        run_command(
+            ["aws", "ec2", "modify-vpc-attribute", "--vpc-id", vpc_id, "--enable-dns-hostnames", "--region", config["aws_region"]],
+            "Failed to enable DNS hostnames"
+        )
+    else:
+        vpc_id = vpcs[0]["VpcId"]
+    
+    # Fetch or create subnets
+    result = run_command(
+        ["aws", "ec2", "describe-subnets", "--filters", f"Name=vpc-id,Values={vpc_id}", "--region", config["aws_region"]],
+        "Failed to describe subnets"
+    )
+    subnets = json.loads(result.stdout).get("Subnets", [])
+    if len(subnets) < 2:
+        azs = json.loads(run_command(
+            ["aws", "ec2", "describe-availability-zones", "--region", config["aws_region"]],
+            "Failed to describe availability zones"
+        ).stdout)["AvailabilityZones"][:2]
+        subnet_ids = []
+        for i, az in enumerate(azs):
+            az_name = az["ZoneName"]
+            result = run_command(
+                ["aws", "ec2", "create-subnet", "--vpc-id", vpc_id, "--cidr-block", f"10.0.{i}.0/24", "--availability-zone", az_name, "--region", config["aws_region"]],
+                f"Failed to create subnet in {az_name}"
+            )
+            subnet_id = json.loads(result.stdout)["Subnet"]["SubnetId"]
+            subnet_ids.append(subnet_id)
+            run_command(
+                ["aws", "ec2", "modify-subnet-attribute", "--subnet-id", subnet_id, "--map-public-ip-on-launch", "--region", config["aws_region"]],
+                f"Failed to make subnet {subnet_id} public"
+            )
+    else:
+        subnet_ids = [s["SubnetId"] for s in subnets[:2]]
+    
+    # Ensure internet gateway
+    result = run_command(
+        ["aws", "ec2", "describe-internet-gateways", "--filters", f"Name=attachment.vpc-id,Values={vpc_id}", "--region", config["aws_region"]],
+        "Failed to describe internet gateways"
+    )
+    igws = json.loads(result.stdout).get("InternetGateways", [])
+    if not igws:
+        result = run_command(
+            ["aws", "ec2", "create-internet-gateway", "--region", config["aws_region"]],
+            "Failed to create internet gateway"
+        )
+        igw_id = json.loads(result.stdout)["InternetGateway"]["InternetGatewayId"]
+        run_command(
+            ["aws", "ec2", "attach-internet-gateway", "--vpc-id", vpc_id, "--internet-gateway-id", igw_id, "--region", config["aws_region"]],
+            "Failed to attach internet gateway"
+        )
+    
+    state["vpc_id"] = vpc_id
+    state["public_subnets"] = subnet_ids
+    state["last_step"] = 1
+    save_state(project_name, state)
+    print(f"VPC ID: {vpc_id}, Subnets: {subnet_ids}")
+    return vpc_id, subnet_ids
+
+def create_ecr_repositories(project_name, state, config):
+    if state["last_step"] >= 2:
+        print("Skipping create_ecr_repositories (already completed)")
+        return
+    if not confirm_step("Create ECR Repositories"):
+        sys.exit("User aborted.")
+    
+    account_id = json.loads(run_command(
+        ["aws", "sts", "get-caller-identity"],
+        "Failed to get AWS account ID"
+    ).stdout)["Account"]
+    repos = [project_name, f"{project_name}-nginx"]
+    for repo in repos:
+        result = subprocess.run(
+            ["aws", "ecr", "describe-repositories", "--repository-names", repo, "--region", config["aws_region"]],
+            capture_output=True, text=True
+        )
+        if result.returncode != 0:
+            run_command(
+                ["aws", "ecr", "create-repository", "--repository-name", repo, "--region", config["aws_region"]],
+                f"Failed to create ECR repository {repo}"
+            )
+        print(f"ECR repository {repo} is ready.")
+    state["last_step"] = 2
+    save_state(project_name, state)
+
+def create_iam_role(project_name, state, config):
+    if state["last_step"] >= 3:
+        print("Skipping create_iam_role (already completed)")
+        return
+    if not confirm_step("Create IAM Role"):
+        sys.exit("User aborted.")
+    
+    account_id = json.loads(run_command(
+        ["aws", "sts", "get-caller-identity"],
+        "Failed to get AWS account ID"
+    ).stdout)["Account"]
+    role_name = "ecsTaskExecutionRole"
+    trust_policy = {
+        "Version": "2012-10-17",
+        "Statement": [
+            {
+                "Effect": "Allow",
+                "Principal": {"Service": "ecs-tasks.amazonaws.com"},
+                "Action": "sts:AssumeRole"
+            }
+        ]
+    }
+    with open("trust_policy.json", "w") as f:
+        json.dump(trust_policy, f)
+    
+    result = subprocess.run(
+        ["aws", "iam", "get-role", "--role-name", role_name],
+        capture_output=True, text=True
+    )
+    if result.returncode != 0:
+        run_command(
+            ["aws", "iam", "create-role", "--role-name", role_name, "--assume-role-policy-document", "file://trust_policy.json"],
+            f"Failed to create IAM role {role_name}"
+        )
+    run_command(
+        ["aws", "iam", "attach-role-policy", "--role-name", role_name, "--policy-arn", "arn:aws:iam::aws:policy/service-role/AmazonECSTaskExecutionRolePolicy"],
+        "Failed to attach ECS task execution policy"
+    )
+    os.remove("trust_policy.json")
+    state["execution_role_arn"] = f"arn:aws:iam::{account_id}:role/{role_name}"
+    state["last_step"] = 3
+    save_state(project_name, state)
+    print(f"IAM role {role_name} configured.")
+
+def create_security_groups(project_name, state, config):
+    if state["last_step"] >= 4:
+        print("Skipping create_security_groups (already completed)")
+        return state["alb_sg_id"], state["ecs_sg_id"]
+    if not confirm_step("Create Security Groups"):
+        sys.exit("User aborted.")
+    
+    vpc_id = state["vpc_id"]
+    alb_sg_name = f"{project_name}-alb-sg"
+    result = run_command(
+        ["aws", "ec2", "describe-security-groups", "--filters", f"Name=vpc-id,Values={vpc_id}", f"Name=group-name,Values={alb_sg_name}", "--region", config["aws_region"]],
+        "Failed to describe ALB security group"
+    )
+    if not json.loads(result.stdout).get("SecurityGroups"):
+        result = run_command(
+            ["aws", "ec2", "create-security-group", "--group-name", alb_sg_name, "--description", "Security group for ALB", "--vpc-id", vpc_id, "--region", config["aws_region"]],
+            "Failed to create ALB security group"
+        )
+        alb_sg_id = json.loads(result.stdout)["GroupId"]
+        run_command(
+            ["aws", "ec2", "authorize-security-group-ingress", "--group-id", alb_sg_id, "--protocol", "tcp", "--port", "80", "--cidr", "0.0.0.0/0", "--region", config["aws_region"]],
+            "Failed to authorize HTTP ingress"
+        )
+        run_command(
+            ["aws", "ec2", "authorize-security-group-ingress", "--group-id", alb_sg_id, "--protocol", "tcp", "--port", "443", "--cidr", "0.0.0.0/0", "--region", config["aws_region"]],
+            "Failed to authorize HTTPS ingress"
+        )
+    else:
+        alb_sg_id = json.loads(result.stdout)["SecurityGroups"][0]["GroupId"]
+    
+    ecs_sg_name = f"{project_name}-ecs-sg"
+    result = run_command(
+        ["aws", "ec2", "describe-security-groups", "--filters", f"Name=vpc-id,Values={vpc_id}", f"Name=group-name,Values={ecs_sg_name}", "--region", config["aws_region"]],
+        "Failed to describe ECS security group"
+    )
+    if not json.loads(result.stdout).get("SecurityGroups"):
+        result = run_command(
+            ["aws", "ec2", "create-security-group", "--group-name", ecs_sg_name, "--description", "Security group for ECS tasks", "--vpc-id", vpc_id, "--region", config["aws_region"]],
+            "Failed to create ECS security group"
+        )
+        ecs_sg_id = json.loads(result.stdout)["GroupId"]
+        run_command(
+            ["aws", "ec2", "authorize-security-group-ingress", "--group-id", ecs_sg_id, "--protocol", "tcp", "--port", "80", "--source-group", alb_sg_id, "--region", config["aws_region"]],
+            "Failed to authorize ECS ingress"
+        )
+    else:
+        ecs_sg_id = json.loads(result.stdout)["SecurityGroups"][0]["GroupId"]
+    
+    state["alb_sg_id"] = alb_sg_id
+    state["ecs_sg_id"] = ecs_sg_id
+    state["last_step"] = 4
+    save_state(project_name, state)
+    print("Security groups configured.")
+    return alb_sg_id, ecs_sg_id
+
+def request_acm_certificate(project_name, state, config):
+    if state["last_step"] >= 5:
+        print("Skipping request_acm_certificate (already completed)")
+        return state["cert_arn"]
+    if not confirm_step("Request ACM Certificate"):
+        sys.exit("User aborted.")
+    
+    domain_name = config["domain_name"]
+    result = run_command(
+        ["aws", "acm", "describe-certificates", "--certificate-statuses", "ISSUED", "--region", config["aws_region"]],
+        "Failed to describe certificates"
+    )
+    certificates = json.loads(result.stdout).get("CertificateSummaryList", [])
+    cert_arn = next((c["CertificateArn"] for c in certificates if c["DomainName"] == domain_name), None)
+    
+    if not cert_arn:
+        result = run_command(
+            ["aws", "acm", "request-certificate", "--domain-name", domain_name, "--validation-method", "DNS", "--region", config["aws_region"]],
+            "Failed to request ACM certificate"
+        )
+        cert_arn = json.loads(result.stdout)["CertificateArn"]
+        
+        time.sleep(10)
+        result = run_command(
+            ["aws", "acm", "describe-certificate", "--certificate-arn", cert_arn, "--region", config["aws_region"]],
+            "Failed to describe certificate"
+        )
+        cert_details = json.loads(result.stdout)["Certificate"]
+        dns_validations = cert_details.get("DomainValidationOptions", [])
+        for validation in dns_validations:
+            if validation["ValidationMethod"] == "DNS" and "ResourceRecord" in validation:
+                record = validation["ResourceRecord"]
+                print(f"Please add this DNS record to validate the certificate for {domain_name}:")
+                print(f"Name: {record['Name']}")
+                print(f"Type: {record['Type']}")
+                print(f"Value: {record['Value']}")
+        print("Press Enter after adding the DNS record...")
+        input()
+        
+        while True:
+            result = run_command(
+                ["aws", "acm", "describe-certificate", "--certificate-arn", cert_arn, "--region", config["aws_region"]],
+                "Failed to check certificate status"
+            )
+            status = json.loads(result.stdout)["Certificate"]["Status"]
+            if status == "ISSUED":
+                break
+            elif status in ["FAILED", "REVOKED", "INACTIVE"]:
+                print("Certificate issuance failed.")
+                sys.exit(1)
+            time.sleep(10)
+    
+    state["cert_arn"] = cert_arn
+    state["last_step"] = 5
+    save_state(project_name, state)
+    print(f"Certificate ARN: {cert_arn}")
+    return cert_arn
+
+def build_and_push_docker(project_name, state, config):
+    if state["last_step"] >= 6:
+        print("Skipping build_and_push_docker (already completed)")
+        return state["fastapi_image"], state["nginx_image"]
+    if not confirm_step("Build and Push Docker Images"):
+        sys.exit("User aborted.")
+    
+    with open("./version.txt", "r") as f:
+        version = f.read().strip()
+    
+    account_id = json.loads(run_command(
+        ["aws", "sts", "get-caller-identity"],
+        "Failed to get AWS account ID"
+    ).stdout)["Account"]
+    region = config["aws_region"]
+    
+    login_password = run_command(
+        ["aws", "ecr", "get-login-password", "--region", region],
+        "Failed to get ECR login password"
+    ).stdout.strip()
+    run_command(
+        ["docker", "login", "--username", "AWS", "--password", login_password, f"{account_id}.dkr.ecr.{region}.amazonaws.com"],
+        "Failed to authenticate Docker to ECR"
+    )
+    
+    fastapi_image = f"{account_id}.dkr.ecr.{region}.amazonaws.com/{project_name}:{version}"
+    run_command(
+        ["docker", "build", "-f", "Dockerfile", "-t", fastapi_image, "."],
+        "Failed to build FastAPI Docker image"
+    )
+    run_command(
+        ["docker", "push", fastapi_image],
+        "Failed to push FastAPI image"
+    )
+    
+    nginx_image = f"{account_id}.dkr.ecr.{region}.amazonaws.com/{project_name}-nginx:{version}"
+    run_command(
+        ["docker", "build", "-f", "Dockerfile", "-t", nginx_image, "."],
+        "Failed to build Nginx Docker image",
+        cwd="./nginx"
+    )
+    run_command(
+        ["docker", "push", nginx_image],
+        "Failed to push Nginx image"
+    )
+    
+    state["fastapi_image"] = fastapi_image
+    state["nginx_image"] = nginx_image
+    state["last_step"] = 6
+    save_state(project_name, state)
+    print("Docker images built and pushed.")
+    return fastapi_image, nginx_image
+
+def create_task_definition(project_name, state, config):
+    if state["last_step"] >= 7:
+        print("Skipping create_task_definition (already completed)")
+        return state["task_def_arn"]
+    if not confirm_step("Create Task Definition"):
+        sys.exit("User aborted.")
+    
+    log_group = f"/ecs/{project_name}-logs"
+    result = run_command(
+        ["aws", "logs", "describe-log-groups", "--log-group-name-prefix", log_group, "--region", config["aws_region"]],
+        "Failed to describe log groups"
+    )
+    if not any(lg["logGroupName"] == log_group for lg in json.loads(result.stdout).get("logGroups", [])):
+        run_command(
+            ["aws", "logs", "create-log-group", "--log-group-name", log_group, "--region", config["aws_region"]],
+            f"Failed to create log group {log_group}"
+        )
+    
+    task_definition = {
+        "family": f"{project_name}-taskdef",
+        "networkMode": "awsvpc",
+        "requiresCompatibilities": ["FARGATE"],
+        "cpu": "512",
+        "memory": "2048",
+        "executionRoleArn": state["execution_role_arn"],
+        "containerDefinitions": [
+            {
+                "name": "fastapi",
+                "image": state["fastapi_image"],
+                "portMappings": [{"containerPort": 8000, "hostPort": 8000, "protocol": "tcp"}],
+                "logConfiguration": {
+                    "logDriver": "awslogs",
+                    "options": {
+                        "awslogs-group": log_group,
+                        "awslogs-region": config["aws_region"],
+                        "awslogs-stream-prefix": "fastapi"
+                    }
+                }
+            },
+            {
+                "name": "nginx",
+                "image": state["nginx_image"],
+                "portMappings": [{"containerPort": 80, "hostPort": 80, "protocol": "tcp"}],
+                "logConfiguration": {
+                    "logDriver": "awslogs",
+                    "options": {
+                        "awslogs-group": log_group,
+                        "awslogs-region": config["aws_region"],
+                        "awslogs-stream-prefix": "nginx"
+                    }
+                }
+            }
+        ]
+    }
+    
+    with open("task_def.json", "w") as f:
+        json.dump(task_definition, f)
+    result = run_command(
+        ["aws", "ecs", "register-task-definition", "--cli-input-json", "file://task_def.json", "--region", config["aws_region"]],
+        "Failed to register task definition"
+    )
+    task_def_arn = json.loads(result.stdout)["taskDefinition"]["taskDefinitionArn"]
+    os.remove("task_def.json")
+    
+    state["task_def_arn"] = task_def_arn
+    state["last_step"] = 7
+    save_state(project_name, state)
+    print("Task definition created.")
+    return task_def_arn
+
+def setup_alb(project_name, state, config):
+    if state["last_step"] >= 8:
+        print("Skipping setup_alb (already completed)")
+        return state["alb_arn"], state["tg_arn"], state["alb_dns"]
+    if not confirm_step("Set Up ALB"):
+        sys.exit("User aborted.")
+    
+    vpc_id = state["vpc_id"]
+    public_subnets = state["public_subnets"]
+    alb_name = f"{project_name}-alb"
+    
+    result = subprocess.run(
+        ["aws", "elbv2", "describe-load-balancers", "--names", alb_name, "--region", config["aws_region"]],
+        capture_output=True, text=True
+    )
+    if result.returncode != 0:
+        run_command(
+            ["aws", "elbv2", "create-load-balancer", "--name", alb_name, "--subnets"] + public_subnets + ["--security-groups", state["alb_sg_id"], "--region", config["aws_region"]],
+            "Failed to create ALB"
+        )
+    alb_arn = json.loads(run_command(
+        ["aws", "elbv2", "describe-load-balancers", "--names", alb_name, "--region", config["aws_region"]],
+        "Failed to describe ALB"
+    ).stdout)["LoadBalancers"][0]["LoadBalancerArn"]
+    alb_dns = json.loads(run_command(
+        ["aws", "elbv2", "describe-load-balancers", "--names", alb_name, "--region", config["aws_region"]],
+        "Failed to get ALB DNS name"
+    ).stdout)["LoadBalancers"][0]["DNSName"]
+    
+    tg_name = f"{project_name}-tg"
+    result = subprocess.run(
+        ["aws", "elbv2", "describe-target-groups", "--names", tg_name, "--region", config["aws_region"]],
+        capture_output=True, text=True
+    )
+    if result.returncode != 0:
+        run_command(
+            ["aws", "elbv2", "create-target-group", "--name", tg_name, "--protocol", "HTTP", "--port", "80", "--vpc-id", vpc_id, "--region", config["aws_region"]],
+            "Failed to create target group"
+        )
+    tg_arn = json.loads(run_command(
+        ["aws", "elbv2", "describe-target-groups", "--names", tg_name, "--region", config["aws_region"]],
+        "Failed to describe target group"
+    ).stdout)["TargetGroups"][0]["TargetGroupArn"]
+    
+    result = run_command(
+        ["aws", "elbv2", "describe-listeners", "--load-balancer-arn", alb_arn, "--region", config["aws_region"]],
+        "Failed to describe listeners"
+    )
+    listeners = json.loads(result.stdout).get("Listeners", [])
+    if not any(l["Port"] == 80 for l in listeners):
+        run_command(
+            ["aws", "elbv2", "create-listener", "--load-balancer-arn", alb_arn, "--protocol", "HTTP", "--port", "80", "--default-actions", "Type=redirect,RedirectConfig={Protocol=HTTPS,Port=443,StatusCode=HTTP_301}", "--region", config["aws_region"]],
+            "Failed to create HTTP listener"
+        )
+    if not any(l["Port"] == 443 for l in listeners):
+        run_command(
+            ["aws", "elbv2", "create-listener", "--load-balancer-arn", alb_arn, "--protocol", "HTTPS", "--port", "443", "--certificates", f"CertificateArn={state['cert_arn']}", "--default-actions", f"Type=forward,TargetGroupArn={tg_arn}", "--region", config["aws_region"]],
+            "Failed to create HTTPS listener"
+        )
+    
+    state["alb_arn"] = alb_arn
+    state["tg_arn"] = tg_arn
+    state["alb_dns"] = alb_dns
+    state["last_step"] = 8
+    save_state(project_name, state)
+    print("ALB configured.")
+    return alb_arn, tg_arn, alb_dns
+
+def deploy_ecs_service(project_name, state, config):
+    if state["last_step"] >= 9:
+        print("Skipping deploy_ecs_service (already completed)")
+        return
+    if not confirm_step("Deploy ECS Service"):
+        sys.exit("User aborted.")
+    
+    cluster_name = f"{project_name}-cluster"
+    result = run_command(
+        ["aws", "ecs", "describe-clusters", "--clusters", cluster_name, "--region", config["aws_region"]],
+        "Failed to describe clusters"
+    )
+    if not json.loads(result.stdout).get("clusters"):
+        run_command(
+            ["aws", "ecs", "create-cluster", "--cluster-name", cluster_name, "--region", config["aws_region"]],
+            "Failed to create ECS cluster"
+        )
+    
+    service_name = f"{project_name}-service"
+    result = run_command(
+        ["aws", "ecs", "describe-services", "--cluster", cluster_name, "--services", service_name, "--region", config["aws_region"]],
+        "Failed to describe services",
+        additional_diagnostics=[["aws", "ecs", "list-tasks", "--cluster", cluster_name, "--service-name", service_name, "--region", config["aws_region"]]]
+    )
+    services = json.loads(result.stdout).get("services", [])
+    if not services or services[0]["status"] == "INACTIVE":
+        run_command(
+            ["aws", "ecs", "create-service", "--cluster", cluster_name, "--service-name", service_name, "--task-definition", state["task_def_arn"], "--desired-count", "1", "--launch-type", "FARGATE", "--network-configuration", f"awsvpcConfiguration={{subnets={json.dumps(state['public_subnets'])},securityGroups=[{state['ecs_sg_id']}],assignPublicIp=ENABLED}}", "--load-balancers", f"targetGroupArn={state['tg_arn']},containerName=nginx,containerPort=80", "--region", config["aws_region"]],
+            "Failed to create ECS service"
+        )
+    else:
+        run_command(
+            ["aws", "ecs", "update-service", "--cluster", cluster_name, "--service", service_name, "--task-definition", state["task_def_arn"], "--region", config["aws_region"]],
+            "Failed to update ECS service"
+        )
+    
+    state["last_step"] = 9
+    save_state(project_name, state)
+    print("ECS service deployed.")
+
+def configure_custom_domain(project_name, state, config):
+    if state["last_step"] >= 10:
+        print("Skipping configure_custom_domain (already completed)")
+        return
+    if not confirm_step("Configure Custom Domain"):
+        sys.exit("User aborted.")
+    
+    domain_name = config["domain_name"]
+    alb_dns = state["alb_dns"]
+    print(f"Please add a CNAME record for {domain_name} pointing to {alb_dns} in your DNS provider.")
+    print("Press Enter after updating the DNS record...")
+    input()
+    
+    while not check_dns_propagation(domain_name, alb_dns):
+        print("DNS propagation not complete. Waiting 30 seconds before retrying...")
+        time.sleep(30)
+    print("DNS propagation confirmed.")
+    
+    state["last_step"] = 10
+    save_state(project_name, state)
+    print("Custom domain configured.")
+
+def test_endpoints(project_name, state, config):
+    if state["last_step"] >= 11:
+        print("Skipping test_endpoints (already completed)")
+        return
+    if not confirm_step("Test Endpoints"):
+        sys.exit("User aborted.")
+    
+    domain = config["domain_name"]
+    time.sleep(30)  # Wait for service to stabilize
+    
+    response = requests.get(f"https://{domain}/health", verify=False)
+    if response.status_code != 200:
+        with open("error_context.md", "w") as f:
+            f.write("Health endpoint test failed:\n")
+            f.write(f"Status Code: {response.status_code}\n")
+            f.write(f"Response: {response.text}\n")
+        sys.exit(1)
+    print("Health endpoint test passed.")
+    
+    payload = {
+        "urls": ["https://example.com"],
+        "browser_config": {"headless": True},
+        "crawler_config": {"stream": False}
+    }
+    response = requests.post(f"https://{domain}/crawl", json=payload, verify=False)
+    if response.status_code != 200:
+        with open("error_context.md", "w") as f:
+            f.write("Crawl endpoint test failed:\n")
+            f.write(f"Status Code: {response.status_code}\n")
+            f.write(f"Response: {response.text}\n")
+        sys.exit(1)
+    print("Crawl endpoint test passed.")
+    
+    state["last_step"] = 11
+    save_state(project_name, state)
+    print("Endpoints tested successfully.")
+
+# Main Deployment Function
+def deploy(project_name, force=False):
+    config_file = f"{project_name}-config.yml"
+    if not os.path.exists(config_file):
+        print(f"Configuration file {config_file} not found. Run 'init' first.")
+        sys.exit(1)
+    
+    with open(config_file, "r") as f:
+        config = yaml.safe_load(f)
+    
+    state = load_state(project_name)
+    if force:
+        state = {"last_step": -1}
+    
+    last_step = state.get("last_step", -1)
+    
+    for step_idx, step_name in enumerate(STEPS):
+        if step_idx <= last_step:
+            print(f"Skipping {step_name} (already completed)")
+            continue
+        print(f"Executing step: {step_name}")
+        func = globals()[step_name]
+        if step_name == "fetch_or_create_vpc_and_subnets":
+            vpc_id, public_subnets = func(project_name, state, config)
+        elif step_name == "create_security_groups":
+            alb_sg_id, ecs_sg_id = func(project_name, state, config)
+        elif step_name == "request_acm_certificate":
+            cert_arn = func(project_name, state, config)
+        elif step_name == "build_and_push_docker":
+            fastapi_image, nginx_image = func(project_name, state, config)
+        elif step_name == "create_task_definition":
+            task_def_arn = func(project_name, state, config)
+        elif step_name == "setup_alb":
+            alb_arn, tg_arn, alb_dns = func(project_name, state, config)
+        elif step_name == "deploy_ecs_service":
+            func(project_name, state, config)
+        elif step_name == "configure_custom_domain":
+            func(project_name, state, config)
+        elif step_name == "test_endpoints":
+            func(project_name, state, config)
+        else:
+            func(project_name, state, config)
+
+# Init Command
+def init(project_name, domain_name, aws_region):
+    config = {
+        "project_name": project_name,
+        "domain_name": domain_name,
+        "aws_region": aws_region
+    }
+    config_file = f"{project_name}-config.yml"
+    with open(config_file, "w") as f:
+        yaml.dump(config, f)
+    print(f"Configuration file {config_file} created.")
+
+# Argument Parser
+parser = argparse.ArgumentParser(description="Crawl4AI Deployment Script")
+subparsers = parser.add_subparsers(dest="command")
+
+# Init Parser
+init_parser = subparsers.add_parser("init", help="Initialize configuration")
+init_parser.add_argument("--project", required=True, help="Project name")
+init_parser.add_argument("--domain", required=True, help="Domain name")
+init_parser.add_argument("--region", required=True, help="AWS region")
+
+# Deploy Parser
+deploy_parser = subparsers.add_parser("deploy", help="Deploy the project")
+deploy_parser.add_argument("--project", required=True, help="Project name")
+deploy_parser.add_argument("--force", action="store_true", help="Force redeployment from start")
+
+args = parser.parse_args()
+
+if args.command == "init":
+    init(args.project, args.domain, args.region)
+elif args.command == "deploy":
+    deploy(args.project, args.force)
+else:
+    parser.print_help()

deploy/aws/docker/.dockerignore

@@ -0,0 +1,31 @@
+# .dockerignore
+*
+
+# Allow specific files and directories when using local installation
+!crawl4ai/
+!docs/
+!deploy/docker/
+!setup.py
+!pyproject.toml
+!README.md
+!LICENSE
+!MANIFEST.in
+!setup.cfg
+!mkdocs.yml
+
+.git/
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.DS_Store
+.env
+.venv
+venv/
+tests/
+coverage.xml
+*.log
+*.swp
+*.egg-info/
+dist/
+build/

deploy/aws/docker/.llm.env.example

@@ -0,0 +1,8 @@
+# LLM Provider Keys
+OPENAI_API_KEY=your_openai_key_here
+DEEPSEEK_API_KEY=your_deepseek_key_here
+ANTHROPIC_API_KEY=your_anthropic_key_here
+GROQ_API_KEY=your_groq_key_here
+TOGETHER_API_KEY=your_together_key_here
+MISTRAL_API_KEY=your_mistral_key_here
+GEMINI_API_TOKEN=your_gemini_key_here

deploy/aws/docker/README.md

@@ -0,0 +1,847 @@
+# Crawl4AI Docker Guide 🐳
+
+## Table of Contents
+- [Prerequisites](#prerequisites)
+- [Installation](#installation)
+  - [Local Build](#local-build)
+  - [Docker Hub](#docker-hub)
+- [Dockerfile Parameters](#dockerfile-parameters)
+- [Using the API](#using-the-api)
+  - [Understanding Request Schema](#understanding-request-schema)
+  - [REST API Examples](#rest-api-examples)
+  - [Python SDK](#python-sdk)
+- [Metrics & Monitoring](#metrics--monitoring)
+- [Deployment Scenarios](#deployment-scenarios)
+- [Complete Examples](#complete-examples)
+- [Getting Help](#getting-help)
+
+## Prerequisites
+
+Before we dive in, make sure you have:
+- Docker installed and running (version 20.10.0 or higher)
+- At least 4GB of RAM available for the container
+- Python 3.10+ (if using the Python SDK)
+- Node.js 16+ (if using the Node.js examples)
+
+> 💡 **Pro tip**: Run `docker info` to check your Docker installation and available resources.
+
+## Installation
+
+### Local Build
+
+Let's get your local environment set up step by step!
+
+#### 1. Building the Image
+
+First, clone the repository and build the Docker image:
+
+```bash
+# Clone the repository
+git clone https://github.com/unclecode/crawl4ai.git
+cd crawl4ai/deploy
+
+# Build the Docker image
+docker build --platform=linux/amd64 --no-cache -t crawl4ai .
+
+# Or build for arm64
+docker build --platform=linux/arm64 --no-cache -t crawl4ai .
+```
+
+#### 2. Environment Setup
+
+If you plan to use LLMs (Language Models), you'll need to set up your API keys. Create a `.llm.env` file:
+
+```env
+# OpenAI
+OPENAI_API_KEY=sk-your-key
+
+# Anthropic
+ANTHROPIC_API_KEY=your-anthropic-key
+
+# DeepSeek
+DEEPSEEK_API_KEY=your-deepseek-key
+
+# Check out https://docs.litellm.ai/docs/providers for more providers!
+```
+
+> 🔑 **Note**: Keep your API keys secure! Never commit them to version control.
+
+#### 3. Running the Container
+
+You have several options for running the container:
+
+Basic run (no LLM support):
+```bash
+docker run -d -p 8000:8000 --name crawl4ai crawl4ai
+```
+
+With LLM support:
+```bash
+docker run -d -p 8000:8000 \
+  --env-file .llm.env \
+  --name crawl4ai \
+  crawl4ai
+```
+
+Using host environment variables (Not a good practice, but works for local testing):
+```bash
+docker run -d -p 8000:8000 \
+  --env-file .llm.env \
+  --env "$(env)" \
+  --name crawl4ai \
+  crawl4ai
+```
+
+#### Multi-Platform Build
+For distributing your image across different architectures, use `buildx`:
+
+```bash
+# Set up buildx builder
+docker buildx create --use
+
+# Build for multiple platforms
+docker buildx build \
+  --platform linux/amd64,linux/arm64 \
+  -t crawl4ai \
+  --push \
+  .
+```
+
+> 💡 **Note**: Multi-platform builds require Docker Buildx and need to be pushed to a registry.
+
+#### Development Build
+For development, you might want to enable all features:
+
+```bash
+docker build -t crawl4ai
+  --build-arg INSTALL_TYPE=all \
+  --build-arg PYTHON_VERSION=3.10 \
+  --build-arg ENABLE_GPU=true \
+  .
+```
+
+#### GPU-Enabled Build
+If you plan to use GPU acceleration:
+
+```bash
+docker build -t crawl4ai
+  --build-arg ENABLE_GPU=true \
+  deploy/docker/
+```
+
+### Build Arguments Explained
+
+| Argument | Description | Default | Options |
+|----------|-------------|---------|----------|
+| PYTHON_VERSION | Python version | 3.10 | 3.8, 3.9, 3.10 |
+| INSTALL_TYPE | Feature set | default | default, all, torch, transformer |
+| ENABLE_GPU | GPU support | false | true, false |
+| APP_HOME | Install path | /app | any valid path |
+
+### Build Best Practices
+
+1. **Choose the Right Install Type**
+   - `default`: Basic installation, smallest image, to be honest, I use this most of the time.
+   - `all`: Full features, larger image (include transformer, and nltk, make sure you really need them)
+
+2. **Platform Considerations**
+   - Let Docker auto-detect platform unless you need cross-compilation
+   - Use --platform for specific architecture requirements
+   - Consider buildx for multi-architecture distribution
+
+3. **Performance Optimization**
+   - The image automatically includes platform-specific optimizations
+   - AMD64 gets OpenMP optimizations
+   - ARM64 gets OpenBLAS optimizations
+
+### Docker Hub
+
+> 🚧 Coming soon! The image will be available at `crawl4ai`. Stay tuned!
+
+## Using the API
+
+In the following sections, we discuss two ways to communicate with the Docker server. One option is to use the client SDK that I developed for Python, and I will soon develop one for Node.js. I highly recommend this approach to avoid mistakes. Alternatively, you can take a more technical route by using the JSON structure and passing it to all the URLs, which I will explain in detail.
+
+### Python SDK
+
+The SDK makes things easier! Here's how to use it:
+
+```python
+from crawl4ai.docker_client import Crawl4aiDockerClient
+from crawl4ai import BrowserConfig, CrawlerRunConfig
+
+async def main():
+    async with Crawl4aiDockerClient(base_url="http://localhost:8000", verbose=True) as client:
+      # If JWT is enabled, you can authenticate like this: (more on this later)
+        # await client.authenticate("test@example.com")
+        
+        # Non-streaming crawl
+        results = await client.crawl(
+            ["https://example.com", "https://python.org"],
+            browser_config=BrowserConfig(headless=True),
+            crawler_config=CrawlerRunConfig()
+        )
+        print(f"Non-streaming results: {results}")
+        
+        # Streaming crawl
+        crawler_config = CrawlerRunConfig(stream=True)
+        async for result in await client.crawl(
+            ["https://example.com", "https://python.org"],
+            browser_config=BrowserConfig(headless=True),
+            crawler_config=crawler_config
+        ):
+            print(f"Streamed result: {result}")
+        
+        # Get schema
+        schema = await client.get_schema()
+        print(f"Schema: {schema}")
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+`Crawl4aiDockerClient` is an async context manager that handles the connection for you. You can pass in optional parameters for more control:
+
+- `base_url` (str): Base URL of the Crawl4AI Docker server
+- `timeout` (float): Default timeout for requests in seconds
+- `verify_ssl` (bool): Whether to verify SSL certificates
+- `verbose` (bool): Whether to show logging output
+- `log_file` (str, optional): Path to log file if file logging is desired
+
+This client SDK generates a properly structured JSON request for the server's HTTP API.
+
+## Second Approach: Direct API Calls
+
+This is super important! The API expects a specific structure that matches our Python classes. Let me show you how it works.
+
+### Understanding Configuration Structure
+
+Let's dive deep into how configurations work in Crawl4AI. Every configuration object follows a consistent pattern of `type` and `params`. This structure enables complex, nested configurations while maintaining clarity.
+
+#### The Basic Pattern
+
+Try this in Python to understand the structure:
+```python
+from crawl4ai import BrowserConfig
+
+# Create a config and see its structure
+config = BrowserConfig(headless=True)
+print(config.dump())
+```
+
+This outputs:
+```json
+{
+    "type": "BrowserConfig",
+    "params": {
+        "headless": true
+    }
+}
+```
+
+#### Simple vs Complex Values
+
+The structure follows these rules:
+- Simple values (strings, numbers, booleans, lists) are passed directly
+- Complex values (classes, dictionaries) use the type-params pattern
+
+For example, with dictionaries:
+```json
+{
+    "browser_config": {
+        "type": "BrowserConfig",
+        "params": {
+            "headless": true,           // Simple boolean - direct value
+            "viewport": {               // Complex dictionary - needs type-params
+                "type": "dict",
+                "value": {
+                    "width": 1200,
+                    "height": 800
+                }
+            }
+        }
+    }
+}
+```
+
+#### Strategy Pattern and Nesting
+
+Strategies (like chunking or content filtering) demonstrate why we need this structure. Consider this chunking configuration:
+
+```json
+{
+    "crawler_config": {
+        "type": "CrawlerRunConfig",
+        "params": {
+            "chunking_strategy": {
+                "type": "RegexChunking",      // Strategy implementation
+                "params": {
+                    "patterns": ["\n\n", "\\.\\s+"]
+                }
+            }
+        }
+    }
+}
+```
+
+Here, `chunking_strategy` accepts any chunking implementation. The `type` field tells the system which strategy to use, and `params` configures that specific strategy.
+
+#### Complex Nested Example
+
+Let's look at a more complex example with content filtering:
+
+```json
+{
+    "crawler_config": {
+        "type": "CrawlerRunConfig",
+        "params": {
+            "markdown_generator": {
+                "type": "DefaultMarkdownGenerator",
+                "params": {
+                    "content_filter": {
+                        "type": "PruningContentFilter",
+                        "params": {
+                            "threshold": 0.48,
+                            "threshold_type": "fixed"
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
+```
+
+This shows how deeply configurations can nest while maintaining a consistent structure.
+
+#### Quick Grammar Overview
+```
+config := {
+    "type": string,
+    "params": {
+        key: simple_value | complex_value
+    }
+}
+
+simple_value := string | number | boolean | [simple_value]
+complex_value := config | dict_value
+
+dict_value := {
+    "type": "dict",
+    "value": object
+}
+```
+
+#### Important Rules 🚨
+
+- Always use the type-params pattern for class instances
+- Use direct values for primitives (numbers, strings, booleans)
+- Wrap dictionaries with {"type": "dict", "value": {...}}
+- Arrays/lists are passed directly without type-params
+- All parameters are optional unless specifically required
+
+#### Pro Tip 💡
+
+The easiest way to get the correct structure is to:
+1. Create configuration objects in Python
+2. Use the `dump()` method to see their JSON representation
+3. Use that JSON in your API calls
+
+Example:
+```python
+from crawl4ai import CrawlerRunConfig, PruningContentFilter
+
+config = CrawlerRunConfig(
+    content_filter=PruningContentFilter(threshold=0.48)
+)
+print(config.dump())  # Use this JSON in your API calls
+```
+
+
+#### More Examples
+
+**Advanced Crawler Configuration**
+
+```json
+{
+    "urls": ["https://example.com"],
+    "crawler_config": {
+        "type": "CrawlerRunConfig",
+        "params": {
+            "cache_mode": "bypass",
+            "markdown_generator": {
+                "type": "DefaultMarkdownGenerator",
+                "params": {
+                    "content_filter": {
+                        "type": "PruningContentFilter",
+                        "params": {
+                            "threshold": 0.48,
+                            "threshold_type": "fixed",
+                            "min_word_threshold": 0
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
+```
+
+**Extraction Strategy**:
+
+```json
+{
+    "crawler_config": {
+        "type": "CrawlerRunConfig",
+        "params": {
+            "extraction_strategy": {
+                "type": "JsonCssExtractionStrategy",
+                "params": {
+                    "schema": {
+                        "baseSelector": "article.post",
+                        "fields": [
+                            {"name": "title", "selector": "h1", "type": "text"},
+                            {"name": "content", "selector": ".content", "type": "html"}
+                        ]
+                    }
+                }
+            }
+        }
+    }
+}
+```
+
+**LLM Extraction Strategy**
+
+```json
+{
+  "crawler_config": {
+    "type": "CrawlerRunConfig",
+    "params": {
+      "extraction_strategy": {
+        "type": "LLMExtractionStrategy",
+        "params": {
+          "instruction": "Extract article title, author, publication date and main content",
+          "provider": "openai/gpt-4",
+          "api_token": "your-api-token",
+          "schema": {
+            "type": "dict",
+            "value": {
+              "title": "Article Schema",
+              "type": "object",
+              "properties": {
+                "title": {
+                  "type": "string",
+                  "description": "The article's headline"
+                },
+                "author": {
+                  "type": "string",
+                  "description": "The author's name"
+                },
+                "published_date": {
+                  "type": "string",
+                  "format": "date-time",
+                  "description": "Publication date and time"
+                },
+                "content": {
+                  "type": "string",
+                  "description": "The main article content"
+                }
+              },
+              "required": ["title", "content"]
+            }
+          }
+        }
+      }
+    }
+  }
+}
+```
+
+**Deep Crawler Example**
+
+```json
+{
+  "crawler_config": {
+    "type": "CrawlerRunConfig",
+    "params": {
+      "deep_crawl_strategy": {
+        "type": "BFSDeepCrawlStrategy",
+        "params": {
+          "max_depth": 3,
+          "max_pages": 100,
+          "filter_chain": {
+            "type": "FastFilterChain",
+            "params": {
+              "filters": [
+                {
+                  "type": "FastContentTypeFilter",
+                  "params": {
+                    "allowed_types": ["text/html", "application/xhtml+xml"]
+                  }
+                },
+                {
+                  "type": "FastDomainFilter",
+                  "params": {
+                    "allowed_domains": ["blog.*", "docs.*"],
+                    "blocked_domains": ["ads.*", "analytics.*"]
+                  }
+                },
+                {
+                  "type": "FastURLPatternFilter",
+                  "params": {
+                    "allowed_patterns": ["^/blog/", "^/docs/"],
+                    "blocked_patterns": [".*/ads/", ".*/sponsored/"]
+                  }
+                }
+              ]
+            }
+          },
+          "url_scorer": {
+            "type": "FastCompositeScorer",
+            "params": {
+              "scorers": [
+                {
+                  "type": "FastKeywordRelevanceScorer",
+                  "params": {
+                    "keywords": ["tutorial", "guide", "documentation"],
+                    "weight": 1.0
+                  }
+                },
+                {
+                  "type": "FastPathDepthScorer",
+                  "params": {
+                    "weight": 0.5,
+                    "preferred_depth": 2
+                  }
+                },
+                {
+                  "type": "FastFreshnessScorer",
+                  "params": {
+                    "weight": 0.8,
+                    "max_age_days": 365
+                  }
+                }
+              ]
+            }
+          }
+        }
+      }
+    }
+  }
+}
+```
+
+### REST API Examples
+
+Let's look at some practical examples:
+
+#### Simple Crawl
+
+```python
+import requests
+
+crawl_payload = {
+    "urls": ["https://example.com"],
+    "browser_config": {"headless": True},
+    "crawler_config": {"stream": False}
+}
+response = requests.post(
+    "http://localhost:8000/crawl",
+    # headers={"Authorization": f"Bearer {token}"},  # If JWT is enabled, more on this later
+    json=crawl_payload
+)
+print(response.json())  # Print the response for debugging
+```
+
+#### Streaming Results
+
+```python
+async def test_stream_crawl(session, token: str):
+    """Test the /crawl/stream endpoint with multiple URLs."""
+    url = "http://localhost:8000/crawl/stream"
+    payload = {
+        "urls": [
+            "https://example.com",
+            "https://example.com/page1",  
+            "https://example.com/page2",  
+            "https://example.com/page3",  
+        ],
+        "browser_config": {"headless": True, "viewport": {"width": 1200}},
+        "crawler_config": {"stream": True, "cache_mode": "aggressive"}
+    }
+
+    # headers = {"Authorization": f"Bearer {token}"} # If JWT is enabled, more on this later
+    
+    try:
+        async with session.post(url, json=payload, headers=headers) as response:
+            status = response.status
+            print(f"Status: {status} (Expected: 200)")
+            assert status == 200, f"Expected 200, got {status}"
+            
+            # Read streaming response line-by-line (NDJSON)
+            async for line in response.content:
+                if line:
+                    data = json.loads(line.decode('utf-8').strip())
+                    print(f"Streamed Result: {json.dumps(data, indent=2)}")
+    except Exception as e:
+        print(f"Error in streaming crawl test: {str(e)}")
+```
+
+## Metrics & Monitoring
+
+Keep an eye on your crawler with these endpoints:
+
+- `/health` - Quick health check
+- `/metrics` - Detailed Prometheus metrics
+- `/schema` - Full API schema
+
+Example health check:
+```bash
+curl http://localhost:8000/health
+```
+
+## Deployment Scenarios
+
+> 🚧 Coming soon! We'll cover:
+> - Kubernetes deployment
+> - Cloud provider setups (AWS, GCP, Azure)
+> - High-availability configurations
+> - Load balancing strategies
+
+## Complete Examples
+
+Check out the `examples` folder in our repository for full working examples! Here are two to get you started:
+[Using Client SDK](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/docker_python_sdk_example.py)
+[Using REST API](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/docker_python_rest_api_example.py)
+
+## Server Configuration
+
+The server's behavior can be customized through the `config.yml` file. Let's explore how to configure your Crawl4AI server for optimal performance and security.
+
+### Understanding config.yml
+
+The configuration file is located at `deploy/docker/config.yml`. You can either modify this file before building the image or mount a custom configuration when running the container.
+
+Here's a detailed breakdown of the configuration options:
+
+```yaml
+# Application Configuration
+app:
+  title: "Crawl4AI API"           # Server title in OpenAPI docs
+  version: "1.0.0"               # API version
+  host: "0.0.0.0"               # Listen on all interfaces
+  port: 8000                    # Server port
+  reload: True                  # Enable hot reloading (development only)
+  timeout_keep_alive: 300       # Keep-alive timeout in seconds
+
+# Rate Limiting Configuration
+rate_limiting:
+  enabled: True                 # Enable/disable rate limiting
+  default_limit: "100/minute"   # Rate limit format: "number/timeunit"
+  trusted_proxies: []          # List of trusted proxy IPs
+  storage_uri: "memory://"     # Use "redis://localhost:6379" for production
+
+# Security Configuration
+security:
+  enabled: false               # Master toggle for security features
+  jwt_enabled: true            # Enable JWT authentication
+  https_redirect: True         # Force HTTPS
+  trusted_hosts: ["*"]         # Allowed hosts (use specific domains in production)
+  headers:                     # Security headers
+    x_content_type_options: "nosniff"
+    x_frame_options: "DENY"
+    content_security_policy: "default-src 'self'"
+    strict_transport_security: "max-age=63072000; includeSubDomains"
+
+# Crawler Configuration
+crawler:
+  memory_threshold_percent: 95.0  # Memory usage threshold
+  rate_limiter:
+    base_delay: [1.0, 2.0]      # Min and max delay between requests
+  timeouts:
+    stream_init: 30.0           # Stream initialization timeout
+    batch_process: 300.0        # Batch processing timeout
+
+# Logging Configuration
+logging:
+  level: "INFO"                 # Log level (DEBUG, INFO, WARNING, ERROR)
+  format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+
+# Observability Configuration
+observability:
+  prometheus:
+    enabled: True              # Enable Prometheus metrics
+    endpoint: "/metrics"       # Metrics endpoint
+  health_check:
+    endpoint: "/health"        # Health check endpoint
+```
+
+### JWT Authentication
+
+When `security.jwt_enabled` is set to `true` in your config.yml, all endpoints require JWT authentication via bearer tokens. Here's how it works:
+
+#### Getting a Token
+```python
+POST /token
+Content-Type: application/json
+
+{
+    "email": "user@example.com"
+}
+```
+
+The endpoint returns:
+```json
+{
+    "email": "user@example.com",
+    "access_token": "eyJ0eXAiOiJKV1QiLCJhbGciOi...",
+    "token_type": "bearer"
+}
+```
+
+#### Using the Token
+Add the token to your requests:
+```bash
+curl -H "Authorization: Bearer eyJ0eXAiOiJKV1QiLCJhbGci..." http://localhost:8000/crawl
+```
+
+Using the Python SDK:
+```python
+from crawl4ai.docker_client import Crawl4aiDockerClient
+
+async with Crawl4aiDockerClient() as client:
+    # Authenticate first
+    await client.authenticate("user@example.com")
+    
+    # Now all requests will include the token automatically
+    result = await client.crawl(urls=["https://example.com"])
+```
+
+#### Production Considerations 💡
+The default implementation uses a simple email verification. For production use, consider:
+- Email verification via OTP/magic links
+- OAuth2 integration
+- Rate limiting token generation
+- Token expiration and refresh mechanisms
+- IP-based restrictions
+
+### Configuration Tips and Best Practices
+
+1. **Production Settings** 🏭
+
+   ```yaml
+   app:
+     reload: False              # Disable reload in production
+     timeout_keep_alive: 120    # Lower timeout for better resource management
+   
+   rate_limiting:
+     storage_uri: "redis://redis:6379"  # Use Redis for distributed rate limiting
+     default_limit: "50/minute"         # More conservative rate limit
+   
+   security:
+     enabled: true                      # Enable all security features
+     trusted_hosts: ["your-domain.com"] # Restrict to your domain
+   ```
+
+2. **Development Settings** 🛠️
+
+   ```yaml
+   app:
+     reload: True               # Enable hot reloading
+     timeout_keep_alive: 300    # Longer timeout for debugging
+   
+   logging:
+     level: "DEBUG"            # More verbose logging
+   ```
+
+3. **High-Traffic Settings** 🚦
+
+   ```yaml
+   crawler:
+     memory_threshold_percent: 85.0  # More conservative memory limit
+     rate_limiter:
+       base_delay: [2.0, 4.0]       # More aggressive rate limiting
+   ```
+
+### Customizing Your Configuration
+
+#### Method 1: Pre-build Configuration
+
+```bash
+# Copy and modify config before building
+cd crawl4ai/deploy
+vim custom-config.yml # Or use any editor
+
+# Build with custom config
+docker build --platform=linux/amd64 --no-cache -t crawl4ai:latest .
+```
+
+#### Method 2: Build-time Configuration
+
+Use a custom config during build:
+
+```bash
+# Build with custom config
+docker build --platform=linux/amd64 --no-cache \
+  --build-arg CONFIG_PATH=/path/to/custom-config.yml \ 
+  -t crawl4ai:latest .
+```
+
+#### Method 3: Runtime Configuration
+```bash
+# Mount custom config at runtime
+docker run -d -p 8000:8000 \
+  -v $(pwd)/custom-config.yml:/app/config.yml \
+  crawl4ai-server:prod
+```
+
+> 💡 Note: When using Method 2, `/path/to/custom-config.yml` is relative to deploy directory.
+> 💡 Note: When using Method 3, ensure your custom config file has all required fields as the container will use this instead of the built-in config.
+
+### Configuration Recommendations
+
+1. **Security First** 🔒
+   - Always enable security in production
+   - Use specific trusted_hosts instead of wildcards
+   - Set up proper rate limiting to protect your server
+   - Consider your environment before enabling HTTPS redirect
+
+2. **Resource Management** 💻
+   - Adjust memory_threshold_percent based on available RAM
+   - Set timeouts according to your content size and network conditions
+   - Use Redis for rate limiting in multi-container setups
+
+3. **Monitoring** 📊
+   - Enable Prometheus if you need metrics
+   - Set DEBUG logging in development, INFO in production
+   - Regular health check monitoring is crucial
+
+4. **Performance Tuning** ⚡
+   - Start with conservative rate limiter delays
+   - Increase batch_process timeout for large content
+   - Adjust stream_init timeout based on initial response times
+
+## Getting Help
+
+We're here to help you succeed with Crawl4AI! Here's how to get support:
+
+- 📖 Check our [full documentation](https://docs.crawl4ai.com)
+- 🐛 Found a bug? [Open an issue](https://github.com/unclecode/crawl4ai/issues)
+- 💬 Join our [Discord community](https://discord.gg/crawl4ai)
+- ⭐ Star us on GitHub to show support!
+
+## Summary
+
+In this guide, we've covered everything you need to get started with Crawl4AI's Docker deployment:
+- Building and running the Docker container
+- Configuring the environment
+- Making API requests with proper typing
+- Using the Python SDK
+- Monitoring your deployment
+
+Remember, the examples in the `examples` folder are your friends - they show real-world usage patterns that you can adapt for your needs.
+
+Keep exploring, and don't hesitate to reach out if you need help! We're building something amazing together. 🚀
+
+Happy crawling! 🕷️

deploy/aws/docker/api.py

@@ -0,0 +1,442 @@
+import os
+import json
+import asyncio
+from typing import List, Tuple
+
+import logging
+from typing import Optional, AsyncGenerator
+from urllib.parse import unquote
+from fastapi import HTTPException, Request, status
+from fastapi.background import BackgroundTasks
+from fastapi.responses import JSONResponse
+from redis import asyncio as aioredis
+
+from crawl4ai import (
+    AsyncWebCrawler,
+    CrawlerRunConfig,
+    LLMExtractionStrategy,
+    CacheMode,
+    BrowserConfig,
+    MemoryAdaptiveDispatcher,
+    RateLimiter
+)
+from crawl4ai.utils import perform_completion_with_backoff
+from crawl4ai.content_filter_strategy import (
+    PruningContentFilter,
+    BM25ContentFilter,
+    LLMContentFilter
+)
+from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
+from crawl4ai.content_scraping_strategy import LXMLWebScrapingStrategy
+
+from utils import (
+    TaskStatus,
+    FilterType,
+    get_base_url,
+    is_task_id,
+    should_cleanup_task,
+    decode_redis_hash
+)
+
+logger = logging.getLogger(__name__)
+
+async def handle_llm_qa(
+    url: str,
+    query: str,
+    config: dict
+) -> str:
+    """Process QA using LLM with crawled content as context."""
+    try:
+        # Extract base URL by finding last '?q=' occurrence
+        last_q_index = url.rfind('?q=')
+        if last_q_index != -1:
+            url = url[:last_q_index]
+
+        # Get markdown content
+        async with AsyncWebCrawler() as crawler:
+            result = await crawler.arun(url)
+            if not result.success:
+                raise HTTPException(
+                    status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+                    detail=result.error_message
+                )
+            content = result.markdown_v2.fit_markdown
+
+        # Create prompt and get LLM response
+        prompt = f"""Use the following content as context to answer the question.
+    Content:
+    {content}
+
+    Question: {query}
+
+    Answer:"""
+
+        response = perform_completion_with_backoff(
+            provider=config["llm"]["provider"],
+            prompt_with_variables=prompt,
+            api_token=os.environ.get(config["llm"].get("api_key_env", ""))
+        )
+
+        return response.choices[0].message.content
+    except Exception as e:
+        logger.error(f"QA processing error: {str(e)}", exc_info=True)
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=str(e)
+        )
+
+async def process_llm_extraction(
+    redis: aioredis.Redis,
+    config: dict,
+    task_id: str,
+    url: str,
+    instruction: str,
+    schema: Optional[str] = None,
+    cache: str = "0"
+) -> None:
+    """Process LLM extraction in background."""
+    try:
+        # If config['llm'] has api_key then ignore the api_key_env
+        api_key = ""
+        if "api_key" in config["llm"]:
+            api_key = config["llm"]["api_key"]
+        else:
+            api_key = os.environ.get(config["llm"].get("api_key_env", None), "")
+        llm_strategy = LLMExtractionStrategy(
+            provider=config["llm"]["provider"],
+            api_token=api_key,
+            instruction=instruction,
+            schema=json.loads(schema) if schema else None,
+        )
+
+        cache_mode = CacheMode.ENABLED if cache == "1" else CacheMode.WRITE_ONLY
+
+        async with AsyncWebCrawler() as crawler:
+            result = await crawler.arun(
+                url=url,
+                config=CrawlerRunConfig(
+                    extraction_strategy=llm_strategy,
+                    scraping_strategy=LXMLWebScrapingStrategy(),
+                    cache_mode=cache_mode
+                )
+            )
+
+        if not result.success:
+            await redis.hset(f"task:{task_id}", mapping={
+                "status": TaskStatus.FAILED,
+                "error": result.error_message
+            })
+            return
+
+        try:
+            content = json.loads(result.extracted_content)
+        except json.JSONDecodeError:
+            content = result.extracted_content
+        await redis.hset(f"task:{task_id}", mapping={
+            "status": TaskStatus.COMPLETED,
+            "result": json.dumps(content)
+        })
+
+    except Exception as e:
+        logger.error(f"LLM extraction error: {str(e)}", exc_info=True)
+        await redis.hset(f"task:{task_id}", mapping={
+            "status": TaskStatus.FAILED,
+            "error": str(e)
+        })
+
+async def handle_markdown_request(
+    url: str,
+    filter_type: FilterType,
+    query: Optional[str] = None,
+    cache: str = "0",
+    config: Optional[dict] = None
+) -> str:
+    """Handle markdown generation requests."""
+    try:
+        decoded_url = unquote(url)
+        if not decoded_url.startswith(('http://', 'https://')):
+            decoded_url = 'https://' + decoded_url
+
+        if filter_type == FilterType.RAW:
+            md_generator = DefaultMarkdownGenerator()
+        else:
+            content_filter = {
+                FilterType.FIT: PruningContentFilter(),
+                FilterType.BM25: BM25ContentFilter(user_query=query or ""),
+                FilterType.LLM: LLMContentFilter(
+                    provider=config["llm"]["provider"],
+                    api_token=os.environ.get(config["llm"].get("api_key_env", None), ""),
+                    instruction=query or "Extract main content"
+                )
+            }[filter_type]
+            md_generator = DefaultMarkdownGenerator(content_filter=content_filter)
+
+        cache_mode = CacheMode.ENABLED if cache == "1" else CacheMode.WRITE_ONLY
+
+        async with AsyncWebCrawler() as crawler:
+            result = await crawler.arun(
+                url=decoded_url,
+                config=CrawlerRunConfig(
+                    markdown_generator=md_generator,
+                    scraping_strategy=LXMLWebScrapingStrategy(),
+                    cache_mode=cache_mode
+                )
+            )
+            
+            if not result.success:
+                raise HTTPException(
+                    status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+                    detail=result.error_message
+                )
+
+            return (result.markdown_v2.raw_markdown 
+                   if filter_type == FilterType.RAW 
+                   else result.markdown_v2.fit_markdown)
+
+    except Exception as e:
+        logger.error(f"Markdown error: {str(e)}", exc_info=True)
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=str(e)
+        )
+
+async def handle_llm_request(
+    redis: aioredis.Redis,
+    background_tasks: BackgroundTasks,
+    request: Request,
+    input_path: str,
+    query: Optional[str] = None,
+    schema: Optional[str] = None,
+    cache: str = "0",
+    config: Optional[dict] = None
+) -> JSONResponse:
+    """Handle LLM extraction requests."""
+    base_url = get_base_url(request)
+    
+    try:
+        if is_task_id(input_path):
+            return await handle_task_status(
+                redis, input_path, base_url
+            )
+
+        if not query:
+            return JSONResponse({
+                "message": "Please provide an instruction",
+                "_links": {
+                    "example": {
+                        "href": f"{base_url}/llm/{input_path}?q=Extract+main+content",
+                        "title": "Try this example"
+                    }
+                }
+            })
+
+        return await create_new_task(
+            redis,
+            background_tasks,
+            input_path,
+            query,
+            schema,
+            cache,
+            base_url,
+            config
+        )
+
+    except Exception as e:
+        logger.error(f"LLM endpoint error: {str(e)}", exc_info=True)
+        return JSONResponse({
+            "error": str(e),
+            "_links": {
+                "retry": {"href": str(request.url)}
+            }
+        }, status_code=status.HTTP_500_INTERNAL_SERVER_ERROR)
+
+async def handle_task_status(
+    redis: aioredis.Redis,
+    task_id: str,
+    base_url: str
+) -> JSONResponse:
+    """Handle task status check requests."""
+    task = await redis.hgetall(f"task:{task_id}")
+    if not task:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail="Task not found"
+        )
+
+    task = decode_redis_hash(task)
+    response = create_task_response(task, task_id, base_url)
+
+    if task["status"] in [TaskStatus.COMPLETED, TaskStatus.FAILED]:
+        if should_cleanup_task(task["created_at"]):
+            await redis.delete(f"task:{task_id}")
+
+    return JSONResponse(response)
+
+async def create_new_task(
+    redis: aioredis.Redis,
+    background_tasks: BackgroundTasks,
+    input_path: str,
+    query: str,
+    schema: Optional[str],
+    cache: str,
+    base_url: str,
+    config: dict
+) -> JSONResponse:
+    """Create and initialize a new task."""
+    decoded_url = unquote(input_path)
+    if not decoded_url.startswith(('http://', 'https://')):
+        decoded_url = 'https://' + decoded_url
+
+    from datetime import datetime
+    task_id = f"llm_{int(datetime.now().timestamp())}_{id(background_tasks)}"
+    
+    await redis.hset(f"task:{task_id}", mapping={
+        "status": TaskStatus.PROCESSING,
+        "created_at": datetime.now().isoformat(),
+        "url": decoded_url
+    })
+
+    background_tasks.add_task(
+        process_llm_extraction,
+        redis,
+        config,
+        task_id,
+        decoded_url,
+        query,
+        schema,
+        cache
+    )
+
+    return JSONResponse({
+        "task_id": task_id,
+        "status": TaskStatus.PROCESSING,
+        "url": decoded_url,
+        "_links": {
+            "self": {"href": f"{base_url}/llm/{task_id}"},
+            "status": {"href": f"{base_url}/llm/{task_id}"}
+        }
+    })
+
+def create_task_response(task: dict, task_id: str, base_url: str) -> dict:
+    """Create response for task status check."""
+    response = {
+        "task_id": task_id,
+        "status": task["status"],
+        "created_at": task["created_at"],
+        "url": task["url"],
+        "_links": {
+            "self": {"href": f"{base_url}/llm/{task_id}"},
+            "refresh": {"href": f"{base_url}/llm/{task_id}"}
+        }
+    }
+
+    if task["status"] == TaskStatus.COMPLETED:
+        response["result"] = json.loads(task["result"])
+    elif task["status"] == TaskStatus.FAILED:
+        response["error"] = task["error"]
+
+    return response
+
+async def stream_results(crawler: AsyncWebCrawler, results_gen: AsyncGenerator) -> AsyncGenerator[bytes, None]:
+    """Stream results with heartbeats and completion markers."""
+    import json
+    from utils import datetime_handler
+
+    try:
+        async for result in results_gen:
+            try:
+                result_dict = result.model_dump()
+                logger.info(f"Streaming result for {result_dict.get('url', 'unknown')}")
+                data = json.dumps(result_dict, default=datetime_handler) + "\n"
+                yield data.encode('utf-8')
+            except Exception as e:
+                logger.error(f"Serialization error: {e}")
+                error_response = {"error": str(e), "url": getattr(result, 'url', 'unknown')}
+                yield (json.dumps(error_response) + "\n").encode('utf-8')
+
+        yield json.dumps({"status": "completed"}).encode('utf-8')
+        
+    except asyncio.CancelledError:
+        logger.warning("Client disconnected during streaming")
+    finally:
+        try:
+            await crawler.close()
+        except Exception as e:
+            logger.error(f"Crawler cleanup error: {e}")
+
+async def handle_crawl_request(
+    urls: List[str],
+    browser_config: dict,
+    crawler_config: dict,
+    config: dict
+) -> dict:
+    """Handle non-streaming crawl requests."""
+    try:
+        browser_config = BrowserConfig.load(browser_config)
+        crawler_config = CrawlerRunConfig.load(crawler_config)
+
+        dispatcher = MemoryAdaptiveDispatcher(
+            memory_threshold_percent=config["crawler"]["memory_threshold_percent"],
+            rate_limiter=RateLimiter(
+                base_delay=tuple(config["crawler"]["rate_limiter"]["base_delay"])
+            )
+        )
+
+        async with AsyncWebCrawler(config=browser_config) as crawler:
+            results = await crawler.arun_many(
+                urls=urls,
+                config=crawler_config,
+                dispatcher=dispatcher
+            )
+            
+            return {
+                "success": True,
+                "results": [result.model_dump() for result in results]
+            }
+
+    except Exception as e:
+        logger.error(f"Crawl error: {str(e)}", exc_info=True)
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=str(e)
+        )
+
+async def handle_stream_crawl_request(
+    urls: List[str],
+    browser_config: dict,
+    crawler_config: dict,
+    config: dict
+) -> Tuple[AsyncWebCrawler, AsyncGenerator]:
+    """Handle streaming crawl requests."""
+    try:
+        browser_config = BrowserConfig.load(browser_config)
+        browser_config.verbose = True
+        crawler_config = CrawlerRunConfig.load(crawler_config)
+        crawler_config.scraping_strategy = LXMLWebScrapingStrategy()
+
+        dispatcher = MemoryAdaptiveDispatcher(
+            memory_threshold_percent=config["crawler"]["memory_threshold_percent"],
+            rate_limiter=RateLimiter(
+                base_delay=tuple(config["crawler"]["rate_limiter"]["base_delay"])
+            )
+        )
+
+        crawler = AsyncWebCrawler(config=browser_config)
+        await crawler.start()
+
+        results_gen = await crawler.arun_many(
+            urls=urls,
+            config=crawler_config,
+            dispatcher=dispatcher
+        )
+
+        return crawler, results_gen
+
+    except Exception as e:
+        if 'crawler' in locals():
+            await crawler.close()
+        logger.error(f"Stream crawl error: {str(e)}", exc_info=True)
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=str(e)
+        )

deploy/aws/docker/auth.py

@@ -0,0 +1,46 @@
+import os
+from datetime import datetime, timedelta, timezone
+from typing import Dict, Optional
+from jwt import JWT, jwk_from_dict
+from jwt.utils import get_int_from_datetime
+from fastapi import Depends, HTTPException
+from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
+from pydantic import EmailStr
+from pydantic.main import BaseModel
+import base64
+
+instance = JWT()
+security = HTTPBearer()
+SECRET_KEY = os.environ.get("SECRET_KEY", "mysecret")
+ACCESS_TOKEN_EXPIRE_MINUTES = 60
+
+def get_jwk_from_secret(secret: str):
+    """Convert a secret string into a JWK object."""
+    secret_bytes = secret.encode('utf-8')
+    b64_secret = base64.urlsafe_b64encode(secret_bytes).rstrip(b'=').decode('utf-8')
+    return jwk_from_dict({"kty": "oct", "k": b64_secret})
+
+def create_access_token(data: dict, expires_delta: Optional[timedelta] = None) -> str:
+    """Create a JWT access token with an expiration."""
+    to_encode = data.copy()
+    expire = datetime.now(timezone.utc) + (expires_delta or timedelta(minutes=ACCESS_TOKEN_EXPIRE_MINUTES))
+    to_encode.update({"exp": get_int_from_datetime(expire)})
+    signing_key = get_jwk_from_secret(SECRET_KEY)
+    return instance.encode(to_encode, signing_key, alg='HS256')
+
+def verify_token(credentials: HTTPAuthorizationCredentials = Depends(security)) -> Dict:
+    """Verify the JWT token from the Authorization header."""
+    token = credentials.credentials
+    verifying_key = get_jwk_from_secret(SECRET_KEY)
+    try:
+        payload = instance.decode(token, verifying_key, do_time_check=True, algorithms='HS256')
+        return payload
+    except Exception:
+        raise HTTPException(status_code=401, detail="Invalid or expired token")
+
+def get_token_dependency(config: Dict):
+    """Return the token dependency if JWT is enabled, else None."""
+    return verify_token if config.get("security", {}).get("jwt_enabled", False) else None
+
+class TokenRequest(BaseModel):
+    email: EmailStr

deploy/aws/docker/config.yml

@@ -0,0 +1,71 @@
+# Application Configuration
+app:
+  title: "Crawl4AI API"
+  version: "1.0.0"
+  host: "0.0.0.0"
+  port: 8000
+  reload: True
+  timeout_keep_alive: 300
+
+# Default LLM Configuration
+llm:
+  provider: "openai/gpt-4o-mini"
+  api_key_env: "OPENAI_API_KEY"
+  # api_key: sk-...  # If you pass the API key directly then api_key_env will be ignored
+
+# Redis Configuration
+redis:
+  host: "localhost"
+  port: 6379
+  db: 0
+  password: ""
+  ssl: False
+  ssl_cert_reqs: None
+  ssl_ca_certs: None
+  ssl_certfile: None
+  ssl_keyfile: None
+  ssl_cert_reqs: None
+  ssl_ca_certs: None
+  ssl_certfile: None
+  ssl_keyfile: None
+
+# Rate Limiting Configuration
+rate_limiting:
+  enabled: True
+  default_limit: "1000/minute"
+  trusted_proxies: []
+  storage_uri: "memory://"  # Use "redis://localhost:6379" for production
+
+# Security Configuration
+security:
+  enabled: true 
+  jwt_enabled: true 
+  https_redirect: false
+  trusted_hosts: ["*"]
+  headers:
+    x_content_type_options: "nosniff"
+    x_frame_options: "DENY"
+    content_security_policy: "default-src 'self'"
+    strict_transport_security: "max-age=63072000; includeSubDomains"
+
+# Crawler Configuration
+crawler:
+  memory_threshold_percent: 95.0
+  rate_limiter:
+    base_delay: [1.0, 2.0]
+  timeouts:
+    stream_init: 30.0  # Timeout for stream initialization
+    batch_process: 300.0  # Timeout for batch processing
+
+# Logging Configuration
+logging:
+  level: "INFO"
+  format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+
+# Observability Configuration
+observability:
+  prometheus:
+    enabled: True
+    endpoint: "/metrics"
+  health_check:
+    endpoint: "/health"

deploy/aws/docker/requirements.txt

@@ -0,0 +1,10 @@
+crawl4ai
+fastapi
+uvicorn
+gunicorn>=23.0.0
+slowapi>=0.1.9
+prometheus-fastapi-instrumentator>=7.0.2
+redis>=5.2.1
+jwt>=1.3.1
+dnspython>=2.7.0
+email-validator>=2.2.0

deploy/aws/docker/server.py

@@ -0,0 +1,181 @@
+import os
+import sys
+import time
+from typing import List, Optional, Dict
+from fastapi import FastAPI, HTTPException, Request, Query, Path, Depends
+from fastapi.responses import StreamingResponse, RedirectResponse, PlainTextResponse, JSONResponse
+from fastapi.middleware.httpsredirect import HTTPSRedirectMiddleware
+from fastapi.middleware.trustedhost import TrustedHostMiddleware
+from pydantic import BaseModel, Field
+from slowapi import Limiter
+from slowapi.util import get_remote_address
+from prometheus_fastapi_instrumentator import Instrumentator
+from redis import asyncio as aioredis
+
+sys.path.append(os.path.dirname(os.path.realpath(__file__)))
+from utils import FilterType, load_config, setup_logging, verify_email_domain
+from api import (
+    handle_markdown_request,
+    handle_llm_qa,
+    handle_stream_crawl_request,
+    handle_crawl_request,
+    stream_results
+)
+from auth import create_access_token, get_token_dependency, TokenRequest  # Import from auth.py
+
+__version__ = "0.2.6"
+
+class CrawlRequest(BaseModel):
+    urls: List[str] = Field(min_length=1, max_length=100)
+    browser_config: Optional[Dict] = Field(default_factory=dict)
+    crawler_config: Optional[Dict] = Field(default_factory=dict)
+
+# Load configuration and setup
+config = load_config()
+setup_logging(config)
+
+# Initialize Redis
+redis = aioredis.from_url(config["redis"].get("uri", "redis://localhost"))
+
+# Initialize rate limiter
+limiter = Limiter(
+    key_func=get_remote_address,
+    default_limits=[config["rate_limiting"]["default_limit"]],
+    storage_uri=config["rate_limiting"]["storage_uri"]
+)
+
+app = FastAPI(
+    title=config["app"]["title"],
+    version=config["app"]["version"]
+)
+
+# Configure middleware
+def setup_security_middleware(app, config):
+    sec_config = config.get("security", {})
+    if sec_config.get("enabled", False):
+        if sec_config.get("https_redirect", False):
+            app.add_middleware(HTTPSRedirectMiddleware)
+        if sec_config.get("trusted_hosts", []) != ["*"]:
+            app.add_middleware(TrustedHostMiddleware, allowed_hosts=sec_config["trusted_hosts"])
+
+setup_security_middleware(app, config)
+
+# Prometheus instrumentation
+if config["observability"]["prometheus"]["enabled"]:
+    Instrumentator().instrument(app).expose(app)
+
+# Get token dependency based on config
+token_dependency = get_token_dependency(config)
+
+# Middleware for security headers
+@app.middleware("http")
+async def add_security_headers(request: Request, call_next):
+    response = await call_next(request)
+    if config["security"]["enabled"]:
+        response.headers.update(config["security"]["headers"])
+    return response
+
+# Token endpoint (always available, but usage depends on config)
+@app.post("/token")
+async def get_token(request_data: TokenRequest):
+    if not verify_email_domain(request_data.email):
+        raise HTTPException(status_code=400, detail="Invalid email domain")
+    token = create_access_token({"sub": request_data.email})
+    return {"email": request_data.email, "access_token": token, "token_type": "bearer"}
+
+# Endpoints with conditional auth
+@app.get("/md/{url:path}")
+@limiter.limit(config["rate_limiting"]["default_limit"])
+async def get_markdown(
+    request: Request,
+    url: str,
+    f: FilterType = FilterType.FIT,
+    q: Optional[str] = None,
+    c: Optional[str] = "0",
+    token_data: Optional[Dict] = Depends(token_dependency)
+):
+    result = await handle_markdown_request(url, f, q, c, config)
+    return PlainTextResponse(result)
+
+@app.get("/llm/{url:path}", description="URL should be without http/https prefix")
+async def llm_endpoint(
+    request: Request,
+    url: str = Path(...),
+    q: Optional[str] = Query(None),
+    token_data: Optional[Dict] = Depends(token_dependency)
+):
+    if not q:
+        raise HTTPException(status_code=400, detail="Query parameter 'q' is required")
+    if not url.startswith(('http://', 'https://')):
+        url = 'https://' + url
+    try:
+        answer = await handle_llm_qa(url, q, config)
+        return JSONResponse({"answer": answer})
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.get("/schema")
+async def get_schema():
+    from crawl4ai import BrowserConfig, CrawlerRunConfig
+    return {"browser": BrowserConfig().dump(), "crawler": CrawlerRunConfig().dump()}
+
+@app.get(config["observability"]["health_check"]["endpoint"])
+async def health():
+    return {"status": "ok", "timestamp": time.time(), "version": __version__}
+
+@app.get(config["observability"]["prometheus"]["endpoint"])
+async def metrics():
+    return RedirectResponse(url=config["observability"]["prometheus"]["endpoint"])
+
+@app.post("/crawl")
+@limiter.limit(config["rate_limiting"]["default_limit"])
+async def crawl(
+    request: Request,
+    crawl_request: CrawlRequest,
+    token_data: Optional[Dict] = Depends(token_dependency)
+):
+    if not crawl_request.urls:
+        raise HTTPException(status_code=400, detail="At least one URL required")
+    
+    results = await handle_crawl_request(
+        urls=crawl_request.urls,
+        browser_config=crawl_request.browser_config,
+        crawler_config=crawl_request.crawler_config,
+        config=config
+    )
+
+    return JSONResponse(results)
+
+
+@app.post("/crawl/stream")
+@limiter.limit(config["rate_limiting"]["default_limit"])
+async def crawl_stream(
+    request: Request,
+    crawl_request: CrawlRequest,
+    token_data: Optional[Dict] = Depends(token_dependency)
+):
+    if not crawl_request.urls:
+        raise HTTPException(status_code=400, detail="At least one URL required")
+
+    crawler, results_gen = await handle_stream_crawl_request(
+        urls=crawl_request.urls,
+        browser_config=crawl_request.browser_config,
+        crawler_config=crawl_request.crawler_config,
+        config=config
+    )
+
+    return StreamingResponse(
+        stream_results(crawler, results_gen),
+        media_type='application/x-ndjson',
+        headers={'Cache-Control': 'no-cache', 'Connection': 'keep-alive', 'X-Stream-Status': 'active'}
+    )
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(
+        "server:app",
+        host=config["app"]["host"],
+        port=config["app"]["port"],
+        reload=config["app"]["reload"],
+        timeout_keep_alive=config["app"]["timeout_keep_alive"]
+    )

deploy/aws/docker/supervisord.conf

@@ -0,0 +1,12 @@
+[supervisord]
+nodaemon=true
+
+[program:redis]
+command=redis-server
+autorestart=true
+priority=10
+
+[program:gunicorn]
+command=gunicorn --bind 0.0.0.0:8000 --workers 4 --threads 2 --timeout 300 --graceful-timeout 60 --keep-alive 65 --log-level debug --worker-class uvicorn.workers.UvicornWorker --max-requests 1000 --max-requests-jitter 50 server:app
+autorestart=true
+priority=20

deploy/aws/docker/utils.py

@@ -0,0 +1,66 @@
+import dns.resolver
+import logging
+import yaml
+from datetime import datetime
+from enum import Enum
+from pathlib import Path
+from fastapi import Request
+from typing import Dict, Optional
+
+class TaskStatus(str, Enum):
+    PROCESSING = "processing"
+    FAILED = "failed"
+    COMPLETED = "completed"
+
+class FilterType(str, Enum):
+    RAW = "raw"
+    FIT = "fit"
+    BM25 = "bm25"
+    LLM = "llm"
+
+def load_config() -> Dict:
+    """Load and return application configuration."""
+    config_path = Path(__file__).parent / "config.yml"
+    with open(config_path, "r") as config_file:
+        return yaml.safe_load(config_file)
+
+def setup_logging(config: Dict) -> None:
+    """Configure application logging."""
+    logging.basicConfig(
+        level=config["logging"]["level"],
+        format=config["logging"]["format"]
+    )
+
+def get_base_url(request: Request) -> str:
+    """Get base URL including scheme and host."""
+    return f"{request.url.scheme}://{request.url.netloc}"
+
+def is_task_id(value: str) -> bool:
+    """Check if the value matches task ID pattern."""
+    return value.startswith("llm_") and "_" in value
+
+def datetime_handler(obj: any) -> Optional[str]:
+    """Handle datetime serialization for JSON."""
+    if hasattr(obj, 'isoformat'):
+        return obj.isoformat()
+    raise TypeError(f"Object of type {type(obj)} is not JSON serializable")
+
+def should_cleanup_task(created_at: str) -> bool:
+    """Check if task should be cleaned up based on creation time."""
+    created = datetime.fromisoformat(created_at)
+    return (datetime.now() - created).total_seconds() > 3600
+
+def decode_redis_hash(hash_data: Dict[bytes, bytes]) -> Dict[str, str]:
+    """Decode Redis hash data from bytes to strings."""
+    return {k.decode('utf-8'): v.decode('utf-8') for k, v in hash_data.items()}
+
+
+
+def verify_email_domain(email: str) -> bool:
+    try:
+        domain = email.split('@')[1]
+        # Try to resolve MX records for the domain.
+        records = dns.resolver.resolve(domain, 'MX')
+        return True if records else False
+    except Exception as e:
+        return False

deploy/aws/howto.md

@@ -0,0 +1,77 @@
+# Crawl4AI API Quickstart
+
+This document shows how to generate an API token and use it to call the `/crawl` and `/md` endpoints.
+
+---
+
+## 1. Crawl Example
+
+Send a POST request to `/crawl` with the following JSON payload:
+
+```json
+{
+  "urls": ["https://example.com"],
+  "browser_config": { "headless": true, "verbose": true },
+  "crawler_config": { "stream": false, "cache_mode": "enabled" }
+}
+```
+
+**cURL Command:**
+
+```bash
+curl -X POST "https://api.crawl4ai.com/crawl" \
+  -H "Authorization: Bearer YOUR_API_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+        "urls": ["https://example.com"],
+        "browser_config": {"headless": true, "verbose": true},
+        "crawler_config": {"stream": false, "cache_mode": "enabled"}
+      }'
+```
+
+---
+
+## 2. Markdown Retrieval Example
+
+To retrieve markdown from a given URL (e.g., `https://example.com`), use:
+
+```bash
+curl -X GET "https://api.crawl4ai.com/md/example.com" \
+  -H "Authorization: Bearer YOUR_API_TOKEN"
+```
+
+---
+
+## 3. Python Code Example (Using `requests`)
+
+Below is a sample Python script that demonstrates using the `requests` library to call the API endpoints:
+
+```python
+import requests
+
+BASE_URL = "https://api.crawl4ai.com"
+TOKEN = "YOUR_API_TOKEN"  # Replace with your actual token
+
+headers = {
+    "Authorization": f"Bearer {TOKEN}",
+    "Content-Type": "application/json"
+}
+
+# Crawl endpoint example
+crawl_payload = {
+    "urls": ["https://example.com"],
+    "browser_config": {"headless": True, "verbose": True},
+    "crawler_config": {"stream": False, "cache_mode": "enabled"}
+}
+
+crawl_response = requests.post(f"{BASE_URL}/crawl", json=crawl_payload, headers=headers)
+print("Crawl Response:", crawl_response.json())
+
+# /md endpoint example
+md_response = requests.get(f"{BASE_URL}/md/example.com", headers=headers)
+print("Markdown Content:", md_response.text)
+```
+
+---
+
+Happy crawling!

deploy/aws/nginx/Dockerfile

@@ -0,0 +1,2 @@
+FROM nginx:alpine
+COPY nginx.conf /etc/nginx/conf.d/default.conf

deploy/aws/nginx/nginx.conf

@@ -0,0 +1,55 @@
+server {
+    listen 80;
+    server_name api.crawl4ai.com;
+
+    # Main logging settings
+    error_log /var/log/nginx/error.log debug;
+    access_log /var/log/nginx/access.log combined buffer=512k flush=1m;
+
+    # Timeout and buffering settings
+    proxy_connect_timeout 300;
+    proxy_send_timeout 300;
+    proxy_read_timeout 300;
+    send_timeout 300;
+    proxy_buffer_size 128k;
+    proxy_buffers 4 256k;
+    proxy_busy_buffers_size 256k;
+
+    # Health check location
+    location /health {
+        proxy_pass http://127.0.0.1:8000/health;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+    }
+
+    # Main proxy for application endpoints
+    location / {
+        proxy_pass http://127.0.0.1:8000;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+        add_header X-Debug-Info $request_uri;
+        proxy_request_buffering off;
+        proxy_http_version 1.1;
+        proxy_set_header Connection "";
+        proxy_buffering off;
+    }
+
+    # New endpoint: serve Nginx error log
+    location /nginx/error {
+        # Using "alias" to serve the error log file
+        alias /var/log/nginx/error.log;
+        # Optionally, you might restrict access with "allow" and "deny" directives.
+    }
+
+    # New endpoint: serve Nginx access log
+    location /nginx/access {
+        alias /var/log/nginx/access.log;
+    }
+
+    client_max_body_size 10M;
+    client_body_buffer_size 128k;
+}

deploy/aws/version.txt

@@ -0,0 +1 @@
+v0.1.0

deploy/docker/README-new.md

@@ -1,644 +0,0 @@
-# Crawl4AI Docker Guide 🐳
-
-## Table of Contents
-- [Prerequisites](#prerequisites)
-- [Installation](#installation)
-  - [Option 1: Using Docker Compose (Recommended)](#option-1-using-docker-compose-recommended)
-  - [Option 2: Manual Local Build & Run](#option-2-manual-local-build--run)
-  - [Option 3: Using Pre-built Docker Hub Images](#option-3-using-pre-built-docker-hub-images)
-- [Dockerfile Parameters](#dockerfile-parameters)
-- [Using the API](#using-the-api)
-  - [Understanding Request Schema](#understanding-request-schema)
-  - [REST API Examples](#rest-api-examples)
-  - [Python SDK](#python-sdk)
-- [Metrics & Monitoring](#metrics--monitoring)
-- [Deployment Scenarios](#deployment-scenarios)
-- [Complete Examples](#complete-examples)
-- [Server Configuration](#server-configuration)
-  - [Understanding config.yml](#understanding-configyml)
-  - [JWT Authentication](#jwt-authentication)
-  - [Configuration Tips and Best Practices](#configuration-tips-and-best-practices)
-  - [Customizing Your Configuration](#customizing-your-configuration)
-  - [Configuration Recommendations](#configuration-recommendations)
-- [Getting Help](#getting-help)
-
-## Prerequisites
-
-Before we dive in, make sure you have:
-- Docker installed and running (version 20.10.0 or higher), including `docker compose` (usually bundled with Docker Desktop).
-- `git` for cloning the repository.
-- At least 4GB of RAM available for the container (more recommended for heavy use).
-- Python 3.10+ (if using the Python SDK).
-- Node.js 16+ (if using the Node.js examples).
-
-> 💡 **Pro tip**: Run `docker info` to check your Docker installation and available resources.
-
-## Installation
-
-We offer several ways to get the Crawl4AI server running. Docker Compose is the easiest way to manage local builds and runs.
-
-### Option 1: Using Docker Compose (Recommended)
-
-Docker Compose simplifies building and running the service, especially for local development and testing across different platforms.
-
-#### 1. Clone Repository
-
-```bash
-git clone https://github.com/unclecode/crawl4ai.git
-cd crawl4ai
-```
-
-#### 2. Environment Setup (API Keys)
-
-If you plan to use LLMs, copy the example environment file and add your API keys. This file should be in the **project root directory**.
-
-```bash
-# Make sure you are in the 'crawl4ai' root directory
-cp deploy/docker/.llm.env.example .llm.env
-
-# Now edit .llm.env and add your API keys
-# Example content:
-# OPENAI_API_KEY=sk-your-key
-# ANTHROPIC_API_KEY=your-anthropic-key
-# ...
-```
-> 🔑 **Note**: Keep your API keys secure! Never commit `.llm.env` to version control.
-
-#### 3. Build and Run with Compose
-
-The `docker-compose.yml` file in the project root defines services for different scenarios using **profiles**.
-
-*   **Build and Run Locally (AMD64):**
-    ```bash
-    # Builds the image locally using Dockerfile and runs it
-    docker compose --profile local-amd64 up --build -d
-    ```
-
-*   **Build and Run Locally (ARM64):**
-    ```bash
-    # Builds the image locally using Dockerfile and runs it
-    docker compose --profile local-arm64 up --build -d
-    ```
-
-*   **Run Pre-built Image from Docker Hub (AMD64):**
-    ```bash
-    # Pulls and runs the specified AMD64 image from Docker Hub
-    # (Set VERSION env var for specific tags, e.g., VERSION=0.5.1-d1)
-    docker compose --profile hub-amd64 up -d
-    ```
-
-*   **Run Pre-built Image from Docker Hub (ARM64):**
-    ```bash
-    # Pulls and runs the specified ARM64 image from Docker Hub
-    docker compose --profile hub-arm64 up -d
-    ```
-
-> The server will be available at `http://localhost:11235`.
-
-#### 4. Stopping Compose Services
-
-```bash
-# Stop the service(s) associated with a profile (e.g., local-amd64)
-docker compose --profile local-amd64 down
-```
-
-### Option 2: Manual Local Build & Run
-
-If you prefer not to use Docker Compose for local builds.
-
-#### 1. Clone Repository & Setup Environment
-
-Follow steps 1 and 2 from the Docker Compose section above (clone repo, `cd crawl4ai`, create `.llm.env` in the root).
-
-#### 2. Build the Image (Multi-Arch)
-
-Use `docker buildx` to build the image. This example builds for multiple platforms and loads the image matching your host architecture into the local Docker daemon.
-
-```bash
-# Make sure you are in the 'crawl4ai' root directory
-docker buildx build --platform linux/amd64,linux/arm64 -t crawl4ai-local:latest --load .
-```
-
-#### 3. Run the Container
-
-*   **Basic run (no LLM support):**
-    ```bash
-    # Replace --platform if your host is ARM64
-    docker run -d \
-      -p 11235:11235 \
-      --name crawl4ai-standalone \
-      --shm-size=1g \
-      --platform linux/amd64 \
-      crawl4ai-local:latest
-    ```
-
-*   **With LLM support:**
-    ```bash
-    # Make sure .llm.env is in the current directory (project root)
-    # Replace --platform if your host is ARM64
-    docker run -d \
-      -p 11235:11235 \
-      --name crawl4ai-standalone \
-      --env-file .llm.env \
-      --shm-size=1g \
-      --platform linux/amd64 \
-      crawl4ai-local:latest
-    ```
-
-> The server will be available at `http://localhost:11235`.
-
-#### 4. Stopping the Manual Container
-
-```bash
-docker stop crawl4ai-standalone && docker rm crawl4ai-standalone
-```
-
-### Option 3: Using Pre-built Docker Hub Images
-
-Pull and run images directly from Docker Hub without building locally.
-
-#### 1. Pull the Image
-
-We use a versioning scheme like `LIBRARY_VERSION-dREVISION` (e.g., `0.5.1-d1`). The `latest` tag points to the most recent stable release. Images are built with multi-arch manifests, so Docker usually pulls the correct version for your system automatically.
-
-```bash
-# Pull a specific version (recommended for stability)
-docker pull unclecode/crawl4ai:0.5.1-d1
-
-# Or pull the latest stable version
-docker pull unclecode/crawl4ai:latest
-```
-
-#### 2. Setup Environment (API Keys)
-
-If using LLMs, create the `.llm.env` file in a directory of your choice, similar to Step 2 in the Compose section.
-
-#### 3. Run the Container
-
-*   **Basic run:**
-    ```bash
-    docker run -d \
-      -p 11235:11235 \
-      --name crawl4ai-hub \
-      --shm-size=1g \
-      unclecode/crawl4ai:0.5.1-d1 # Or use :latest
-    ```
-
-*   **With LLM support:**
-    ```bash
-    # Make sure .llm.env is in the current directory you are running docker from
-    docker run -d \
-      -p 11235:11235 \
-      --name crawl4ai-hub \
-      --env-file .llm.env \
-      --shm-size=1g \
-      unclecode/crawl4ai:0.5.1-d1 # Or use :latest
-    ```
-
-> The server will be available at `http://localhost:11235`.
-
-#### 4. Stopping the Hub Container
-
-```bash
-docker stop crawl4ai-hub && docker rm crawl4ai-hub
-```
-
-#### Docker Hub Versioning Explained
-
-*   **Image Name:** `unclecode/crawl4ai`
-*   **Tag Format:** `LIBRARY_VERSION-dREVISION`
-    *   `LIBRARY_VERSION`: The Semantic Version of the core `crawl4ai` Python library included (e.g., `0.5.1`).
-    *   `dREVISION`: An incrementing number (starting at `d1`) for Docker build changes made *without* changing the library version (e.g., base image updates, dependency fixes). Resets to `d1` for each new `LIBRARY_VERSION`.
-*   **Example:** `unclecode/crawl4ai:0.5.1-d1`
-*   **`latest` Tag:** Points to the most recent stable `LIBRARY_VERSION-dREVISION`.
-*   **Multi-Arch:** Images support `linux/amd64` and `linux/arm64`. Docker automatically selects the correct architecture.
-
----
-
-*(Rest of the document remains largely the same, but with key updates below)*
-
----
-
-## Dockerfile Parameters
-
-You can customize the image build process using build arguments (`--build-arg`). These are typically used via `docker buildx build` or within the `docker-compose.yml` file.
-
-```bash
-# Example: Build with 'all' features using buildx
-docker buildx build \
-  --platform linux/amd64,linux/arm64 \
-  --build-arg INSTALL_TYPE=all \
-  -t yourname/crawl4ai-all:latest \
-  --load \
-  . # Build from root context
-```
-
-### Build Arguments Explained
-
-| Argument     | Description                              | Default   | Options                            |
-| :----------- | :--------------------------------------- | :-------- | :--------------------------------- |
-| INSTALL_TYPE | Feature set                              | `default` | `default`, `all`, `torch`, `transformer` |
-| ENABLE_GPU   | GPU support (CUDA for AMD64)           | `false`   | `true`, `false`                    |
-| APP_HOME     | Install path inside container (advanced) | `/app`    | any valid path                   |
-| USE_LOCAL    | Install library from local source        | `true`    | `true`, `false`                    |
-| GITHUB_REPO  | Git repo to clone if USE_LOCAL=false   | *(see Dockerfile)* | any git URL                  |
-| GITHUB_BRANCH| Git branch to clone if USE_LOCAL=false   | `main`    | any branch name                  |
-
-*(Note: PYTHON_VERSION is fixed by the `FROM` instruction in the Dockerfile)*
-
-### Build Best Practices
-
-1.  **Choose the Right Install Type**
-    *   `default`: Basic installation, smallest image size. Suitable for most standard web scraping and markdown generation.
-    *   `all`: Full features including `torch` and `transformers` for advanced extraction strategies (e.g., CosineStrategy, certain LLM filters). Significantly larger image. Ensure you need these extras.
-2.  **Platform Considerations**
-    *   Use `buildx` for building multi-architecture images, especially for pushing to registries.
-    *   Use `docker compose` profiles (`local-amd64`, `local-arm64`) for easy platform-specific local builds.
-3.  **Performance Optimization**
-    *   The image automatically includes platform-specific optimizations (OpenMP for AMD64, OpenBLAS for ARM64).
-
----
-
-## Using the API
-
-Communicate with the running Docker server via its REST API (defaulting to `http://localhost:11235`). You can use the Python SDK or make direct HTTP requests.
-
-### Python SDK
-
-Install the SDK: `pip install crawl4ai`
-
-```python
-import asyncio
-from crawl4ai.docker_client import Crawl4aiDockerClient
-from crawl4ai import BrowserConfig, CrawlerRunConfig, CacheMode # Assuming you have crawl4ai installed
-
-async def main():
-    # Point to the correct server port
-    async with Crawl4aiDockerClient(base_url="http://localhost:11235", verbose=True) as client:
-        # If JWT is enabled on the server, authenticate first:
-        # await client.authenticate("user@example.com") # See Server Configuration section
-
-        # Example Non-streaming crawl
-        print("--- Running Non-Streaming Crawl ---")
-        results = await client.crawl(
-            ["https://httpbin.org/html"],
-            browser_config=BrowserConfig(headless=True), # Use library classes for config aid
-            crawler_config=CrawlerRunConfig(cache_mode=CacheMode.BYPASS)
-        )
-        if results: # client.crawl returns None on failure
-          print(f"Non-streaming results success: {results.success}")
-          if results.success:
-              for result in results: # Iterate through the CrawlResultContainer
-                  print(f"URL: {result.url}, Success: {result.success}")
-        else:
-            print("Non-streaming crawl failed.")
-
-
-        # Example Streaming crawl
-        print("\n--- Running Streaming Crawl ---")
-        stream_config = CrawlerRunConfig(stream=True, cache_mode=CacheMode.BYPASS)
-        try:
-            async for result in await client.crawl( # client.crawl returns an async generator for streaming
-                ["https://httpbin.org/html", "https://httpbin.org/links/5/0"],
-                browser_config=BrowserConfig(headless=True),
-                crawler_config=stream_config
-            ):
-                print(f"Streamed result: URL: {result.url}, Success: {result.success}")
-        except Exception as e:
-            print(f"Streaming crawl failed: {e}")
-
-
-        # Example Get schema
-        print("\n--- Getting Schema ---")
-        schema = await client.get_schema()
-        print(f"Schema received: {bool(schema)}") # Print whether schema was received
-
-if __name__ == "__main__":
-    asyncio.run(main())
-```
-
-*(SDK parameters like timeout, verify_ssl etc. remain the same)*
-
-### Second Approach: Direct API Calls
-
-Crucially, when sending configurations directly via JSON, they **must** follow the `{"type": "ClassName", "params": {...}}` structure for any non-primitive value (like config objects or strategies). Dictionaries must be wrapped as `{"type": "dict", "value": {...}}`.
-
-*(Keep the detailed explanation of Configuration Structure, Basic Pattern, Simple vs Complex, Strategy Pattern, Complex Nested Example, Quick Grammar Overview, Important Rules, Pro Tip)*
-
-#### More Examples *(Ensure Schema example uses type/value wrapper)*
-
-**Advanced Crawler Configuration**
-*(Keep example, ensure cache_mode uses valid enum value like "bypass")*
-
-**Extraction Strategy**
-```json
-{
-    "crawler_config": {
-        "type": "CrawlerRunConfig",
-        "params": {
-            "extraction_strategy": {
-                "type": "JsonCssExtractionStrategy",
-                "params": {
-                    "schema": {
-                        "type": "dict",
-                        "value": {
-                           "baseSelector": "article.post",
-                           "fields": [
-                               {"name": "title", "selector": "h1", "type": "text"},
-                               {"name": "content", "selector": ".content", "type": "html"}
-                           ]
-                         }
-                    }
-                }
-            }
-        }
-    }
-}
-```
-
-**LLM Extraction Strategy** *(Keep example, ensure schema uses type/value wrapper)*
-*(Keep Deep Crawler Example)*
-
-### REST API Examples
-
-Update URLs to use port `11235`.
-
-#### Simple Crawl
-
-```python
-import requests
-
-# Configuration objects converted to the required JSON structure
-browser_config_payload = {
-    "type": "BrowserConfig",
-    "params": {"headless": True}
-}
-crawler_config_payload = {
-    "type": "CrawlerRunConfig",
-    "params": {"stream": False, "cache_mode": "bypass"} # Use string value of enum
-}
-
-crawl_payload = {
-    "urls": ["https://httpbin.org/html"],
-    "browser_config": browser_config_payload,
-    "crawler_config": crawler_config_payload
-}
-response = requests.post(
-    "http://localhost:11235/crawl", # Updated port
-    # headers={"Authorization": f"Bearer {token}"},  # If JWT is enabled
-    json=crawl_payload
-)
-print(f"Status Code: {response.status_code}")
-if response.ok:
-    print(response.json())
-else:
-    print(f"Error: {response.text}")
-
-```
-
-#### Streaming Results
-
-```python
-import json
-import httpx # Use httpx for async streaming example
-
-async def test_stream_crawl(token: str = None): # Made token optional
-    """Test the /crawl/stream endpoint with multiple URLs."""
-    url = "http://localhost:11235/crawl/stream" # Updated port
-    payload = {
-        "urls": [
-            "https://httpbin.org/html",
-            "https://httpbin.org/links/5/0",
-        ],
-        "browser_config": {
-            "type": "BrowserConfig",
-            "params": {"headless": True, "viewport": {"type": "dict", "value": {"width": 1200, "height": 800}}} # Viewport needs type:dict
-        },
-        "crawler_config": {
-            "type": "CrawlerRunConfig",
-            "params": {"stream": True, "cache_mode": "bypass"}
-        }
-    }
-
-    headers = {}
-    # if token:
-    #    headers = {"Authorization": f"Bearer {token}"} # If JWT is enabled
-
-    try:
-        async with httpx.AsyncClient() as client:
-            async with client.stream("POST", url, json=payload, headers=headers, timeout=120.0) as response:
-                print(f"Status: {response.status_code} (Expected: 200)")
-                response.raise_for_status() # Raise exception for bad status codes
-
-                # Read streaming response line-by-line (NDJSON)
-                async for line in response.aiter_lines():
-                    if line:
-                        try:
-                            data = json.loads(line)
-                            # Check for completion marker
-                            if data.get("status") == "completed":
-                                print("Stream completed.")
-                                break
-                            print(f"Streamed Result: {json.dumps(data, indent=2)}")
-                        except json.JSONDecodeError:
-                            print(f"Warning: Could not decode JSON line: {line}")
-
-    except httpx.HTTPStatusError as e:
-         print(f"HTTP error occurred: {e.response.status_code} - {e.response.text}")
-    except Exception as e:
-        print(f"Error in streaming crawl test: {str(e)}")
-
-# To run this example:
-# import asyncio
-# asyncio.run(test_stream_crawl())
-```
-
----
-
-## Metrics & Monitoring
-
-Keep an eye on your crawler with these endpoints:
-
-- `/health` - Quick health check
-- `/metrics` - Detailed Prometheus metrics
-- `/schema` - Full API schema
-
-Example health check:
-```bash
-curl http://localhost:11235/health
-```
-
----
-
-*(Deployment Scenarios and Complete Examples sections remain the same, maybe update links if examples moved)*
-
----
-
-## Server Configuration
-
-The server's behavior can be customized through the `config.yml` file.
-
-### Understanding config.yml
-
-The configuration file is loaded from `/app/config.yml` inside the container. By default, the file from `deploy/docker/config.yml` in the repository is copied there during the build.
-
-Here's a detailed breakdown of the configuration options (using defaults from `deploy/docker/config.yml`):
-
-```yaml
-# Application Configuration
-app:
-  title: "Crawl4AI API"
-  version: "1.0.0" # Consider setting this to match library version, e.g., "0.5.1"
-  host: "0.0.0.0"
-  port: 8020 # NOTE: This port is used ONLY when running server.py directly. Gunicorn overrides this (see supervisord.conf).
-  reload: False # Default set to False - suitable for production
-  timeout_keep_alive: 300
-
-# Default LLM Configuration
-llm:
-  provider: "openai/gpt-4o-mini"
-  api_key_env: "OPENAI_API_KEY"
-  # api_key: sk-...  # If you pass the API key directly then api_key_env will be ignored
-
-# Redis Configuration (Used by internal Redis server managed by supervisord)
-redis:
-  host: "localhost"
-  port: 6379
-  db: 0
-  password: ""
-  # ... other redis options ...
-
-# Rate Limiting Configuration
-rate_limiting:
-  enabled: True
-  default_limit: "1000/minute"
-  trusted_proxies: []
-  storage_uri: "memory://"  # Use "redis://localhost:6379" if you need persistent/shared limits
-
-# Security Configuration
-security:
-  enabled: false # Master toggle for security features
-  jwt_enabled: false # Enable JWT authentication (requires security.enabled=true)
-  https_redirect: false # Force HTTPS (requires security.enabled=true)
-  trusted_hosts: ["*"] # Allowed hosts (use specific domains in production)
-  headers: # Security headers (applied if security.enabled=true)
-    x_content_type_options: "nosniff"
-    x_frame_options: "DENY"
-    content_security_policy: "default-src 'self'"
-    strict_transport_security: "max-age=63072000; includeSubDomains"
-
-# Crawler Configuration
-crawler:
-  memory_threshold_percent: 95.0
-  rate_limiter:
-    base_delay: [1.0, 2.0] # Min/max delay between requests in seconds for dispatcher
-  timeouts:
-    stream_init: 30.0  # Timeout for stream initialization
-    batch_process: 300.0 # Timeout for non-streaming /crawl processing
-
-# Logging Configuration
-logging:
-  level: "INFO"
-  format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
-
-# Observability Configuration
-observability:
-  prometheus:
-    enabled: True
-    endpoint: "/metrics"
-  health_check:
-    endpoint: "/health"
-```
-
-*(JWT Authentication section remains the same, just note the default port is now 11235 for requests)*
-
-*(Configuration Tips and Best Practices remain the same)*
-
-### Customizing Your Configuration
-
-You can override the default `config.yml`.
-
-#### Method 1: Modify Before Build
-
-1.  Edit the `deploy/docker/config.yml` file in your local repository clone.
-2.  Build the image using `docker buildx` or `docker compose --profile local-... up --build`. The modified file will be copied into the image.
-
-#### Method 2: Runtime Mount (Recommended for Custom Deploys)
-
-1.  Create your custom configuration file, e.g., `my-custom-config.yml` locally. Ensure it contains all necessary sections.
-2.  Mount it when running the container:
-
-    *   **Using `docker run`:**
-        ```bash
-        # Assumes my-custom-config.yml is in the current directory
-        docker run -d -p 11235:11235 \
-          --name crawl4ai-custom-config \
-          --env-file .llm.env \
-          --shm-size=1g \
-          -v $(pwd)/my-custom-config.yml:/app/config.yml \
-          unclecode/crawl4ai:latest # Or your specific tag
-        ```
-
-    *   **Using `docker-compose.yml`:** Add a `volumes` section to the service definition:
-        ```yaml
-        services:
-          crawl4ai-hub-amd64: # Or your chosen service
-            image: unclecode/crawl4ai:latest
-            profiles: ["hub-amd64"]
-            <<: *base-config
-            volumes:
-              # Mount local custom config over the default one in the container
-              - ./my-custom-config.yml:/app/config.yml
-              # Keep the shared memory volume from base-config
-              - /dev/shm:/dev/shm
-        ```
-        *(Note: Ensure `my-custom-config.yml` is in the same directory as `docker-compose.yml`)*
-
-> 💡 When mounting, your custom file *completely replaces* the default one. Ensure it's a valid and complete configuration.
-
-### Configuration Recommendations
-
-1. **Security First** 🔒
-   - Always enable security in production
-   - Use specific trusted_hosts instead of wildcards
-   - Set up proper rate limiting to protect your server
-   - Consider your environment before enabling HTTPS redirect
-
-2. **Resource Management** 💻
-   - Adjust memory_threshold_percent based on available RAM
-   - Set timeouts according to your content size and network conditions
-   - Use Redis for rate limiting in multi-container setups
-
-3. **Monitoring** 📊
-   - Enable Prometheus if you need metrics
-   - Set DEBUG logging in development, INFO in production
-   - Regular health check monitoring is crucial
-
-4. **Performance Tuning** ⚡
-   - Start with conservative rate limiter delays
-   - Increase batch_process timeout for large content
-   - Adjust stream_init timeout based on initial response times
-
-## Getting Help
-
-We're here to help you succeed with Crawl4AI! Here's how to get support:
-
-- 📖 Check our [full documentation](https://docs.crawl4ai.com)
-- 🐛 Found a bug? [Open an issue](https://github.com/unclecode/crawl4ai/issues)
-- 💬 Join our [Discord community](https://discord.gg/crawl4ai)
-- ⭐ Star us on GitHub to show support!
-
-## Summary
-
-In this guide, we've covered everything you need to get started with Crawl4AI's Docker deployment:
-- Building and running the Docker container
-- Configuring the environment
-- Making API requests with proper typing
-- Using the Python SDK
-- Monitoring your deployment
-
-Remember, the examples in the `examples` folder are your friends - they show real-world usage patterns that you can adapt for your needs.
-
-Keep exploring, and don't hesitate to reach out if you need help! We're building something amazing together. 🚀
-
-Happy crawling! 🕷️

deploy/docker/README.md

@@ -554,7 +554,7 @@ async def test_stream_crawl(session, token: str):
             "https://example.com/page3",  
         ],
         "browser_config": {"headless": True, "viewport": {"width": 1200}},
-        "crawler_config": {"stream": True, "cache_mode": "bypass"}
+        "crawler_config": {"stream": True, "cache_mode": "aggressive"}
     }
 
     # headers = {"Authorization": f"Bearer {token}"} # If JWT is enabled, more on this later

deploy/docker/api.py

@@ -2,7 +2,6 @@ import os
 import json
 import asyncio
 from typing import List, Tuple
-from functools import partial
 
 import logging
 from typing import Optional, AsyncGenerator
@@ -388,25 +387,20 @@ async def handle_crawl_request(
             )
         )
 
-        crawler: AsyncWebCrawler = AsyncWebCrawler(config=browser_config)
+        async with AsyncWebCrawler(config=browser_config) as crawler:
-        await crawler.start()
+            results = await crawler.arun_many(
-        results = []
+                urls=urls,
-        func = getattr(crawler, "arun" if len(urls) == 1 else "arun_many")
+                config=crawler_config,
-        partial_func = partial(func, 
+                dispatcher=dispatcher
-                                urls[0] if len(urls) == 1 else urls, 
+            )
-                                config=crawler_config, 
+            
-                                dispatcher=dispatcher)
+            return {
-        results = await partial_func()
+                "success": True,
-        await crawler.close()
+                "results": [result.model_dump() for result in results]
-        return {
+            }
-            "success": True,
-            "results": [result.model_dump() for result in results]
-        }
 
     except Exception as e:
         logger.error(f"Crawl error: {str(e)}", exc_info=True)
-        if 'crawler' in locals():
-            await crawler.close()
         raise HTTPException(
             status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
             detail=str(e)

deploy/docker/config.yml

@@ -4,7 +4,7 @@ app:
   version: "1.0.0"
   host: "0.0.0.0"
   port: 8020
-  reload: False
+  reload: True
   timeout_keep_alive: 300
 
 # Default LLM Configuration
@@ -68,4 +68,4 @@ observability:
     enabled: True
     endpoint: "/metrics"
   health_check:
-    endpoint: "/health"
+    endpoint: "/health"

deploy/docker/requirements.txt

@@ -1,3 +1,4 @@
+crawl4ai
 fastapi
 uvicorn
 gunicorn>=23.0.0

deploy/docker/supervisord.conf

@@ -1,28 +1,12 @@
 [supervisord]
-nodaemon=true                   ; Run supervisord in the foreground
+nodaemon=true
-logfile=/dev/null               ; Log supervisord output to stdout/stderr
-logfile_maxbytes=0
 
 [program:redis]
-command=/usr/bin/redis-server --loglevel notice ; Path to redis-server on Alpine
+command=redis-server
-user=appuser                    ; Run redis as our non-root user
 autorestart=true
 priority=10
-stdout_logfile=/dev/stdout      ; Redirect redis stdout to container stdout
-stdout_logfile_maxbytes=0
-stderr_logfile=/dev/stderr      ; Redirect redis stderr to container stderr
-stderr_logfile_maxbytes=0
 
 [program:gunicorn]
-command=/usr/local/bin/gunicorn --bind 0.0.0.0:11235 --workers 2 --threads 2 --timeout 120 --graceful-timeout 30 --keep-alive 60 --log-level info --worker-class uvicorn.workers.UvicornWorker server:app
+command=gunicorn --bind 0.0.0.0:8000 --workers 4 --threads 2 --timeout 300 --graceful-timeout 60 --keep-alive 65 --log-level debug --worker-class uvicorn.workers.UvicornWorker --max-requests 1000 --max-requests-jitter 50 server:app
-directory=/app                  ; Working directory for the app
-user=appuser                    ; Run gunicorn as our non-root user
 autorestart=true
-priority=20
+priority=20
-environment=PYTHONUNBUFFERED=1  ; Ensure Python output is sent straight to logs
-stdout_logfile=/dev/stdout      ; Redirect gunicorn stdout to container stdout
-stdout_logfile_maxbytes=0
-stderr_logfile=/dev/stderr      ; Redirect gunicorn stderr to container stderr
-stderr_logfile_maxbytes=0
-
-# Optional: Add filebeat or other logging agents here if needed

deploy/gcloud-function/Dockerfile

@@ -0,0 +1,63 @@
+FROM --platform=linux/amd64 python:3.10-slim
+
+# Install system dependencies required for Chromium and Git
+RUN apt-get update && apt-get install -y \
+    python3-dev \
+    pkg-config \
+    libjpeg-dev \
+    gcc \
+    build-essential \
+    libnss3 \
+    libnspr4 \
+    libatk1.0-0 \
+    libatk-bridge2.0-0 \
+    libcups2 \
+    libdrm2 \
+    libxkbcommon0 \
+    libxcomposite1 \
+    libxdamage1 \
+    libxfixes3 \
+    libxrandr2 \
+    libgbm1 \
+    libasound2 \
+    libpango-1.0-0 \
+    libcairo2 \
+    procps \
+    git \
+    socat \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# Make a directory for crawl4ai call it crawl4ai_repo
+# RUN mkdir crawl4ai_repo
+
+# # Clone Crawl4ai from the next branch and install it
+# RUN git clone --branch next https://github.com/unclecode/crawl4ai.git ./crawl4ai_repo \
+#     && cd crawl4ai_repo \
+#     && pip install . \
+#     && cd .. \
+#     && rm -rf crawl4ai_repo
+
+RUN python3 -m venv /app/venv
+ENV PATH="/app/venv/bin:$PATH"
+# RUN pip install git+https://github.com/unclecode/crawl4ai.git@next
+   
+# Copy requirements and install remaining dependencies
+COPY requirements.txt .
+RUN pip install -r requirements.txt
+
+# Copy application files
+COPY resources /app/resources
+COPY main.py .
+COPY start.sh .
+
+# Set permissions for Chrome binary and start script
+RUN chmod +x /app/resources/chrome/headless_shell && \
+    chmod -R 755 /app/resources/chrome && \
+    chmod +x start.sh
+
+ENV FUNCTION_TARGET=crawl
+EXPOSE 8080 9223
+
+CMD ["/app/start.sh"]

deploy/gcloud-function/config.yml

@@ -0,0 +1,8 @@
+project_id: PROJECT_ID
+region: REGION_NAME
+artifact_repo: ARTIFACT_REPO_NAME
+function_name: FUNCTION_NAME
+memory: "2048MB"
+timeout: "540s"
+local_image: "gcr.io/ARTIFACT_REPO_NAME/crawl4ai:latest"
+test_query_url: "https://example.com"

deploy/gcloud-function/deploy.py

@@ -0,0 +1,187 @@
+#!/usr/bin/env python3
+import argparse
+import subprocess
+import sys
+import yaml
+import requests
+
+def run_command(cmd, explanation, require_confirm=True, allow_already_exists=False):
+    print("\n=== {} ===".format(explanation))
+    if require_confirm:
+        input("Press Enter to run: [{}]\n".format(cmd))
+    print("Running: {}".format(cmd))
+    result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
+    if result.returncode != 0:
+        if allow_already_exists and "ALREADY_EXISTS" in result.stderr:
+            print("Repository already exists, skipping creation.")
+            return ""
+        print("Error:\n{}".format(result.stderr))
+        sys.exit(1)
+    out = result.stdout.strip()
+    if out:
+        print("Output:\n{}".format(out))
+    return out
+
+def load_config():
+    try:
+        with open("config.yml", "r") as f:
+            config = yaml.safe_load(f)
+    except Exception as e:
+        print("Failed to load config.yml: {}".format(e))
+        sys.exit(1)
+    required = ["project_id", "region", "artifact_repo", "function_name", "local_image"]
+    for key in required:
+        if key not in config or not config[key]:
+            print("Missing required config parameter: {}".format(key))
+            sys.exit(1)
+    return config
+
+def deploy_function(config):
+    project_id     = config["project_id"]
+    region         = config["region"]
+    artifact_repo  = config["artifact_repo"]
+    function_name  = config["function_name"]
+    memory         = config.get("memory", "2048MB")
+    timeout        = config.get("timeout", "540s")
+    local_image    = config["local_image"]
+    test_query_url = config.get("test_query_url", "https://example.com")
+
+    # Repository image format: "<region>-docker.pkg.dev/<project_id>/<artifact_repo>/<function_name>:latest"
+    repo_image = f"{region}-docker.pkg.dev/{project_id}/{artifact_repo}/{function_name}:latest"
+
+    # 1. Create Artifact Registry repository (skip if exists)
+    cmd = f"gcloud artifacts repositories create {artifact_repo} --repository-format=docker --location={region} --project={project_id}"
+    run_command(cmd, "Creating Artifact Registry repository (if it doesn't exist)", allow_already_exists=True)
+
+    # 2. Tag the local Docker image with the repository image name
+    cmd = f"docker tag {local_image} {repo_image}"
+    run_command(cmd, "Tagging Docker image for Artifact Registry")
+
+    # 3. Authenticate Docker to Artifact Registry
+    cmd = f"gcloud auth configure-docker {region}-docker.pkg.dev"
+    run_command(cmd, "Authenticating Docker to Artifact Registry")
+
+    # 4. Push the tagged Docker image to Artifact Registry
+    cmd = f"docker push {repo_image}"
+    run_command(cmd, "Pushing Docker image to Artifact Registry")
+
+    # 5. Deploy the Cloud Function using the custom container
+    cmd = (
+        f"gcloud beta functions deploy {function_name} "
+        f"--gen2 "
+        f"--runtime=python310 "
+        f"--entry-point=crawl "
+        f"--region={region} "
+        f"--docker-repository={region}-docker.pkg.dev/{project_id}/{artifact_repo} "
+        f"--trigger-http "
+        f"--memory={memory} "
+        f"--timeout={timeout} "
+        f"--project={project_id}"
+    )
+    run_command(cmd, "Deploying Cloud Function using custom container")
+
+    # 6. Set the Cloud Function to allow public (unauthenticated) invocations
+    cmd = (
+        f"gcloud functions add-iam-policy-binding {function_name} "
+        f"--region={region} "
+        f"--member='allUsers' "
+        f"--role='roles/cloudfunctions.invoker' "
+        f"--project={project_id}"
+        f"--quiet"
+    )
+    run_command(cmd, "Setting Cloud Function IAM to allow public invocations")
+
+    # 7. Retrieve the deployed Cloud Function URL
+    cmd = (
+        f"gcloud functions describe {function_name} "
+        f"--region={region} "
+        f"--project={project_id} "
+        f"--format='value(serviceConfig.uri)'"
+    )
+    deployed_url = run_command(cmd, "Extracting deployed Cloud Function URL", require_confirm=False)
+    print("\nDeployed URL: {}\n".format(deployed_url))
+
+    # 8. Test the deployed function
+    test_url = f"{deployed_url}?url={test_query_url}"
+    print("Testing function with: {}".format(test_url))
+    try:
+        response = requests.get(test_url)
+        print("Response status: {}".format(response.status_code))
+        print("Response body:\n{}".format(response.text))
+        if response.status_code == 200:
+            print("Test successful!")
+        else:
+            print("Non-200 response; check function logs.")
+    except Exception as e:
+        print("Test request error: {}".format(e))
+        sys.exit(1)
+
+    # 9. Final usage help
+    print("\nDeployment complete!")
+    print("Invoke your function with:")
+    print(f"curl '{deployed_url}?url={test_query_url}'")
+    print("For further instructions, refer to your documentation.")
+
+def delete_function(config):
+    project_id    = config["project_id"]
+    region        = config["region"]
+    function_name = config["function_name"]
+    cmd = f"gcloud functions delete {function_name} --region={region} --project={project_id} --quiet"
+    run_command(cmd, "Deleting Cloud Function")
+
+def describe_function(config):
+    project_id    = config["project_id"]
+    region        = config["region"]
+    function_name = config["function_name"]
+    cmd = (
+        f"gcloud functions describe {function_name} "
+        f"--region={region} "
+        f"--project={project_id} "
+        f"--format='value(serviceConfig.uri)'"
+    )
+    deployed_url = run_command(cmd, "Describing Cloud Function to extract URL", require_confirm=False)
+    print("\nCloud Function URL: {}\n".format(deployed_url))
+
+def clear_all(config):
+    print("\n=== CLEAR ALL RESOURCES ===")
+    project_id    = config["project_id"]
+    region        = config["region"]
+    artifact_repo = config["artifact_repo"]
+
+    confirm = input("WARNING: This will DELETE the Cloud Function and the Artifact Registry repository. Are you sure? (y/N): ")
+    if confirm.lower() != "y":
+        print("Aborting clear operation.")
+        sys.exit(0)
+
+    # Delete the Cloud Function
+    delete_function(config)
+    # Delete the Artifact Registry repository
+    cmd = f"gcloud artifacts repositories delete {artifact_repo} --location={region} --project={project_id} --quiet"
+    run_command(cmd, "Deleting Artifact Registry repository", require_confirm=False)
+    print("All resources cleared.")
+
+def main():
+    parser = argparse.ArgumentParser(description="Deploy, delete, describe, or clear Cloud Function resources using config.yml")
+    subparsers = parser.add_subparsers(dest="command", required=True)
+
+    subparsers.add_parser("deploy", help="Deploy the Cloud Function")
+    subparsers.add_parser("delete", help="Delete the deployed Cloud Function")
+    subparsers.add_parser("describe", help="Describe the Cloud Function and return its URL")
+    subparsers.add_parser("clear", help="Delete the Cloud Function and Artifact Registry repository")
+
+    args = parser.parse_args()
+    config = load_config()
+
+    if args.command == "deploy":
+        deploy_function(config)
+    elif args.command == "delete":
+        delete_function(config)
+    elif args.command == "describe":
+        describe_function(config)
+    elif args.command == "clear":
+        clear_all(config)
+    else:
+        parser.print_help()
+
+if __name__ == "__main__":
+    main()

deploy/gcloud-function/guide.md

@@ -0,0 +1,204 @@
+# Deploying Crawl4ai on Google Cloud Functions
+
+This guide explains how to deploy **Crawl4ai**—an open‑source web crawler library—on Google Cloud Functions Gen2 using a custom container. We assume your project folder already includes:
+
+- **Dockerfile:** Builds your container image (which installs Crawl4ai from its Git repository).
+- **start.sh:** Activates your virtual environment and starts the function (using the Functions Framework).
+- **main.py:** Contains your function logic with the entry point `crawl` (and imports Crawl4ai).
+
+The guide is divided into two parts:
+1. Manual deployment steps (using CLI commands)
+2. Automated deployment using a Python script (`deploy.py`)
+
+---
+
+## Part 1: Manual Deployment Process
+
+### Prerequisites
+
+- **Google Cloud Project:** Ensure your project is active and billing is enabled.
+- **Google Cloud CLI & Docker:** Installed and configured on your local machine.
+- **Permissions:** You must have rights to create Cloud Functions and Artifact Registry repositories.
+- **Files:** Your Dockerfile, start.sh, and main.py should be in the same directory.
+
+### Step 1: Build Your Docker Image
+
+Your Dockerfile packages Crawl4ai along with all its dependencies. Build your image with:
+
+```bash
+docker build -t gcr.io/<PROJECT_ID>/<FUNCTION_NAME>:latest .
+```
+
+Replace `<PROJECT_ID>` with your Google Cloud project ID and `<FUNCTION_NAME>` with your chosen function name (for example, `crawl4ai-t1`).
+
+### Step 2: Create an Artifact Registry Repository
+
+Cloud Functions Gen2 requires your custom container image to reside in an Artifact Registry repository. Create one by running:
+
+```bash
+gcloud artifacts repositories create <ARTIFACT_REPO> \
+  --repository-format=docker \
+  --location=<REGION> \
+  --project=<PROJECT_ID>
+```
+
+Replace `<ARTIFACT_REPO>` (for example, `crawl4ai`) and `<REGION>` (for example, `asia-east1`).  
+> **Note:** If you receive an `ALREADY_EXISTS` error, the repository is already created; simply proceed to the next step.
+
+### Step 3: Tag Your Docker Image
+
+Tag your locally built Docker image so it matches the Artifact Registry format:
+
+```bash
+docker tag gcr.io/<PROJECT_ID>/<FUNCTION_NAME>:latest <REGION>-docker.pkg.dev/<PROJECT_ID>/<ARTIFACT_REPO>/<FUNCTION_NAME>:latest
+```
+
+This step “renames” the image so you can push it to your repository.
+
+### Step 4: Authenticate Docker to Artifact Registry
+
+Configure Docker authentication to the Artifact Registry:
+
+```bash
+gcloud auth configure-docker <REGION>-docker.pkg.dev
+```
+
+This ensures Docker can securely push images to your registry using your Cloud credentials.
+
+### Step 5: Push the Docker Image
+
+Push the tagged image to Artifact Registry:
+
+```bash
+docker push <REGION>-docker.pkg.dev/<PROJECT_ID>/<ARTIFACT_REPO>/<FUNCTION_NAME>:latest
+```
+
+Once complete, your container image (with Crawl4ai installed) is hosted in Artifact Registry.
+
+### Step 6: Deploy the Cloud Function
+
+Deploy your function using the custom container image. Run:
+
+```bash
+gcloud beta functions deploy <FUNCTION_NAME> \
+  --gen2 \
+  --region=<REGION> \
+  --docker-repository=<REGION>-docker.pkg.dev/<PROJECT_ID>/<ARTIFACT_REPO> \
+  --trigger-http \
+  --memory=2048MB \
+  --timeout=540s \
+  --project=<PROJECT_ID>
+```
+
+This command tells Cloud Functions Gen2 to pull your container image from Artifact Registry and deploy it. Make sure your main.py defines the `crawl` entry point.
+
+### Step 7: Make the Function Public
+
+To allow external (unauthenticated) access, update the function’s IAM policy:
+
+```bash
+gcloud functions add-iam-policy-binding <FUNCTION_NAME> \
+  --region=<REGION> \
+  --member="allUsers" \
+  --role="roles/cloudfunctions.invoker" \
+  --project=<PROJECT_ID> \
+  --quiet
+```
+
+Using the `--quiet` flag ensures the command runs non‑interactively so the policy is applied immediately.
+
+### Step 8: Retrieve and Test Your Function URL
+
+Get the URL for your deployed function:
+
+```bash
+gcloud functions describe <FUNCTION_NAME> \
+  --region=<REGION> \
+  --project=<PROJECT_ID> \
+  --format='value(serviceConfig.uri)'
+```
+
+Test your deployment with a sample GET request (using curl or your browser):
+
+```bash
+curl "<FUNCTION_URL>?url=https://example.com"
+```
+
+Replace `<FUNCTION_URL>` with the output URL from the previous command. A successful test (HTTP status 200) means Crawl4ai is running on Cloud Functions.
+
+---
+
+## Part 2: Automated Deployment with deploy.py
+
+For a more streamlined process, use the provided `deploy.py` script. This Python script automates the manual steps, prompting you to confirm key actions and providing detailed logs throughout the process.
+
+### What deploy.py Does:
+
+- **Reads Parameters:** It loads a `config.yml` file containing all necessary parameters such as `project_id`, `region`, `artifact_repo`, `function_name`, `local_image`, etc.
+- **Creates/Skips Repository:** It creates the Artifact Registry repository (or skips if it already exists).
+- **Tags & Pushes:** It tags your local Docker image and pushes it to the Artifact Registry.
+- **Deploys the Function:** It deploys the Cloud Function with your custom container.
+- **Updates IAM:** It sets the IAM policy to allow public access (using the `--quiet` flag).
+- **Tests the Deployment:** It extracts the deployed URL and performs a test request.
+- **Additional Commands:** You can also use subcommands in the script to delete or describe the deployed function, or even clear all resources.
+
+### Example config.yml
+
+Create a `config.yml` file in the same folder as your Dockerfile. An example configuration:
+
+```yaml
+project_id: your-project-id
+region: asia-east1
+artifact_repo: crawl4ai
+function_name: crawl4ai-t1
+memory: "2048MB"
+timeout: "540s"
+local_image: "gcr.io/your-project-id/crawl4ai-t1:latest"
+test_query_url: "https://example.com"
+```
+
+### How to Use deploy.py
+
+- **Deploy the Function:**
+
+  ```bash
+  python deploy.py deploy
+  ```
+
+  The script will guide you through each step, display the output, and ask for confirmation before executing critical commands.
+
+- **Describe the Function:**
+
+  If you forget the function URL and want to retrieve it later:
+
+  ```bash
+  python deploy.py describe
+  ```
+
+- **Delete the Function:**
+
+  To remove just the Cloud Function:
+
+  ```bash
+  python deploy.py delete
+  ```
+
+- **Clear All Resources:**
+
+  To delete both the Cloud Function and the Artifact Registry repository:
+
+  ```bash
+  python deploy.py clear
+  ```
+
+---
+
+## Conclusion
+
+This guide has walked you through two deployment methods for Crawl4ai on Google Cloud Functions Gen2:
+
+1. **Manual Deployment:** Building your Docker image, pushing it to Artifact Registry, deploying the Cloud Function, and setting up IAM.
+2. **Automated Deployment:** Using `deploy.py` with a configuration file to handle the entire process interactively.
+
+By following these instructions, you can deploy, test, and manage your Crawl4ai-based Cloud Function with ease. Enjoy using Crawl4ai in your cloud environment!
+

deploy/gcloud-function/main.py

@@ -0,0 +1,158 @@
+# Cleanup Chrome process on module unload
+import atexit
+import asyncio
+import logging
+import functions_framework
+from flask import jsonify, Request
+import os
+import sys
+import time
+import subprocess
+import signal
+import requests
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+logger.info(f"Python version: {sys.version}")
+logger.info(f"Python path: {sys.path}")
+
+# Try to find where crawl4ai is coming from
+try:
+    import crawl4ai
+    logger.info(f"Crawl4AI module location: {crawl4ai.__file__}")
+    logger.info(f"Contents of crawl4ai: {dir(crawl4ai)}")
+except ImportError:
+    logger.error("Crawl4AI module not found")
+
+# Now attempt the import
+from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode, CrawlResult
+
+# Configure logging
+logging.basicConfig(level=logging.DEBUG)
+logger = logging.getLogger(__name__)
+
+# Paths and constants
+FUNCTION_DIR = os.path.dirname(os.path.realpath(__file__))
+CHROME_BINARY = os.path.join(FUNCTION_DIR, "resources/chrome/headless_shell")
+CDP_PORT = 9222
+
+def start_chrome():
+    """Start Chrome process synchronously with exponential backoff."""
+    logger.debug("Starting Chrome process...")
+    chrome_args = [
+        CHROME_BINARY,
+        f"--remote-debugging-port={CDP_PORT}",
+        "--remote-debugging-address=0.0.0.0",
+        "--no-sandbox",
+        "--disable-setuid-sandbox",
+        "--headless=new",
+        "--disable-gpu",
+        "--disable-dev-shm-usage",
+        "--no-zygote",
+        "--single-process",
+        "--disable-features=site-per-process",
+        "--no-first-run",
+        "--disable-extensions"
+    ]
+    
+    process = subprocess.Popen(
+        chrome_args,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        preexec_fn=os.setsid
+    )
+    
+    logger.debug(f"Chrome process started with PID: {process.pid}")
+    
+    # Wait for CDP endpoint with exponential backoff
+    wait_time = 1  # Start with 1 second
+    max_wait_time = 16  # Cap at 16 seconds per retry
+    max_attempts = 10  # Total attempts
+    for attempt in range(max_attempts):
+        try:
+            response = requests.get(f"http://127.0.0.1:{CDP_PORT}/json/version", timeout=2)
+            if response.status_code == 200:
+                # Get ws URL from response
+                ws_url = response.json()['webSocketDebuggerUrl']
+                logger.debug("Chrome CDP is ready")
+                logger.debug(f"CDP URL: {ws_url}")
+                return process
+        except requests.exceptions.ConnectionError:
+            logger.debug(f"Waiting for CDP endpoint (attempt {attempt + 1}/{max_attempts}), retrying in {wait_time} seconds")
+            time.sleep(wait_time)
+            wait_time = min(wait_time * 2, max_wait_time)  # Double wait time, up to max
+    
+    # If we get here, all retries failed
+    stdout, stderr = process.communicate()  # Get output for debugging
+    logger.error(f"Chrome stdout: {stdout.decode()}")
+    logger.error(f"Chrome stderr: {stderr.decode()}")
+    raise Exception("Chrome CDP endpoint failed to start after retries")
+
+async def fetch_with_crawl4ai(url: str) -> dict:
+    """Fetch page content using Crawl4ai and return the result object"""
+    # Get CDP URL from the running Chrome instance
+    version_response = requests.get(f'http://localhost:{CDP_PORT}/json/version')
+    cdp_url = version_response.json()['webSocketDebuggerUrl']
+    
+    # Configure and run Crawl4ai
+    browser_config = BrowserConfig(cdp_url=cdp_url, use_managed_browser=True)
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        crawler_config = CrawlerRunConfig(
+            cache_mode=CacheMode.BYPASS,
+        )
+        result : CrawlResult = await crawler.arun(
+            url=url, config=crawler_config
+        )
+        return result.model_dump()  # Convert Pydantic model to dict for JSON response
+
+# Start Chrome when the module loads
+logger.info("Starting Chrome process on module load")
+chrome_process = start_chrome()
+
+@functions_framework.http
+def crawl(request: Request):
+    """HTTP Cloud Function to fetch web content using Crawl4ai"""
+    try:
+        url = request.args.get('url')
+        if not url:
+            return jsonify({'error': 'URL parameter is required', 'status': 400}), 400
+        
+        # Create and run an asyncio event loop
+        loop = asyncio.new_event_loop()
+        asyncio.set_event_loop(loop)
+        
+        try:
+            result = loop.run_until_complete(
+                asyncio.wait_for(fetch_with_crawl4ai(url), timeout=10.0)
+            )
+            return jsonify({
+                'status': 200,
+                'data': result
+            })
+        finally:
+            loop.close()
+            
+    except Exception as e:
+        error_msg = f"Unexpected error: {str(e)}"
+        logger.error(error_msg, exc_info=True)
+        return jsonify({
+            'error': error_msg,
+            'status': 500,
+            'details': {
+                'error_type': type(e).__name__,
+                'stack_trace': str(e),
+                'chrome_running': chrome_process.poll() is None if chrome_process else False
+            }
+        }), 500
+
+
+@atexit.register
+def cleanup():
+    """Cleanup Chrome process on shutdown"""
+    if chrome_process and chrome_process.poll() is None:
+        try:
+            os.killpg(os.getpgid(chrome_process.pid), signal.SIGTERM)
+            logger.info("Chrome process terminated")
+        except Exception as e:
+            logger.error(f"Failed to terminate Chrome process: {e}")

deploy/gcloud-function/requirements.txt

@@ -0,0 +1,5 @@
+functions-framework==3.*
+flask==2.3.3
+requests==2.31.0
+websockets==12.0
+git+https://github.com/unclecode/crawl4ai.git@next

deploy/gcloud-function/resources/chrome/fonts.conf

@@ -0,0 +1,10 @@
+<?xml version="1.0" ?>
+<!DOCTYPE fontconfig SYSTEM "fonts.dtd">
+<fontconfig>
+  <dir>/var/task/.fonts</dir>
+  <dir>/var/task/fonts</dir>
+  <dir>/opt/fonts</dir>
+  <dir>/tmp/fonts</dir>
+  <cachedir>/tmp/fonts-cache/</cachedir>
+  <config></config>
+</fontconfig>

deploy/gcloud-function/resources/chrome/vk_swiftshader_icd.json

@@ -0,0 +1 @@
+{"file_format_version": "1.0.0", "ICD": {"library_path": "./libvk_swiftshader.so", "api_version": "1.0.5"}}

deploy/lambda/Dockerfile

@@ -0,0 +1,104 @@
+FROM python:3.12-bookworm AS python-builder
+
+RUN pip install poetry
+
+ENV POETRY_NO_INTERACTION=1 \
+    POETRY_CACHE_DIR=/tmp/poetry_cache
+
+WORKDIR /app
+
+COPY pyproject.toml poetry.lock ./
+RUN --mount=type=cache,target=$POETRY_CACHE_DIR poetry export -f requirements.txt -o requirements.txt
+
+# Install build dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    python3-dev \
+    python3-setuptools \
+    python3-wheel \
+    python3-pip \
+    gcc \
+    g++ \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install specific dependencies that have build issues
+RUN pip install --no-cache-dir cchardet
+
+FROM python:3.12-bookworm
+
+# Install AWS Lambda Runtime Interface Client
+RUN python3 -m pip install --no-cache-dir awslambdaric
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    curl \
+    wget \
+    gnupg \
+    git \
+    cmake \
+    pkg-config \
+    python3-dev \
+    libjpeg-dev \
+    redis-server \
+    supervisor \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libglib2.0-0 \
+    libnss3 \
+    libnspr4 \
+    libatk1.0-0 \
+    libatk-bridge2.0-0 \
+    libcups2 \
+    libdrm2 \
+    libdbus-1-3 \
+    libxcb1 \
+    libxkbcommon0 \
+    libx11-6 \
+    libxcomposite1 \
+    libxdamage1 \
+    libxext6 \
+    libxfixes3 \
+    libxrandr2 \
+    libgbm1 \
+    libpango-1.0-0 \
+    libcairo2 \
+    libasound2 \
+    libatspi2.0-0 \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install build essentials for any compilations needed
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    python3-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set up function directory and browser path
+ARG FUNCTION_DIR="/function"
+RUN mkdir -p "${FUNCTION_DIR}/pw-browsers"
+RUN mkdir -p "/tmp/.crawl4ai"
+
+# Set critical environment variables
+ENV PLAYWRIGHT_BROWSERS_PATH="${FUNCTION_DIR}/pw-browsers" \
+    HOME="/tmp" \
+    CRAWL4_AI_BASE_DIRECTORY="/tmp/.crawl4ai"
+
+# Create Craw4ai base directory
+RUN mkdir -p ${CRAWL4_AI_BASE_DIRECTORY}
+
+RUN pip install --no-cache-dir faust-cchardet
+
+# Install Crawl4ai and dependencies
+RUN pip install --no-cache-dir git+https://github.com/unclecode/crawl4ai.git@next
+
+# Install Chromium only (no deps flag)
+RUN playwright install chromium
+
+# Copy function code
+COPY lambda_function.py ${FUNCTION_DIR}/
+
+# Set working directory
+WORKDIR ${FUNCTION_DIR}
+
+ENTRYPOINT [ "/usr/local/bin/python", "-m", "awslambdaric" ]
+CMD [ "lambda_function.handler" ]

deploy/lambda/guide.md

@@ -0,0 +1,345 @@
+# Deploying Crawl4ai on AWS Lambda
+
+This guide walks you through deploying Crawl4ai as an AWS Lambda function with API Gateway integration. You'll learn how to set up, test, and clean up your deployment.
+
+## Prerequisites
+
+Before you begin, ensure you have:
+
+- AWS CLI installed and configured (`aws configure`)
+- Docker installed and running
+- Python 3.8+ installed
+- Basic familiarity with AWS services
+
+## Project Files
+
+Your project directory should contain:
+
+- `Dockerfile`: Container configuration for Lambda
+- `lambda_function.py`: Lambda handler code
+- `deploy.py`: Our deployment script
+
+## Step 1: Install Required Python Packages
+
+Install the Python packages needed for our deployment script:
+
+```bash
+pip install typer rich
+```
+
+## Step 2: Run the Deployment Script
+
+Our Python script automates the entire deployment process:
+
+```bash
+python deploy.py
+```
+
+The script will guide you through:
+
+1. Configuration setup (AWS region, function name, memory allocation)
+2. Docker image building
+3. ECR repository creation
+4. Lambda function deployment
+5. API Gateway setup
+6. Provisioned concurrency configuration (optional)
+
+Follow the prompts and confirm each step by pressing Enter.
+
+## Step 3: Manual Deployment (Alternative to the Script)
+
+If you prefer to deploy manually or understand what the script does, follow these steps:
+
+### Building and Pushing the Docker Image
+
+```bash
+# Build the Docker image
+docker build -t crawl4ai-lambda .
+
+# Create an ECR repository (if it doesn't exist)
+aws ecr create-repository --repository-name crawl4ai-lambda
+
+# Get ECR login password and login
+aws ecr get-login-password | docker login --username AWS --password-stdin $(aws sts get-caller-identity --query Account --output text).dkr.ecr.us-east-1.amazonaws.com
+
+# Tag the image
+ECR_URI=$(aws ecr describe-repositories --repository-names crawl4ai-lambda --query 'repositories[0].repositoryUri' --output text)
+docker tag crawl4ai-lambda:latest $ECR_URI:latest
+
+# Push the image to ECR
+docker push $ECR_URI:latest
+```
+
+### Creating the Lambda Function
+
+```bash
+# Get IAM role ARN (create it if needed)
+ROLE_ARN=$(aws iam get-role --role-name lambda-execution-role --query 'Role.Arn' --output text)
+
+# Create Lambda function
+aws lambda create-function \
+    --function-name crawl4ai-function \
+    --package-type Image \
+    --code ImageUri=$ECR_URI:latest \
+    --role $ROLE_ARN \
+    --timeout 300 \
+    --memory-size 4096 \
+    --ephemeral-storage Size=10240 \
+    --environment "Variables={CRAWL4_AI_BASE_DIRECTORY=/tmp/.crawl4ai,HOME=/tmp,PLAYWRIGHT_BROWSERS_PATH=/function/pw-browsers}"
+```
+
+If you're updating an existing function:
+
+```bash
+# Update function code
+aws lambda update-function-code \
+    --function-name crawl4ai-function \
+    --image-uri $ECR_URI:latest
+
+# Update function configuration
+aws lambda update-function-configuration \
+    --function-name crawl4ai-function \
+    --timeout 300 \
+    --memory-size 4096 \
+    --ephemeral-storage Size=10240 \
+    --environment "Variables={CRAWL4_AI_BASE_DIRECTORY=/tmp/.crawl4ai,HOME=/tmp,PLAYWRIGHT_BROWSERS_PATH=/function/pw-browsers}"
+```
+
+### Setting Up API Gateway
+
+```bash
+# Create API Gateway
+API_ID=$(aws apigateway create-rest-api --name crawl4ai-api --query 'id' --output text)
+
+# Get root resource ID
+PARENT_ID=$(aws apigateway get-resources --rest-api-id $API_ID --query 'items[?path==`/`].id' --output text)
+
+# Create resource
+RESOURCE_ID=$(aws apigateway create-resource --rest-api-id $API_ID --parent-id $PARENT_ID --path-part "crawl" --query 'id' --output text)
+
+# Create POST method
+aws apigateway put-method --rest-api-id $API_ID --resource-id $RESOURCE_ID --http-method POST --authorization-type NONE
+
+# Get Lambda function ARN
+LAMBDA_ARN=$(aws lambda get-function --function-name crawl4ai-function --query 'Configuration.FunctionArn' --output text)
+
+# Set Lambda integration
+aws apigateway put-integration \
+    --rest-api-id $API_ID \
+    --resource-id $RESOURCE_ID \
+    --http-method POST \
+    --type AWS_PROXY \
+    --integration-http-method POST \
+    --uri arn:aws:apigateway:us-east-1:lambda:path/2015-03-31/functions/$LAMBDA_ARN/invocations
+
+# Deploy API
+aws apigateway create-deployment --rest-api-id $API_ID --stage-name prod
+
+# Set Lambda permission
+ACCOUNT_ID=$(aws sts get-caller-identity --query Account --output text)
+aws lambda add-permission \
+    --function-name crawl4ai-function \
+    --statement-id apigateway \
+    --action lambda:InvokeFunction \
+    --principal apigateway.amazonaws.com \
+    --source-arn "arn:aws:execute-api:us-east-1:$ACCOUNT_ID:$API_ID/*/POST/crawl"
+```
+
+### Setting Up Provisioned Concurrency (Optional)
+
+This reduces cold starts:
+
+```bash
+# Publish a version
+VERSION=$(aws lambda publish-version --function-name crawl4ai-function --query 'Version' --output text)
+
+# Create alias
+aws lambda create-alias \
+    --function-name crawl4ai-function \
+    --name prod \
+    --function-version $VERSION
+
+# Configure provisioned concurrency
+aws lambda put-provisioned-concurrency-config \
+    --function-name crawl4ai-function \
+    --qualifier prod \
+    --provisioned-concurrent-executions 2
+
+# Update API Gateway to use alias
+LAMBDA_ALIAS_ARN="arn:aws:lambda:us-east-1:$ACCOUNT_ID:function:crawl4ai-function:prod"
+aws apigateway put-integration \
+    --rest-api-id $API_ID \
+    --resource-id $RESOURCE_ID \
+    --http-method POST \
+    --type AWS_PROXY \
+    --integration-http-method POST \
+    --uri arn:aws:apigateway:us-east-1:lambda:path/2015-03-31/functions/$LAMBDA_ALIAS_ARN/invocations
+
+# Redeploy API Gateway
+aws apigateway create-deployment --rest-api-id $API_ID --stage-name prod
+```
+
+## Step 4: Testing the Deployment
+
+Once deployed, test your function with:
+
+```bash
+ENDPOINT_URL="https://$API_ID.execute-api.us-east-1.amazonaws.com/prod/crawl"
+
+# Test with curl
+curl -X POST $ENDPOINT_URL \
+  -H "Content-Type: application/json" \
+  -d '{"url":"https://example.com"}'
+```
+
+Or using Python:
+
+```python
+import requests
+import json
+
+url = "https://your-api-id.execute-api.us-east-1.amazonaws.com/prod/crawl"
+payload = {
+    "url": "https://example.com",
+    "browser_config": {
+        "headless": True,
+        "verbose": False
+    },
+    "crawler_config": {
+        "crawler_config": {
+            "type": "CrawlerRunConfig",
+            "params": {
+                "markdown_generator": {
+                    "type": "DefaultMarkdownGenerator",
+                    "params": {
+                        "content_filter": {
+                            "type": "PruningContentFilter",
+                            "params": {
+                                "threshold": 0.48,
+                                "threshold_type": "fixed"
+                            }
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
+
+response = requests.post(url, json=payload)
+result = response.json()
+print(json.dumps(result, indent=2))
+```
+
+## Step 5: Cleaning Up Resources
+
+To remove all AWS resources created for this deployment:
+
+```bash
+python deploy.py cleanup
+```
+
+Or manually:
+
+```bash
+# Delete API Gateway
+aws apigateway delete-rest-api --rest-api-id $API_ID
+
+# Remove provisioned concurrency (if configured)
+aws lambda delete-provisioned-concurrency-config \
+    --function-name crawl4ai-function \
+    --qualifier prod
+
+# Delete alias (if created)
+aws lambda delete-alias \
+    --function-name crawl4ai-function \
+    --name prod
+
+# Delete Lambda function
+aws lambda delete-function --function-name crawl4ai-function
+
+# Delete ECR repository
+aws ecr delete-repository --repository-name crawl4ai-lambda --force
+```
+
+## Troubleshooting
+
+### Cold Start Issues
+
+If experiencing long cold starts:
+- Enable provisioned concurrency
+- Increase memory allocation (4096 MB recommended)
+- Ensure the Lambda function has enough ephemeral storage
+
+### Permission Errors
+
+If you encounter permission errors:
+- Check the IAM role has the necessary permissions
+- Ensure API Gateway has permission to invoke the Lambda function
+
+### Container Size Issues
+
+If your container is too large:
+- Optimize the Dockerfile
+- Use multi-stage builds
+- Consider removing unnecessary dependencies
+
+## Performance Considerations
+
+- Lambda memory affects CPU allocation - higher memory means faster execution
+- Provisioned concurrency eliminates cold starts but costs more
+- Optimize the Playwright setup for faster browser initialization
+
+## Security Best Practices
+
+- Use the principle of least privilege for IAM roles
+- Implement API Gateway authentication for production deployments
+- Consider using AWS KMS for storing sensitive configuration
+
+## Useful AWS Console Links
+
+Here are quick links to access important AWS console pages for monitoring and managing your deployment:
+
+| Resource | Console Link |
+|----------|-------------|
+| Lambda Functions | [AWS Lambda Console](https://console.aws.amazon.com/lambda/home#/functions) |
+| Lambda Function Logs | [CloudWatch Logs](https://console.aws.amazon.com/cloudwatch/home#logsV2:log-groups) |
+| API Gateway | [API Gateway Console](https://console.aws.amazon.com/apigateway/home) |
+| ECR Repositories | [ECR Console](https://console.aws.amazon.com/ecr/repositories) |
+| IAM Roles | [IAM Console](https://console.aws.amazon.com/iamv2/home#/roles) |
+| CloudWatch Metrics | [CloudWatch Metrics](https://console.aws.amazon.com/cloudwatch/home#metricsV2) |
+
+### Monitoring Lambda Execution
+
+To monitor your Lambda function:
+
+1. Go to the [Lambda function console](https://console.aws.amazon.com/lambda/home#/functions)
+2. Select your function (`crawl4ai-function`)
+3. Click the "Monitor" tab to see:
+   - Invocation metrics
+   - Success/failure rates
+   - Duration statistics
+
+### Viewing Lambda Logs
+
+To see detailed execution logs:
+
+1. Go to [CloudWatch Logs](https://console.aws.amazon.com/cloudwatch/home#logsV2:log-groups)
+2. Find the log group named `/aws/lambda/crawl4ai-function`
+3. Click to see the latest log streams
+4. Each stream contains logs from a function execution
+
+### Checking API Gateway Traffic
+
+To monitor API requests:
+
+1. Go to the [API Gateway console](https://console.aws.amazon.com/apigateway/home)
+2. Select your API (`crawl4ai-api`)
+3. Click "Dashboard" to see:
+   - API calls
+   - Latency
+   - Error rates
+
+## Conclusion
+
+You now have Crawl4ai running as a serverless function on AWS Lambda! This setup allows you to crawl websites on-demand without maintaining infrastructure, while paying only for the compute time you use.

deploy/lambda/lambda_function.py

@@ -0,0 +1,107 @@
+import json
+import asyncio
+import os
+
+# Ensure environment variables and directories are set
+os.environ['CRAWL4_AI_BASE_DIRECTORY'] = '/tmp/.crawl4ai'
+os.environ['HOME'] = '/tmp'
+
+# Create directory if it doesn't exist
+os.makedirs('/tmp/.crawl4ai', exist_ok=True)
+
+from crawl4ai import (
+    AsyncWebCrawler,
+    BrowserConfig,
+    CrawlerRunConfig,
+    CacheMode
+)
+
+
+def handler(event, context):
+    # Parse the incoming event (API Gateway request)
+    try:
+        body = json.loads(event.get('body', '{}'))
+        
+        url = body.get('url')
+        if not url:
+            return {
+                'statusCode': 400,
+                'body': json.dumps({'error': 'URL is required'})
+            }
+        
+        # Get optional configurations or use defaults
+        browser_config_dict = body.get('browser_config', {})
+        crawler_config_dict = body.get('crawler_config', {})
+        
+        # Run the crawler
+        result = asyncio.run(crawl(url, browser_config_dict, crawler_config_dict))
+        
+        # Return successful response
+        return {
+            'statusCode': 200,
+            'headers': {
+                'Content-Type': 'application/json'
+            },
+            'body': json.dumps(result)
+        }
+    
+    except Exception as e:
+        # Handle errors
+        import traceback
+        return {
+            'statusCode': 500,
+            'body': json.dumps({
+                'error': str(e),
+                'traceback': traceback.format_exc()
+            })
+        }
+
+async def crawl(url, browser_config_dict, crawler_config_dict):
+    """
+    Run the crawler with the provided configurations, with Lambda-specific settings
+    """
+    # Start with user-provided config but override with Lambda-required settings
+    base_browser_config = BrowserConfig.load(browser_config_dict) if browser_config_dict else BrowserConfig()
+    
+    # Apply Lambda-specific browser configurations
+    browser_config = BrowserConfig(
+        verbose=True,
+        browser_type="chromium",
+        headless=True,
+        user_agent_mode="random",
+        light_mode=True,
+        use_managed_browser=False,
+        extra_args=[
+            "--headless=new",
+            "--no-sandbox",
+            "--disable-dev-shm-usage",
+            "--disable-setuid-sandbox",
+            "--remote-allow-origins=*",
+            "--autoplay-policy=user-gesture-required",
+            "--single-process",            
+        ],
+        # # Carry over any other settings from user config that aren't overridden
+        # **{k: v for k, v in base_browser_config.model_dump().items() 
+        #    if k not in ['verbose', 'browser_type', 'headless', 'user_agent_mode', 
+        #                'light_mode', 'use_managed_browser', 'extra_args']}
+    )
+    
+    # Start with user-provided crawler config but ensure cache is bypassed
+    base_crawler_config = CrawlerRunConfig.load(crawler_config_dict) if crawler_config_dict else CrawlerRunConfig()
+    
+    # Apply Lambda-specific crawler configurations
+    crawler_config = CrawlerRunConfig(
+        exclude_external_links=base_crawler_config.exclude_external_links,
+        remove_overlay_elements=True,
+        magic=True,
+        cache_mode=CacheMode.BYPASS,
+        # Carry over markdown generator and other settings
+        markdown_generator=base_crawler_config.markdown_generator
+    )
+    
+    # Perform the crawl with Lambda-optimized settings
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result = await crawler.arun(url=url, config=crawler_config)
+        
+        # Return serializable results
+        return result.model_dump()

deploy/modal/crawl4ai_api_service.py

@@ -0,0 +1,543 @@
+import os
+import time
+import uuid
+from datetime import datetime
+from typing import Dict, Any, Optional, List
+
+import modal
+from modal import Image, App, Volume, Secret, web_endpoint, function
+
+# Configuration
+APP_NAME = "crawl4ai-api"
+CRAWL4AI_VERSION = "next"  # Using the 'next' branch
+PYTHON_VERSION = "3.10"  # Compatible with playwright
+DEFAULT_CREDITS = 1000
+
+# Create a custom image with Crawl4ai and its dependencies
+image = Image.debian_slim(python_version=PYTHON_VERSION).pip_install(
+    ["fastapi[standard]", "pymongo", "pydantic"]
+).run_commands(
+    "apt-get update",
+    "apt-get install -y software-properties-common",
+    "apt-get install -y git",
+    "apt-add-repository non-free",
+    "apt-add-repository contrib",
+    # Install crawl4ai from the next branch
+    f"pip install -U git+https://github.com/unclecode/crawl4ai.git@{CRAWL4AI_VERSION}",
+    "pip install -U fastapi[standard]",
+    "pip install -U pydantic",
+    # Install playwright and browsers
+    "crawl4ai-setup",
+)
+
+# Create persistent volume for user database
+user_db = Volume.from_name("crawl4ai-users", create_if_missing=True)
+
+# Create admin secret for secure operations
+admin_secret = Secret.from_name("admin-secret", create_if_missing=True)
+
+# Define the app
+app = App(APP_NAME, image=image)
+
+# Default configurations
+DEFAULT_BROWSER_CONFIG = {
+    "headless": True,
+    "verbose": False,
+}
+
+DEFAULT_CRAWLER_CONFIG = {
+    "crawler_config": {
+        "type": "CrawlerRunConfig",
+        "params": {
+            "markdown_generator": {
+                "type": "DefaultMarkdownGenerator",
+                "params": {
+                    "content_filter": {
+                        "type": "PruningContentFilter",
+                        "params": {
+                            "threshold": 0.48,
+                            "threshold_type": "fixed"
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
+
+# Database operations
+@app.function(volumes={"/data": user_db})
+def init_db() -> None:
+    """Initialize database with indexes."""
+    from pymongo import MongoClient, ASCENDING
+    
+    client = MongoClient("mongodb://localhost:27017")
+    db = client.crawl4ai_db
+    
+    # Ensure indexes for faster lookups
+    db.users.create_index([("api_token", ASCENDING)], unique=True)
+    db.users.create_index([("email", ASCENDING)], unique=True)
+    
+    # Create usage stats collection
+    db.usage_stats.create_index([("user_id", ASCENDING), ("timestamp", ASCENDING)])
+    
+    print("Database initialized with required indexes")
+
+@app.function(volumes={"/data": user_db})
+def get_user_by_token(api_token: str) -> Optional[Dict[str, Any]]:
+    """Get user by API token."""
+    from pymongo import MongoClient
+    from bson.objectid import ObjectId
+    
+    client = MongoClient("mongodb://localhost:27017")
+    db = client.crawl4ai_db
+    
+    user = db.users.find_one({"api_token": api_token})
+    if not user:
+        return None
+    
+    # Convert ObjectId to string for serialization
+    user["_id"] = str(user["_id"])
+    return user
+
+@app.function(volumes={"/data": user_db})
+def create_user(email: str, name: str) -> Dict[str, Any]:
+    """Create a new user with initial credits."""
+    from pymongo import MongoClient
+    from bson.objectid import ObjectId
+    
+    client = MongoClient("mongodb://localhost:27017")
+    db = client.crawl4ai_db
+    
+    # Generate API token
+    api_token = str(uuid.uuid4())
+    
+    user = {
+        "email": email,
+        "name": name,
+        "api_token": api_token,
+        "credits": DEFAULT_CREDITS,
+        "created_at": datetime.utcnow(),
+        "updated_at": datetime.utcnow(),
+        "is_active": True
+    }
+    
+    try:
+        result = db.users.insert_one(user)
+        user["_id"] = str(result.inserted_id)
+        return user
+    except Exception as e:
+        if "duplicate key error" in str(e):
+            return {"error": "User with this email already exists"}
+        raise
+
+@app.function(volumes={"/data": user_db})
+def update_user_credits(api_token: str, amount: int) -> Dict[str, Any]:
+    """Update user credits (add or subtract)."""
+    from pymongo import MongoClient
+    
+    client = MongoClient("mongodb://localhost:27017")
+    db = client.crawl4ai_db
+    
+    # First get current user to check credits
+    user = db.users.find_one({"api_token": api_token})
+    if not user:
+        return {"success": False, "error": "User not found"}
+    
+    # For deductions, ensure sufficient credits
+    if amount < 0 and user["credits"] + amount < 0:
+        return {"success": False, "error": "Insufficient credits"}
+    
+    # Update credits
+    result = db.users.update_one(
+        {"api_token": api_token},
+        {
+            "$inc": {"credits": amount},
+            "$set": {"updated_at": datetime.utcnow()}
+        }
+    )
+    
+    if result.modified_count == 1:
+        # Get updated user
+        updated_user = db.users.find_one({"api_token": api_token})
+        return {
+            "success": True, 
+            "credits": updated_user["credits"]
+        }
+    else:
+        return {"success": False, "error": "Failed to update credits"}
+
+@app.function(volumes={"/data": user_db})
+def log_usage(user_id: str, url: str, success: bool, error: Optional[str] = None) -> None:
+    """Log usage statistics."""
+    from pymongo import MongoClient
+    from bson.objectid import ObjectId
+    
+    client = MongoClient("mongodb://localhost:27017")
+    db = client.crawl4ai_db
+    
+    log_entry = {
+        "user_id": user_id,
+        "url": url,
+        "timestamp": datetime.utcnow(),
+        "success": success,
+        "error": error
+    }
+    
+    db.usage_stats.insert_one(log_entry)
+
+# Main crawling function
+@app.function(timeout=300)  # 5 minute timeout
+async def crawl(
+    url: str,
+    browser_config: Optional[Dict[str, Any]] = None,
+    crawler_config: Optional[Dict[str, Any]] = None,
+) -> Dict[str, Any]:
+    """
+    Crawl a given URL using Crawl4ai.
+    
+    Args:
+        url: The URL to crawl
+        browser_config: Optional browser configuration to override defaults
+        crawler_config: Optional crawler configuration to override defaults
+        
+    Returns:
+        A dictionary containing the crawl results
+    """
+    from crawl4ai import (
+        AsyncWebCrawler,
+        BrowserConfig,
+        CrawlerRunConfig,
+        CrawlResult
+    )
+
+    # Prepare browser config using the loader method
+    if browser_config is None:
+        browser_config = DEFAULT_BROWSER_CONFIG
+    browser_config_obj = BrowserConfig.load(browser_config)
+    
+    # Prepare crawler config using the loader method
+    if crawler_config is None:
+        crawler_config = DEFAULT_CRAWLER_CONFIG
+    crawler_config_obj = CrawlerRunConfig.load(crawler_config)    
+    
+    # Perform the crawl
+    async with AsyncWebCrawler(config=browser_config_obj) as crawler:
+        result: CrawlResult = await crawler.arun(url=url, config=crawler_config_obj)
+        
+        # Return serializable results
+        try:
+            # Try newer Pydantic v2 method
+            return result.model_dump()
+        except AttributeError:
+            try:
+                # Try older Pydantic v1 method
+                return result.dict()
+            except AttributeError:
+                # Fallback to manual conversion
+                return {
+                    "url": result.url,
+                    "title": result.title,
+                    "status": result.status,
+                    "content": str(result.content) if hasattr(result, "content") else None,
+                    "links": [{"url": link.url, "text": link.text} for link in result.links] if hasattr(result, "links") else [],
+                    "markdown_v2": {
+                        "raw_markdown": result.markdown_v2.raw_markdown if hasattr(result, "markdown_v2") else None
+                    }
+                }
+
+# API endpoints
+@app.function()
+@web_endpoint(method="POST")
+def crawl_endpoint(data: Dict[str, Any]) -> Dict[str, Any]:
+    """
+    Web endpoint that accepts POST requests with JSON data containing:
+    - api_token: User's API token
+    - url: The URL to crawl
+    - browser_config: Optional browser configuration
+    - crawler_config: Optional crawler configuration
+    
+    Returns the crawl results and remaining credits.
+    """
+    # Extract and validate API token
+    api_token = data.get("api_token")
+    if not api_token:
+        return {
+            "success": False,
+            "error": "API token is required",
+            "status_code": 401
+        }
+    
+    # Verify user
+    user = get_user_by_token.remote(api_token)
+    if not user:
+        return {
+            "success": False,
+            "error": "Invalid API token",
+            "status_code": 401
+        }
+    
+    if not user.get("is_active", False):
+        return {
+            "success": False,
+            "error": "Account is inactive",
+            "status_code": 403
+        }
+    
+    # Validate URL
+    url = data.get("url")
+    if not url:
+        return {
+            "success": False,
+            "error": "URL is required",
+            "status_code": 400
+        }
+    
+    # Check credits
+    if user.get("credits", 0) <= 0:
+        return {
+            "success": False,
+            "error": "Insufficient credits",
+            "status_code": 403
+        }
+    
+    # Deduct credit first (1 credit per call)
+    credit_result = update_user_credits.remote(api_token, -1)
+    if not credit_result.get("success", False):
+        return {
+            "success": False,
+            "error": credit_result.get("error", "Failed to process credits"),
+            "status_code": 500
+        }
+    
+    # Extract configs
+    browser_config = data.get("browser_config")
+    crawler_config = data.get("crawler_config")
+    
+    # Perform crawl
+    try:
+        start_time = time.time()
+        result = crawl.remote(url, browser_config, crawler_config)
+        execution_time = time.time() - start_time
+        
+        # Log successful usage
+        log_usage.spawn(user["_id"], url, True)
+        
+        return {
+            "success": True,
+            "data": result,
+            "credits_remaining": credit_result.get("credits"),
+            "execution_time_seconds": round(execution_time, 2),
+            "status_code": 200
+        }
+    except Exception as e:
+        # Log failed usage
+        log_usage.spawn(user["_id"], url, False, str(e))
+        
+        # Return error
+        return {
+            "success": False,
+            "error": f"Crawling error: {str(e)}",
+            "credits_remaining": credit_result.get("credits"),
+            "status_code": 500
+        }
+
+# Admin endpoints
+@app.function(secrets=[admin_secret])
+@web_endpoint(method="POST")
+def admin_create_user(data: Dict[str, Any]) -> Dict[str, Any]:
+    """Admin endpoint to create new users."""
+    # Validate admin token
+    admin_token = data.get("admin_token")
+    if admin_token != os.environ.get("ADMIN_TOKEN"):
+        return {
+            "success": False,
+            "error": "Invalid admin token",
+            "status_code": 401
+        }
+    
+    # Validate input
+    email = data.get("email")
+    name = data.get("name")
+    
+    if not email or not name:
+        return {
+            "success": False,
+            "error": "Email and name are required",
+            "status_code": 400
+        }
+    
+    # Create user
+    user = create_user.remote(email, name)
+    
+    if "error" in user:
+        return {
+            "success": False,
+            "error": user["error"],
+            "status_code": 400
+        }
+    
+    return {
+        "success": True,
+        "data": {
+            "user_id": user["_id"],
+            "email": user["email"],
+            "name": user["name"],
+            "api_token": user["api_token"],
+            "credits": user["credits"],
+            "created_at": user["created_at"].isoformat() if isinstance(user["created_at"], datetime) else user["created_at"]
+        },
+        "status_code": 201
+    }
+
+@app.function(secrets=[admin_secret])
+@web_endpoint(method="POST")
+def admin_update_credits(data: Dict[str, Any]) -> Dict[str, Any]:
+    """Admin endpoint to update user credits."""
+    # Validate admin token
+    admin_token = data.get("admin_token")
+    if admin_token != os.environ.get("ADMIN_TOKEN"):
+        return {
+            "success": False,
+            "error": "Invalid admin token",
+            "status_code": 401
+        }
+    
+    # Validate input
+    api_token = data.get("api_token")
+    amount = data.get("amount")
+    
+    if not api_token:
+        return {
+            "success": False,
+            "error": "API token is required",
+            "status_code": 400
+        }
+    
+    if not isinstance(amount, int):
+        return {
+            "success": False,
+            "error": "Amount must be an integer",
+            "status_code": 400
+        }
+    
+    # Update credits
+    result = update_user_credits.remote(api_token, amount)
+    
+    if not result.get("success", False):
+        return {
+            "success": False,
+            "error": result.get("error", "Failed to update credits"),
+            "status_code": 400
+        }
+    
+    return {
+        "success": True,
+        "data": {
+            "credits": result["credits"]
+        },
+        "status_code": 200
+    }
+
+@app.function(secrets=[admin_secret])
+@web_endpoint(method="GET")
+def admin_get_users(admin_token: str) -> Dict[str, Any]:
+    """Admin endpoint to list all users."""
+    # Validate admin token
+    if admin_token != os.environ.get("ADMIN_TOKEN"):
+        return {
+            "success": False,
+            "error": "Invalid admin token",
+            "status_code": 401
+        }
+    
+    users = get_all_users.remote()
+    
+    return {
+        "success": True,
+        "data": users,
+        "status_code": 200
+    }
+
+@app.function(volumes={"/data": user_db})
+def get_all_users() -> List[Dict[str, Any]]:
+    """Get all users (for admin)."""
+    from pymongo import MongoClient
+    
+    client = MongoClient("mongodb://localhost:27017")
+    db = client.crawl4ai_db
+    
+    users = []
+    for user in db.users.find():
+        # Convert ObjectId to string
+        user["_id"] = str(user["_id"])
+        # Convert datetime to ISO format
+        for field in ["created_at", "updated_at"]:
+            if field in user and isinstance(user[field], datetime):
+                user[field] = user[field].isoformat()
+        users.append(user)
+    
+    return users
+
+# Public endpoints
+@app.function()
+@web_endpoint(method="GET")
+def health_check() -> Dict[str, Any]:
+    """Health check endpoint."""
+    return {
+        "status": "online",
+        "service": APP_NAME,
+        "version": CRAWL4AI_VERSION,
+        "timestamp": datetime.utcnow().isoformat()
+    }
+
+@app.function()
+@web_endpoint(method="GET")
+def check_credits(api_token: str) -> Dict[str, Any]:
+    """Check user credits."""
+    if not api_token:
+        return {
+            "success": False,
+            "error": "API token is required",
+            "status_code": 401
+        }
+    
+    user = get_user_by_token.remote(api_token)
+    if not user:
+        return {
+            "success": False,
+            "error": "Invalid API token",
+            "status_code": 401
+        }
+    
+    return {
+        "success": True,
+        "data": {
+            "credits": user["credits"],
+            "email": user["email"],
+            "name": user["name"]
+        },
+        "status_code": 200
+    }
+
+# Local entrypoint for testing
+@app.local_entrypoint()
+def main(url: str = "https://www.modal.com"):
+    """Command line entrypoint for local testing."""
+    print("Initializing database...")
+    init_db.remote()
+    
+    print(f"Testing crawl on URL: {url}")
+    result = crawl.remote(url)
+    
+    # Print sample of result
+    print("\nCrawl Result Sample:")
+    if "title" in result:
+        print(f"Title: {result['title']}")
+    if "status" in result:
+        print(f"Status: {result['status']}")
+    if "links" in result:
+        print(f"Links found: {len(result['links'])}")
+    if "markdown_v2" in result and result["markdown_v2"] and "raw_markdown" in result["markdown_v2"]:
+        print("\nMarkdown Preview (first 300 chars):")
+        print(result["markdown_v2"]["raw_markdown"][:300] + "...")

deploy/modal/entry.py

@@ -0,0 +1,127 @@
+import modal
+from typing import Optional, Dict, Any
+
+# Create a custom image with Crawl4ai and its dependencies
+# "pip install crawl4ai",
+image = modal.Image.debian_slim(python_version="3.10").pip_install(["fastapi[standard]"]).run_commands(
+    "apt-get update",
+    "apt-get install -y software-properties-common",
+    "apt-get install -y git",
+    "apt-add-repository non-free",
+    "apt-add-repository contrib",
+    "pip install -U git+https://github.com/unclecode/crawl4ai.git@next",
+    "pip install -U fastapi[standard]",
+    "pip install -U pydantic",
+    "crawl4ai-setup",  # This installs playwright and downloads chromium
+    # Print fastpi version
+    "python -m fastapi --version",
+)
+
+# Define the app
+app = modal.App("crawl4ai", image=image)
+
+# Define default configurations
+DEFAULT_BROWSER_CONFIG = {
+    "headless": True,
+    "verbose": False,
+}
+
+DEFAULT_CRAWLER_CONFIG = {
+    "crawler_config": {
+        "type": "CrawlerRunConfig",
+        "params": {
+            "markdown_generator": {
+                "type": "DefaultMarkdownGenerator",
+                "params": {
+                    "content_filter": {
+                        "type": "PruningContentFilter",
+                        "params": {
+                            "threshold": 0.48,
+                            "threshold_type": "fixed"
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
+
+@app.function(timeout=300)  # 5 minute timeout
+async def crawl(
+    url: str,
+    browser_config: Optional[Dict[str, Any]] = None,
+    crawler_config: Optional[Dict[str, Any]] = None,
+) -> Dict[str, Any]:
+    """
+    Crawl a given URL using Crawl4ai.
+    
+    Args:
+        url: The URL to crawl
+        browser_config: Optional browser configuration to override defaults
+        crawler_config: Optional crawler configuration to override defaults
+        
+    Returns:
+        A dictionary containing the crawl results
+    """
+    from crawl4ai import (
+        AsyncWebCrawler,
+        BrowserConfig,
+        CrawlerRunConfig,
+        CrawlResult
+    )
+
+
+    # Prepare browser config using the loader method
+    if browser_config is None:
+        browser_config = DEFAULT_BROWSER_CONFIG
+    browser_config_obj = BrowserConfig.load(browser_config)
+    
+    # Prepare crawler config using the loader method
+    if crawler_config is None:
+        crawler_config = DEFAULT_CRAWLER_CONFIG
+    crawler_config_obj = CrawlerRunConfig.load(crawler_config)    
+    
+    
+    # Perform the crawl
+    async with AsyncWebCrawler(config=browser_config_obj) as crawler:
+        result: CrawlResult = await crawler.arun(url=url, config=crawler_config_obj)
+        
+        # Return serializable results
+        try:
+            # Try newer Pydantic v2 method
+            return result.model_dump()
+        except AttributeError:
+            try:
+                # Try older Pydantic v1 method
+                return result.__dict__
+            except AttributeError:
+                # Fallback to returning the raw result
+                return result
+
+@app.function()
+@modal.web_endpoint(method="POST")
+def crawl_endpoint(data: Dict[str, Any]) -> Dict[str, Any]:
+    """
+    Web endpoint that accepts POST requests with JSON data containing:
+    - url: The URL to crawl
+    - browser_config: Optional browser configuration
+    - crawler_config: Optional crawler configuration
+    
+    Returns the crawl results.
+    """
+    url = data.get("url")
+    if not url:
+        return {"error": "URL is required"}
+    
+    browser_config = data.get("browser_config")
+    crawler_config = data.get("crawler_config")
+    
+    return crawl.remote(url, browser_config, crawler_config)
+
+@app.local_entrypoint()
+def main(url: str = "https://www.modal.com"):
+    """
+    Command line entrypoint for local testing.
+    """
+    result = crawl.remote(url)
+    print(result)

deploy/modal/guide.md

@@ -0,0 +1,453 @@
+# Deploying Crawl4ai with Modal: A Comprehensive Tutorial
+
+Hey there! UncleCode here. I'm excited to show you how to deploy Crawl4ai using Modal - a fantastic serverless platform that makes deployment super simple and scalable.
+
+In this tutorial, I'll walk you through deploying your own Crawl4ai instance on Modal's infrastructure. This will give you a powerful, scalable web crawling solution without having to worry about infrastructure management.
+
+## What is Modal?
+
+Modal is a serverless platform that allows you to run Python functions in the cloud without managing servers. It's perfect for deploying Crawl4ai because:
+
+1. It handles all the infrastructure for you
+2. It scales automatically based on demand
+3. It makes deployment incredibly simple
+
+## Prerequisites
+
+Before we get started, you'll need:
+
+- A Modal account (sign up at [modal.com](https://modal.com))
+- Python 3.10 or later installed on your local machine
+- Basic familiarity with Python and command-line operations
+
+## Step 1: Setting Up Your Modal Account
+
+First, sign up for a Modal account at [modal.com](https://modal.com) if you haven't already. Modal offers a generous free tier that's perfect for getting started.
+
+After signing up, install the Modal CLI and authenticate:
+
+```bash
+pip install modal
+modal token new
+```
+
+This will open a browser window where you can authenticate and generate a token for the CLI.
+
+## Step 2: Creating Your Crawl4ai Deployment
+
+Now, let's create a Python file called `crawl4ai_modal.py` with our deployment code:
+
+```python
+import modal
+from typing import Optional, Dict, Any
+
+# Create a custom image with Crawl4ai and its dependencies
+image = modal.Image.debian_slim(python_version="3.10").pip_install(
+    ["fastapi[standard]"]
+).run_commands(
+    "apt-get update",
+    "apt-get install -y software-properties-common",
+    "apt-get install -y git",
+    "apt-add-repository non-free",
+    "apt-add-repository contrib",
+    "pip install -U crawl4ai",
+    "pip install -U fastapi[standard]",
+    "pip install -U pydantic",
+    "crawl4ai-setup",  # This installs playwright and downloads chromium
+)
+
+# Define the app
+app = modal.App("crawl4ai", image=image)
+
+# Define default configurations
+DEFAULT_BROWSER_CONFIG = {
+    "headless": True,
+    "verbose": False,
+}
+
+DEFAULT_CRAWLER_CONFIG = {
+    "crawler_config": {
+        "type": "CrawlerRunConfig",
+        "params": {
+            "markdown_generator": {
+                "type": "DefaultMarkdownGenerator",
+                "params": {
+                    "content_filter": {
+                        "type": "PruningContentFilter",
+                        "params": {
+                            "threshold": 0.48,
+                            "threshold_type": "fixed"
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
+
+@app.function(timeout=300)  # 5 minute timeout
+async def crawl(
+    url: str,
+    browser_config: Optional[Dict[str, Any]] = None,
+    crawler_config: Optional[Dict[str, Any]] = None,
+) -> Dict[str, Any]:
+    """
+    Crawl a given URL using Crawl4ai.
+    
+    Args:
+        url: The URL to crawl
+        browser_config: Optional browser configuration to override defaults
+        crawler_config: Optional crawler configuration to override defaults
+        
+    Returns:
+        A dictionary containing the crawl results
+    """
+    from crawl4ai import (
+        AsyncWebCrawler,
+        BrowserConfig,
+        CrawlerRunConfig,
+        CrawlResult
+    )
+
+    # Prepare browser config using the loader method
+    if browser_config is None:
+        browser_config = DEFAULT_BROWSER_CONFIG
+    browser_config_obj = BrowserConfig.load(browser_config)
+    
+    # Prepare crawler config using the loader method
+    if crawler_config is None:
+        crawler_config = DEFAULT_CRAWLER_CONFIG
+    crawler_config_obj = CrawlerRunConfig.load(crawler_config)    
+    
+    # Perform the crawl
+    async with AsyncWebCrawler(config=browser_config_obj) as crawler:
+        result: CrawlResult = await crawler.arun(url=url, config=crawler_config_obj)
+        
+        # Return serializable results
+        try:
+            # Try newer Pydantic v2 method
+            return result.model_dump()
+        except AttributeError:
+            try:
+                # Try older Pydantic v1 method
+                return result.dict()
+            except AttributeError:
+                # Fallback to manual conversion
+                return {
+                    "url": result.url,
+                    "title": result.title,
+                    "status": result.status,
+                    "content": str(result.content) if hasattr(result, "content") else None,
+                    "links": [{"url": link.url, "text": link.text} for link in result.links] if hasattr(result, "links") else [],
+                    "markdown_v2": {
+                        "raw_markdown": result.markdown_v2.raw_markdown if hasattr(result, "markdown_v2") else None
+                    }
+                }
+
+@app.function()
+@modal.web_endpoint(method="POST")
+def crawl_endpoint(data: Dict[str, Any]) -> Dict[str, Any]:
+    """
+    Web endpoint that accepts POST requests with JSON data containing:
+    - url: The URL to crawl
+    - browser_config: Optional browser configuration
+    - crawler_config: Optional crawler configuration
+    
+    Returns the crawl results.
+    """
+    url = data.get("url")
+    if not url:
+        return {"error": "URL is required"}
+    
+    browser_config = data.get("browser_config")
+    crawler_config = data.get("crawler_config")
+    
+    return crawl.remote(url, browser_config, crawler_config)
+
+@app.local_entrypoint()
+def main(url: str = "https://www.modal.com"):
+    """
+    Command line entrypoint for local testing.
+    """
+    result = crawl.remote(url)
+    print(result)
+```
+
+## Step 3: Understanding the Code Components
+
+Let's break down what's happening in this code:
+
+### 1. Image Definition
+
+```python
+image = modal.Image.debian_slim(python_version="3.10").pip_install(
+    ["fastapi[standard]"]
+).run_commands(
+    "apt-get update",
+    "apt-get install -y software-properties-common",
+    "apt-get install -y git",
+    "apt-add-repository non-free",
+    "apt-add-repository contrib",
+    "pip install -U git+https://github.com/unclecode/crawl4ai.git@next",
+    "pip install -U fastapi[standard]",
+    "pip install -U pydantic",
+    "crawl4ai-setup",  # This installs playwright and downloads chromium
+)
+```
+
+This section defines the container image that Modal will use to run your code. It:
+- Starts with a Debian Slim base image with Python 3.10
+- Installs FastAPI
+- Updates the system packages
+- Installs Git and other dependencies
+- Installs Crawl4ai from the GitHub repository
+- Runs the Crawl4ai setup to install Playwright and download Chromium
+
+### 2. Modal App Definition
+
+```python
+app = modal.App("crawl4ai", image=image)
+```
+
+This creates a Modal application named "crawl4ai" that uses the image we defined above.
+
+### 3. Default Configurations
+
+```python
+DEFAULT_BROWSER_CONFIG = {
+    "headless": True,
+    "verbose": False,
+}
+
+DEFAULT_CRAWLER_CONFIG = {
+    "crawler_config": {
+        "type": "CrawlerRunConfig",
+        "params": {
+            "markdown_generator": {
+                "type": "DefaultMarkdownGenerator",
+                "params": {
+                    "content_filter": {
+                        "type": "PruningContentFilter",
+                        "params": {
+                            "threshold": 0.48,
+                            "threshold_type": "fixed"
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
+```
+
+These define the default configurations for the browser and crawler. You can customize these settings based on your specific needs.
+
+### 4. The Crawl Function
+
+```python
+@app.function(timeout=300)
+async def crawl(url, browser_config, crawler_config):
+    # Function implementation
+```
+
+This is the main function that performs the crawling. It:
+- Takes a URL and optional configurations
+- Sets up the browser and crawler with those configurations
+- Performs the crawl
+- Returns the results in a serializable format
+
+The `@app.function(timeout=300)` decorator tells Modal to run this function in the cloud with a 5-minute timeout.
+
+### 5. The Web Endpoint
+
+```python
+@app.function()
+@modal.web_endpoint(method="POST")
+def crawl_endpoint(data: Dict[str, Any]) -> Dict[str, Any]:
+    # Function implementation
+```
+
+This creates a web endpoint that accepts POST requests. It:
+- Extracts the URL and configurations from the request
+- Calls the crawl function with those parameters
+- Returns the results
+
+### 6. Local Entrypoint
+
+```python
+@app.local_entrypoint()
+def main(url: str = "https://www.modal.com"):
+    # Function implementation
+```
+
+This provides a way to test the application from the command line.
+
+## Step 4: Testing Locally
+
+Before deploying, let's test our application locally:
+
+```bash
+modal run crawl4ai_modal.py --url "https://example.com"
+```
+
+This command will:
+1. Upload your code to Modal
+2. Create the necessary containers
+3. Run the `main` function with the specified URL
+4. Return the results
+
+Modal will handle all the infrastructure setup for you. You should see the crawling results printed to your console.
+
+## Step 5: Deploying Your Application
+
+Once you're satisfied with the local testing, it's time to deploy:
+
+```bash
+modal deploy crawl4ai_modal.py
+```
+
+This will deploy your application to Modal's cloud. The deployment process will output URLs for your web endpoints.
+
+You should see output similar to:
+
+```
+✓ Deployed crawl4ai.
+  URLs:
+    crawl_endpoint => https://your-username--crawl-endpoint.modal.run
+```
+
+Save this URL - you'll need it to make requests to your deployment.
+
+## Step 6: Using Your Deployment
+
+Now that your application is deployed, you can use it by sending POST requests to the endpoint URL:
+
+```bash
+curl -X POST https://your-username--crawl-endpoint.modal.run \
+  -H "Content-Type: application/json" \
+  -d '{"url": "https://example.com"}'
+```
+
+Or in Python:
+
+```python
+import requests
+
+response = requests.post(
+    "https://your-username--crawl-endpoint.modal.run",
+    json={"url": "https://example.com"}
+)
+
+result = response.json()
+print(result)
+```
+
+You can also customize the browser and crawler configurations:
+
+```python
+requests.post(
+    "https://your-username--crawl-endpoint.modal.run",
+    json={
+        "url": "https://example.com",
+        "browser_config": {
+            "headless": False,
+            "verbose": True
+        },
+        "crawler_config": {
+            "crawler_config": {
+                "type": "CrawlerRunConfig",
+                "params": {
+                    "markdown_generator": {
+                        "type": "DefaultMarkdownGenerator",
+                        "params": {
+                            "content_filter": {
+                                "type": "PruningContentFilter",
+                                "params": {
+                                    "threshold": 0.6,  # Adjusted threshold
+                                    "threshold_type": "fixed"
+                                }
+                            }
+                        }
+                    }
+                }
+            }
+        }
+    }
+)
+```
+
+## Step 7: Calling Your Deployment from Another Python Script
+
+You can also call your deployed function directly from another Python script:
+
+```python
+import modal
+
+# Get a reference to the deployed function
+crawl_function = modal.Function.from_name("crawl4ai", "crawl")
+
+# Call the function
+result = crawl_function.remote("https://example.com")
+print(result)
+```
+
+## Understanding Modal's Execution Flow
+
+To understand how Modal works, it's important to know:
+
+1. **Local vs. Remote Execution**: When you call a function with `.remote()`, it runs in Modal's cloud, not on your local machine.
+
+2. **Container Lifecycle**: Modal creates containers on-demand and destroys them when they're not needed.
+
+3. **Caching**: Modal caches your container images to speed up subsequent runs.
+
+4. **Serverless Scaling**: Modal automatically scales your application based on demand.
+
+## Customizing Your Deployment
+
+You can customize your deployment in several ways:
+
+### Changing the Crawl4ai Version
+
+To use a different version of Crawl4ai, update the installation command in the image definition:
+
+```python
+"pip install -U git+https://github.com/unclecode/crawl4ai.git@main",  # Use main branch
+```
+
+### Adjusting Resource Limits
+
+You can change the resources allocated to your functions:
+
+```python
+@app.function(timeout=600, cpu=2, memory=4096)  # 10 minute timeout, 2 CPUs, 4GB RAM
+async def crawl(...):
+    # Function implementation
+```
+
+### Keeping Containers Warm
+
+To reduce cold start times, you can keep containers warm:
+
+```python
+@app.function(keep_warm=1)  # Keep 1 container warm
+async def crawl(...):
+    # Function implementation
+```
+
+## Conclusion
+
+That's it! You've successfully deployed Crawl4ai on Modal. You now have a scalable web crawling solution that can handle as many requests as you need without requiring any infrastructure management.
+
+The beauty of this setup is its simplicity - Modal handles all the hard parts, letting you focus on using Crawl4ai to extract the data you need.
+
+Feel free to reach out if you have any questions or need help with your deployment!
+
+Happy crawling!
+- UncleCode
+
+## Additional Resources
+
+- [Modal Documentation](https://modal.com/docs)
+- [Crawl4ai GitHub Repository](https://github.com/unclecode/crawl4ai)
+- [Crawl4ai Documentation](https://docs.crawl4ai.com)

deploy/modal/test_modal.py

@@ -0,0 +1,317 @@
+
+#!/usr/bin/env python3
+"""
+Crawl4ai API Testing Script
+
+This script tests all endpoints of the Crawl4ai API service and demonstrates their usage.
+"""
+
+import argparse
+import json
+import sys
+import time
+from typing import Dict, Any, List, Optional
+
+import requests
+
+# Colors for terminal output
+class Colors:
+    HEADER = '\033[95m'
+    BLUE = '\033[94m'
+    GREEN = '\033[92m'
+    YELLOW = '\033[93m'
+    RED = '\033[91m'
+    ENDC = '\033[0m'
+    BOLD = '\033[1m'
+    UNDERLINE = '\033[4m'
+
+def print_header(text: str) -> None:
+    """Print a formatted header."""
+    print(f"\n{Colors.HEADER}{Colors.BOLD}{'=' * 80}{Colors.ENDC}")
+    print(f"{Colors.HEADER}{Colors.BOLD}{text.center(80)}{Colors.ENDC}")
+    print(f"{Colors.HEADER}{Colors.BOLD}{'=' * 80}{Colors.ENDC}\n")
+
+def print_step(text: str) -> None:
+    """Print a formatted step description."""
+    print(f"{Colors.BLUE}{Colors.BOLD}>> {text}{Colors.ENDC}")
+
+def print_success(text: str) -> None:
+    """Print a success message."""
+    print(f"{Colors.GREEN}✓ {text}{Colors.ENDC}")
+
+def print_warning(text: str) -> None:
+    """Print a warning message."""
+    print(f"{Colors.YELLOW}⚠ {text}{Colors.ENDC}")
+
+def print_error(text: str) -> None:
+    """Print an error message."""
+    print(f"{Colors.RED}✗ {text}{Colors.ENDC}")
+
+def print_json(data: Dict[str, Any]) -> None:
+    """Pretty print JSON data."""
+    print(json.dumps(data, indent=2))
+
+def make_request(method: str, url: str, params: Optional[Dict[str, Any]] = None, 
+                 json_data: Optional[Dict[str, Any]] = None, 
+                 expected_status: int = 200) -> Dict[str, Any]:
+    """Make an HTTP request and handle errors."""
+    print_step(f"Making {method.upper()} request to {url}")
+    
+    if params:
+        print(f"  Parameters: {params}")
+    if json_data:
+        print(f"  JSON Data: {json_data}")
+    
+    try:
+        response = requests.request(
+            method=method,
+            url=url,
+            params=params,
+            json=json_data,
+            timeout=300  # 5 minute timeout for crawling operations
+        )
+        
+        status_code = response.status_code
+        print(f"  Status Code: {status_code}")
+        
+        try:
+            data = response.json()
+            print("  Response:")
+            print_json(data)
+            
+            if status_code != expected_status:
+                print_error(f"Expected status code {expected_status}, got {status_code}")
+                return data
+            
+            print_success("Request successful")
+            return data
+        except ValueError:
+            print_error("Response is not valid JSON")
+            print(response.text)
+            return {"error": "Invalid JSON response"}
+            
+    except requests.RequestException as e:
+        print_error(f"Request failed: {str(e)}")
+        return {"error": str(e)}
+
+def test_health_check(base_url: str) -> bool:
+    """Test the health check endpoint."""
+    print_header("Testing Health Check Endpoint")
+    
+    response = make_request("GET", f"{base_url}/health_check")
+    
+    if "status" in response and response["status"] == "online":
+        print_success("Health check passed")
+        return True
+    else:
+        print_error("Health check failed")
+        return False
+
+def test_admin_create_user(base_url: str, admin_token: str, email: str, name: str) -> Optional[str]:
+    """Test creating a new user."""
+    print_header("Testing Admin User Creation")
+    
+    response = make_request(
+        "POST", 
+        f"{base_url}/admin_create_user",
+        json_data={
+            "admin_token": admin_token,
+            "email": email,
+            "name": name
+        },
+        expected_status=201
+    )
+    
+    if response.get("success") and "data" in response:
+        api_token = response["data"].get("api_token")
+        if api_token:
+            print_success(f"User created successfully with API token: {api_token}")
+            return api_token
+    
+    print_error("Failed to create user")
+    return None
+
+def test_check_credits(base_url: str, api_token: str) -> Optional[int]:
+    """Test checking user credits."""
+    print_header("Testing Check Credits Endpoint")
+    
+    response = make_request(
+        "GET",
+        f"{base_url}/check_credits",
+        params={"api_token": api_token}
+    )
+    
+    if response.get("success") and "data" in response:
+        credits = response["data"].get("credits")
+        if credits is not None:
+            print_success(f"User has {credits} credits")
+            return credits
+    
+    print_error("Failed to check credits")
+    return None
+
+def test_crawl_endpoint(base_url: str, api_token: str, url: str) -> bool:
+    """Test the crawl endpoint."""
+    print_header("Testing Crawl Endpoint")
+    
+    response = make_request(
+        "POST",
+        f"{base_url}/crawl_endpoint",
+        json_data={
+            "api_token": api_token,
+            "url": url
+        }
+    )
+    
+    if response.get("success") and "data" in response:
+        print_success("Crawl completed successfully")
+        
+        # Display some crawl result data
+        data = response["data"]
+        if "title" in data:
+            print(f"Page Title: {data['title']}")
+        if "status" in data:
+            print(f"Status: {data['status']}")
+        if "links" in data:
+            print(f"Links found: {len(data['links'])}")
+        if "markdown_v2" in data and data["markdown_v2"] and "raw_markdown" in data["markdown_v2"]:
+            print("Markdown Preview (first 200 chars):")
+            print(data["markdown_v2"]["raw_markdown"][:200] + "...")
+            
+        credits_remaining = response.get("credits_remaining")
+        if credits_remaining is not None:
+            print(f"Credits remaining: {credits_remaining}")
+            
+        return True
+    
+    print_error("Crawl failed")
+    return False
+
+def test_admin_update_credits(base_url: str, admin_token: str, api_token: str, amount: int) -> bool:
+    """Test updating user credits."""
+    print_header("Testing Admin Update Credits")
+    
+    response = make_request(
+        "POST",
+        f"{base_url}/admin_update_credits",
+        json_data={
+            "admin_token": admin_token,
+            "api_token": api_token,
+            "amount": amount
+        }
+    )
+    
+    if response.get("success") and "data" in response:
+        print_success(f"Credits updated successfully, new balance: {response['data'].get('credits')}")
+        return True
+    
+    print_error("Failed to update credits")
+    return False
+
+def test_admin_get_users(base_url: str, admin_token: str) -> List[Dict[str, Any]]:
+    """Test getting all users."""
+    print_header("Testing Admin Get All Users")
+    
+    response = make_request(
+        "GET",
+        f"{base_url}/admin_get_users",
+        params={"admin_token": admin_token}
+    )
+    
+    if response.get("success") and "data" in response:
+        users = response["data"]
+        print_success(f"Retrieved {len(users)} users")
+        return users
+    
+    print_error("Failed to get users")
+    return []
+
+def run_full_test(base_url: str, admin_token: str) -> None:
+    """Run all tests in sequence."""
+    # Remove trailing slash if present
+    base_url = base_url.rstrip('/')
+    
+    # Test 1: Health Check
+    if not test_health_check(base_url):
+        print_error("Health check failed, aborting tests")
+        sys.exit(1)
+    
+    # Test 2: Create a test user
+    email = f"test-user-{int(time.time())}@example.com"
+    name = "Test User"
+    api_token = test_admin_create_user(base_url, admin_token, email, name)
+    
+    if not api_token:
+        print_error("User creation failed, aborting tests")
+        sys.exit(1)
+    
+    # Test 3: Check initial credits
+    initial_credits = test_check_credits(base_url, api_token)
+    
+    if initial_credits is None:
+        print_error("Credit check failed, aborting tests")
+        sys.exit(1)
+    
+    # Test 4: Perform a crawl
+    test_url = "https://news.ycombinator.com"
+    crawl_success = test_crawl_endpoint(base_url, api_token, test_url)
+    
+    if not crawl_success:
+        print_warning("Crawl test failed, but continuing with other tests")
+    
+    # Test 5: Check credits after crawl
+    post_crawl_credits = test_check_credits(base_url, api_token)
+    
+    if post_crawl_credits is not None and initial_credits is not None:
+        if post_crawl_credits == initial_credits - 1:
+            print_success("Credit deduction verified")
+        else:
+            print_warning(f"Unexpected credit change: {initial_credits} -> {post_crawl_credits}")
+    
+    # Test 6: Add credits
+    add_credits_amount = 50
+    if test_admin_update_credits(base_url, admin_token, api_token, add_credits_amount):
+        print_success(f"Added {add_credits_amount} credits")
+    
+    # Test 7: Check credits after addition
+    post_addition_credits = test_check_credits(base_url, api_token)
+    
+    if post_addition_credits is not None and post_crawl_credits is not None:
+        if post_addition_credits == post_crawl_credits + add_credits_amount:
+            print_success("Credit addition verified")
+        else:
+            print_warning(f"Unexpected credit change: {post_crawl_credits} -> {post_addition_credits}")
+    
+    # Test 8: Get all users
+    users = test_admin_get_users(base_url, admin_token)
+    
+    if users:
+        # Check if our test user is in the list
+        test_user = next((user for user in users if user.get("email") == email), None)
+        if test_user:
+            print_success("Test user found in users list")
+        else:
+            print_warning("Test user not found in users list")
+    
+    # Final report
+    print_header("Test Summary")
+    
+    print_success("All endpoints tested successfully")
+    print(f"Test user created with email: {email}")
+    print(f"API token: {api_token}")
+    print(f"Final credit balance: {post_addition_credits}")
+
+def main():
+    parser = argparse.ArgumentParser(description="Test Crawl4ai API endpoints")
+    parser.add_argument("--base-url", required=True, help="Base URL of the Crawl4ai API (e.g., https://username--crawl4ai-api.modal.run)")
+    parser.add_argument("--admin-token", required=True, help="Admin token for authentication")
+    
+    args = parser.parse_args()
+    
+    print_header("Crawl4ai API Test Script")
+    print(f"Testing API at: {args.base_url}")
+    
+    run_full_test(args.base_url, args.admin_token)
+
+if __name__ == "__main__":
+    main()

docker-compose.yml

@@ -1,30 +1,15 @@
-# docker-compose.yml
+# Base configuration (not a service, just a reusable config block)
-
-# Base configuration anchor for reusability
 x-base-config: &base-config
   ports:
-    # Map host port 11235 to container port 11235 (where Gunicorn will listen)
     - "11235:11235"
-    # - "8080:8080" # Uncomment if needed
+    - "8000:8000"
-
+    - "9222:9222"
-  # Load API keys primarily from .llm.env file
+    - "8080:8080"
-  # Create .llm.env in the root directory .llm.env.example
-  env_file:
-    - .llm.env
-
-  # Define environment variables, allowing overrides from host environment
-  # Syntax ${VAR:-} uses host env var 'VAR' if set, otherwise uses value from .llm.env
   environment:
+    - CRAWL4AI_API_TOKEN=${CRAWL4AI_API_TOKEN:-}
     - OPENAI_API_KEY=${OPENAI_API_KEY:-}
-    - DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY:-}
+    - CLAUDE_API_KEY=${CLAUDE_API_KEY:-}
-    - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-}
-    - GROQ_API_KEY=${GROQ_API_KEY:-}
-    - TOGETHER_API_KEY=${TOGETHER_API_KEY:-}
-    - MISTRAL_API_KEY=${MISTRAL_API_KEY:-}
-    - GEMINI_API_TOKEN=${GEMINI_API_TOKEN:-}
-
   volumes:
-    # Mount /dev/shm for Chromium/Playwright performance
     - /dev/shm:/dev/shm
   deploy:
     resources:
@@ -34,47 +19,47 @@ x-base-config: &base-config
         memory: 1G
   restart: unless-stopped
   healthcheck:
-    # IMPORTANT: Ensure Gunicorn binds to 11235 in supervisord.conf
     test: ["CMD", "curl", "-f", "http://localhost:11235/health"]
     interval: 30s
     timeout: 10s
     retries: 3
-    start_period: 40s # Give the server time to start
+    start_period: 40s
-  # Run the container as the non-root user defined in the Dockerfile
-  user: "appuser"
 
 services:
-  # --- Local Build Services ---
+  # Local build services for different platforms
-  crawl4ai-local-amd64:
+  crawl4ai-amd64:
     build:
-      context: . # Build context is the root directory
+      context: .
-      dockerfile: Dockerfile # Dockerfile is in the root directory
+      dockerfile: Dockerfile
       args:
-        INSTALL_TYPE: ${INSTALL_TYPE:-default}
+        PYTHON_VERSION: "3.10"
-        ENABLE_GPU: ${ENABLE_GPU:-false}
+        INSTALL_TYPE: ${INSTALL_TYPE:-basic}
-        # PYTHON_VERSION arg is omitted as it's fixed by 'FROM python:3.10-slim' in Dockerfile
+        ENABLE_GPU: false
-    platform: linux/amd64
+      platforms:
+        - linux/amd64
     profiles: ["local-amd64"]
-    <<: *base-config # Inherit base configuration
+    <<: *base-config  # extends yerine doğrudan yapılandırmayı dahil ettik
 
-  crawl4ai-local-arm64:
+  crawl4ai-arm64:
     build:
-      context: . # Build context is the root directory
+      context: .
-      dockerfile: Dockerfile # Dockerfile is in the root directory
+      dockerfile: Dockerfile
       args:
-        INSTALL_TYPE: ${INSTALL_TYPE:-default}
+        PYTHON_VERSION: "3.10"
-        ENABLE_GPU: ${ENABLE_GPU:-false}
+        INSTALL_TYPE: ${INSTALL_TYPE:-basic}
-    platform: linux/arm64
+        ENABLE_GPU: false
+      platforms:
+        - linux/arm64
     profiles: ["local-arm64"]
     <<: *base-config
 
-  # --- Docker Hub Image Services ---
+  # Hub services for different platforms and versions
   crawl4ai-hub-amd64:
-    image: unclecode/crawl4ai:${VERSION:-latest}-amd64
+    image: unclecode/crawl4ai:${VERSION:-basic}-amd64
     profiles: ["hub-amd64"]
     <<: *base-config
 
   crawl4ai-hub-arm64:
-    image: unclecode/crawl4ai:${VERSION:-latest}-arm64
+    image: unclecode/crawl4ai:${VERSION:-basic}-arm64
     profiles: ["hub-arm64"]
     <<: *base-config

docs/examples/README_BUILTIN_BROWSER.md

@@ -1,123 +0,0 @@
-# Builtin Browser in Crawl4AI
-
-This document explains the builtin browser feature in Crawl4AI and how to use it effectively.
-
-## What is the Builtin Browser?
-
-The builtin browser is a persistent Chrome instance that Crawl4AI manages for you. It runs in the background and can be used by multiple crawling operations, eliminating the need to start and stop browsers for each crawl.
-
-Benefits include:
-- **Faster startup times** - The browser is already running, so your scripts start faster
-- **Shared resources** - All your crawling scripts can use the same browser instance
-- **Simplified management** - No need to worry about CDP URLs or browser processes
-- **Persistent cookies and sessions** - Browser state persists between script runs
-- **Less resource usage** - Only one browser instance for multiple scripts
-
-## Using the Builtin Browser
-
-### In Python Code
-
-Using the builtin browser in your code is simple:
-
-```python
-from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig
-
-# Create browser config with builtin mode
-browser_config = BrowserConfig(
-    browser_mode="builtin",  # This is the key setting!
-    headless=True            # Can be headless or not
-)
-
-# Create the crawler
-crawler = AsyncWebCrawler(config=browser_config)
-
-# Use it - no need to explicitly start()
-result = await crawler.arun("https://example.com")
-```
-
-Key points:
-1. Set `browser_mode="builtin"` in your BrowserConfig
-2. No need for explicit `start()` call - the crawler will automatically connect to the builtin browser
-3. No need to use a context manager or call `close()` - the browser stays running
-
-### Via CLI
-
-The CLI provides commands to manage the builtin browser:
-
-```bash
-# Start the builtin browser
-crwl browser start
-
-# Check its status
-crwl browser status
-
-# Open a visible window to see what the browser is doing
-crwl browser view --url https://example.com
-
-# Stop it when no longer needed
-crwl browser stop
-
-# Restart with different settings
-crwl browser restart --no-headless
-```
-
-When crawling via CLI, simply add the builtin browser mode:
-
-```bash
-crwl https://example.com -b "browser_mode=builtin"
-```
-
-## How It Works
-
-1. When a crawler with `browser_mode="builtin"` is created:
-   - It checks if a builtin browser is already running
-   - If not, it automatically launches one
-   - It connects to the browser via CDP (Chrome DevTools Protocol)
-
-2. The browser process continues running after your script exits
-   - This means it's ready for the next crawl
-   - You can manage it via the CLI commands
-
-3. During installation, Crawl4AI attempts to create a builtin browser automatically
-
-## Example
-
-See the [builtin_browser_example.py](builtin_browser_example.py) file for a complete example.
-
-Run it with:
-
-```bash
-python builtin_browser_example.py
-```
-
-## When to Use
-
-The builtin browser is ideal for:
-- Scripts that run frequently
-- Development and testing workflows
-- Applications that need to minimize startup time
-- Systems where you want to manage browser instances centrally
-
-You might not want to use it when:
-- Running one-off scripts
-- When you need different browser configurations for different tasks
-- In environments where persistent processes are not allowed
-
-## Troubleshooting
-
-If you encounter issues:
-
-1. Check the browser status:
-   ```
-   crwl browser status
-   ```
-
-2. Try restarting it:
-   ```
-   crwl browser restart
-   ```
-
-3. If problems persist, stop it and let Crawl4AI start a fresh one:
-   ```
-   crwl browser stop
-   ```

docs/examples/arun_vs_arun_many.py

@@ -1,79 +0,0 @@
-import asyncio
-import time
-from crawl4ai.async_webcrawler import AsyncWebCrawler, CacheMode
-from crawl4ai.async_configs import CrawlerRunConfig
-from crawl4ai.async_dispatcher import MemoryAdaptiveDispatcher, RateLimiter
-
-VERBOSE = False
-
-async def crawl_sequential(urls):
-    config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS, verbose=VERBOSE)
-    results = []
-    start_time = time.perf_counter()
-    async with AsyncWebCrawler() as crawler:
-        for url in urls:
-            result_container = await crawler.arun(url=url, config=config)
-            results.append(result_container[0])
-    total_time = time.perf_counter() - start_time
-    return total_time, results
-
-async def crawl_parallel_dispatcher(urls):
-    config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS, verbose=VERBOSE)
-    # Dispatcher with rate limiter enabled (default behavior)
-    dispatcher = MemoryAdaptiveDispatcher(
-        rate_limiter=RateLimiter(base_delay=(1.0, 3.0), max_delay=60.0, max_retries=3),
-        max_session_permit=50,
-    )
-    start_time = time.perf_counter()
-    async with AsyncWebCrawler() as crawler:
-        result_container = await crawler.arun_many(urls=urls, config=config, dispatcher=dispatcher)
-        results = []
-        if isinstance(result_container, list):
-            results = result_container
-        else:
-            async for res in result_container:
-                results.append(res)
-    total_time = time.perf_counter() - start_time
-    return total_time, results
-
-async def crawl_parallel_no_rate_limit(urls):
-    config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS, verbose=VERBOSE)
-    # Dispatcher with no rate limiter and a high session permit to avoid queuing
-    dispatcher = MemoryAdaptiveDispatcher(
-        rate_limiter=None,
-        max_session_permit=len(urls)  # allow all URLs concurrently
-    )
-    start_time = time.perf_counter()
-    async with AsyncWebCrawler() as crawler:
-        result_container = await crawler.arun_many(urls=urls, config=config, dispatcher=dispatcher)
-        results = []
-        if isinstance(result_container, list):
-            results = result_container
-        else:
-            async for res in result_container:
-                results.append(res)
-    total_time = time.perf_counter() - start_time
-    return total_time, results
-
-async def main():
-    urls = ["https://example.com"] * 100
-    print(f"Crawling {len(urls)} URLs sequentially...")
-    seq_time, seq_results = await crawl_sequential(urls)
-    print(f"Sequential crawling took: {seq_time:.2f} seconds\n")
-    
-    print(f"Crawling {len(urls)} URLs in parallel using arun_many with dispatcher (with rate limit)...")
-    disp_time, disp_results = await crawl_parallel_dispatcher(urls)
-    print(f"Parallel (dispatcher with rate limiter) took: {disp_time:.2f} seconds\n")
-       
-    print(f"Crawling {len(urls)} URLs in parallel using dispatcher with no rate limiter...")
-    no_rl_time, no_rl_results = await crawl_parallel_no_rate_limit(urls)
-    print(f"Parallel (dispatcher without rate limiter) took: {no_rl_time:.2f} seconds\n")
-    
-    print("Crawl4ai - Crawling Comparison")
-    print("--------------------------------------------------------")
-    print(f"Sequential crawling took: {seq_time:.2f} seconds")
-    print(f"Parallel (dispatcher with rate limiter) took: {disp_time:.2f} seconds")
-    print(f"Parallel (dispatcher without rate limiter) took: {no_rl_time:.2f} seconds")
-    
-if __name__ == "__main__":
-    asyncio.run(main())

docs/examples/builtin_browser_example.py

@@ -1,86 +0,0 @@
-#!/usr/bin/env python3
-"""
-Builtin Browser Example
-
-This example demonstrates how to use Crawl4AI's builtin browser feature,
-which simplifies the browser management process. With builtin mode:
-
-- No need to manually start or connect to a browser
-- No need to manage CDP URLs or browser processes
-- Automatically connects to an existing browser or launches one if needed
-- Browser persists between script runs, reducing startup time
-- No explicit cleanup or close() calls needed
-
-The example also demonstrates "auto-starting" where you don't need to explicitly
-call start() method on the crawler.
-"""
-
-import asyncio
-from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
-import time
-
-async def crawl_with_builtin_browser():
-    """
-    Simple example of crawling with the builtin browser.
-    
-    Key features:
-    1. browser_mode="builtin" in BrowserConfig
-    2. No explicit start() call needed
-    3. No explicit close() needed
-    """
-    print("\n=== Crawl4AI Builtin Browser Example ===\n")
-    
-    # Create a browser configuration with builtin mode
-    browser_config = BrowserConfig(
-        browser_mode="builtin",  # This is the key setting!
-        headless=True            # Can run headless for background operation
-    )
-    
-    # Create crawler run configuration
-    crawler_config = CrawlerRunConfig(
-        cache_mode=CacheMode.BYPASS,  # Skip cache for this demo
-        screenshot=True,              # Take a screenshot
-        verbose=True                  # Show verbose logging
-    )
-    
-    # Create the crawler instance
-    # Note: We don't need to use "async with" context manager
-    crawler = AsyncWebCrawler(config=browser_config)
-    
-    # Start crawling several URLs - no explicit start() needed!
-    # The crawler will automatically connect to the builtin browser
-    print("\n➡️ Crawling first URL...")
-    t0 = time.time()
-    result1 = await crawler.arun(
-        url="https://crawl4ai.com",
-        config=crawler_config
-    )
-    t1 = time.time()
-    print(f"✅ First URL crawled in {t1-t0:.2f} seconds")
-    print(f"   Got {len(result1.markdown.raw_markdown)} characters of content")
-    print(f"   Title: {result1.metadata.get('title', 'No title')}")
-    
-    # Try another URL - the browser is already running, so this should be faster
-    print("\n➡️ Crawling second URL...")
-    t0 = time.time()
-    result2 = await crawler.arun(
-        url="https://example.com",
-        config=crawler_config
-    )
-    t1 = time.time()
-    print(f"✅ Second URL crawled in {t1-t0:.2f} seconds")
-    print(f"   Got {len(result2.markdown.raw_markdown)} characters of content")
-    print(f"   Title: {result2.metadata.get('title', 'No title')}")
-    
-    # The builtin browser continues running in the background
-    # No need to explicitly close it
-    print("\n🔄 The builtin browser remains running for future use")
-    print("   You can use 'crwl browser status' to check its status")
-    print("   or 'crwl browser stop' to stop it when completely done")
-
-async def main():
-    """Run the example"""
-    await crawl_with_builtin_browser()
-
-if __name__ == "__main__":
-    asyncio.run(main())

docs/examples/crawler_monitor_example.py

@@ -1,209 +0,0 @@
-"""
-CrawlerMonitor Example
-
-This example demonstrates how to use the CrawlerMonitor component 
-to visualize and track web crawler operations in real-time.
-"""
-
-import time
-import uuid
-import random
-import threading
-from crawl4ai.components.crawler_monitor import CrawlerMonitor
-from crawl4ai.models import CrawlStatus
-
-def simulate_webcrawler_operations(monitor, num_tasks=20):
-    """
-    Simulates a web crawler's operations with multiple tasks and different states.
-    
-    Args:
-        monitor: The CrawlerMonitor instance
-        num_tasks: Number of tasks to simulate
-    """
-    print(f"Starting simulation with {num_tasks} tasks...")
-    
-    # Create and register all tasks first
-    task_ids = []
-    for i in range(num_tasks):
-        task_id = str(uuid.uuid4())
-        url = f"https://example.com/page{i}"
-        monitor.add_task(task_id, url)
-        task_ids.append((task_id, url))
-        
-        # Small delay between task creation
-        time.sleep(0.2)
-    
-    # Process tasks with a variety of different behaviors
-    threads = []
-    for i, (task_id, url) in enumerate(task_ids):
-        # Create a thread for each task
-        thread = threading.Thread(
-            target=process_task,
-            args=(monitor, task_id, url, i)
-        )
-        thread.daemon = True
-        threads.append(thread)
-    
-    # Start threads in batches to simulate concurrent processing
-    batch_size = 4  # Process 4 tasks at a time
-    for i in range(0, len(threads), batch_size):
-        batch = threads[i:i+batch_size]
-        for thread in batch:
-            thread.start()
-            time.sleep(0.5)  # Stagger thread start times
-        
-        # Wait a bit before starting next batch
-        time.sleep(random.uniform(1.0, 3.0))
-        
-        # Update queue statistics
-        update_queue_stats(monitor)
-        
-        # Simulate memory pressure changes
-        active_threads = [t for t in threads if t.is_alive()]
-        if len(active_threads) > 8:
-            monitor.update_memory_status("CRITICAL")
-        elif len(active_threads) > 4:
-            monitor.update_memory_status("PRESSURE")
-        else:
-            monitor.update_memory_status("NORMAL")
-    
-    # Wait for all threads to complete
-    for thread in threads:
-        thread.join()
-    
-    # Final updates
-    update_queue_stats(monitor)
-    monitor.update_memory_status("NORMAL")
-    
-    print("Simulation completed!")
-    
-def process_task(monitor, task_id, url, index):
-    """Simulate processing of a single task."""
-    # Tasks start in queued state (already added)
-    
-    # Simulate waiting in queue
-    wait_time = random.uniform(0.5, 3.0)
-    time.sleep(wait_time)
-    
-    # Start processing - move to IN_PROGRESS
-    monitor.update_task(
-        task_id=task_id,
-        status=CrawlStatus.IN_PROGRESS,
-        start_time=time.time(),
-        wait_time=wait_time
-    )
-    
-    # Simulate task processing with memory usage changes
-    total_process_time = random.uniform(2.0, 10.0)
-    step_time = total_process_time / 5  # Update in 5 steps
-    
-    for step in range(5):
-        # Simulate increasing then decreasing memory usage
-        if step < 3:  # First 3 steps - increasing
-            memory_usage = random.uniform(5.0, 20.0) * (step + 1)
-        else:  # Last 2 steps - decreasing
-            memory_usage = random.uniform(5.0, 20.0) * (5 - step)
-            
-        # Update peak memory if this is higher
-        peak = max(memory_usage, monitor.get_task_stats(task_id).get("peak_memory", 0))
-        
-        monitor.update_task(
-            task_id=task_id,
-            memory_usage=memory_usage,
-            peak_memory=peak
-        )
-        
-        time.sleep(step_time)
-    
-    # Determine final state - 80% success, 20% failure
-    if index % 5 == 0:  # Every 5th task fails
-        monitor.update_task(
-            task_id=task_id,
-            status=CrawlStatus.FAILED,
-            end_time=time.time(),
-            memory_usage=0.0,
-            error_message="Connection timeout"
-        )
-    else:
-        monitor.update_task(
-            task_id=task_id,
-            status=CrawlStatus.COMPLETED,
-            end_time=time.time(),
-            memory_usage=0.0
-        )
-
-def update_queue_stats(monitor):
-    """Update queue statistics based on current tasks."""
-    task_stats = monitor.get_all_task_stats()
-    
-    # Count queued tasks
-    queued_tasks = [
-        stats for stats in task_stats.values() 
-        if stats["status"] == CrawlStatus.QUEUED.name
-    ]
-    
-    total_queued = len(queued_tasks)
-    
-    if total_queued > 0:
-        current_time = time.time()
-        # Calculate wait times
-        wait_times = [
-            current_time - stats.get("enqueue_time", current_time)
-            for stats in queued_tasks
-        ]
-        highest_wait_time = max(wait_times) if wait_times else 0.0
-        avg_wait_time = sum(wait_times) / len(wait_times) if wait_times else 0.0
-    else:
-        highest_wait_time = 0.0
-        avg_wait_time = 0.0
-    
-    # Update monitor
-    monitor.update_queue_statistics(
-        total_queued=total_queued,
-        highest_wait_time=highest_wait_time,
-        avg_wait_time=avg_wait_time
-    )
-
-def main():
-    # Initialize the monitor
-    monitor = CrawlerMonitor(
-        urls_total=20,  # Total URLs to process
-        refresh_rate=0.5,  # Update UI twice per second
-        enable_ui=True,    # Enable terminal UI
-        max_width=120     # Set maximum width to 120 characters
-    )
-    
-    # Start the monitor
-    monitor.start()
-    
-    try:
-        # Run simulation
-        simulate_webcrawler_operations(monitor)
-        
-        # Keep monitor running a bit to see final state
-        print("Waiting to view final state...")
-        time.sleep(5)
-        
-    except KeyboardInterrupt:
-        print("\nExample interrupted by user")
-    finally:
-        # Stop the monitor
-        monitor.stop()
-        print("Example completed!")
-        
-        # Print some statistics
-        summary = monitor.get_summary()
-        print("\nCrawler Statistics Summary:")
-        print(f"Total URLs: {summary['urls_total']}")
-        print(f"Completed: {summary['urls_completed']}")
-        print(f"Completion percentage: {summary['completion_percentage']:.1f}%")
-        print(f"Peak memory usage: {summary['peak_memory_percent']:.1f}%")
-        
-        # Print task status counts
-        status_counts = summary['status_counts']
-        print("\nTask Status Counts:")
-        for status, count in status_counts.items():
-            print(f"  {status}: {count}")
-
-if __name__ == "__main__":
-    main()

docs/examples/crypto_analysis_example.py

@@ -18,20 +18,11 @@ Key Features:
 
 import asyncio
 import pandas as pd
-import numpy as np
-import re
 import plotly.express as px
-from crawl4ai import (
+from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode, LXMLWebScrapingStrategy
-    AsyncWebCrawler,
-    BrowserConfig,
-    CrawlerRunConfig,
-    CacheMode,
-    LXMLWebScrapingStrategy,
-)
 from crawl4ai import CrawlResult
 from typing import List
-
+from IPython.display import HTML
-__current_dir__ = __file__.rsplit("/", 1)[0]
 
 class CryptoAlphaGenerator:
     """
@@ -40,319 +31,134 @@ class CryptoAlphaGenerator:
     - Liquidity scores
     - Momentum-risk ratios
     - Machine learning-inspired trading signals
-
+    
     Methods:
     analyze_tables(): Process raw tables into trading insights
     create_visuals(): Generate institutional-grade visualizations
     generate_insights(): Create plain English trading recommendations
     """
-
+    
     def clean_data(self, df: pd.DataFrame) -> pd.DataFrame:
         """
-        Convert crypto market data to machine-readable format.
+        Convert crypto market data to machine-readable format
-        Handles currency symbols, units (B=Billions), and percentage values.
+        Handles currency symbols, units (B=Billions), and percentage values
         """
-        # Make a copy to avoid SettingWithCopyWarning
+        # Clean numeric columns
-        df = df.copy()
+        df['Price'] = df['Price'].str.replace('[^\d.]', '', regex=True).astype(float)
-        
+        df['Market Cap'] = df['Market Cap'].str.extract(r'\$([\d.]+)B')[0].astype(float) * 1e9
-        # Clean Price column (handle currency symbols)
+        df['Volume(24h)'] = df['Volume(24h)'].str.extract(r'\$([\d.]+)B')[0].astype(float) * 1e9
-        df["Price"] = df["Price"].astype(str).str.replace("[^\d.]", "", regex=True).astype(float)
-        
-        # Handle Market Cap and Volume, considering both Billions and Trillions
-        def convert_large_numbers(value):
-            if pd.isna(value):
-                return float('nan')
-            value = str(value)
-            multiplier = 1
-            if 'B' in value:
-                multiplier = 1e9
-            elif 'T' in value:
-                multiplier = 1e12
-            # Handle cases where the value might already be numeric
-            cleaned_value = re.sub(r"[^\d.]", "", value)
-            return float(cleaned_value) * multiplier if cleaned_value else float('nan')
-        
-        df["Market Cap"] = df["Market Cap"].apply(convert_large_numbers)
-        df["Volume(24h)"] = df["Volume(24h)"].apply(convert_large_numbers)
         
         # Convert percentages to decimal values
-        for col in ["1h %", "24h %", "7d %"]:
+        for col in ['1h %', '24h %', '7d %']:
-            if col in df.columns:
+            df[col] = df[col].str.replace('%', '').astype(float) / 100
-                # First ensure it's string, then clean
+            
-                df[col] = (
-                    df[col].astype(str)
-                    .str.replace("%", "")
-                    .str.replace(",", ".")
-                    .replace("nan", np.nan)
-                )
-                df[col] = pd.to_numeric(df[col], errors='coerce') / 100
-        
         return df
 
     def calculate_metrics(self, df: pd.DataFrame) -> pd.DataFrame:
         """
         Compute advanced trading metrics used by quantitative funds:
-
+        
         1. Volume/Market Cap Ratio - Measures liquidity efficiency
-           (High ratio = Underestimated attention, and small-cap = higher growth potential)
+           (High ratio = Underestimated attention)
-
+           
-        2. Volatility Score - Risk-adjusted momentum potential - Shows how stable is the trend
+        2. Volatility Score - Risk-adjusted momentum potential
            (STD of 1h/24h/7d returns)
-
+           
-        3. Momentum Score - Weighted average of returns - Shows how strong is the trend
+        3. Momentum Score - Weighted average of returns
            (1h:30% + 24h:50% + 7d:20%)
-
+           
         4. Volume Anomaly - 3σ deviation detection
-           (Flags potential insider activity) - Unusual trading activity – Flags coins with volume spikes (potential insider buying or news).
+           (Flags potential insider activity)
         """
         # Liquidity Metrics
-        df["Volume/Market Cap Ratio"] = df["Volume(24h)"] / df["Market Cap"]
+        df['Volume/Market Cap Ratio'] = df['Volume(24h)'] / df['Market Cap']
-
+        
         # Risk Metrics
-        df["Volatility Score"] = df[["1h %", "24h %", "7d %"]].std(axis=1)
+        df['Volatility Score'] = df[['1h %','24h %','7d %']].std(axis=1)
-
+        
         # Momentum Metrics
-        df["Momentum Score"] = df["1h %"] * 0.3 + df["24h %"] * 0.5 + df["7d %"] * 0.2
+        df['Momentum Score'] = (df['1h %']*0.3 + df['24h %']*0.5 + df['7d %']*0.2)
-
+        
         # Anomaly Detection
-        median_vol = df["Volume(24h)"].median()
+        median_vol = df['Volume(24h)'].median()
-        df["Volume Anomaly"] = df["Volume(24h)"] > 3 * median_vol
+        df['Volume Anomaly'] = df['Volume(24h)'] > 3 * median_vol
-
+        
         # Value Flags
-        # Undervalued Flag - Low market cap and high momentum
+        df['Undervalued Flag'] = (df['Market Cap'] < 1e9) & (df['Momentum Score'] > 0.05)
-        # (High growth potential and low attention)
+        df['Liquid Giant'] = (df['Volume/Market Cap Ratio'] > 0.15) & (df['Market Cap'] > 1e9)
-        df["Undervalued Flag"] = (df["Market Cap"] < 1e9) & (
+        
-            df["Momentum Score"] > 0.05
-        )
-        # Liquid Giant Flag - High volume/market cap ratio and large market cap
-        # (High liquidity and large market cap = institutional interest)
-        df["Liquid Giant"] = (df["Volume/Market Cap Ratio"] > 0.15) & (
-            df["Market Cap"] > 1e9
-        )
-
         return df
 
-    def generate_insights_simple(self, df: pd.DataFrame) -> str:
+    def create_visuals(self, df: pd.DataFrame) -> dict:
         """
-        Generates an ultra-actionable crypto trading report with:
+        Generate three institutional-grade visualizations:
-        - Risk-tiered opportunities (High/Medium/Low)
+        
-        - Concrete examples for each trade type
+        1. 3D Market Map - X:Size, Y:Liquidity, Z:Momentum
-        - Entry/exit strategies spelled out
+        2. Liquidity Tree - Color:Volume Efficiency
-        - Visual cues for quick scanning
+        3. Momentum Leaderboard - Top sustainable movers
         """
-        report = [
+        # 3D Market Overview
-            "🚀 **CRYPTO TRADING CHEAT SHEET** 🚀",
+        fig1 = px.scatter_3d(
-            "*Based on quantitative signals + hedge fund tactics*",
+            df, 
-            "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+            x='Market Cap', 
-        ]
+            y='Volume/Market Cap Ratio',
-
+            z='Momentum Score',
-        # 1. HIGH-RISK: Undervalued Small-Caps (Momentum Plays)
+            size='Volatility Score',
-        high_risk = df[df["Undervalued Flag"]].sort_values("Momentum Score", ascending=False)
+            color='Volume Anomaly',
-        if not high_risk.empty:
+            hover_name='Name',
-            example_coin = high_risk.iloc[0]
+            title='Smart Money Market Map: Spot Overlooked Opportunities',
-            report.extend([
+            labels={'Market Cap': 'Size (Log $)', 'Volume/Market Cap Ratio': 'Liquidity Power'},
-                "\n🔥 **HIGH-RISK: Rocket Fuel Small-Caps**",
+            log_x=True,
-                f"*Example Trade:* {example_coin['Name']} (Price: ${example_coin['Price']:.6f})",
+            template='plotly_dark'
-                "📊 *Why?* Tiny market cap (<$1B) but STRONG momentum (+{:.0f}% last week)".format(example_coin['7d %']*100),
+        )
-                "🎯 *Strategy:*",
+        
-                "1. Wait for 5-10% dip from recent high (${:.6f} → Buy under ${:.6f})".format(
+        # Liquidity Efficiency Tree
-                    example_coin['Price'] / (1 - example_coin['24h %']),  # Approx recent high
+        fig2 = px.treemap(
-                    example_coin['Price'] * 0.95
+            df,
-                ),
+            path=['Name'], 
-                "2. Set stop-loss at -10% (${:.6f})".format(example_coin['Price'] * 0.90),
+            values='Market Cap',
-                "3. Take profit at +20% (${:.6f})".format(example_coin['Price'] * 1.20),
+            color='Volume/Market Cap Ratio',
-                "⚠️ *Risk Warning:* These can drop 30% fast! Never bet more than 5% of your portfolio.",
+            hover_data=['Momentum Score'],
-                "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+            title='Liquidity Forest: Green = High Trading Efficiency',
-            ])
+            color_continuous_scale='RdYlGn'
-
+        )
-        # 2. MEDIUM-RISK: Liquid Giants (Swing Trades)
+        
-        medium_risk = df[df["Liquid Giant"]].sort_values("Volume/Market Cap Ratio", ascending=False)
+        # Momentum Leaders
-        if not medium_risk.empty:
+        fig3 = px.bar(
-            example_coin = medium_risk.iloc[0]
+            df.sort_values('Momentum Score', ascending=False).head(10),
-            report.extend([
+            x='Name', 
-                "\n💎 **MEDIUM-RISK: Liquid Giants (Safe Swing Trades)**",
+            y='Momentum Score',
-                f"*Example Trade:* {example_coin['Name']} (Market Cap: ${example_coin['Market Cap']/1e9:.1f}B)",
+            color='Volatility Score',
-                "📊 *Why?* Huge volume (${:.1f}M/day) makes it easy to enter/exit".format(example_coin['Volume(24h)']/1e6),
+            title='Sustainable Momentum Leaders (Low Volatility + High Growth)',
-                "🎯 *Strategy:*",
+            text='7d %',
-                "1. Buy when 24h volume > 15% of market cap (Current: {:.0f}%)".format(example_coin['Volume/Market Cap Ratio']*100),
+            template='plotly_dark'
-                "2. Hold 1-4 weeks (Big coins trend longer)",
+        )
-                "3. Exit when momentum drops below 5% (Current: {:.0f}%)".format(example_coin['Momentum Score']*100),
+        
-                "📉 *Pro Tip:* Watch Bitcoin's trend - if BTC drops 5%, these usually follow.",
+        return {'market_map': fig1, 'liquidity_tree': fig2, 'momentum_leaders': fig3}
-                "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
-            ])
-
-        # 3. LOW-RISK: Stable Momentum (DCA Targets)
-        low_risk = df[
-            (df["Momentum Score"] > 0.05) & 
-            (df["Volatility Score"] < 0.03)
-        ].sort_values("Market Cap", ascending=False)
-        if not low_risk.empty:
-            example_coin = low_risk.iloc[0]
-            report.extend([
-                "\n🛡️ **LOW-RISK: Steady Climbers (DCA & Forget)**",
-                f"*Example Trade:* {example_coin['Name']} (Volatility: {example_coin['Volatility Score']:.2f}/5)",
-                "📊 *Why?* Rises steadily (+{:.0f}%/week) with LOW drama".format(example_coin['7d %']*100),
-                "🎯 *Strategy:*",
-                "1. Buy small amounts every Tuesday/Friday (DCA)",
-                "2. Hold for 3+ months (Compound gains work best here)",
-                "3. Sell 10% at every +25% milestone",
-                "💰 *Best For:* Long-term investors who hate sleepless nights",
-                "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
-            ])
-
-        # Volume Spike Alerts
-        anomalies = df[df["Volume Anomaly"]].sort_values("Volume(24h)", ascending=False)
-        if not anomalies.empty:
-            example_coin = anomalies.iloc[0]
-            report.extend([
-                "\n🚨 **Volume Spike Alert (Possible News/Whale Action)**",
-                f"*Coin:* {example_coin['Name']} (Volume: ${example_coin['Volume(24h)']/1e6:.1f}M, usual: ${example_coin['Volume(24h)']/3/1e6:.1f}M)",
-                "🔍 *Check:* Twitter/CoinGecko for news before trading",
-                "⚡ *If no news:* Could be insider buying - watch price action:",
-                "- Break above today's high → Buy with tight stop-loss",
-                "- Fade back down → Avoid (may be a fakeout)"
-            ])
-
-        # Pro Tip Footer
-        report.append("\n✨ *Pro Tip:* Bookmark this report & check back in 24h to see if signals held up.")
-
-        return "\n".join(report)
 
     def generate_insights(self, df: pd.DataFrame) -> str:
         """
-        Generates a tactical trading report with:
+        Create plain English trading insights explaining:
-        - Top 3 trades per risk level (High/Medium/Low)
+        - Volume spikes and their implications
-        - Auto-calculated entry/exit prices
+        - Risk-reward ratios of top movers
-        - BTC chart toggle tip
+        - Liquidity warnings for large positions
         """
-        # Filter top candidates for each risk level
+        top_coin = df.sort_values('Momentum Score', ascending=False).iloc[0]
-        high_risk = (
+        anomaly_coins = df[df['Volume Anomaly']].sort_values('Volume(24h)', ascending=False)
-            df[df["Undervalued Flag"]]
-            .sort_values("Momentum Score", ascending=False)
-            .head(3)
-        )
-        medium_risk = (
-            df[df["Liquid Giant"]]
-            .sort_values("Volume/Market Cap Ratio", ascending=False)
-            .head(3)
-        )
-        low_risk = (
-            df[(df["Momentum Score"] > 0.05) & (df["Volatility Score"] < 0.03)]
-            .sort_values("Momentum Score", ascending=False)
-            .head(3)
-        )
-
-        report = ["# 🎯 Crypto Trading Tactical Report (Top 3 Per Risk Tier)"]
         
-        # 1. High-Risk Trades (Small-Cap Momentum)
+        report = f"""
-        if not high_risk.empty:
+        🚀 Top Alpha Opportunity: {top_coin['Name']}
-            report.append("\n## 🔥 HIGH RISK: Small-Cap Rockets (5-50% Potential)")
+        - Momentum Score: {top_coin['Momentum Score']:.2%} (Top 1%)
-            for i, coin in high_risk.iterrows():
+        - Risk-Reward Ratio: {top_coin['Momentum Score']/top_coin['Volatility Score']:.1f}
-                current_price = coin["Price"]
+        - Liquidity Warning: {'✅ Safe' if top_coin['Liquid Giant'] else '⚠️ Thin Markets'}
-                entry = current_price * 0.95  # -5% dip
-                stop_loss = current_price * 0.90  # -10%
-                take_profit = current_price * 1.20  # +20%
-                
-                report.append(
-                    f"\n### {coin['Name']} (Momentum: {coin['Momentum Score']:.1%})"
-                    f"\n- **Current Price:** ${current_price:.4f}"
-                    f"\n- **Entry:** < ${entry:.4f} (Wait for pullback)"
-                    f"\n- **Stop-Loss:** ${stop_loss:.4f} (-10%)"
-                    f"\n- **Target:** ${take_profit:.4f} (+20%)"
-                    f"\n- **Risk/Reward:** 1:2"
-                    f"\n- **Watch:** Volume spikes above {coin['Volume(24h)']/1e6:.1f}M"
-                )
-
-        # 2. Medium-Risk Trades (Liquid Giants)
-        if not medium_risk.empty:
-            report.append("\n## 💎 MEDIUM RISK: Liquid Swing Trades (10-30% Potential)")
-            for i, coin in medium_risk.iterrows():
-                current_price = coin["Price"]
-                entry = current_price * 0.98  # -2% dip
-                stop_loss = current_price * 0.94  # -6%
-                take_profit = current_price * 1.15  # +15%
-                
-                report.append(
-                    f"\n### {coin['Name']} (Liquidity Score: {coin['Volume/Market Cap Ratio']:.1%})"
-                    f"\n- **Current Price:** ${current_price:.2f}"
-                    f"\n- **Entry:** < ${entry:.2f} (Buy slight dips)"
-                    f"\n- **Stop-Loss:** ${stop_loss:.2f} (-6%)"
-                    f"\n- **Target:** ${take_profit:.2f} (+15%)"
-                    f"\n- **Hold Time:** 1-3 weeks"
-                    f"\n- **Key Metric:** Volume/Cap > 15%"
-                )
-
-        # 3. Low-Risk Trades (Stable Momentum)
-        if not low_risk.empty:
-            report.append("\n## 🛡️ LOW RISK: Steady Gainers (5-15% Potential)")
-            for i, coin in low_risk.iterrows():
-                current_price = coin["Price"]
-                entry = current_price * 0.99  # -1% dip
-                stop_loss = current_price * 0.97  # -3%
-                take_profit = current_price * 1.10  # +10%
-                
-                report.append(
-                    f"\n### {coin['Name']} (Stability Score: {1/coin['Volatility Score']:.1f}x)"
-                    f"\n- **Current Price:** ${current_price:.2f}"
-                    f"\n- **Entry:** < ${entry:.2f} (Safe zone)"
-                    f"\n- **Stop-Loss:** ${stop_loss:.2f} (-3%)"
-                    f"\n- **Target:** ${take_profit:.2f} (+10%)"
-                    f"\n- **DCA Suggestion:** 3 buys over 72 hours"
-                )
-
-        # Volume Anomaly Alert
-        anomalies = df[df["Volume Anomaly"]].sort_values("Volume(24h)", ascending=False).head(2)
-        if not anomalies.empty:
-            report.append("\n⚠️ **Volume Spike Alerts**")
-            for i, coin in anomalies.iterrows():
-                report.append(
-                    f"- {coin['Name']}: Volume {coin['Volume(24h)']/1e6:.1f}M "
-                    f"(3x normal) | Price moved: {coin['24h %']:.1%}"
-                )
-
-        # Pro Tip
-        report.append(
-            "\n📊 **Chart Hack:** Hide BTC in visuals:\n"
-            "```python\n"
-            "# For 3D Map:\n"
-            "fig.update_traces(visible=False, selector={'name':'Bitcoin'})\n"
-            "# For Treemap:\n"
-            "df = df[df['Name'] != 'Bitcoin']\n"
-            "```"
-        )
-
-        return "\n".join(report)
-
-    def create_visuals(self, df: pd.DataFrame) -> dict:
-        """Enhanced visuals with BTC toggle support"""
-        # 3D Market Map (with BTC toggle hint)
-        fig1 = px.scatter_3d(
-            df,
-            x="Market Cap",
-            y="Volume/Market Cap Ratio",
-            z="Momentum Score",
-            color="Name",  # Color by name to allow toggling
-            hover_name="Name",
-            title="Market Map (Toggle BTC in legend to focus on alts)",
-            log_x=True
-        )
-        fig1.update_traces(
-            marker=dict(size=df["Volatility Score"]*100 + 5)  # Dynamic sizing
-        )
         
-        # Liquidity Tree (exclude BTC if too dominant)
+        🔥 Volume Spikes Detected ({len(anomaly_coins)} coins):
-        if df[df["Name"] == "BitcoinBTC"]["Market Cap"].values[0] > df["Market Cap"].median() * 10:
+        {anomaly_coins[['Name', 'Volume(24h)']].head(3).to_markdown(index=False)}
-            df = df[df["Name"] != "BitcoinBTC"]
         
-        fig2 = px.treemap(
+        💡 Smart Money Tip: Coins with Volume/Cap > 15% and Momentum > 5% 
-            df,
+        historically outperform by 22% weekly returns.
-            path=["Name"],
+        """
-            values="Market Cap",
+        return report
-            color="Volume/Market Cap Ratio",
-            title="Liquidity Tree (BTC auto-removed if dominant)"
-        )
-        
-        return {"market_map": fig1, "liquidity_tree": fig2}
 
 async def main():
     """
@@ -365,79 +171,60 @@ async def main():
     """
     # Configure browser with anti-detection features
     browser_config = BrowserConfig(
-        headless=False,
+        headless=True,
+        stealth=True,
+        block_resources=["image", "media"]
     )
-
+    
     # Initialize crawler with smart table detection
     crawler = AsyncWebCrawler(config=browser_config)
     await crawler.start()
-
+    
     try:
         # Set up scraping parameters
         crawl_config = CrawlerRunConfig(
             cache_mode=CacheMode.BYPASS,
-            table_score_threshold=8,  # Strict table detection
+            scraping_strategy=LXMLWebScrapingStrategy(
-            keep_data_attributes=True,
+                table_score_threshold=8,  # Strict table detection
-            scraping_strategy=LXMLWebScrapingStrategy(),
+                keep_data_attributes=True
-            scan_full_page=True,
+            )
-            scroll_delay=0.2,
         )
-
+        
-        # # Execute market data extraction
+        # Execute market data extraction
-        # results: List[CrawlResult] = await crawler.arun(
+        results: List[CrawlResult] = await crawler.arun(
-        #     url="https://coinmarketcap.com/?page=1", config=crawl_config
+            url='https://coinmarketcap.com/?page=1',
-        # )
+            config=crawl_config
-
+        )
-        # # Process results
+        
-        # raw_df = pd.DataFrame()
+        # Process results
-        # for result in results:
+        for result in results:
-        #     if result.success and result.media["tables"]:
+            if result.success and result.media['tables']:
-        #         # Extract primary market table
+                # Extract primary market table
-        #         # DataFrame
+                raw_df = pd.DataFrame(
-        #         raw_df = pd.DataFrame(
+                    result.media['tables'][0]['rows'],
-        #             result.media["tables"][0]["rows"],
+                    columns=result.media['tables'][0]['headers']
-        #             columns=result.media["tables"][0]["headers"],
+                )
-        #         )
+                
-        #         break
+                # Initialize analysis engine
-
+                analyzer = CryptoAlphaGenerator()
-
+                clean_df = analyzer.clean_data(raw_df)
-        # This is for debugging only
+                analyzed_df = analyzer.calculate_metrics(clean_df)
-        # ////// Remove this in production from here..
+                
-        # Save raw data for debugging
+                # Generate outputs
-        # raw_df.to_csv(f"{__current_dir__}/tmp/raw_crypto_data.csv", index=False)
+                visuals = analyzer.create_visuals(analyzed_df)
-        # print("🔍 Raw data saved to 'raw_crypto_data.csv'")
+                insights = analyzer.generate_insights(analyzed_df)
-
+                
-        # Read from file for debugging
+                # Save visualizations
-        raw_df = pd.read_csv(f"{__current_dir__}/tmp/raw_crypto_data.csv")
+                visuals['market_map'].write_html("market_map.html")
-        # ////// ..to here
+                visuals['liquidity_tree'].write_html("liquidity_tree.html")
-
+                
-        # Select top 20
+                # Display results
-        raw_df = raw_df.head(50)
+                print("🔑 Key Trading Insights:")
-        # Remove "Buy" from name
+                print(insights)
-        raw_df["Name"] = raw_df["Name"].str.replace("Buy", "")
+                print("\n📊 Open 'market_map.html' for interactive analysis")
-
-        # Initialize analysis engine
-        analyzer = CryptoAlphaGenerator()
-        clean_df = analyzer.clean_data(raw_df)
-        analyzed_df = analyzer.calculate_metrics(clean_df)
-
-        # Generate outputs
-        visuals = analyzer.create_visuals(analyzed_df)
-        insights = analyzer.generate_insights(analyzed_df)
-
-        # Save visualizations
-        visuals["market_map"].write_html(f"{__current_dir__}/tmp/market_map.html")
-        visuals["liquidity_tree"].write_html(f"{__current_dir__}/tmp/liquidity_tree.html")
-
-        # Display results
-        print("🔑 Key Trading Insights:")
-        print(insights)
-        print("\n📊 Open 'market_map.html' for interactive analysis")
-        print("\n📊 Open 'liquidity_tree.html' for interactive analysis")
 
     finally:
         await crawler.close()
 
-
 if __name__ == "__main__":
-    asyncio.run(main())
+    asyncio.run(main())

docs/examples/docker_python_rest_api.py

@@ -73,7 +73,7 @@ async def test_stream_crawl(session, token: str):
             # "https://news.ycombinator.com/news"
         ],
         "browser_config": {"headless": True, "viewport": {"width": 1200}},
-        "crawler_config": {"stream": True, "cache_mode": "bypass"}
+        "crawler_config": {"stream": True, "cache_mode": "aggressive"}
     }
     headers = {"Authorization": f"Bearer {token}"}
     print(f"\nTesting Streaming Crawl: {url}")

docs/examples/hello_world.py

@@ -9,26 +9,6 @@ from crawl4ai import (
     CrawlResult
 )
 
-async def example_cdp():
-    browser_conf = BrowserConfig(
-        headless=False,
-        cdp_url="http://localhost:9223"
-    )
-    crawler_config = CrawlerRunConfig(
-        session_id="test",
-        js_code = """(() => { return {"result": "Hello World!"} })()""",
-        js_only=True
-    )
-    async with AsyncWebCrawler(
-        config=browser_conf,
-        verbose=True,
-    ) as crawler:
-        result : CrawlResult = await crawler.arun(
-            url="https://www.helloworld.org",
-            config=crawler_config,
-        )
-        print(result.js_execution_result)
-                   
 
 async def main():
     browser_config = BrowserConfig(headless=True, verbose=True)
@@ -36,15 +16,18 @@ async def main():
         crawler_config = CrawlerRunConfig(
             cache_mode=CacheMode.BYPASS,
             markdown_generator=DefaultMarkdownGenerator(
-                content_filter=PruningContentFilter(
+                # content_filter=PruningContentFilter(
-                     threshold=0.48, threshold_type="fixed", min_word_threshold=0
+                #     threshold=0.48, threshold_type="fixed", min_word_threshold=0
-                )
+                # )
             ),
         )
         result : CrawlResult = await crawler.arun(
-            url="https://www.helloworld.org", config=crawler_config
+            # url="https://www.helloworld.org", config=crawler_config
+            url="https://www.kidocode.com", config=crawler_config
         )
         print(result.markdown.raw_markdown[:500])
+        # print(result.model_dump())
+
 
 if __name__ == "__main__":
     asyncio.run(main())

docs/examples/network_console_capture_example.py

@@ -1,477 +0,0 @@
-import asyncio
-import json
-import os
-import base64
-from pathlib import Path
-from typing import List, Dict, Any
-from datetime import datetime
-
-from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, CacheMode, CrawlResult
-from crawl4ai import BrowserConfig
-
-__cur_dir__ = Path(__file__).parent
-
-# Create temp directory if it doesn't exist
-os.makedirs(os.path.join(__cur_dir__, "tmp"), exist_ok=True)
-
-async def demo_basic_network_capture():
-    """Basic network request capturing example"""
-    print("\n=== 1. Basic Network Request Capturing ===")
-    
-    async with AsyncWebCrawler() as crawler:
-        config = CrawlerRunConfig(
-            capture_network_requests=True,
-            wait_until="networkidle"  # Wait for network to be idle
-        )
-        
-        result = await crawler.arun(
-            url="https://example.com/",
-            config=config
-        )
-        
-        if result.success and result.network_requests:
-            print(f"Captured {len(result.network_requests)} network events")
-            
-            # Count by event type
-            event_types = {}
-            for req in result.network_requests:
-                event_type = req.get("event_type", "unknown")
-                event_types[event_type] = event_types.get(event_type, 0) + 1
-            
-            print("Event types:")
-            for event_type, count in event_types.items():
-                print(f"  - {event_type}: {count}")
-            
-            # Show a sample request and response
-            request = next((r for r in result.network_requests if r.get("event_type") == "request"), None)
-            response = next((r for r in result.network_requests if r.get("event_type") == "response"), None)
-            
-            if request:
-                print("\nSample request:")
-                print(f"  URL: {request.get('url')}")
-                print(f"  Method: {request.get('method')}")
-                print(f"  Headers: {list(request.get('headers', {}).keys())}")
-            
-            if response:
-                print("\nSample response:")
-                print(f"  URL: {response.get('url')}")
-                print(f"  Status: {response.get('status')} {response.get('status_text', '')}")
-                print(f"  Headers: {list(response.get('headers', {}).keys())}")
-
-async def demo_basic_console_capture():
-    """Basic console message capturing example"""
-    print("\n=== 2. Basic Console Message Capturing ===")
-    
-    # Create a simple HTML file with console messages
-    html_file = os.path.join(__cur_dir__, "tmp", "console_test.html")
-    with open(html_file, "w") as f:
-        f.write("""
-        <!DOCTYPE html>
-        <html>
-        <head>
-            <title>Console Test</title>
-        </head>
-        <body>
-            <h1>Console Message Test</h1>
-            <script>
-                console.log("This is a basic log message");
-                console.info("This is an info message");
-                console.warn("This is a warning message");
-                console.error("This is an error message");
-                
-                // Generate an error
-                try {
-                    nonExistentFunction();
-                } catch (e) {
-                    console.error("Caught error:", e);
-                }
-            </script>
-        </body>
-        </html>
-        """)
-    
-    async with AsyncWebCrawler() as crawler:
-        config = CrawlerRunConfig(
-            capture_console_messages=True,
-            wait_until="networkidle"  # Wait to make sure all scripts execute
-        )
-        
-        result = await crawler.arun(
-            url=f"file://{html_file}",
-            config=config
-        )
-        
-        if result.success and result.console_messages:
-            print(f"Captured {len(result.console_messages)} console messages")
-            
-            # Count by message type
-            message_types = {}
-            for msg in result.console_messages:
-                msg_type = msg.get("type", "unknown")
-                message_types[msg_type] = message_types.get(msg_type, 0) + 1
-            
-            print("Message types:")
-            for msg_type, count in message_types.items():
-                print(f"  - {msg_type}: {count}")
-            
-            # Show all messages
-            print("\nAll console messages:")
-            for i, msg in enumerate(result.console_messages, 1):
-                print(f"  {i}. [{msg.get('type', 'unknown')}] {msg.get('text', '')}")
-
-async def demo_combined_capture():
-    """Capturing both network requests and console messages"""
-    print("\n=== 3. Combined Network and Console Capture ===")
-    
-    async with AsyncWebCrawler() as crawler:
-        config = CrawlerRunConfig(
-            capture_network_requests=True,
-            capture_console_messages=True,
-            wait_until="networkidle"
-        )
-        
-        result = await crawler.arun(
-            url="https://httpbin.org/html",
-            config=config
-        )
-        
-        if result.success:
-            network_count = len(result.network_requests) if result.network_requests else 0
-            console_count = len(result.console_messages) if result.console_messages else 0
-            
-            print(f"Captured {network_count} network events and {console_count} console messages")
-            
-            # Save the captured data to a JSON file for analysis
-            output_file = os.path.join(__cur_dir__, "tmp", "capture_data.json")
-            with open(output_file, "w") as f:
-                json.dump({
-                    "url": result.url,
-                    "timestamp": datetime.now().isoformat(),
-                    "network_requests": result.network_requests,
-                    "console_messages": result.console_messages
-                }, f, indent=2)
-            
-            print(f"Full capture data saved to {output_file}")
-
-async def analyze_spa_network_traffic():
-    """Analyze network traffic of a Single-Page Application"""
-    print("\n=== 4. Analyzing SPA Network Traffic ===")
-    
-    async with AsyncWebCrawler(config=BrowserConfig(
-        headless=True,
-        viewport_width=1280,
-        viewport_height=800
-    )) as crawler:
-        config = CrawlerRunConfig(
-            capture_network_requests=True,
-            capture_console_messages=True,
-            # Wait longer to ensure all resources are loaded
-            wait_until="networkidle",
-            page_timeout=60000,  # 60 seconds
-        )
-        
-        result = await crawler.arun(
-            url="https://weather.com",
-            config=config
-        )
-        
-        if result.success and result.network_requests:
-            # Extract different types of requests
-            requests = []
-            responses = []
-            failures = []
-            
-            for event in result.network_requests:
-                event_type = event.get("event_type")
-                if event_type == "request":
-                    requests.append(event)
-                elif event_type == "response":
-                    responses.append(event)
-                elif event_type == "request_failed":
-                    failures.append(event)
-            
-            print(f"Captured {len(requests)} requests, {len(responses)} responses, and {len(failures)} failures")
-            
-            # Analyze request types
-            resource_types = {}
-            for req in requests:
-                resource_type = req.get("resource_type", "unknown")
-                resource_types[resource_type] = resource_types.get(resource_type, 0) + 1
-            
-            print("\nResource types:")
-            for resource_type, count in sorted(resource_types.items(), key=lambda x: x[1], reverse=True):
-                print(f"  - {resource_type}: {count}")
-            
-            # Analyze API calls
-            api_calls = [r for r in requests if "api" in r.get("url", "").lower()]
-            if api_calls:
-                print(f"\nDetected {len(api_calls)} API calls:")
-                for i, call in enumerate(api_calls[:5], 1):  # Show first 5
-                    print(f"  {i}. {call.get('method')} {call.get('url')}")
-                if len(api_calls) > 5:
-                    print(f"     ... and {len(api_calls) - 5} more")
-            
-            # Analyze response status codes
-            status_codes = {}
-            for resp in responses:
-                status = resp.get("status", 0)
-                status_codes[status] = status_codes.get(status, 0) + 1
-            
-            print("\nResponse status codes:")
-            for status, count in sorted(status_codes.items()):
-                print(f"  - {status}: {count}")
-            
-            # Analyze failures
-            if failures:
-                print("\nFailed requests:")
-                for i, failure in enumerate(failures[:5], 1):  # Show first 5
-                    print(f"  {i}. {failure.get('url')} - {failure.get('failure_text')}")
-                if len(failures) > 5:
-                    print(f"     ... and {len(failures) - 5} more")
-            
-            # Check for console errors
-            if result.console_messages:
-                errors = [msg for msg in result.console_messages if msg.get("type") == "error"]
-                if errors:
-                    print(f"\nDetected {len(errors)} console errors:")
-                    for i, error in enumerate(errors[:3], 1):  # Show first 3
-                        print(f"  {i}. {error.get('text', '')[:100]}...")
-                    if len(errors) > 3:
-                        print(f"     ... and {len(errors) - 3} more")
-            
-            # Save analysis to file
-            output_file = os.path.join(__cur_dir__, "tmp", "weather_network_analysis.json")
-            with open(output_file, "w") as f:
-                json.dump({
-                    "url": result.url,
-                    "timestamp": datetime.now().isoformat(),
-                    "statistics": {
-                        "request_count": len(requests),
-                        "response_count": len(responses),
-                        "failure_count": len(failures),
-                        "resource_types": resource_types,
-                        "status_codes": {str(k): v for k, v in status_codes.items()},
-                        "api_call_count": len(api_calls),
-                        "console_error_count": len(errors) if result.console_messages else 0
-                    },
-                    "network_requests": result.network_requests,
-                    "console_messages": result.console_messages
-                }, f, indent=2)
-            
-            print(f"\nFull analysis saved to {output_file}")
-
-async def demo_security_analysis():
-    """Using network capture for security analysis"""
-    print("\n=== 5. Security Analysis with Network Capture ===")
-    
-    async with AsyncWebCrawler() as crawler:
-        config = CrawlerRunConfig(
-            capture_network_requests=True,
-            capture_console_messages=True,
-            wait_until="networkidle"
-        )
-        
-        # A site that makes multiple third-party requests
-        result = await crawler.arun(
-            url="https://www.nytimes.com/",
-            config=config
-        )
-        
-        if result.success and result.network_requests:
-            print(f"Captured {len(result.network_requests)} network events")
-            
-            # Extract all domains
-            domains = set()
-            for req in result.network_requests:
-                if req.get("event_type") == "request":
-                    url = req.get("url", "")
-                    try:
-                        from urllib.parse import urlparse
-                        domain = urlparse(url).netloc
-                        if domain:
-                            domains.add(domain)
-                    except:
-                        pass
-            
-            print(f"\nDetected requests to {len(domains)} unique domains:")
-            main_domain = urlparse(result.url).netloc
-            
-            # Separate first-party vs third-party domains
-            first_party = [d for d in domains if main_domain in d]
-            third_party = [d for d in domains if main_domain not in d]
-            
-            print(f"  - First-party domains: {len(first_party)}")
-            print(f"  - Third-party domains: {len(third_party)}")
-            
-            # Look for potential trackers/analytics
-            tracking_keywords = ["analytics", "tracker", "pixel", "tag", "stats", "metric", "collect", "beacon"]
-            potential_trackers = []
-            
-            for domain in third_party:
-                if any(keyword in domain.lower() for keyword in tracking_keywords):
-                    potential_trackers.append(domain)
-            
-            if potential_trackers:
-                print(f"\nPotential tracking/analytics domains ({len(potential_trackers)}):")
-                for i, domain in enumerate(sorted(potential_trackers)[:10], 1):
-                    print(f"  {i}. {domain}")
-                if len(potential_trackers) > 10:
-                    print(f"     ... and {len(potential_trackers) - 10} more")
-            
-            # Check for insecure (HTTP) requests
-            insecure_requests = [
-                req.get("url") for req in result.network_requests 
-                if req.get("event_type") == "request" and req.get("url", "").startswith("http://")
-            ]
-            
-            if insecure_requests:
-                print(f"\nWarning: Found {len(insecure_requests)} insecure (HTTP) requests:")
-                for i, url in enumerate(insecure_requests[:5], 1):
-                    print(f"  {i}. {url}")
-                if len(insecure_requests) > 5:
-                    print(f"     ... and {len(insecure_requests) - 5} more")
-            
-            # Save security analysis to file
-            output_file = os.path.join(__cur_dir__, "tmp", "security_analysis.json")
-            with open(output_file, "w") as f:
-                json.dump({
-                    "url": result.url,
-                    "main_domain": main_domain,
-                    "timestamp": datetime.now().isoformat(),
-                    "analysis": {
-                        "total_requests": len([r for r in result.network_requests if r.get("event_type") == "request"]),
-                        "unique_domains": len(domains),
-                        "first_party_domains": first_party,
-                        "third_party_domains": third_party,
-                        "potential_trackers": potential_trackers,
-                        "insecure_requests": insecure_requests
-                    }
-                }, f, indent=2)
-            
-            print(f"\nFull security analysis saved to {output_file}")
-
-async def demo_performance_analysis():
-    """Using network capture for performance analysis"""
-    print("\n=== 6. Performance Analysis with Network Capture ===")
-    
-    async with AsyncWebCrawler() as crawler:
-        config = CrawlerRunConfig(
-            capture_network_requests=True,
-            page_timeout=60 * 2 * 1000  # 120 seconds
-        )
-        
-        result = await crawler.arun(
-            url="https://www.cnn.com/",
-            config=config
-        )
-        
-        if result.success and result.network_requests:
-            # Filter only response events with timing information
-            responses_with_timing = [
-                r for r in result.network_requests 
-                if r.get("event_type") == "response" and r.get("request_timing")
-            ]
-            
-            if responses_with_timing:
-                print(f"Analyzing timing for {len(responses_with_timing)} network responses")
-                
-                # Group by resource type
-                resource_timings = {}
-                for resp in responses_with_timing:
-                    url = resp.get("url", "")
-                    timing = resp.get("request_timing", {})
-                    
-                    # Determine resource type from URL extension
-                    ext = url.split(".")[-1].lower() if "." in url.split("/")[-1] else "unknown"
-                    if ext in ["jpg", "jpeg", "png", "gif", "webp", "svg", "ico"]:
-                        resource_type = "image"
-                    elif ext in ["js"]:
-                        resource_type = "javascript"
-                    elif ext in ["css"]:
-                        resource_type = "css"
-                    elif ext in ["woff", "woff2", "ttf", "otf", "eot"]:
-                        resource_type = "font"
-                    else:
-                        resource_type = "other"
-                    
-                    if resource_type not in resource_timings:
-                        resource_timings[resource_type] = []
-                    
-                    # Calculate request duration if timing information is available
-                    if isinstance(timing, dict) and "requestTime" in timing and "receiveHeadersEnd" in timing:
-                        # Convert to milliseconds
-                        duration = (timing["receiveHeadersEnd"] - timing["requestTime"]) * 1000
-                        resource_timings[resource_type].append({
-                            "url": url,
-                            "duration_ms": duration
-                        })
-                    if isinstance(timing, dict) and "requestStart" in timing and "responseStart" in timing and "startTime" in timing:
-                        # Convert to milliseconds
-                        duration = (timing["responseStart"] - timing["requestStart"]) * 1000
-                        resource_timings[resource_type].append({
-                            "url": url,
-                            "duration_ms": duration
-                        })
-                
-                # Calculate statistics for each resource type
-                print("\nPerformance by resource type:")
-                for resource_type, timings in resource_timings.items():
-                    if timings:
-                        durations = [t["duration_ms"] for t in timings]
-                        avg_duration = sum(durations) / len(durations)
-                        max_duration = max(durations)
-                        slowest_resource = next(t["url"] for t in timings if t["duration_ms"] == max_duration)
-                        
-                        print(f"  {resource_type.upper()}:")
-                        print(f"    - Count: {len(timings)}")
-                        print(f"    - Avg time: {avg_duration:.2f} ms")
-                        print(f"    - Max time: {max_duration:.2f} ms")
-                        print(f"    - Slowest: {slowest_resource}")
-                
-                # Identify the slowest resources overall
-                all_timings = []
-                for resource_type, timings in resource_timings.items():
-                    for timing in timings:
-                        timing["type"] = resource_type
-                        all_timings.append(timing)
-                
-                all_timings.sort(key=lambda x: x["duration_ms"], reverse=True)
-                
-                print("\nTop 5 slowest resources:")
-                for i, timing in enumerate(all_timings[:5], 1):
-                    print(f"  {i}. [{timing['type']}] {timing['url']} - {timing['duration_ms']:.2f} ms")
-                
-                # Save performance analysis to file
-                output_file = os.path.join(__cur_dir__, "tmp", "performance_analysis.json")
-                with open(output_file, "w") as f:
-                    json.dump({
-                        "url": result.url,
-                        "timestamp": datetime.now().isoformat(),
-                        "resource_timings": resource_timings,
-                        "slowest_resources": all_timings[:10]  # Save top 10
-                    }, f, indent=2)
-                
-                print(f"\nFull performance analysis saved to {output_file}")
-
-async def main():
-    """Run all demo functions sequentially"""
-    print("=== Network and Console Capture Examples ===")
-    
-    # Make sure tmp directory exists
-    os.makedirs(os.path.join(__cur_dir__, "tmp"), exist_ok=True)
-    
-    # Run basic examples
-    # await demo_basic_network_capture()
-    await demo_basic_console_capture()
-    # await demo_combined_capture()
-    
-    # Run advanced examples
-    # await analyze_spa_network_traffic()
-    # await demo_security_analysis()
-    # await demo_performance_analysis()
-    
-    print("\n=== Examples Complete ===")
-    print(f"Check the tmp directory for output files: {os.path.join(__cur_dir__, 'tmp')}")
-
-if __name__ == "__main__":
-    asyncio.run(main())

docs/examples/quickstart_async.py

@@ -0,0 +1,675 @@
+import os, sys
+
+from crawl4ai import LLMConfig
+
+# append parent directory to system path
+sys.path.append(
+    os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+)
+os.environ["FIRECRAWL_API_KEY"] = "fc-84b370ccfad44beabc686b38f1769692"
+
+import asyncio
+# import nest_asyncio
+# nest_asyncio.apply()
+
+import time
+import json
+import os
+import re
+from typing import Dict, List
+from bs4 import BeautifulSoup
+from pydantic import BaseModel, Field
+from crawl4ai import AsyncWebCrawler, CacheMode
+from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
+from crawl4ai.content_filter_strategy import PruningContentFilter
+from crawl4ai.extraction_strategy import (
+    JsonCssExtractionStrategy,
+    LLMExtractionStrategy,
+)
+
+__location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
+
+print("Crawl4AI: Advanced Web Crawling and Data Extraction")
+print("GitHub Repository: https://github.com/unclecode/crawl4ai")
+print("Twitter: @unclecode")
+print("Website: https://crawl4ai.com")
+
+
+async def simple_crawl():
+    print("\n--- Basic Usage ---")
+    async with AsyncWebCrawler(verbose=True) as crawler:
+        result = await crawler.arun(
+            url="https://www.nbcnews.com/business", cache_mode=CacheMode.BYPASS
+        )
+        print(result.markdown[:500])  # Print first 500 characters
+
+
+async def simple_example_with_running_js_code():
+    print("\n--- Executing JavaScript and Using CSS Selectors ---")
+    # New code to handle the wait_for parameter
+    wait_for = """() => {
+        return Array.from(document.querySelectorAll('article.tease-card')).length > 10;
+    }"""
+
+    # wait_for can be also just a css selector
+    # wait_for = "article.tease-card:nth-child(10)"
+
+    async with AsyncWebCrawler(verbose=True) as crawler:
+        js_code = [
+            "const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();"
+        ]
+        result = await crawler.arun(
+            url="https://www.nbcnews.com/business",
+            js_code=js_code,
+            # wait_for=wait_for,
+            cache_mode=CacheMode.BYPASS,
+        )
+        print(result.markdown[:500])  # Print first 500 characters
+
+
+async def simple_example_with_css_selector():
+    print("\n--- Using CSS Selectors ---")
+    async with AsyncWebCrawler(verbose=True) as crawler:
+        result = await crawler.arun(
+            url="https://www.nbcnews.com/business",
+            css_selector=".wide-tease-item__description",
+            cache_mode=CacheMode.BYPASS,
+        )
+        print(result.markdown[:500])  # Print first 500 characters
+
+
+async def use_proxy():
+    print("\n--- Using a Proxy ---")
+    print(
+        "Note: Replace 'http://your-proxy-url:port' with a working proxy to run this example."
+    )
+    # Uncomment and modify the following lines to use a proxy
+    async with AsyncWebCrawler(
+        verbose=True, proxy="http://your-proxy-url:port"
+    ) as crawler:
+        result = await crawler.arun(
+            url="https://www.nbcnews.com/business", cache_mode=CacheMode.BYPASS
+        )
+        if result.success:
+            print(result.markdown[:500])  # Print first 500 characters
+
+
+async def capture_and_save_screenshot(url: str, output_path: str):
+    async with AsyncWebCrawler(verbose=True) as crawler:
+        result = await crawler.arun(
+            url=url, screenshot=True, cache_mode=CacheMode.BYPASS
+        )
+
+        if result.success and result.screenshot:
+            import base64
+
+            # Decode the base64 screenshot data
+            screenshot_data = base64.b64decode(result.screenshot)
+
+            # Save the screenshot as a JPEG file
+            with open(output_path, "wb") as f:
+                f.write(screenshot_data)
+
+            print(f"Screenshot saved successfully to {output_path}")
+        else:
+            print("Failed to capture screenshot")
+
+
+class OpenAIModelFee(BaseModel):
+    model_name: str = Field(..., description="Name of the OpenAI model.")
+    input_fee: str = Field(..., description="Fee for input token for the OpenAI model.")
+    output_fee: str = Field(
+        ..., description="Fee for output token for the OpenAI model."
+    )
+
+
+async def extract_structured_data_using_llm(
+    provider: str, api_token: str = None, extra_headers: Dict[str, str] = None
+):
+    print(f"\n--- Extracting Structured Data with {provider} ---")
+
+    if api_token is None and provider != "ollama":
+        print(f"API token is required for {provider}. Skipping this example.")
+        return
+
+    # extra_args = {}
+    extra_args = {
+        "temperature": 0,
+        "top_p": 0.9,
+        "max_tokens": 2000,
+        # any other supported parameters for litellm
+    }
+    if extra_headers:
+        extra_args["extra_headers"] = extra_headers
+
+    async with AsyncWebCrawler(verbose=True) as crawler:
+        result = await crawler.arun(
+            url="https://openai.com/api/pricing/",
+            word_count_threshold=1,
+            extraction_strategy=LLMExtractionStrategy(
+                llm_config=LLMConfig(provider=provider,api_token=api_token),
+                schema=OpenAIModelFee.model_json_schema(),
+                extraction_type="schema",
+                instruction="""From the crawled content, extract all mentioned model names along with their fees for input and output tokens. 
+                Do not miss any models in the entire content. One extracted model JSON format should look like this: 
+                {"model_name": "GPT-4", "input_fee": "US$10.00 / 1M tokens", "output_fee": "US$30.00 / 1M tokens"}.""",
+                extra_args=extra_args,
+            ),
+            cache_mode=CacheMode.BYPASS,
+        )
+        print(result.extracted_content)
+
+
+async def extract_structured_data_using_css_extractor():
+    print("\n--- Using JsonCssExtractionStrategy for Fast Structured Output ---")
+    schema = {
+        "name": "KidoCode Courses",
+        "baseSelector": "section.charge-methodology .w-tab-content > div",
+        "fields": [
+            {
+                "name": "section_title",
+                "selector": "h3.heading-50",
+                "type": "text",
+            },
+            {
+                "name": "section_description",
+                "selector": ".charge-content",
+                "type": "text",
+            },
+            {
+                "name": "course_name",
+                "selector": ".text-block-93",
+                "type": "text",
+            },
+            {
+                "name": "course_description",
+                "selector": ".course-content-text",
+                "type": "text",
+            },
+            {
+                "name": "course_icon",
+                "selector": ".image-92",
+                "type": "attribute",
+                "attribute": "src",
+            },
+        ],
+    }
+
+    async with AsyncWebCrawler(headless=True, verbose=True) as crawler:
+        # Create the JavaScript that handles clicking multiple times
+        js_click_tabs = """
+        (async () => {
+            const tabs = document.querySelectorAll("section.charge-methodology .tabs-menu-3 > div");
+            
+            for(let tab of tabs) {
+                // scroll to the tab
+                tab.scrollIntoView();
+                tab.click();
+                // Wait for content to load and animations to complete
+                await new Promise(r => setTimeout(r, 500));
+            }
+        })();
+        """
+
+        result = await crawler.arun(
+            url="https://www.kidocode.com/degrees/technology",
+            extraction_strategy=JsonCssExtractionStrategy(schema, verbose=True),
+            js_code=[js_click_tabs],
+            cache_mode=CacheMode.BYPASS,
+        )
+
+        companies = json.loads(result.extracted_content)
+        print(f"Successfully extracted {len(companies)} companies")
+        print(json.dumps(companies[0], indent=2))
+
+
+# Advanced Session-Based Crawling with Dynamic Content 🔄
+async def crawl_dynamic_content_pages_method_1():
+    print("\n--- Advanced Multi-Page Crawling with JavaScript Execution ---")
+    first_commit = ""
+
+    async def on_execution_started(page):
+        nonlocal first_commit
+        try:
+            while True:
+                await page.wait_for_selector("li.Box-sc-g0xbh4-0 h4")
+                commit = await page.query_selector("li.Box-sc-g0xbh4-0 h4")
+                commit = await commit.evaluate("(element) => element.textContent")
+                commit = re.sub(r"\s+", "", commit)
+                if commit and commit != first_commit:
+                    first_commit = commit
+                    break
+                await asyncio.sleep(0.5)
+        except Exception as e:
+            print(f"Warning: New content didn't appear after JavaScript execution: {e}")
+
+    async with AsyncWebCrawler(verbose=True) as crawler:
+        crawler.crawler_strategy.set_hook("on_execution_started", on_execution_started)
+
+        url = "https://github.com/microsoft/TypeScript/commits/main"
+        session_id = "typescript_commits_session"
+        all_commits = []
+
+        js_next_page = """
+        (() => {
+            const button = document.querySelector('a[data-testid="pagination-next-button"]');
+            if (button) button.click();
+        })();
+        """
+
+        for page in range(3):  # Crawl 3 pages
+            result = await crawler.arun(
+                url=url,
+                session_id=session_id,
+                css_selector="li.Box-sc-g0xbh4-0",
+                js=js_next_page if page > 0 else None,
+                cache_mode=CacheMode.BYPASS,
+                js_only=page > 0,
+                headless=False,
+            )
+
+            assert result.success, f"Failed to crawl page {page + 1}"
+
+            soup = BeautifulSoup(result.cleaned_html, "html.parser")
+            commits = soup.select("li")
+            all_commits.extend(commits)
+
+            print(f"Page {page + 1}: Found {len(commits)} commits")
+
+        await crawler.crawler_strategy.kill_session(session_id)
+        print(f"Successfully crawled {len(all_commits)} commits across 3 pages")
+
+
+async def crawl_dynamic_content_pages_method_2():
+    print("\n--- Advanced Multi-Page Crawling with JavaScript Execution ---")
+
+    async with AsyncWebCrawler(verbose=True) as crawler:
+        url = "https://github.com/microsoft/TypeScript/commits/main"
+        session_id = "typescript_commits_session"
+        all_commits = []
+        last_commit = ""
+
+        js_next_page_and_wait = """
+        (async () => {
+            const getCurrentCommit = () => {
+                const commits = document.querySelectorAll('li.Box-sc-g0xbh4-0 h4');
+                return commits.length > 0 ? commits[0].textContent.trim() : null;
+            };
+
+            const initialCommit = getCurrentCommit();
+            const button = document.querySelector('a[data-testid="pagination-next-button"]');
+            if (button) button.click();
+
+            // Poll for changes
+            while (true) {
+                await new Promise(resolve => setTimeout(resolve, 100)); // Wait 100ms
+                const newCommit = getCurrentCommit();
+                if (newCommit && newCommit !== initialCommit) {
+                    break;
+                }
+            }
+        })();
+        """
+
+        schema = {
+            "name": "Commit Extractor",
+            "baseSelector": "li.Box-sc-g0xbh4-0",
+            "fields": [
+                {
+                    "name": "title",
+                    "selector": "h4.markdown-title",
+                    "type": "text",
+                    "transform": "strip",
+                },
+            ],
+        }
+        extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)
+
+        for page in range(3):  # Crawl 3 pages
+            result = await crawler.arun(
+                url=url,
+                session_id=session_id,
+                css_selector="li.Box-sc-g0xbh4-0",
+                extraction_strategy=extraction_strategy,
+                js_code=js_next_page_and_wait if page > 0 else None,
+                js_only=page > 0,
+                cache_mode=CacheMode.BYPASS,
+                headless=False,
+            )
+
+            assert result.success, f"Failed to crawl page {page + 1}"
+
+            commits = json.loads(result.extracted_content)
+            all_commits.extend(commits)
+
+            print(f"Page {page + 1}: Found {len(commits)} commits")
+
+        await crawler.crawler_strategy.kill_session(session_id)
+        print(f"Successfully crawled {len(all_commits)} commits across 3 pages")
+
+
+async def crawl_dynamic_content_pages_method_3():
+    print(
+        "\n--- Advanced Multi-Page Crawling with JavaScript Execution using `wait_for` ---"
+    )
+
+    async with AsyncWebCrawler(verbose=True) as crawler:
+        url = "https://github.com/microsoft/TypeScript/commits/main"
+        session_id = "typescript_commits_session"
+        all_commits = []
+
+        js_next_page = """
+        const commits = document.querySelectorAll('li.Box-sc-g0xbh4-0 h4');
+        if (commits.length > 0) {
+            window.firstCommit = commits[0].textContent.trim();
+        }
+        const button = document.querySelector('a[data-testid="pagination-next-button"]');
+        if (button) button.click();
+        """
+
+        wait_for = """() => {
+            const commits = document.querySelectorAll('li.Box-sc-g0xbh4-0 h4');
+            if (commits.length === 0) return false;
+            const firstCommit = commits[0].textContent.trim();
+            return firstCommit !== window.firstCommit;
+        }"""
+
+        schema = {
+            "name": "Commit Extractor",
+            "baseSelector": "li.Box-sc-g0xbh4-0",
+            "fields": [
+                {
+                    "name": "title",
+                    "selector": "h4.markdown-title",
+                    "type": "text",
+                    "transform": "strip",
+                },
+            ],
+        }
+        extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)
+
+        for page in range(3):  # Crawl 3 pages
+            result = await crawler.arun(
+                url=url,
+                session_id=session_id,
+                css_selector="li.Box-sc-g0xbh4-0",
+                extraction_strategy=extraction_strategy,
+                js_code=js_next_page if page > 0 else None,
+                wait_for=wait_for if page > 0 else None,
+                js_only=page > 0,
+                cache_mode=CacheMode.BYPASS,
+                headless=False,
+            )
+
+            assert result.success, f"Failed to crawl page {page + 1}"
+
+            commits = json.loads(result.extracted_content)
+            all_commits.extend(commits)
+
+            print(f"Page {page + 1}: Found {len(commits)} commits")
+
+        await crawler.crawler_strategy.kill_session(session_id)
+        print(f"Successfully crawled {len(all_commits)} commits across 3 pages")
+
+
+async def crawl_custom_browser_type():
+    # Use Firefox
+    start = time.time()
+    async with AsyncWebCrawler(
+        browser_type="firefox", verbose=True, headless=True
+    ) as crawler:
+        result = await crawler.arun(
+            url="https://www.example.com", cache_mode=CacheMode.BYPASS
+        )
+        print(result.markdown[:500])
+        print("Time taken: ", time.time() - start)
+
+    # Use WebKit
+    start = time.time()
+    async with AsyncWebCrawler(
+        browser_type="webkit", verbose=True, headless=True
+    ) as crawler:
+        result = await crawler.arun(
+            url="https://www.example.com", cache_mode=CacheMode.BYPASS
+        )
+        print(result.markdown[:500])
+        print("Time taken: ", time.time() - start)
+
+    # Use Chromium (default)
+    start = time.time()
+    async with AsyncWebCrawler(verbose=True, headless=True) as crawler:
+        result = await crawler.arun(
+            url="https://www.example.com", cache_mode=CacheMode.BYPASS
+        )
+        print(result.markdown[:500])
+        print("Time taken: ", time.time() - start)
+
+
+async def crawl_with_user_simultion():
+    async with AsyncWebCrawler(verbose=True, headless=True) as crawler:
+        url = "YOUR-URL-HERE"
+        result = await crawler.arun(
+            url=url,
+            cache_mode=CacheMode.BYPASS,
+            magic=True,  # Automatically detects and removes overlays, popups, and other elements that block content
+            # simulate_user = True,# Causes a series of random mouse movements and clicks to simulate user interaction
+            # override_navigator = True # Overrides the navigator object to make it look like a real user
+        )
+
+        print(result.markdown)
+
+
+async def speed_comparison():
+    # print("\n--- Speed Comparison ---")
+    # print("Firecrawl (simulated):")
+    # print("Time taken: 7.02 seconds")
+    # print("Content length: 42074 characters")
+    # print("Images found: 49")
+    # print()
+    # Simulated Firecrawl performance
+    from firecrawl import FirecrawlApp
+
+    app = FirecrawlApp(api_key=os.environ["FIRECRAWL_API_KEY"])
+    start = time.time()
+    scrape_status = app.scrape_url(
+        "https://www.nbcnews.com/business", params={"formats": ["markdown", "html"]}
+    )
+    end = time.time()
+    print("Firecrawl:")
+    print(f"Time taken: {end - start:.2f} seconds")
+    print(f"Content length: {len(scrape_status['markdown'])} characters")
+    print(f"Images found: {scrape_status['markdown'].count('cldnry.s-nbcnews.com')}")
+    print()
+
+    async with AsyncWebCrawler() as crawler:
+        # Crawl4AI simple crawl
+        start = time.time()
+        result = await crawler.arun(
+            url="https://www.nbcnews.com/business",
+            word_count_threshold=0,
+            cache_mode=CacheMode.BYPASS,
+            verbose=False,
+        )
+        end = time.time()
+        print("Crawl4AI (simple crawl):")
+        print(f"Time taken: {end - start:.2f} seconds")
+        print(f"Content length: {len(result.markdown)} characters")
+        print(f"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}")
+        print()
+
+        # Crawl4AI with advanced content filtering
+        start = time.time()
+        result = await crawler.arun(
+            url="https://www.nbcnews.com/business",
+            word_count_threshold=0,
+            markdown_generator=DefaultMarkdownGenerator(
+                content_filter=PruningContentFilter(
+                    threshold=0.48, threshold_type="fixed", min_word_threshold=0
+                )
+                # content_filter=BM25ContentFilter(user_query=None, bm25_threshold=1.0)
+            ),
+            cache_mode=CacheMode.BYPASS,
+            verbose=False,
+        )
+        end = time.time()
+        print("Crawl4AI (Markdown Plus):")
+        print(f"Time taken: {end - start:.2f} seconds")
+        print(f"Content length: {len(result.markdown.raw_markdown)} characters")
+        print(f"Fit Markdown: {len(result.markdown.fit_markdown)} characters")
+        print(f"Images found: {result.markdown.raw_markdown.count('cldnry.s-nbcnews.com')}")
+        print()
+
+        # Crawl4AI with JavaScript execution
+        start = time.time()
+        result = await crawler.arun(
+            url="https://www.nbcnews.com/business",
+            js_code=[
+                "const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();"
+            ],
+            word_count_threshold=0,
+            cache_mode=CacheMode.BYPASS,
+            markdown_generator=DefaultMarkdownGenerator(
+                content_filter=PruningContentFilter(
+                    threshold=0.48, threshold_type="fixed", min_word_threshold=0
+                )
+                # content_filter=BM25ContentFilter(user_query=None, bm25_threshold=1.0)
+            ),
+            verbose=False,
+        )
+        end = time.time()
+        print("Crawl4AI (with JavaScript execution):")
+        print(f"Time taken: {end - start:.2f} seconds")
+        print(f"Content length: {len(result.markdown.raw_markdown)} characters")
+        print(f"Fit Markdown: {len(result.markdown.fit_markdown)} characters")
+        print(f"Images found: {result.markdown.raw_markdown.count('cldnry.s-nbcnews.com')}")
+
+    print("\nNote on Speed Comparison:")
+    print("The speed test conducted here may not reflect optimal conditions.")
+    print("When we call Firecrawl's API, we're seeing its best performance,")
+    print("while Crawl4AI's performance is limited by the local network speed.")
+    print("For a more accurate comparison, it's recommended to run these tests")
+    print("on servers with a stable and fast internet connection.")
+    print("Despite these limitations, Crawl4AI still demonstrates faster performance.")
+    print("If you run these tests in an environment with better network conditions,")
+    print("you may observe an even more significant speed advantage for Crawl4AI.")
+
+
+async def generate_knowledge_graph():
+    class Entity(BaseModel):
+        name: str
+        description: str
+
+    class Relationship(BaseModel):
+        entity1: Entity
+        entity2: Entity
+        description: str
+        relation_type: str
+
+    class KnowledgeGraph(BaseModel):
+        entities: List[Entity]
+        relationships: List[Relationship]
+
+    extraction_strategy = LLMExtractionStrategy(
+        llm_config=LLMConfig(provider="openai/gpt-4o-mini",  api_token=os.getenv("OPENAI_API_KEY")),  # In case of Ollama just pass "no-token"
+        schema=KnowledgeGraph.model_json_schema(),
+        extraction_type="schema",
+        instruction="""Extract entities and relationships from the given text.""",
+    )
+    async with AsyncWebCrawler() as crawler:
+        url = "https://paulgraham.com/love.html"
+        result = await crawler.arun(
+            url=url,
+            cache_mode=CacheMode.BYPASS,
+            extraction_strategy=extraction_strategy,
+            # magic=True
+        )
+        # print(result.extracted_content)
+        with open(os.path.join(__location__, "kb.json"), "w") as f:
+            f.write(result.extracted_content)
+
+
+async def fit_markdown_remove_overlay():
+    async with AsyncWebCrawler(
+        headless=True,  # Set to False to see what is happening
+        verbose=True,
+        user_agent_mode="random",
+        user_agent_generator_config={"device_type": "mobile", "os_type": "android"},
+    ) as crawler:
+        result = await crawler.arun(
+            url="https://www.kidocode.com/degrees/technology",
+            cache_mode=CacheMode.BYPASS,
+            markdown_generator=DefaultMarkdownGenerator(
+                content_filter=PruningContentFilter(
+                    threshold=0.48, threshold_type="fixed", min_word_threshold=0
+                ),
+                options={"ignore_links": True},
+            ),
+            # markdown_generator=DefaultMarkdownGenerator(
+            #     content_filter=BM25ContentFilter(user_query="", bm25_threshold=1.0),
+            #     options={
+            #         "ignore_links": True
+            #     }
+            # ),
+        )
+
+        if result.success:
+            print(len(result.markdown.raw_markdown))
+            print(len(result.markdown.markdown_with_citations))
+            print(len(result.markdown.fit_markdown))
+
+            # Save clean html
+            with open(os.path.join(__location__, "output/cleaned_html.html"), "w") as f:
+                f.write(result.cleaned_html)
+
+            with open(
+                os.path.join(__location__, "output/output_raw_markdown.md"), "w"
+            ) as f:
+                f.write(result.markdown.raw_markdown)
+
+            with open(
+                os.path.join(__location__, "output/output_markdown_with_citations.md"),
+                "w",
+            ) as f:
+                f.write(result.markdown.markdown_with_citations)
+
+            with open(
+                os.path.join(__location__, "output/output_fit_markdown.md"), "w"
+            ) as f:
+                f.write(result.markdown.fit_markdown)
+
+    print("Done")
+
+
+async def main():
+    # await extract_structured_data_using_llm("openai/gpt-4o", os.getenv("OPENAI_API_KEY"))
+
+    # await simple_crawl()
+    # await simple_example_with_running_js_code()
+    # await simple_example_with_css_selector()
+    # # await use_proxy()
+    # await capture_and_save_screenshot("https://www.example.com", os.path.join(__location__, "tmp/example_screenshot.jpg"))
+    # await extract_structured_data_using_css_extractor()
+
+    # LLM extraction examples
+    # await extract_structured_data_using_llm()
+    # await extract_structured_data_using_llm("huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct", os.getenv("HUGGINGFACE_API_KEY"))
+    # await extract_structured_data_using_llm("ollama/llama3.2")
+
+    # You always can pass custom headers to the extraction strategy
+    # custom_headers = {
+    #     "Authorization": "Bearer your-custom-token",
+    #     "X-Custom-Header": "Some-Value"
+    # }
+    # await extract_structured_data_using_llm(extra_headers=custom_headers)
+
+    # await crawl_dynamic_content_pages_method_1()
+    # await crawl_dynamic_content_pages_method_2()
+    await crawl_dynamic_content_pages_method_3()
+
+    # await crawl_custom_browser_type()
+
+    # await speed_comparison()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/quickstart_examples_set_1.py

@@ -1,412 +0,0 @@
-import asyncio
-import os
-import json
-import base64
-from pathlib import Path
-from typing import List
-from crawl4ai.proxy_strategy import ProxyConfig
-
-from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, CacheMode, CrawlResult
-from crawl4ai import RoundRobinProxyStrategy
-from crawl4ai import JsonCssExtractionStrategy, LLMExtractionStrategy
-from crawl4ai import LLMConfig
-from crawl4ai import PruningContentFilter, BM25ContentFilter
-from crawl4ai import DefaultMarkdownGenerator
-from crawl4ai import BFSDeepCrawlStrategy, DomainFilter, FilterChain
-from crawl4ai import BrowserConfig
-
-__cur_dir__ = Path(__file__).parent
-
-async def demo_basic_crawl():
-    """Basic web crawling with markdown generation"""
-    print("\n=== 1. Basic Web Crawling ===")
-    async with AsyncWebCrawler(config = BrowserConfig(
-        viewport_height=800,
-        viewport_width=1200,
-        headless=True,
-        verbose=True,
-    )) as crawler:
-        results: List[CrawlResult] = await crawler.arun(
-            url="https://news.ycombinator.com/"
-        )
-
-        for i, result in enumerate(results):
-            print(f"Result {i + 1}:")
-            print(f"Success: {result.success}")
-            if result.success:
-                print(f"Markdown length: {len(result.markdown.raw_markdown)} chars")
-                print(f"First 100 chars: {result.markdown.raw_markdown[:100]}...")
-            else:
-                print("Failed to crawl the URL")
-
-async def demo_parallel_crawl():
-    """Crawl multiple URLs in parallel"""
-    print("\n=== 2. Parallel Crawling ===")
-
-    urls = [
-        "https://news.ycombinator.com/",
-        "https://example.com/",
-        "https://httpbin.org/html",
-    ]
-
-    async with AsyncWebCrawler() as crawler:
-        results: List[CrawlResult] = await crawler.arun_many(
-            urls=urls,
-        )
-
-        print(f"Crawled {len(results)} URLs in parallel:")
-        for i, result in enumerate(results):
-            print(
-                f"  {i + 1}. {result.url} - {'Success' if result.success else 'Failed'}"
-            )
-
-async def demo_fit_markdown():
-    """Generate focused markdown with LLM content filter"""
-    print("\n=== 3. Fit Markdown with LLM Content Filter ===")
-
-    async with AsyncWebCrawler() as crawler:
-        result: CrawlResult = await crawler.arun(
-            url = "https://en.wikipedia.org/wiki/Python_(programming_language)",
-            config=CrawlerRunConfig(
-                markdown_generator=DefaultMarkdownGenerator(
-                    content_filter=PruningContentFilter()
-                )
-            ),
-        )
-
-        # Print stats and save the fit markdown
-        print(f"Raw: {len(result.markdown.raw_markdown)} chars")
-        print(f"Fit: {len(result.markdown.fit_markdown)} chars")
-
-async def demo_llm_structured_extraction_no_schema():
-    # Create a simple LLM extraction strategy (no schema required)
-    extraction_strategy = LLMExtractionStrategy(
-        llm_config=LLMConfig(
-            provider="groq/qwen-2.5-32b",
-            api_token="env:GROQ_API_KEY",
-        ),
-        instruction="This is news.ycombinator.com, extract all news, and for each, I want title, source url, number of comments.",
-        extract_type="schema",
-        schema="{title: string, url: string, comments: int}",
-        extra_args={
-            "temperature": 0.0,
-            "max_tokens": 4096,
-        },
-        verbose=True,
-    )
-
-    config = CrawlerRunConfig(extraction_strategy=extraction_strategy)
-
-    async with AsyncWebCrawler() as crawler:
-        results: List[CrawlResult] = await crawler.arun(
-            "https://news.ycombinator.com/", config=config
-        )
-
-        for result in results:
-            print(f"URL: {result.url}")
-            print(f"Success: {result.success}")
-            if result.success:
-                data = json.loads(result.extracted_content)
-                print(json.dumps(data, indent=2))
-            else:
-                print("Failed to extract structured data")
-
-async def demo_css_structured_extraction_no_schema():
-    """Extract structured data using CSS selectors"""
-    print("\n=== 5. CSS-Based Structured Extraction ===")
-    # Sample HTML for schema generation (one-time cost)
-    sample_html = """
-<div class="body-post clear">
-    <a class="story-link" href="https://thehackernews.com/2025/04/malicious-python-packages-on-pypi.html">
-        <div class="clear home-post-box cf">
-            <div class="home-img clear">
-                <div class="img-ratio">
-                    <img alt="..." src="...">
-                </div>
-            </div>
-            <div class="clear home-right">
-                <h2 class="home-title">Malicious Python Packages on PyPI Downloaded 39,000+ Times, Steal Sensitive Data</h2>
-                <div class="item-label">
-                    <span class="h-datetime"><i class="icon-font icon-calendar"></i>Apr 05, 2025</span>
-                    <span class="h-tags">Malware / Supply Chain Attack</span>
-                </div>
-                <div class="home-desc"> Cybersecurity researchers have...</div>
-            </div>
-        </div>
-    </a>
-</div>
-    """
-
-    # Check if schema file exists
-    schema_file_path = f"{__cur_dir__}/tmp/schema.json"
-    if os.path.exists(schema_file_path):
-        with open(schema_file_path, "r") as f:
-            schema = json.load(f)
-    else:
-        # Generate schema using LLM (one-time setup)
-        schema = JsonCssExtractionStrategy.generate_schema(
-            html=sample_html,
-            llm_config=LLMConfig(
-                provider="groq/qwen-2.5-32b",
-                api_token="env:GROQ_API_KEY",
-            ),
-            query="From https://thehackernews.com/, I have shared a sample of one news div with a title, date, and description. Please generate a schema for this news div.",
-        )
-
-    print(f"Generated schema: {json.dumps(schema, indent=2)}")
-    # Save the schema to a file , and use it for future extractions, in result for such extraction you will call LLM once
-    with open(f"{__cur_dir__}/tmp/schema.json", "w") as f:
-        json.dump(schema, f, indent=2)
-
-    # Create no-LLM extraction strategy with the generated schema
-    extraction_strategy = JsonCssExtractionStrategy(schema)
-    config = CrawlerRunConfig(extraction_strategy=extraction_strategy)
-
-    # Use the fast CSS extraction (no LLM calls during extraction)
-    async with AsyncWebCrawler() as crawler:
-        results: List[CrawlResult] = await crawler.arun(
-            "https://thehackernews.com", config=config
-        )
-
-        for result in results:
-            print(f"URL: {result.url}")
-            print(f"Success: {result.success}")
-            if result.success:
-                data = json.loads(result.extracted_content)
-                print(json.dumps(data, indent=2))
-            else:
-                print("Failed to extract structured data")
-
-async def demo_deep_crawl():
-    """Deep crawling with BFS strategy"""
-    print("\n=== 6. Deep Crawling ===")
-
-    filter_chain = FilterChain([DomainFilter(allowed_domains=["crawl4ai.com"])])
-
-    deep_crawl_strategy = BFSDeepCrawlStrategy(
-        max_depth=1, max_pages=5, filter_chain=filter_chain
-    )
-
-    async with AsyncWebCrawler() as crawler:
-        results: List[CrawlResult] = await crawler.arun(
-            url="https://docs.crawl4ai.com",
-            config=CrawlerRunConfig(deep_crawl_strategy=deep_crawl_strategy),
-        )
-
-        print(f"Deep crawl returned {len(results)} pages:")
-        for i, result in enumerate(results):
-            depth = result.metadata.get("depth", "unknown")
-            print(f"  {i + 1}. {result.url} (Depth: {depth})")
-
-async def demo_js_interaction():
-    """Execute JavaScript to load more content"""
-    print("\n=== 7. JavaScript Interaction ===")
-
-    # A simple page that needs JS to reveal content
-    async with AsyncWebCrawler(config=BrowserConfig(headless=False)) as crawler:
-        # Initial load
-
-        news_schema = {
-            "name": "news",
-            "baseSelector": "tr.athing",
-            "fields": [
-                {
-                    "name": "title",
-                    "selector": "span.titleline",
-                    "type": "text",
-                }
-            ],
-        }
-        results: List[CrawlResult] = await crawler.arun(
-            url="https://news.ycombinator.com",
-            config=CrawlerRunConfig(
-                session_id="hn_session",  # Keep session
-                extraction_strategy=JsonCssExtractionStrategy(schema=news_schema),
-            ),
-        )
-
-        news = []
-        for result in results:
-            if result.success:
-                data = json.loads(result.extracted_content)
-                news.extend(data)
-                print(json.dumps(data, indent=2))
-            else:
-                print("Failed to extract structured data")
-
-        print(f"Initial items: {len(news)}")
-
-        # Click "More" link
-        more_config = CrawlerRunConfig(
-            js_code="document.querySelector('a.morelink').click();",
-            js_only=True,  # Continue in same page
-            session_id="hn_session",  # Keep session
-            extraction_strategy=JsonCssExtractionStrategy(
-                schema=news_schema,
-            ),
-        )
-
-        result: List[CrawlResult] = await crawler.arun(
-            url="https://news.ycombinator.com", config=more_config
-        )
-
-        # Extract new items
-        for result in results:
-            if result.success:
-                data = json.loads(result.extracted_content)
-                news.extend(data)
-                print(json.dumps(data, indent=2))
-            else:
-                print("Failed to extract structured data")
-        print(f"Total items: {len(news)}")
-
-async def demo_media_and_links():
-    """Extract media and links from a page"""
-    print("\n=== 8. Media and Links Extraction ===")
-
-    async with AsyncWebCrawler() as crawler:
-        result: List[CrawlResult] = await crawler.arun("https://en.wikipedia.org/wiki/Main_Page")
-
-        for i, result in enumerate(result):
-            # Extract and save all images
-            images = result.media.get("images", [])
-            print(f"Found {len(images)} images")
-
-            # Extract and save all links (internal and external)
-            internal_links = result.links.get("internal", [])
-            external_links = result.links.get("external", [])
-            print(f"Found {len(internal_links)} internal links")
-            print(f"Found {len(external_links)} external links")
-
-            # Print some of the images and links
-            for image in images[:3]:
-                print(f"Image: {image['src']}")
-            for link in internal_links[:3]:
-                print(f"Internal link: {link['href']}")
-            for link in external_links[:3]:
-                print(f"External link: {link['href']}")
-
-            # # Save everything to files
-            with open(f"{__cur_dir__}/tmp/images.json", "w") as f:
-                json.dump(images, f, indent=2)
-
-            with open(f"{__cur_dir__}/tmp/links.json", "w") as f:
-                json.dump(
-                    {"internal": internal_links, "external": external_links},
-                    f,
-                    indent=2,
-                )
-
-async def demo_screenshot_and_pdf():
-    """Capture screenshot and PDF of a page"""
-    print("\n=== 9. Screenshot and PDF Capture ===")
-
-    async with AsyncWebCrawler() as crawler:
-        result: List[CrawlResult] = await crawler.arun(
-            # url="https://example.com",
-            url="https://en.wikipedia.org/wiki/Giant_anteater",
-            config=CrawlerRunConfig(screenshot=True, pdf=True),
-        )
-
-        for i, result in enumerate(result):
-            # if result.screenshot_data:
-            if result.screenshot:
-                # Save screenshot
-                screenshot_path = f"{__cur_dir__}/tmp/example_screenshot.png"
-                with open(screenshot_path, "wb") as f:
-                    f.write(base64.b64decode(result.screenshot))
-                print(f"Screenshot saved to {screenshot_path}")
-
-            # if result.pdf_data:
-            if result.pdf:
-                # Save PDF
-                pdf_path = f"{__cur_dir__}/tmp/example.pdf"
-                with open(pdf_path, "wb") as f:
-                    f.write(result.pdf)
-                print(f"PDF saved to {pdf_path}")
-
-async def demo_proxy_rotation():
-    """Proxy rotation for multiple requests"""
-    print("\n=== 10. Proxy Rotation ===")
-
-    # Example proxies (replace with real ones)
-    proxies = [
-        ProxyConfig(server="http://proxy1.example.com:8080"),
-        ProxyConfig(server="http://proxy2.example.com:8080"),
-    ]
-
-    proxy_strategy = RoundRobinProxyStrategy(proxies)
-
-    print(f"Using {len(proxies)} proxies in rotation")
-    print(
-        "Note: This example uses placeholder proxies - replace with real ones to test"
-    )
-
-    async with AsyncWebCrawler() as crawler:
-        config = CrawlerRunConfig(
-            proxy_rotation_strategy=proxy_strategy
-        )
-
-        # In a real scenario, these would be run and the proxies would rotate
-        print("In a real scenario, requests would rotate through the available proxies")
-
-async def demo_raw_html_and_file():
-    """Process raw HTML and local files"""
-    print("\n=== 11. Raw HTML and Local Files ===")
-
-    raw_html = """
-    <html><body>
-        <h1>Sample Article</h1>
-        <p>This is sample content for testing Crawl4AI's raw HTML processing.</p>
-    </body></html>
-    """
-
-    # Save to file
-    file_path = Path("docs/examples/tmp/sample.html").absolute()
-    with open(file_path, "w") as f:
-        f.write(raw_html)
-
-    async with AsyncWebCrawler() as crawler:
-        # Crawl raw HTML
-        raw_result = await crawler.arun(
-            url="raw:" + raw_html, config=CrawlerRunConfig(cache_mode=CacheMode.BYPASS)
-        )
-        print("Raw HTML processing:")
-        print(f"  Markdown: {raw_result.markdown.raw_markdown[:50]}...")
-
-        # Crawl local file
-        file_result = await crawler.arun(
-            url=f"file://{file_path}",
-            config=CrawlerRunConfig(cache_mode=CacheMode.BYPASS),
-        )
-        print("\nLocal file processing:")
-        print(f"  Markdown: {file_result.markdown.raw_markdown[:50]}...")
-
-    # Clean up
-    os.remove(file_path)
-    print(f"Processed both raw HTML and local file ({file_path})")
-
-async def main():
-    """Run all demo functions sequentially"""
-    print("=== Comprehensive Crawl4AI Demo ===")
-    print("Note: Some examples require API keys or other configurations")
-
-    # Run all demos
-    await demo_basic_crawl()
-    await demo_parallel_crawl()
-    await demo_fit_markdown()
-    await demo_llm_structured_extraction_no_schema()
-    await demo_css_structured_extraction_no_schema()
-    await demo_deep_crawl()
-    await demo_js_interaction()
-    await demo_media_and_links()
-    await demo_screenshot_and_pdf()
-    # # await demo_proxy_rotation()
-    await demo_raw_html_and_file()
-
-    # Clean up any temp files that may have been created
-    print("\n=== Demo Complete ===")
-    print("Check for any generated files (screenshots, PDFs) in the current directory")
-
-if __name__ == "__main__":
-    asyncio.run(main())

docs/examples/quickstart_examples_set_2.py

@@ -1,562 +0,0 @@
-import os, sys
-
-from crawl4ai.types import LLMConfig
-
-sys.path.append(
-    os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-)
-
-import asyncio
-import time
-import json
-import re
-from typing import Dict
-from bs4 import BeautifulSoup
-from pydantic import BaseModel, Field
-from crawl4ai import AsyncWebCrawler, CacheMode, BrowserConfig, CrawlerRunConfig
-from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
-from crawl4ai.content_filter_strategy import PruningContentFilter
-from crawl4ai.extraction_strategy import (
-    JsonCssExtractionStrategy,
-    LLMExtractionStrategy,
-)
-
-__location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
-
-print("Crawl4AI: Advanced Web Crawling and Data Extraction")
-print("GitHub Repository: https://github.com/unclecode/crawl4ai")
-print("Twitter: @unclecode")
-print("Website: https://crawl4ai.com")
-
-
-# Basic Example - Simple Crawl
-async def simple_crawl():
-    print("\n--- Basic Usage ---")
-    browser_config = BrowserConfig(headless=True)
-    crawler_config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS)
-
-    async with AsyncWebCrawler(config=browser_config) as crawler:
-        result = await crawler.arun(
-            url="https://www.nbcnews.com/business", config=crawler_config
-        )
-        print(result.markdown[:500])
-
-
-async def clean_content():
-    crawler_config = CrawlerRunConfig(
-        cache_mode=CacheMode.BYPASS,
-        excluded_tags=["nav", "footer", "aside"],
-        remove_overlay_elements=True,
-        markdown_generator=DefaultMarkdownGenerator(
-            content_filter=PruningContentFilter(
-                threshold=0.48, threshold_type="fixed", min_word_threshold=0
-            ),
-            options={"ignore_links": True},
-        ),
-    )
-    async with AsyncWebCrawler() as crawler:
-        result = await crawler.arun(
-            url="https://en.wikipedia.org/wiki/Apple",
-            config=crawler_config,
-        )
-        full_markdown_length = len(result.markdown.raw_markdown)
-        fit_markdown_length = len(result.markdown.fit_markdown)
-        print(f"Full Markdown Length: {full_markdown_length}")
-        print(f"Fit Markdown Length: {fit_markdown_length}")
-
-
-async def link_analysis():
-    crawler_config = CrawlerRunConfig(
-        cache_mode=CacheMode.ENABLED,
-        exclude_external_links=True,
-        exclude_social_media_links=True,
-    )
-    async with AsyncWebCrawler() as crawler:
-        result = await crawler.arun(
-            url="https://www.nbcnews.com/business",
-            config=crawler_config,
-        )
-        print(f"Found {len(result.links['internal'])} internal links")
-        print(f"Found {len(result.links['external'])} external links")
-
-        for link in result.links["internal"][:5]:
-            print(f"Href: {link['href']}\nText: {link['text']}\n")
-
-
-# JavaScript Execution Example
-async def simple_example_with_running_js_code():
-    print("\n--- Executing JavaScript and Using CSS Selectors ---")
-
-    browser_config = BrowserConfig(headless=True, java_script_enabled=True)
-
-    crawler_config = CrawlerRunConfig(
-        cache_mode=CacheMode.BYPASS,
-        js_code="const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();",
-        # wait_for="() => { return Array.from(document.querySelectorAll('article.tease-card')).length > 10; }"
-    )
-
-    async with AsyncWebCrawler(config=browser_config) as crawler:
-        result = await crawler.arun(
-            url="https://www.nbcnews.com/business", config=crawler_config
-        )
-        print(result.markdown[:500])
-
-
-# CSS Selector Example
-async def simple_example_with_css_selector():
-    print("\n--- Using CSS Selectors ---")
-    browser_config = BrowserConfig(headless=True)
-    crawler_config = CrawlerRunConfig(
-        cache_mode=CacheMode.BYPASS, css_selector=".wide-tease-item__description"
-    )
-
-    async with AsyncWebCrawler(config=browser_config) as crawler:
-        result = await crawler.arun(
-            url="https://www.nbcnews.com/business", config=crawler_config
-        )
-        print(result.markdown[:500])
-
-
-async def media_handling():
-    crawler_config = CrawlerRunConfig(
-        cache_mode=CacheMode.BYPASS, exclude_external_images=True, screenshot=True
-    )
-    async with AsyncWebCrawler() as crawler:
-        result = await crawler.arun(
-            url="https://www.nbcnews.com/business", config=crawler_config
-        )
-        for img in result.media["images"][:5]:
-            print(f"Image URL: {img['src']}, Alt: {img['alt']}, Score: {img['score']}")
-
-
-async def custom_hook_workflow(verbose=True):
-    async with AsyncWebCrawler() as crawler:
-        # Set a 'before_goto' hook to run custom code just before navigation
-        crawler.crawler_strategy.set_hook(
-            "before_goto",
-            lambda page, context: print("[Hook] Preparing to navigate..."),
-        )
-
-        # Perform the crawl operation
-        result = await crawler.arun(url="https://crawl4ai.com")
-        print(result.markdown.raw_markdown[:500].replace("\n", " -- "))
-
-
-# Proxy Example
-async def use_proxy():
-    print("\n--- Using a Proxy ---")
-    browser_config = BrowserConfig(
-        headless=True,
-        proxy_config={
-            "server": "http://proxy.example.com:8080",
-            "username": "username",
-            "password": "password",
-        },
-    )
-    crawler_config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS)
-
-    async with AsyncWebCrawler(config=browser_config) as crawler:
-        result = await crawler.arun(
-            url="https://www.nbcnews.com/business", config=crawler_config
-        )
-        if result.success:
-            print(result.markdown[:500])
-
-
-# Screenshot Example
-async def capture_and_save_screenshot(url: str, output_path: str):
-    browser_config = BrowserConfig(headless=True)
-    crawler_config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS, screenshot=True)
-
-    async with AsyncWebCrawler(config=browser_config) as crawler:
-        result = await crawler.arun(url=url, config=crawler_config)
-
-        if result.success and result.screenshot:
-            import base64
-
-            screenshot_data = base64.b64decode(result.screenshot)
-            with open(output_path, "wb") as f:
-                f.write(screenshot_data)
-            print(f"Screenshot saved successfully to {output_path}")
-        else:
-            print("Failed to capture screenshot")
-
-
-# LLM Extraction Example
-class OpenAIModelFee(BaseModel):
-    model_name: str = Field(..., description="Name of the OpenAI model.")
-    input_fee: str = Field(..., description="Fee for input token for the OpenAI model.")
-    output_fee: str = Field(
-        ..., description="Fee for output token for the OpenAI model."
-    )
-
-
-async def extract_structured_data_using_llm(
-    provider: str, api_token: str = None, extra_headers: Dict[str, str] = None
-):
-    print(f"\n--- Extracting Structured Data with {provider} ---")
-
-    if api_token is None and provider != "ollama":
-        print(f"API token is required for {provider}. Skipping this example.")
-        return
-
-    browser_config = BrowserConfig(headless=True)
-
-    extra_args = {"temperature": 0, "top_p": 0.9, "max_tokens": 2000}
-    if extra_headers:
-        extra_args["extra_headers"] = extra_headers
-
-    crawler_config = CrawlerRunConfig(
-        cache_mode=CacheMode.BYPASS,
-        word_count_threshold=1,
-        page_timeout=80000,
-        extraction_strategy=LLMExtractionStrategy(
-            llm_config=LLMConfig(provider=provider,api_token=api_token),
-            schema=OpenAIModelFee.model_json_schema(),
-            extraction_type="schema",
-            instruction="""From the crawled content, extract all mentioned model names along with their fees for input and output tokens. 
-            Do not miss any models in the entire content.""",
-            extra_args=extra_args,
-        ),
-    )
-
-    async with AsyncWebCrawler(config=browser_config) as crawler:
-        result = await crawler.arun(
-            url="https://openai.com/api/pricing/", config=crawler_config
-        )
-        print(result.extracted_content)
-
-
-# CSS Extraction Example
-async def extract_structured_data_using_css_extractor():
-    print("\n--- Using JsonCssExtractionStrategy for Fast Structured Output ---")
-    schema = {
-        "name": "KidoCode Courses",
-        "baseSelector": "section.charge-methodology .framework-collection-item.w-dyn-item",
-        "fields": [
-            {
-                "name": "section_title",
-                "selector": "h3.heading-50",
-                "type": "text",
-            },
-            {
-                "name": "section_description",
-                "selector": ".charge-content",
-                "type": "text",
-            },
-            {
-                "name": "course_name",
-                "selector": ".text-block-93",
-                "type": "text",
-            },
-            {
-                "name": "course_description",
-                "selector": ".course-content-text",
-                "type": "text",
-            },
-            {
-                "name": "course_icon",
-                "selector": ".image-92",
-                "type": "attribute",
-                "attribute": "src",
-            },
-        ],
-    }
-
-    browser_config = BrowserConfig(headless=True, java_script_enabled=True)
-
-    js_click_tabs = """
-    (async () => {
-        const tabs = document.querySelectorAll("section.charge-methodology .tabs-menu-3 > div");
-        for(let tab of tabs) {
-            tab.scrollIntoView();
-            tab.click();
-            await new Promise(r => setTimeout(r, 500));
-        }
-    })();
-    """
-
-    crawler_config = CrawlerRunConfig(
-        cache_mode=CacheMode.BYPASS,
-        extraction_strategy=JsonCssExtractionStrategy(schema),
-        js_code=[js_click_tabs],
-        delay_before_return_html=1
-    )
-
-    async with AsyncWebCrawler(config=browser_config) as crawler:
-        result = await crawler.arun(
-            url="https://www.kidocode.com/degrees/technology", config=crawler_config
-        )
-
-        companies = json.loads(result.extracted_content)
-        print(f"Successfully extracted {len(companies)} companies")
-        print(json.dumps(companies[0], indent=2))
-
-
-# Dynamic Content Examples - Method 1
-async def crawl_dynamic_content_pages_method_1():
-    print("\n--- Advanced Multi-Page Crawling with JavaScript Execution ---")
-    first_commit = ""
-
-    async def on_execution_started(page, **kwargs):
-        nonlocal first_commit
-        try:
-            while True:
-                await page.wait_for_selector("li.Box-sc-g0xbh4-0 h4")
-                commit = await page.query_selector("li.Box-sc-g0xbh4-0 h4")
-                commit = await commit.evaluate("(element) => element.textContent")
-                commit = re.sub(r"\s+", "", commit)
-                if commit and commit != first_commit:
-                    first_commit = commit
-                    break
-                await asyncio.sleep(0.5)
-        except Exception as e:
-            print(f"Warning: New content didn't appear after JavaScript execution: {e}")
-
-    browser_config = BrowserConfig(headless=False, java_script_enabled=True)
-
-    async with AsyncWebCrawler(config=browser_config) as crawler:
-        crawler.crawler_strategy.set_hook("on_execution_started", on_execution_started)
-
-        url = "https://github.com/microsoft/TypeScript/commits/main"
-        session_id = "typescript_commits_session"
-        all_commits = []
-
-        js_next_page = """
-        const button = document.querySelector('a[data-testid="pagination-next-button"]');
-        if (button) button.click();
-        """
-
-        for page in range(3):
-            crawler_config = CrawlerRunConfig(
-                cache_mode=CacheMode.BYPASS,
-                css_selector="li.Box-sc-g0xbh4-0",
-                js_code=js_next_page if page > 0 else None,
-                js_only=page > 0,
-                session_id=session_id,
-            )
-
-            result = await crawler.arun(url=url, config=crawler_config)
-            assert result.success, f"Failed to crawl page {page + 1}"
-
-            soup = BeautifulSoup(result.cleaned_html, "html.parser")
-            commits = soup.select("li")
-            all_commits.extend(commits)
-
-            print(f"Page {page + 1}: Found {len(commits)} commits")
-
-        print(f"Successfully crawled {len(all_commits)} commits across 3 pages")
-
-
-# Dynamic Content Examples - Method 2
-async def crawl_dynamic_content_pages_method_2():
-    print("\n--- Advanced Multi-Page Crawling with JavaScript Execution ---")
-
-    browser_config = BrowserConfig(headless=False, java_script_enabled=True)
-
-    js_next_page_and_wait = """
-    (async () => {
-        const getCurrentCommit = () => {
-            const commits = document.querySelectorAll('li.Box-sc-g0xbh4-0 h4');
-            return commits.length > 0 ? commits[0].textContent.trim() : null;
-        };
-
-        const initialCommit = getCurrentCommit();
-        const button = document.querySelector('a[data-testid="pagination-next-button"]');
-        if (button) button.click();
-
-        while (true) {
-            await new Promise(resolve => setTimeout(resolve, 100));
-            const newCommit = getCurrentCommit();
-            if (newCommit && newCommit !== initialCommit) {
-                break;
-            }
-        }
-    })();
-    """
-
-    schema = {
-        "name": "Commit Extractor",
-        "baseSelector": "li.Box-sc-g0xbh4-0",
-        "fields": [
-            {
-                "name": "title",
-                "selector": "h4.markdown-title",
-                "type": "text",
-                "transform": "strip",
-            },
-        ],
-    }
-
-    async with AsyncWebCrawler(config=browser_config) as crawler:
-        url = "https://github.com/microsoft/TypeScript/commits/main"
-        session_id = "typescript_commits_session"
-        all_commits = []
-
-        extraction_strategy = JsonCssExtractionStrategy(schema)
-
-        for page in range(3):
-            crawler_config = CrawlerRunConfig(
-                cache_mode=CacheMode.BYPASS,
-                css_selector="li.Box-sc-g0xbh4-0",
-                extraction_strategy=extraction_strategy,
-                js_code=js_next_page_and_wait if page > 0 else None,
-                js_only=page > 0,
-                session_id=session_id,
-            )
-
-            result = await crawler.arun(url=url, config=crawler_config)
-            assert result.success, f"Failed to crawl page {page + 1}"
-
-            commits = json.loads(result.extracted_content)
-            all_commits.extend(commits)
-            print(f"Page {page + 1}: Found {len(commits)} commits")
-
-        print(f"Successfully crawled {len(all_commits)} commits across 3 pages")
-
-
-async def cosine_similarity_extraction():
-    from crawl4ai.extraction_strategy import CosineStrategy
-    crawl_config = CrawlerRunConfig(
-        cache_mode=CacheMode.BYPASS,
-        extraction_strategy=CosineStrategy(
-            word_count_threshold=10,
-            max_dist=0.2,  # Maximum distance between two words
-            linkage_method="ward",  # Linkage method for hierarchical clustering (ward, complete, average, single)
-            top_k=3,  # Number of top keywords to extract
-            sim_threshold=0.3,  # Similarity threshold for clustering
-            semantic_filter="McDonald's economic impact, American consumer trends",  # Keywords to filter the content semantically using embeddings
-            verbose=True,
-        ),
-    )
-    async with AsyncWebCrawler() as crawler:
-        result = await crawler.arun(
-            url="https://www.nbcnews.com/business/consumer/how-mcdonalds-e-coli-crisis-inflation-politics-reflect-american-story-rcna177156",
-            config=crawl_config,
-        )
-        print(json.loads(result.extracted_content)[:5])
-
-
-# Browser Comparison
-async def crawl_custom_browser_type():
-    print("\n--- Browser Comparison ---")
-
-    # Firefox
-    browser_config_firefox = BrowserConfig(browser_type="firefox", headless=True)
-    start = time.time()
-    async with AsyncWebCrawler(config=browser_config_firefox) as crawler:
-        result = await crawler.arun(
-            url="https://www.example.com",
-            config=CrawlerRunConfig(cache_mode=CacheMode.BYPASS),
-        )
-        print("Firefox:", time.time() - start)
-        print(result.markdown[:500])
-
-    # WebKit
-    browser_config_webkit = BrowserConfig(browser_type="webkit", headless=True)
-    start = time.time()
-    async with AsyncWebCrawler(config=browser_config_webkit) as crawler:
-        result = await crawler.arun(
-            url="https://www.example.com",
-            config=CrawlerRunConfig(cache_mode=CacheMode.BYPASS),
-        )
-        print("WebKit:", time.time() - start)
-        print(result.markdown[:500])
-
-    # Chromium (default)
-    browser_config_chromium = BrowserConfig(browser_type="chromium", headless=True)
-    start = time.time()
-    async with AsyncWebCrawler(config=browser_config_chromium) as crawler:
-        result = await crawler.arun(
-            url="https://www.example.com",
-            config=CrawlerRunConfig(cache_mode=CacheMode.BYPASS),
-        )
-        print("Chromium:", time.time() - start)
-        print(result.markdown[:500])
-
-
-# Anti-Bot and User Simulation
-async def crawl_with_user_simulation():
-    browser_config = BrowserConfig(
-        headless=True,
-        user_agent_mode="random",
-        user_agent_generator_config={"device_type": "mobile", "os_type": "android"},
-    )
-
-    crawler_config = CrawlerRunConfig(
-        cache_mode=CacheMode.BYPASS,
-        magic=True,
-        simulate_user=True,
-        override_navigator=True,
-    )
-
-    async with AsyncWebCrawler(config=browser_config) as crawler:
-        result = await crawler.arun(url="YOUR-URL-HERE", config=crawler_config)
-        print(result.markdown)
-
-
-async def ssl_certification():
-    # Configure crawler to fetch SSL certificate
-    config = CrawlerRunConfig(
-        fetch_ssl_certificate=True,
-        cache_mode=CacheMode.BYPASS,  # Bypass cache to always get fresh certificates
-    )
-
-    async with AsyncWebCrawler() as crawler:
-        result = await crawler.arun(url="https://example.com", config=config)
-
-        if result.success and result.ssl_certificate:
-            cert = result.ssl_certificate
-
-            tmp_dir = os.path.join(__location__, "tmp")
-            os.makedirs(tmp_dir, exist_ok=True)
-
-            # 1. Access certificate properties directly
-            print("\nCertificate Information:")
-            print(f"Issuer: {cert.issuer.get('CN', '')}")
-            print(f"Valid until: {cert.valid_until}")
-            print(f"Fingerprint: {cert.fingerprint}")
-
-            # 2. Export certificate in different formats
-            cert.to_json(os.path.join(tmp_dir, "certificate.json"))  # For analysis
-            print("\nCertificate exported to:")
-            print(f"- JSON: {os.path.join(tmp_dir, 'certificate.json')}")
-
-            pem_data = cert.to_pem(
-                os.path.join(tmp_dir, "certificate.pem")
-            )  # For web servers
-            print(f"- PEM: {os.path.join(tmp_dir, 'certificate.pem')}")
-
-            der_data = cert.to_der(
-                os.path.join(tmp_dir, "certificate.der")
-            )  # For Java apps
-            print(f"- DER: {os.path.join(tmp_dir, 'certificate.der')}")
-
-
-# Main execution
-async def main():
-    # Basic examples
-    await simple_crawl()
-    await simple_example_with_running_js_code()
-    await simple_example_with_css_selector()
-
-    # Advanced examples
-    await extract_structured_data_using_css_extractor()
-    await extract_structured_data_using_llm(
-        "openai/gpt-4o", os.getenv("OPENAI_API_KEY")
-    )
-    await crawl_dynamic_content_pages_method_1()
-    await crawl_dynamic_content_pages_method_2()
-
-    # Browser comparisons
-    await crawl_custom_browser_type()
-
-    # Screenshot example
-    await capture_and_save_screenshot(
-        "https://www.example.com",
-        os.path.join(__location__, "tmp/example_screenshot.jpg")
-    )
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

docs/examples/quickstart_sync.py

@@ -0,0 +1,405 @@
+import os
+import time
+from crawl4ai import LLMConfig
+from crawl4ai.web_crawler import WebCrawler
+from crawl4ai.chunking_strategy import *
+from crawl4ai.extraction_strategy import *
+from crawl4ai.crawler_strategy import *
+from rich import print
+from rich.console import Console
+from functools import lru_cache
+
+console = Console()
+
+
+@lru_cache()
+def create_crawler():
+    crawler = WebCrawler(verbose=True)
+    crawler.warmup()
+    return crawler
+
+
+def print_result(result):
+    # Print each key in one line and just the first 10 characters of each one's value and three dots
+    console.print("\t[bold]Result:[/bold]")
+    for key, value in result.model_dump().items():
+        if isinstance(value, str) and value:
+            console.print(f"\t{key}: [green]{value[:20]}...[/green]")
+    if result.extracted_content:
+        items = json.loads(result.extracted_content)
+        print(f"\t[bold]{len(items)} blocks is extracted![/bold]")
+
+
+def cprint(message, press_any_key=False):
+    console.print(message)
+    if press_any_key:
+        console.print("Press any key to continue...", style="")
+        input()
+
+
+def basic_usage(crawler):
+    cprint(
+        "🛠️ [bold cyan]Basic Usage: Simply provide a URL and let Crawl4ai do the magic![/bold cyan]"
+    )
+    result = crawler.run(url="https://www.nbcnews.com/business", only_text=True)
+    cprint("[LOG] 📦 [bold yellow]Basic crawl result:[/bold yellow]")
+    print_result(result)
+
+
+def basic_usage_some_params(crawler):
+    cprint(
+        "🛠️ [bold cyan]Basic Usage: Simply provide a URL and let Crawl4ai do the magic![/bold cyan]"
+    )
+    result = crawler.run(
+        url="https://www.nbcnews.com/business", word_count_threshold=1, only_text=True
+    )
+    cprint("[LOG] 📦 [bold yellow]Basic crawl result:[/bold yellow]")
+    print_result(result)
+
+
+def screenshot_usage(crawler):
+    cprint("\n📸 [bold cyan]Let's take a screenshot of the page![/bold cyan]")
+    result = crawler.run(url="https://www.nbcnews.com/business", screenshot=True)
+    cprint("[LOG] 📦 [bold yellow]Screenshot result:[/bold yellow]")
+    # Save the screenshot to a file
+    with open("screenshot.png", "wb") as f:
+        f.write(base64.b64decode(result.screenshot))
+    cprint("Screenshot saved to 'screenshot.png'!")
+    print_result(result)
+
+
+def understanding_parameters(crawler):
+    cprint(
+        "\n🧠 [bold cyan]Understanding 'bypass_cache' and 'include_raw_html' parameters:[/bold cyan]"
+    )
+    cprint(
+        "By default, Crawl4ai caches the results of your crawls. This means that subsequent crawls of the same URL will be much faster! Let's see this in action."
+    )
+
+    # First crawl (reads from cache)
+    cprint("1️⃣ First crawl (caches the result):", True)
+    start_time = time.time()
+    result = crawler.run(url="https://www.nbcnews.com/business")
+    end_time = time.time()
+    cprint(
+        f"[LOG] 📦 [bold yellow]First crawl took {end_time - start_time} seconds and result (from cache):[/bold yellow]"
+    )
+    print_result(result)
+
+    # Force to crawl again
+    cprint("2️⃣ Second crawl (Force to crawl again):", True)
+    start_time = time.time()
+    result = crawler.run(url="https://www.nbcnews.com/business", bypass_cache=True)
+    end_time = time.time()
+    cprint(
+        f"[LOG] 📦 [bold yellow]Second crawl took {end_time - start_time} seconds and result (forced to crawl):[/bold yellow]"
+    )
+    print_result(result)
+
+
+def add_chunking_strategy(crawler):
+    # Adding a chunking strategy: RegexChunking
+    cprint(
+        "\n🧩 [bold cyan]Let's add a chunking strategy: RegexChunking![/bold cyan]",
+        True,
+    )
+    cprint(
+        "RegexChunking is a simple chunking strategy that splits the text based on a given regex pattern. Let's see it in action!"
+    )
+    result = crawler.run(
+        url="https://www.nbcnews.com/business",
+        chunking_strategy=RegexChunking(patterns=["\n\n"]),
+    )
+    cprint("[LOG] 📦 [bold yellow]RegexChunking result:[/bold yellow]")
+    print_result(result)
+
+    # Adding another chunking strategy: NlpSentenceChunking
+    cprint(
+        "\n🔍 [bold cyan]Time to explore another chunking strategy: NlpSentenceChunking![/bold cyan]",
+        True,
+    )
+    cprint(
+        "NlpSentenceChunking uses NLP techniques to split the text into sentences. Let's see how it performs!"
+    )
+    result = crawler.run(
+        url="https://www.nbcnews.com/business", chunking_strategy=NlpSentenceChunking()
+    )
+    cprint("[LOG] 📦 [bold yellow]NlpSentenceChunking result:[/bold yellow]")
+    print_result(result)
+
+
+def add_extraction_strategy(crawler):
+    # Adding an extraction strategy: CosineStrategy
+    cprint(
+        "\n🧠 [bold cyan]Let's get smarter with an extraction strategy: CosineStrategy![/bold cyan]",
+        True,
+    )
+    cprint(
+        "CosineStrategy uses cosine similarity to extract semantically similar blocks of text. Let's see it in action!"
+    )
+    result = crawler.run(
+        url="https://www.nbcnews.com/business",
+        extraction_strategy=CosineStrategy(
+            word_count_threshold=10,
+            max_dist=0.2,
+            linkage_method="ward",
+            top_k=3,
+            sim_threshold=0.3,
+            verbose=True,
+        ),
+    )
+    cprint("[LOG] 📦 [bold yellow]CosineStrategy result:[/bold yellow]")
+    print_result(result)
+
+    # Using semantic_filter with CosineStrategy
+    cprint(
+        "You can pass other parameters like 'semantic_filter' to the CosineStrategy to extract semantically similar blocks of text. Let's see it in action!"
+    )
+    result = crawler.run(
+        url="https://www.nbcnews.com/business",
+        extraction_strategy=CosineStrategy(
+            semantic_filter="inflation rent prices",
+        ),
+    )
+    cprint(
+        "[LOG] 📦 [bold yellow]CosineStrategy result with semantic filter:[/bold yellow]"
+    )
+    print_result(result)
+
+
+def add_llm_extraction_strategy(crawler):
+    # Adding an LLM extraction strategy without instructions
+    cprint(
+        "\n🤖 [bold cyan]Time to bring in the big guns: LLMExtractionStrategy without instructions![/bold cyan]",
+        True,
+    )
+    cprint(
+        "LLMExtractionStrategy uses a large language model to extract relevant information from the web page. Let's see it in action!"
+    )
+    result = crawler.run(
+        url="https://www.nbcnews.com/business",
+        extraction_strategy=LLMExtractionStrategy(
+            llm_config =  LLMConfig(provider="openai/gpt-4o", api_token=os.getenv("OPENAI_API_KEY"))
+        ),
+    )
+    cprint(
+        "[LOG] 📦 [bold yellow]LLMExtractionStrategy (no instructions) result:[/bold yellow]"
+    )
+    print_result(result)
+
+    # Adding an LLM extraction strategy with instructions
+    cprint(
+        "\n📜 [bold cyan]Let's make it even more interesting: LLMExtractionStrategy with instructions![/bold cyan]",
+        True,
+    )
+    cprint(
+        "Let's say we are only interested in financial news. Let's see how LLMExtractionStrategy performs with instructions!"
+    )
+    result = crawler.run(
+        url="https://www.nbcnews.com/business",
+        extraction_strategy=LLMExtractionStrategy(
+            llm_config=LLMConfig(provider="openai/gpt-4o",api_token=os.getenv("OPENAI_API_KEY")),
+            instruction="I am interested in only financial news",
+        ),
+    )
+    cprint(
+        "[LOG] 📦 [bold yellow]LLMExtractionStrategy (with instructions) result:[/bold yellow]"
+    )
+    print_result(result)
+
+    result = crawler.run(
+        url="https://www.nbcnews.com/business",
+        extraction_strategy=LLMExtractionStrategy(
+            llm_config=LLMConfig(provider="openai/gpt-4o",api_token=os.getenv("OPENAI_API_KEY")),
+            instruction="Extract only content related to technology",
+        ),
+    )
+    cprint(
+        "[LOG] 📦 [bold yellow]LLMExtractionStrategy (with technology instruction) result:[/bold yellow]"
+    )
+    print_result(result)
+
+
+def targeted_extraction(crawler):
+    # Using a CSS selector to extract only H2 tags
+    cprint(
+        "\n🎯 [bold cyan]Targeted extraction: Let's use a CSS selector to extract only H2 tags![/bold cyan]",
+        True,
+    )
+    result = crawler.run(url="https://www.nbcnews.com/business", css_selector="h2")
+    cprint("[LOG] 📦 [bold yellow]CSS Selector (H2 tags) result:[/bold yellow]")
+    print_result(result)
+
+
+def interactive_extraction(crawler):
+    # Passing JavaScript code to interact with the page
+    cprint(
+        "\n🖱️ [bold cyan]Let's get interactive: Passing JavaScript code to click 'Load More' button![/bold cyan]",
+        True,
+    )
+    cprint(
+        "In this example we try to click the 'Load More' button on the page using JavaScript code."
+    )
+    js_code = """
+    const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More'));
+    loadMoreButton && loadMoreButton.click();
+    """
+    # crawler_strategy = LocalSeleniumCrawlerStrategy(js_code=js_code)
+    # crawler = WebCrawler(crawler_strategy=crawler_strategy, always_by_pass_cache=True)
+    result = crawler.run(url="https://www.nbcnews.com/business", js=js_code)
+    cprint(
+        "[LOG] 📦 [bold yellow]JavaScript Code (Load More button) result:[/bold yellow]"
+    )
+    print_result(result)
+
+
+def multiple_scrip(crawler):
+    # Passing JavaScript code to interact with the page
+    cprint(
+        "\n🖱️ [bold cyan]Let's get interactive: Passing JavaScript code to click 'Load More' button![/bold cyan]",
+        True,
+    )
+    cprint(
+        "In this example we try to click the 'Load More' button on the page using JavaScript code."
+    )
+    js_code = [
+        """
+    const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More'));
+    loadMoreButton && loadMoreButton.click();
+    """
+    ] * 2
+    # crawler_strategy = LocalSeleniumCrawlerStrategy(js_code=js_code)
+    # crawler = WebCrawler(crawler_strategy=crawler_strategy, always_by_pass_cache=True)
+    result = crawler.run(url="https://www.nbcnews.com/business", js=js_code)
+    cprint(
+        "[LOG] 📦 [bold yellow]JavaScript Code (Load More button) result:[/bold yellow]"
+    )
+    print_result(result)
+
+
+def using_crawler_hooks(crawler):
+    # Example usage of the hooks for authentication and setting a cookie
+    def on_driver_created(driver):
+        print("[HOOK] on_driver_created")
+        # Example customization: maximize the window
+        driver.maximize_window()
+
+        # Example customization: logging in to a hypothetical website
+        driver.get("https://example.com/login")
+
+        from selenium.webdriver.support.ui import WebDriverWait
+        from selenium.webdriver.common.by import By
+        from selenium.webdriver.support import expected_conditions as EC
+
+        WebDriverWait(driver, 10).until(
+            EC.presence_of_element_located((By.NAME, "username"))
+        )
+        driver.find_element(By.NAME, "username").send_keys("testuser")
+        driver.find_element(By.NAME, "password").send_keys("password123")
+        driver.find_element(By.NAME, "login").click()
+        WebDriverWait(driver, 10).until(
+            EC.presence_of_element_located((By.ID, "welcome"))
+        )
+        # Add a custom cookie
+        driver.add_cookie({"name": "test_cookie", "value": "cookie_value"})
+        return driver
+
+    def before_get_url(driver):
+        print("[HOOK] before_get_url")
+        # Example customization: add a custom header
+        # Enable Network domain for sending headers
+        driver.execute_cdp_cmd("Network.enable", {})
+        # Add a custom header
+        driver.execute_cdp_cmd(
+            "Network.setExtraHTTPHeaders", {"headers": {"X-Test-Header": "test"}}
+        )
+        return driver
+
+    def after_get_url(driver):
+        print("[HOOK] after_get_url")
+        # Example customization: log the URL
+        print(driver.current_url)
+        return driver
+
+    def before_return_html(driver, html):
+        print("[HOOK] before_return_html")
+        # Example customization: log the HTML
+        print(len(html))
+        return driver
+
+    cprint(
+        "\n🔗 [bold cyan]Using Crawler Hooks: Let's see how we can customize the crawler using hooks![/bold cyan]",
+        True,
+    )
+
+    crawler_strategy = LocalSeleniumCrawlerStrategy(verbose=True)
+    crawler_strategy.set_hook("on_driver_created", on_driver_created)
+    crawler_strategy.set_hook("before_get_url", before_get_url)
+    crawler_strategy.set_hook("after_get_url", after_get_url)
+    crawler_strategy.set_hook("before_return_html", before_return_html)
+
+    crawler = WebCrawler(verbose=True, crawler_strategy=crawler_strategy)
+    crawler.warmup()
+    result = crawler.run(url="https://example.com")
+
+    cprint("[LOG] 📦 [bold yellow]Crawler Hooks result:[/bold yellow]")
+    print_result(result=result)
+
+
+def using_crawler_hooks_dleay_example(crawler):
+    def delay(driver):
+        print("Delaying for 5 seconds...")
+        time.sleep(5)
+        print("Resuming...")
+
+    def create_crawler():
+        crawler_strategy = LocalSeleniumCrawlerStrategy(verbose=True)
+        crawler_strategy.set_hook("after_get_url", delay)
+        crawler = WebCrawler(verbose=True, crawler_strategy=crawler_strategy)
+        crawler.warmup()
+        return crawler
+
+    cprint(
+        "\n🔗 [bold cyan]Using Crawler Hooks: Let's add a delay after fetching the url to make sure entire page is fetched.[/bold cyan]"
+    )
+    crawler = create_crawler()
+    result = crawler.run(url="https://google.com", bypass_cache=True)
+
+    cprint("[LOG] 📦 [bold yellow]Crawler Hooks result:[/bold yellow]")
+    print_result(result)
+
+
+def main():
+    cprint(
+        "🌟 [bold green]Welcome to the Crawl4ai Quickstart Guide! Let's dive into some web crawling fun! 🌐[/bold green]"
+    )
+    cprint(
+        "⛳️ [bold cyan]First Step: Create an instance of WebCrawler and call the `warmup()` function.[/bold cyan]"
+    )
+    cprint(
+        "If this is the first time you're running Crawl4ai, this might take a few seconds to load required model files."
+    )
+
+    crawler = create_crawler()
+
+    crawler.always_by_pass_cache = True
+    basic_usage(crawler)
+    # basic_usage_some_params(crawler)
+    understanding_parameters(crawler)
+
+    crawler.always_by_pass_cache = True
+    screenshot_usage(crawler)
+    add_chunking_strategy(crawler)
+    add_extraction_strategy(crawler)
+    add_llm_extraction_strategy(crawler)
+    targeted_extraction(crawler)
+    interactive_extraction(crawler)
+    multiple_scrip(crawler)
+
+    cprint(
+        "\n🎉 [bold green]Congratulations! You've made it through the Crawl4ai Quickstart Guide! Now go forth and crawl the web like a pro! 🕸️[/bold green]"
+    )
+
+
+if __name__ == "__main__":
+    main()

docs/examples/quickstart_v0.ipynb

@@ -0,0 +1,735 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6yLvrXn7yZQI"
+      },
+      "source": [
+        "# Crawl4AI: Advanced Web Crawling and Data Extraction\n",
+        "\n",
+        "Welcome to this interactive notebook showcasing Crawl4AI, an advanced asynchronous web crawling and data extraction library.\n",
+        "\n",
+        "- GitHub Repository: [https://github.com/unclecode/crawl4ai](https://github.com/unclecode/crawl4ai)\n",
+        "- Twitter: [@unclecode](https://twitter.com/unclecode)\n",
+        "- Website: [https://crawl4ai.com](https://crawl4ai.com)\n",
+        "\n",
+        "Let's explore the powerful features of Crawl4AI!"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "KIn_9nxFyZQK"
+      },
+      "source": [
+        "## Installation\n",
+        "\n",
+        "First, let's install Crawl4AI from GitHub:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "mSnaxLf3zMog"
+      },
+      "outputs": [],
+      "source": [
+        "!sudo apt-get update && sudo apt-get install -y libwoff1 libopus0 libwebp6 libwebpdemux2 libenchant1c2a libgudev-1.0-0 libsecret-1-0 libhyphen0 libgdk-pixbuf2.0-0 libegl1 libnotify4 libxslt1.1 libevent-2.1-7 libgles2 libvpx6 libxcomposite1 libatk1.0-0 libatk-bridge2.0-0 libepoxy0 libgtk-3-0 libharfbuzz-icu0"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "xlXqaRtayZQK"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install crawl4ai\n",
+        "!pip install nest-asyncio\n",
+        "!playwright install"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "qKCE7TI7yZQL"
+      },
+      "source": [
+        "Now, let's import the necessary libraries:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "id": "I67tr7aAyZQL"
+      },
+      "outputs": [],
+      "source": [
+        "import asyncio\n",
+        "import nest_asyncio\n",
+        "from crawl4ai import AsyncWebCrawler\n",
+        "from crawl4ai.extraction_strategy import JsonCssExtractionStrategy, LLMExtractionStrategy\n",
+        "import json\n",
+        "import time\n",
+        "from pydantic import BaseModel, Field\n",
+        "\n",
+        "nest_asyncio.apply()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "h7yR_Rt_yZQM"
+      },
+      "source": [
+        "## Basic Usage\n",
+        "\n",
+        "Let's start with a simple crawl example:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "yBh6hf4WyZQM",
+        "outputId": "0f83af5c-abba-4175-ed95-70b7512e6bcc"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "[LOG] 🌤️  Warming up the AsyncWebCrawler\n",
+            "[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
+            "[LOG] 🚀 Content extracted for https://www.nbcnews.com/business, success: True, time taken: 0.05 seconds\n",
+            "[LOG] 🚀 Extraction done for https://www.nbcnews.com/business, time taken: 0.05 seconds.\n",
+            "18102\n"
+          ]
+        }
+      ],
+      "source": [
+        "async def simple_crawl():\n",
+        "    async with AsyncWebCrawler(verbose=True) as crawler:\n",
+        "        result = await crawler.arun(url=\"https://www.nbcnews.com/business\")\n",
+        "        print(len(result.markdown))\n",
+        "await simple_crawl()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9rtkgHI28uI4"
+      },
+      "source": [
+        "💡 By default, **Crawl4AI** caches the result of every URL, so the next time you call it, you’ll get an instant result. But if you want to bypass the cache, just set `bypass_cache=True`."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "MzZ0zlJ9yZQM"
+      },
+      "source": [
+        "## Advanced Features\n",
+        "\n",
+        "### Executing JavaScript and Using CSS Selectors"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "gHStF86xyZQM",
+        "outputId": "34d0fb6d-4dec-4677-f76e-85a1f082829b"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "[LOG] 🌤️  Warming up the AsyncWebCrawler\n",
+            "[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
+            "[LOG] 🕸️ Crawling https://www.nbcnews.com/business using AsyncPlaywrightCrawlerStrategy...\n",
+            "[LOG] ✅ Crawled https://www.nbcnews.com/business successfully!\n",
+            "[LOG] 🚀 Crawling done for https://www.nbcnews.com/business, success: True, time taken: 6.06 seconds\n",
+            "[LOG] 🚀 Content extracted for https://www.nbcnews.com/business, success: True, time taken: 0.10 seconds\n",
+            "[LOG] 🔥 Extracting semantic blocks for https://www.nbcnews.com/business, Strategy: AsyncWebCrawler\n",
+            "[LOG] 🚀 Extraction done for https://www.nbcnews.com/business, time taken: 0.11 seconds.\n",
+            "41135\n"
+          ]
+        }
+      ],
+      "source": [
+        "async def js_and_css():\n",
+        "    async with AsyncWebCrawler(verbose=True) as crawler:\n",
+        "        js_code = [\"const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();\"]\n",
+        "        result = await crawler.arun(\n",
+        "            url=\"https://www.nbcnews.com/business\",\n",
+        "            js_code=js_code,\n",
+        "            # css_selector=\"YOUR_CSS_SELECTOR_HERE\",\n",
+        "            bypass_cache=True\n",
+        "        )\n",
+        "        print(len(result.markdown))\n",
+        "\n",
+        "await js_and_css()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cqE_W4coyZQM"
+      },
+      "source": [
+        "### Using a Proxy\n",
+        "\n",
+        "Note: You'll need to replace the proxy URL with a working proxy for this example to run successfully."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "QjAyiAGqyZQM"
+      },
+      "outputs": [],
+      "source": [
+        "async def use_proxy():\n",
+        "    async with AsyncWebCrawler(verbose=True, proxy=\"http://your-proxy-url:port\") as crawler:\n",
+        "        result = await crawler.arun(\n",
+        "            url=\"https://www.nbcnews.com/business\",\n",
+        "            bypass_cache=True\n",
+        "        )\n",
+        "        print(result.markdown[:500])  # Print first 500 characters\n",
+        "\n",
+        "# Uncomment the following line to run the proxy example\n",
+        "# await use_proxy()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "XTZ88lbayZQN"
+      },
+      "source": [
+        "### Extracting Structured Data with OpenAI\n",
+        "\n",
+        "Note: You'll need to set your OpenAI API key as an environment variable for this example to work."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 14,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "fIOlDayYyZQN",
+        "outputId": "cb8359cc-dee0-4762-9698-5dfdcee055b8"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "[LOG] 🌤️  Warming up the AsyncWebCrawler\n",
+            "[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
+            "[LOG] 🕸️ Crawling https://openai.com/api/pricing/ using AsyncPlaywrightCrawlerStrategy...\n",
+            "[LOG] ✅ Crawled https://openai.com/api/pricing/ successfully!\n",
+            "[LOG] 🚀 Crawling done for https://openai.com/api/pricing/, success: True, time taken: 3.77 seconds\n",
+            "[LOG] 🚀 Content extracted for https://openai.com/api/pricing/, success: True, time taken: 0.21 seconds\n",
+            "[LOG] 🔥 Extracting semantic blocks for https://openai.com/api/pricing/, Strategy: AsyncWebCrawler\n",
+            "[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 0\n",
+            "[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 1\n",
+            "[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 2\n",
+            "[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 3\n",
+            "[LOG] Extracted 4 blocks from URL: https://openai.com/api/pricing/ block index: 3\n",
+            "[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 4\n",
+            "[LOG] Extracted 5 blocks from URL: https://openai.com/api/pricing/ block index: 0\n",
+            "[LOG] Extracted 1 blocks from URL: https://openai.com/api/pricing/ block index: 4\n",
+            "[LOG] Extracted 8 blocks from URL: https://openai.com/api/pricing/ block index: 1\n",
+            "[LOG] Extracted 12 blocks from URL: https://openai.com/api/pricing/ block index: 2\n",
+            "[LOG] 🚀 Extraction done for https://openai.com/api/pricing/, time taken: 8.55 seconds.\n",
+            "5029\n"
+          ]
+        }
+      ],
+      "source": [
+        "import os\n",
+        "from google.colab import userdata\n",
+        "os.environ['OPENAI_API_KEY'] = userdata.get('OPENAI_API_KEY')\n",
+        "\n",
+        "class OpenAIModelFee(BaseModel):\n",
+        "    model_name: str = Field(..., description=\"Name of the OpenAI model.\")\n",
+        "    input_fee: str = Field(..., description=\"Fee for input token for the OpenAI model.\")\n",
+        "    output_fee: str = Field(..., description=\"Fee for output token for the OpenAI model.\")\n",
+        "\n",
+        "async def extract_openai_fees():\n",
+        "    async with AsyncWebCrawler(verbose=True) as crawler:\n",
+        "        result = await crawler.arun(\n",
+        "            url='https://openai.com/api/pricing/',\n",
+        "            word_count_threshold=1,\n",
+        "            extraction_strategy=LLMExtractionStrategy(\n",
+        "                provider=\"openai/gpt-4o\", api_token=os.getenv('OPENAI_API_KEY'),\n",
+        "                schema=OpenAIModelFee.schema(),\n",
+        "                extraction_type=\"schema\",\n",
+        "                instruction=\"\"\"From the crawled content, extract all mentioned model names along with their fees for input and output tokens.\n",
+        "                Do not miss any models in the entire content. One extracted model JSON format should look like this:\n",
+        "                {\"model_name\": \"GPT-4\", \"input_fee\": \"US$10.00 / 1M tokens\", \"output_fee\": \"US$30.00 / 1M tokens\"}.\"\"\"\n",
+        "            ),\n",
+        "            bypass_cache=True,\n",
+        "        )\n",
+        "        print(len(result.extracted_content))\n",
+        "\n",
+        "# Uncomment the following line to run the OpenAI extraction example\n",
+        "await extract_openai_fees()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BypA5YxEyZQN"
+      },
+      "source": [
+        "### Advanced Multi-Page Crawling with JavaScript Execution"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tfkcVQ0b7mw-"
+      },
+      "source": [
+        "## Advanced Multi-Page Crawling with JavaScript Execution\n",
+        "\n",
+        "This example demonstrates Crawl4AI's ability to handle complex crawling scenarios, specifically extracting commits from multiple pages of a GitHub repository. The challenge here is that clicking the \"Next\" button doesn't load a new page, but instead uses asynchronous JavaScript to update the content. This is a common hurdle in modern web crawling.\n",
+        "\n",
+        "To overcome this, we use Crawl4AI's custom JavaScript execution to simulate clicking the \"Next\" button, and implement a custom hook to detect when new data has loaded. Our strategy involves comparing the first commit's text before and after \"clicking\" Next, waiting until it changes to confirm new data has rendered. This showcases Crawl4AI's flexibility in handling dynamic content and its ability to implement custom logic for even the most challenging crawling tasks."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 11,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "qUBKGpn3yZQN",
+        "outputId": "3e555b6a-ed33-42f4-cce9-499a923fbe17"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "[LOG] 🌤️  Warming up the AsyncWebCrawler\n",
+            "[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
+            "[LOG] 🕸️ Crawling https://github.com/microsoft/TypeScript/commits/main using AsyncPlaywrightCrawlerStrategy...\n",
+            "[LOG] ✅ Crawled https://github.com/microsoft/TypeScript/commits/main successfully!\n",
+            "[LOG] 🚀 Crawling done for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 5.16 seconds\n",
+            "[LOG] 🚀 Content extracted for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.28 seconds\n",
+            "[LOG] 🔥 Extracting semantic blocks for https://github.com/microsoft/TypeScript/commits/main, Strategy: AsyncWebCrawler\n",
+            "[LOG] 🚀 Extraction done for https://github.com/microsoft/TypeScript/commits/main, time taken: 0.28 seconds.\n",
+            "Page 1: Found 35 commits\n",
+            "[LOG] 🕸️ Crawling https://github.com/microsoft/TypeScript/commits/main using AsyncPlaywrightCrawlerStrategy...\n",
+            "[LOG] ✅ Crawled https://github.com/microsoft/TypeScript/commits/main successfully!\n",
+            "[LOG] 🚀 Crawling done for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.78 seconds\n",
+            "[LOG] 🚀 Content extracted for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.90 seconds\n",
+            "[LOG] 🔥 Extracting semantic blocks for https://github.com/microsoft/TypeScript/commits/main, Strategy: AsyncWebCrawler\n",
+            "[LOG] 🚀 Extraction done for https://github.com/microsoft/TypeScript/commits/main, time taken: 0.90 seconds.\n",
+            "Page 2: Found 35 commits\n",
+            "[LOG] 🕸️ Crawling https://github.com/microsoft/TypeScript/commits/main using AsyncPlaywrightCrawlerStrategy...\n",
+            "[LOG] ✅ Crawled https://github.com/microsoft/TypeScript/commits/main successfully!\n",
+            "[LOG] 🚀 Crawling done for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 2.00 seconds\n",
+            "[LOG] 🚀 Content extracted for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.74 seconds\n",
+            "[LOG] 🔥 Extracting semantic blocks for https://github.com/microsoft/TypeScript/commits/main, Strategy: AsyncWebCrawler\n",
+            "[LOG] 🚀 Extraction done for https://github.com/microsoft/TypeScript/commits/main, time taken: 0.75 seconds.\n",
+            "Page 3: Found 35 commits\n",
+            "Successfully crawled 105 commits across 3 pages\n"
+          ]
+        }
+      ],
+      "source": [
+        "import re\n",
+        "from bs4 import BeautifulSoup\n",
+        "\n",
+        "async def crawl_typescript_commits():\n",
+        "    first_commit = \"\"\n",
+        "    async def on_execution_started(page):\n",
+        "        nonlocal first_commit\n",
+        "        try:\n",
+        "            while True:\n",
+        "                await page.wait_for_selector('li.Box-sc-g0xbh4-0 h4')\n",
+        "                commit = await page.query_selector('li.Box-sc-g0xbh4-0 h4')\n",
+        "                commit = await commit.evaluate('(element) => element.textContent')\n",
+        "                commit = re.sub(r'\\s+', '', commit)\n",
+        "                if commit and commit != first_commit:\n",
+        "                    first_commit = commit\n",
+        "                    break\n",
+        "                await asyncio.sleep(0.5)\n",
+        "        except Exception as e:\n",
+        "            print(f\"Warning: New content didn't appear after JavaScript execution: {e}\")\n",
+        "\n",
+        "    async with AsyncWebCrawler(verbose=True) as crawler:\n",
+        "        crawler.crawler_strategy.set_hook('on_execution_started', on_execution_started)\n",
+        "\n",
+        "        url = \"https://github.com/microsoft/TypeScript/commits/main\"\n",
+        "        session_id = \"typescript_commits_session\"\n",
+        "        all_commits = []\n",
+        "\n",
+        "        js_next_page = \"\"\"\n",
+        "        const button = document.querySelector('a[data-testid=\"pagination-next-button\"]');\n",
+        "        if (button) button.click();\n",
+        "        \"\"\"\n",
+        "\n",
+        "        for page in range(3):  # Crawl 3 pages\n",
+        "            result = await crawler.arun(\n",
+        "                url=url,\n",
+        "                session_id=session_id,\n",
+        "                css_selector=\"li.Box-sc-g0xbh4-0\",\n",
+        "                js=js_next_page if page > 0 else None,\n",
+        "                bypass_cache=True,\n",
+        "                js_only=page > 0\n",
+        "            )\n",
+        "\n",
+        "            assert result.success, f\"Failed to crawl page {page + 1}\"\n",
+        "\n",
+        "            soup = BeautifulSoup(result.cleaned_html, 'html.parser')\n",
+        "            commits = soup.select(\"li\")\n",
+        "            all_commits.extend(commits)\n",
+        "\n",
+        "            print(f\"Page {page + 1}: Found {len(commits)} commits\")\n",
+        "\n",
+        "        await crawler.crawler_strategy.kill_session(session_id)\n",
+        "        print(f\"Successfully crawled {len(all_commits)} commits across 3 pages\")\n",
+        "\n",
+        "await crawl_typescript_commits()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "EJRnYsp6yZQN"
+      },
+      "source": [
+        "### Using JsonCssExtractionStrategy for Fast Structured Output"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1ZMqIzB_8SYp"
+      },
+      "source": [
+        "The JsonCssExtractionStrategy is a powerful feature of Crawl4AI that allows for precise, structured data extraction from web pages. Here's how it works:\n",
+        "\n",
+        "1. You define a schema that describes the pattern of data you're interested in extracting.\n",
+        "2. The schema includes a base selector that identifies repeating elements on the page.\n",
+        "3. Within the schema, you define fields, each with its own selector and type.\n",
+        "4. These field selectors are applied within the context of each base selector element.\n",
+        "5. The strategy supports nested structures, lists within lists, and various data types.\n",
+        "6. You can even include computed fields for more complex data manipulation.\n",
+        "\n",
+        "This approach allows for highly flexible and precise data extraction, transforming semi-structured web content into clean, structured JSON data. It's particularly useful for extracting consistent data patterns from pages like product listings, news articles, or search results.\n",
+        "\n",
+        "For more details and advanced usage, check out the full documentation on the Crawl4AI website."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 12,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "trCMR2T9yZQN",
+        "outputId": "718d36f4-cccf-40f4-8d8c-c3ba73524d16"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "[LOG] 🌤️  Warming up the AsyncWebCrawler\n",
+            "[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
+            "[LOG] 🕸️ Crawling https://www.nbcnews.com/business using AsyncPlaywrightCrawlerStrategy...\n",
+            "[LOG] ✅ Crawled https://www.nbcnews.com/business successfully!\n",
+            "[LOG] 🚀 Crawling done for https://www.nbcnews.com/business, success: True, time taken: 7.00 seconds\n",
+            "[LOG] 🚀 Content extracted for https://www.nbcnews.com/business, success: True, time taken: 0.32 seconds\n",
+            "[LOG] 🔥 Extracting semantic blocks for https://www.nbcnews.com/business, Strategy: AsyncWebCrawler\n",
+            "[LOG] 🚀 Extraction done for https://www.nbcnews.com/business, time taken: 0.48 seconds.\n",
+            "Successfully extracted 11 news teasers\n",
+            "{\n",
+            "  \"category\": \"Business News\",\n",
+            "  \"headline\": \"NBC ripped up its Olympics playbook for 2024 \\u2014 so far, the new strategy paid off\",\n",
+            "  \"summary\": \"The Olympics have long been key to NBCUniversal. Paris marked the 18th Olympic Games broadcast by NBC in the U.S.\",\n",
+            "  \"time\": \"13h ago\",\n",
+            "  \"image\": {\n",
+            "    \"src\": \"https://media-cldnry.s-nbcnews.com/image/upload/t_focal-200x100,f_auto,q_auto:best/rockcms/2024-09/240903-nbc-olympics-ch-1344-c7a486.jpg\",\n",
+            "    \"alt\": \"Mike Tirico.\"\n",
+            "  },\n",
+            "  \"link\": \"https://www.nbcnews.com/business\"\n",
+            "}\n"
+          ]
+        }
+      ],
+      "source": [
+        "async def extract_news_teasers():\n",
+        "    schema = {\n",
+        "        \"name\": \"News Teaser Extractor\",\n",
+        "        \"baseSelector\": \".wide-tease-item__wrapper\",\n",
+        "        \"fields\": [\n",
+        "            {\n",
+        "                \"name\": \"category\",\n",
+        "                \"selector\": \".unibrow span[data-testid='unibrow-text']\",\n",
+        "                \"type\": \"text\",\n",
+        "            },\n",
+        "            {\n",
+        "                \"name\": \"headline\",\n",
+        "                \"selector\": \".wide-tease-item__headline\",\n",
+        "                \"type\": \"text\",\n",
+        "            },\n",
+        "            {\n",
+        "                \"name\": \"summary\",\n",
+        "                \"selector\": \".wide-tease-item__description\",\n",
+        "                \"type\": \"text\",\n",
+        "            },\n",
+        "            {\n",
+        "                \"name\": \"time\",\n",
+        "                \"selector\": \"[data-testid='wide-tease-date']\",\n",
+        "                \"type\": \"text\",\n",
+        "            },\n",
+        "            {\n",
+        "                \"name\": \"image\",\n",
+        "                \"type\": \"nested\",\n",
+        "                \"selector\": \"picture.teasePicture img\",\n",
+        "                \"fields\": [\n",
+        "                    {\"name\": \"src\", \"type\": \"attribute\", \"attribute\": \"src\"},\n",
+        "                    {\"name\": \"alt\", \"type\": \"attribute\", \"attribute\": \"alt\"},\n",
+        "                ],\n",
+        "            },\n",
+        "            {\n",
+        "                \"name\": \"link\",\n",
+        "                \"selector\": \"a[href]\",\n",
+        "                \"type\": \"attribute\",\n",
+        "                \"attribute\": \"href\",\n",
+        "            },\n",
+        "        ],\n",
+        "    }\n",
+        "\n",
+        "    extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)\n",
+        "\n",
+        "    async with AsyncWebCrawler(verbose=True) as crawler:\n",
+        "        result = await crawler.arun(\n",
+        "            url=\"https://www.nbcnews.com/business\",\n",
+        "            extraction_strategy=extraction_strategy,\n",
+        "            bypass_cache=True,\n",
+        "        )\n",
+        "\n",
+        "        assert result.success, \"Failed to crawl the page\"\n",
+        "\n",
+        "        news_teasers = json.loads(result.extracted_content)\n",
+        "        print(f\"Successfully extracted {len(news_teasers)} news teasers\")\n",
+        "        print(json.dumps(news_teasers[0], indent=2))\n",
+        "\n",
+        "await extract_news_teasers()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "FnyVhJaByZQN"
+      },
+      "source": [
+        "## Speed Comparison\n",
+        "\n",
+        "Let's compare the speed of Crawl4AI with Firecrawl, a paid service. Note that we can't run Firecrawl in this Colab environment, so we'll simulate its performance based on previously recorded data."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "agDD186f3wig"
+      },
+      "source": [
+        "💡 **Note on Speed Comparison:**\n",
+        "\n",
+        "The speed test conducted here is running on Google Colab, where the internet speed and performance can vary and may not reflect optimal conditions. When we call Firecrawl's API, we're seeing its best performance, while Crawl4AI's performance is limited by Colab's network speed.\n",
+        "\n",
+        "For a more accurate comparison, it's recommended to run these tests on your own servers or computers with a stable and fast internet connection. Despite these limitations, Crawl4AI still demonstrates faster performance in this environment.\n",
+        "\n",
+        "If you run these tests locally, you may observe an even more significant speed advantage for Crawl4AI compared to other services."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "F7KwHv8G1LbY"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install firecrawl"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "91813zILyZQN",
+        "outputId": "663223db-ab89-4976-b233-05ceca62b19b"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Firecrawl (simulated):\n",
+            "Time taken: 4.38 seconds\n",
+            "Content length: 41967 characters\n",
+            "Images found: 49\n",
+            "\n",
+            "Crawl4AI (simple crawl):\n",
+            "Time taken: 4.22 seconds\n",
+            "Content length: 18221 characters\n",
+            "Images found: 49\n",
+            "\n",
+            "Crawl4AI (with JavaScript execution):\n",
+            "Time taken: 9.13 seconds\n",
+            "Content length: 34243 characters\n",
+            "Images found: 89\n"
+          ]
+        }
+      ],
+      "source": [
+        "import os\n",
+        "from google.colab import userdata\n",
+        "os.environ['FIRECRAWL_API_KEY'] = userdata.get('FIRECRAWL_API_KEY')\n",
+        "import time\n",
+        "from firecrawl import FirecrawlApp\n",
+        "\n",
+        "async def speed_comparison():\n",
+        "    # Simulated Firecrawl performance\n",
+        "    app = FirecrawlApp(api_key=os.environ['FIRECRAWL_API_KEY'])\n",
+        "    start = time.time()\n",
+        "    scrape_status = app.scrape_url(\n",
+        "    'https://www.nbcnews.com/business',\n",
+        "    params={'formats': ['markdown', 'html']}\n",
+        "    )\n",
+        "    end = time.time()\n",
+        "    print(\"Firecrawl (simulated):\")\n",
+        "    print(f\"Time taken: {end - start:.2f} seconds\")\n",
+        "    print(f\"Content length: {len(scrape_status['markdown'])} characters\")\n",
+        "    print(f\"Images found: {scrape_status['markdown'].count('cldnry.s-nbcnews.com')}\")\n",
+        "    print()\n",
+        "\n",
+        "    async with AsyncWebCrawler() as crawler:\n",
+        "        # Crawl4AI simple crawl\n",
+        "        start = time.time()\n",
+        "        result = await crawler.arun(\n",
+        "            url=\"https://www.nbcnews.com/business\",\n",
+        "            word_count_threshold=0,\n",
+        "            bypass_cache=True,\n",
+        "            verbose=False\n",
+        "        )\n",
+        "        end = time.time()\n",
+        "        print(\"Crawl4AI (simple crawl):\")\n",
+        "        print(f\"Time taken: {end - start:.2f} seconds\")\n",
+        "        print(f\"Content length: {len(result.markdown)} characters\")\n",
+        "        print(f\"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}\")\n",
+        "        print()\n",
+        "\n",
+        "        # Crawl4AI with JavaScript execution\n",
+        "        start = time.time()\n",
+        "        result = await crawler.arun(\n",
+        "            url=\"https://www.nbcnews.com/business\",\n",
+        "            js_code=[\"const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();\"],\n",
+        "            word_count_threshold=0,\n",
+        "            bypass_cache=True,\n",
+        "            verbose=False\n",
+        "        )\n",
+        "        end = time.time()\n",
+        "        print(\"Crawl4AI (with JavaScript execution):\")\n",
+        "        print(f\"Time taken: {end - start:.2f} seconds\")\n",
+        "        print(f\"Content length: {len(result.markdown)} characters\")\n",
+        "        print(f\"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}\")\n",
+        "\n",
+        "await speed_comparison()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "OBFFYVJIyZQN"
+      },
+      "source": [
+        "If you run on a local machine with a proper internet speed:\n",
+        "- Simple crawl: Crawl4AI is typically over 3-4 times faster than Firecrawl.\n",
+        "- With JavaScript execution: Even when executing JavaScript to load more content (potentially doubling the number of images found), Crawl4AI is still faster than Firecrawl's simple crawl.\n",
+        "\n",
+        "Please note that actual performance may vary depending on network conditions and the specific content being crawled."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "A6_1RK1_yZQO"
+      },
+      "source": [
+        "## Conclusion\n",
+        "\n",
+        "In this notebook, we've explored the powerful features of Crawl4AI, including:\n",
+        "\n",
+        "1. Basic crawling\n",
+        "2. JavaScript execution and CSS selector usage\n",
+        "3. Proxy support\n",
+        "4. Structured data extraction with OpenAI\n",
+        "5. Advanced multi-page crawling with JavaScript execution\n",
+        "6. Fast structured output using JsonCssExtractionStrategy\n",
+        "7. Speed comparison with other services\n",
+        "\n",
+        "Crawl4AI offers a fast, flexible, and powerful solution for web crawling and data extraction tasks. Its asynchronous architecture and advanced features make it suitable for a wide range of applications, from simple web scraping to complex, multi-page data extraction scenarios.\n",
+        "\n",
+        "For more information and advanced usage, please visit the [Crawl4AI documentation](https://docs.crawl4ai.com/).\n",
+        "\n",
+        "Happy crawling!"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "venv",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.10.13"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

docs/md_v2/advanced/network-console-capture.md

@@ -1,205 +0,0 @@
-# Network Requests & Console Message Capturing
-
-Crawl4AI can capture all network requests and browser console messages during a crawl, which is invaluable for debugging, security analysis, or understanding page behavior.
-
-## Configuration
-
-To enable network and console capturing, use these configuration options:
-
-```python
-from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
-
-# Enable both network request capture and console message capture
-config = CrawlerRunConfig(
-    capture_network_requests=True,  # Capture all network requests and responses
-    capture_console_messages=True   # Capture all browser console output
-)
-```
-
-## Example Usage
-
-```python
-import asyncio
-import json
-from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
-
-async def main():
-    # Enable both network request capture and console message capture
-    config = CrawlerRunConfig(
-        capture_network_requests=True,
-        capture_console_messages=True
-    )
-    
-    async with AsyncWebCrawler() as crawler:
-        result = await crawler.arun(
-            url="https://example.com",
-            config=config
-        )
-        
-        if result.success:
-            # Analyze network requests
-            if result.network_requests:
-                print(f"Captured {len(result.network_requests)} network events")
-                
-                # Count request types
-                request_count = len([r for r in result.network_requests if r.get("event_type") == "request"])
-                response_count = len([r for r in result.network_requests if r.get("event_type") == "response"])
-                failed_count = len([r for r in result.network_requests if r.get("event_type") == "request_failed"])
-                
-                print(f"Requests: {request_count}, Responses: {response_count}, Failed: {failed_count}")
-                
-                # Find API calls
-                api_calls = [r for r in result.network_requests 
-                            if r.get("event_type") == "request" and "api" in r.get("url", "")]
-                if api_calls:
-                    print(f"Detected {len(api_calls)} API calls:")
-                    for call in api_calls[:3]:  # Show first 3
-                        print(f"  - {call.get('method')} {call.get('url')}")
-            
-            # Analyze console messages
-            if result.console_messages:
-                print(f"Captured {len(result.console_messages)} console messages")
-                
-                # Group by type
-                message_types = {}
-                for msg in result.console_messages:
-                    msg_type = msg.get("type", "unknown")
-                    message_types[msg_type] = message_types.get(msg_type, 0) + 1
-                
-                print("Message types:", message_types)
-                
-                # Show errors (often the most important)
-                errors = [msg for msg in result.console_messages if msg.get("type") == "error"]
-                if errors:
-                    print(f"Found {len(errors)} console errors:")
-                    for err in errors[:2]:  # Show first 2
-                        print(f"  - {err.get('text', '')[:100]}")
-            
-            # Export all captured data to a file for detailed analysis
-            with open("network_capture.json", "w") as f:
-                json.dump({
-                    "url": result.url,
-                    "network_requests": result.network_requests or [],
-                    "console_messages": result.console_messages or []
-                }, f, indent=2)
-            
-            print("Exported detailed capture data to network_capture.json")
-
-if __name__ == "__main__":
-    asyncio.run(main())
-```
-
-## Captured Data Structure
-
-### Network Requests
-
-The `result.network_requests` contains a list of dictionaries, each representing a network event with these common fields:
-
-| Field | Description |
-|-------|-------------|
-| `event_type` | Type of event: `"request"`, `"response"`, or `"request_failed"` |
-| `url` | The URL of the request |
-| `timestamp` | Unix timestamp when the event was captured |
-
-#### Request Event Fields
-
-```json
-{
-  "event_type": "request",
-  "url": "https://example.com/api/data.json",
-  "method": "GET",
-  "headers": {"User-Agent": "...", "Accept": "..."},
-  "post_data": "key=value&otherkey=value",
-  "resource_type": "fetch",
-  "is_navigation_request": false,
-  "timestamp": 1633456789.123
-}
-```
-
-#### Response Event Fields
-
-```json
-{
-  "event_type": "response",
-  "url": "https://example.com/api/data.json",
-  "status": 200,
-  "status_text": "OK",
-  "headers": {"Content-Type": "application/json", "Cache-Control": "..."},
-  "from_service_worker": false,
-  "request_timing": {"requestTime": 1234.56, "receiveHeadersEnd": 1234.78},
-  "timestamp": 1633456789.456
-}
-```
-
-#### Failed Request Event Fields
-
-```json
-{
-  "event_type": "request_failed",
-  "url": "https://example.com/missing.png",
-  "method": "GET",
-  "resource_type": "image",
-  "failure_text": "net::ERR_ABORTED 404",
-  "timestamp": 1633456789.789
-}
-```
-
-### Console Messages
-
-The `result.console_messages` contains a list of dictionaries, each representing a console message with these common fields:
-
-| Field | Description |
-|-------|-------------|
-| `type` | Message type: `"log"`, `"error"`, `"warning"`, `"info"`, etc. |
-| `text` | The message text |
-| `timestamp` | Unix timestamp when the message was captured |
-
-#### Console Message Example
-
-```json
-{
-  "type": "error",
-  "text": "Uncaught TypeError: Cannot read property 'length' of undefined",
-  "location": "https://example.com/script.js:123:45",
-  "timestamp": 1633456790.123
-}
-```
-
-## Key Benefits
-
-- **Full Request Visibility**: Capture all network activity including:
-  - Requests (URLs, methods, headers, post data)
-  - Responses (status codes, headers, timing)
-  - Failed requests (with error messages)
-  
-- **Console Message Access**: View all JavaScript console output:
-  - Log messages
-  - Warnings
-  - Errors with stack traces
-  - Developer debugging information
-
-- **Debugging Power**: Identify issues such as:
-  - Failed API calls or resource loading
-  - JavaScript errors affecting page functionality
-  - CORS or other security issues
-  - Hidden API endpoints and data flows
-
-- **Security Analysis**: Detect:
-  - Unexpected third-party requests
-  - Data leakage in request payloads
-  - Suspicious script behavior
-
-- **Performance Insights**: Analyze:
-  - Request timing data
-  - Resource loading patterns
-  - Potential bottlenecks
-
-## Use Cases
-
-1. **API Discovery**: Identify hidden endpoints and data flows in single-page applications
-2. **Debugging**: Track down JavaScript errors affecting page functionality
-3. **Security Auditing**: Detect unwanted third-party requests or data leakage
-4. **Performance Analysis**: Identify slow-loading resources
-5. **Ad/Tracker Analysis**: Detect and catalog advertising or tracking calls
-
-This capability is especially valuable for complex sites with heavy JavaScript, single-page applications, or when you need to understand the exact communication happening between a browser and servers.

docs/md_v2/api/crawl-result.md

@@ -15,7 +15,6 @@ class CrawlResult(BaseModel):
     downloaded_files: Optional[List[str]] = None
     screenshot: Optional[str] = None
     pdf : Optional[bytes] = None
-    mhtml: Optional[str] = None
     markdown: Optional[Union[str, MarkdownGenerationResult]] = None
     extracted_content: Optional[str] = None
     metadata: Optional[dict] = None
@@ -237,16 +236,7 @@ if result.pdf:
         f.write(result.pdf)
 ```
 
-### 5.5 **`mhtml`** *(Optional[str])*  
+### 5.5 **`metadata`** *(Optional[dict])*  
-**What**: MHTML snapshot of the page if `capture_mhtml=True` in `CrawlerRunConfig`. MHTML (MIME HTML) format preserves the entire web page with all its resources (CSS, images, scripts, etc.) in a single file.  
-**Usage**:
-```python
-if result.mhtml:
-    with open("page.mhtml", "w", encoding="utf-8") as f:
-        f.write(result.mhtml)
-```
-
-### 5.6 **`metadata`** *(Optional[dict])*  
 **What**: Page-level metadata if discovered (title, description, OG data, etc.).  
 **Usage**:
 ```python
@@ -281,69 +271,7 @@ for result in results:
 
 ---
 
-## 7. Network Requests & Console Messages
+## 7. Example: Accessing Everything
-
-When you enable network and console message capturing in `CrawlerRunConfig` using `capture_network_requests=True` and `capture_console_messages=True`, the `CrawlResult` will include these fields:
-
-### 7.1 **`network_requests`** *(Optional[List[Dict[str, Any]]])*
-**What**: A list of dictionaries containing information about all network requests, responses, and failures captured during the crawl.
-**Structure**:
-- Each item has an `event_type` field that can be `"request"`, `"response"`, or `"request_failed"`.
-- Request events include `url`, `method`, `headers`, `post_data`, `resource_type`, and `is_navigation_request`.
-- Response events include `url`, `status`, `status_text`, `headers`, and `request_timing`.
-- Failed request events include `url`, `method`, `resource_type`, and `failure_text`.
-- All events include a `timestamp` field.
-
-**Usage**:
-```python
-if result.network_requests:
-    # Count different types of events
-    requests = [r for r in result.network_requests if r.get("event_type") == "request"]
-    responses = [r for r in result.network_requests if r.get("event_type") == "response"]
-    failures = [r for r in result.network_requests if r.get("event_type") == "request_failed"]
-    
-    print(f"Captured {len(requests)} requests, {len(responses)} responses, and {len(failures)} failures")
-    
-    # Analyze API calls
-    api_calls = [r for r in requests if "api" in r.get("url", "")]
-    
-    # Identify failed resources
-    for failure in failures:
-        print(f"Failed to load: {failure.get('url')} - {failure.get('failure_text')}")
-```
-
-### 7.2 **`console_messages`** *(Optional[List[Dict[str, Any]]])*
-**What**: A list of dictionaries containing all browser console messages captured during the crawl.
-**Structure**:
-- Each item has a `type` field indicating the message type (e.g., `"log"`, `"error"`, `"warning"`, etc.).
-- The `text` field contains the actual message text.
-- Some messages include `location` information (URL, line, column).
-- All messages include a `timestamp` field.
-
-**Usage**:
-```python
-if result.console_messages:
-    # Count messages by type
-    message_types = {}
-    for msg in result.console_messages:
-        msg_type = msg.get("type", "unknown")
-        message_types[msg_type] = message_types.get(msg_type, 0) + 1
-    
-    print(f"Message type counts: {message_types}")
-    
-    # Display errors (which are usually most important)
-    for msg in result.console_messages:
-        if msg.get("type") == "error":
-            print(f"Error: {msg.get('text')}")
-```
-
-These fields provide deep visibility into the page's network activity and browser console, which is invaluable for debugging, security analysis, and understanding complex web applications.
-
-For more details on network and console capturing, see the [Network & Console Capture documentation](../advanced/network-console-capture.md).
-
----
-
-## 8. Example: Accessing Everything
 
 ```python
 async def handle_result(result: CrawlResult):
@@ -376,36 +304,16 @@ async def handle_result(result: CrawlResult):
     if result.extracted_content:
         print("Structured data:", result.extracted_content)
     
-    # Screenshot/PDF/MHTML
+    # Screenshot/PDF
     if result.screenshot:
         print("Screenshot length:", len(result.screenshot))
     if result.pdf:
         print("PDF bytes length:", len(result.pdf))
-    if result.mhtml:
-        print("MHTML length:", len(result.mhtml))
-        
-    # Network and console capturing
-    if result.network_requests:
-        print(f"Network requests captured: {len(result.network_requests)}")
-        # Analyze request types
-        req_types = {}
-        for req in result.network_requests:
-            if "resource_type" in req:
-                req_types[req["resource_type"]] = req_types.get(req["resource_type"], 0) + 1
-        print(f"Resource types: {req_types}")
-        
-    if result.console_messages:
-        print(f"Console messages captured: {len(result.console_messages)}")
-        # Count by message type
-        msg_types = {}
-        for msg in result.console_messages:
-            msg_types[msg.get("type", "unknown")] = msg_types.get(msg.get("type", "unknown"), 0) + 1
-        print(f"Message types: {msg_types}")
 ```
 
 ---
 
-## 9. Key Points & Future
+## 8. Key Points & Future
 
 1. **Deprecated legacy properties of CrawlResult**  
    - `markdown_v2` - Deprecated in v0.5. Just use `markdown`. It holds the `MarkdownGenerationResult` now!

docs/md_v2/api/parameters.md

@@ -140,7 +140,6 @@ If your page is a single-page app with repeated JS updates, set `js_only=True` i
 | **`screenshot_wait_for`**                  | `float or None`     | Extra wait time before the screenshot.                                                                    |
 | **`screenshot_height_threshold`**          | `int` (~20000)      | If the page is taller than this, alternate screenshot strategies are used.                                |
 | **`pdf`**                                  | `bool` (False)      | If `True`, returns a PDF in `result.pdf`.                                                                 |
-| **`capture_mhtml`**                        | `bool` (False)      | If `True`, captures an MHTML snapshot of the page in `result.mhtml`. MHTML includes all page resources (CSS, images, etc.) in a single file. |
 | **`image_description_min_word_threshold`** | `int` (~50)         | Minimum words for an image’s alt text or description to be considered valid.                              |
 | **`image_score_threshold`**                | `int` (~3)          | Filter out low-scoring images. The crawler scores images by relevance (size, context, etc.).              |
 | **`exclude_external_images`**              | `bool` (False)      | Exclude images from other domains.                                                                        |

docs/md_v2/ask_ai/ask-ai.css

@@ -1,444 +0,0 @@
-/* ==== File: docs/ask_ai/ask_ai.css ==== */
-
-/* --- Basic Reset & Font --- */
-body {
-    /* Attempt to inherit variables from parent window (iframe context) */
-    /* Fallback values if variables are not inherited */
-    --fallback-bg: #070708;
-    --fallback-font: #e8e9ed;
-    --fallback-secondary: #a3abba;
-    --fallback-primary: #50ffff;
-    --fallback-primary-dimmed: #09b5a5;
-    --fallback-border: #1d1d20;
-    --fallback-code-bg: #1e1e1e;
-    --fallback-invert-font: #222225;
-    --font-stack: dm, Monaco, Courier New, monospace, serif;
-
-    font-family: var(--font-stack, "Courier New", monospace); /* Use theme font stack */
-    background-color: var(--background-color, var(--fallback-bg));
-    color: var(--font-color, var(--fallback-font));
-    margin: 0;
-    padding: 0;
-    font-size: 14px; /* Match global font size */
-    line-height: 1.5em; /* Match global line height */
-    height: 100vh; /* Ensure body takes full height */
-    overflow: hidden; /* Prevent body scrollbars, panels handle scroll */
-    display: flex; /* Use flex for the main container */
-}
-
-a {
-    color: var(--secondary-color, var(--fallback-secondary));
-    text-decoration: none;
-    transition: color 0.2s;
-}
-a:hover {
-    color: var(--primary-color, var(--fallback-primary));
-}
-
-/* --- Main Container Layout --- */
-.ai-assistant-container {
-    display: flex;
-    width: 100%;
-    height: 100%;
-    background-color: var(--background-color, var(--fallback-bg));
-}
-
-/* --- Sidebar Styling --- */
-.sidebar {
-    flex-shrink: 0; /* Prevent sidebars from shrinking */
-    height: 100%;
-    display: flex;
-    flex-direction: column;
-    /* background-color: var(--code-bg-color, var(--fallback-code-bg)); */
-    overflow-y: hidden; /* Header fixed, list scrolls */
-}
-
-.left-sidebar {
-    flex-basis: 240px; /* Width of history panel */
-    border-right: 1px solid var(--progress-bar-background, var(--fallback-border));
-}
-
-.right-sidebar {
-    flex-basis: 280px; /* Width of citations panel */
-    border-left: 1px solid var(--progress-bar-background, var(--fallback-border));
-}
-
-.sidebar header {
-    padding: 0.6em 1em;
-    border-bottom: 1px solid var(--progress-bar-background, var(--fallback-border));
-    flex-shrink: 0;
-    display: flex;
-    justify-content: space-between;
-    align-items: center;
-}
-
-.sidebar header h3 {
-    margin: 0;
-    font-size: 1.1em;
-    color: var(--font-color, var(--fallback-font));
-}
-
-.sidebar ul {
-    list-style: none;
-    padding: 0;
-    margin: 0;
-    overflow-y: auto; /* Enable scrolling for the list */
-    flex-grow: 1; /* Allow list to take remaining space */
-    padding: 0.5em 0;
-}
-
-.sidebar ul li {
-    padding: 0.3em 1em;
-}
-.sidebar ul li.no-citations,
-.sidebar ul li.no-history {
-    color: var(--secondary-color, var(--fallback-secondary));
-    font-style: italic;
-    font-size: 0.9em;
-    padding-left: 1em;
-}
-
-.sidebar ul li a {
-    color: var(--secondary-color, var(--fallback-secondary));
-    text-decoration: none;
-    display: block;
-    padding: 0.2em 0.5em;
-    border-radius: 3px;
-    transition: background-color 0.2s, color 0.2s;
-}
-
-.sidebar ul li a:hover {
-    color: var(--primary-color, var(--fallback-primary));
-    background-color: rgba(80, 255, 255, 0.08); /* Use primary color with alpha */
-}
-/* Style for active history item */
-#history-list li.active a {
-    color: var(--primary-dimmed-color, var(--fallback-primary-dimmed));
-    font-weight: bold;
-    background-color: rgba(80, 255, 255, 0.12);
-}
-
-/* --- Chat Panel Styling --- */
-#chat-panel {
-    flex-grow: 1; /* Take remaining space */
-    display: flex;
-    flex-direction: column;
-    height: 100%;
-    overflow: hidden; /* Prevent overflow, internal elements handle scroll */
-}
-
-#chat-messages {
-    flex-grow: 1;
-    overflow-y: auto; /* Scrollable chat history */
-    padding: 1em 1.5em;
-    border-bottom: 1px solid var(--progress-bar-background, var(--fallback-border));
-}
-
-.message {
-    margin-bottom: 1em;
-    padding: 0.8em 1.2em;
-    border-radius: 8px;
-    max-width: 90%; /* Slightly wider */
-    line-height: 1.6;
-    /* Apply pre-wrap for better handling of spaces/newlines AND wrapping */
-    white-space: pre-wrap;
-    word-wrap: break-word; /* Ensure long words break */
-}
-
-.user-message {
-    background-color: var(--progress-bar-background, var(--fallback-border)); /* User message background */
-    color: var(--font-color, var(--fallback-font));
-    margin-left: auto; /* Align user messages to the right */
-    text-align: left;
-}
-
-.ai-message {
-    background-color: var(--code-bg-color, var(--fallback-code-bg)); /* AI message background */
-    color: var(--font-color, var(--fallback-font));
-    margin-right: auto; /* Align AI messages to the left */
-    border: 1px solid var(--progress-bar-background, var(--fallback-border));
-}
-.ai-message.welcome-message {
-    border: none;
-    background-color: transparent;
-    max-width: 100%;
-    text-align: center;
-    color: var(--secondary-color, var(--fallback-secondary));
-    white-space: normal;
-}
-
-/* Styles for code within messages */
-.ai-message code {
-    background-color: var(--invert-font-color, var(--fallback-invert-font)) !important; /* Use light bg for code */
-    /* color: var(--background-color, var(--fallback-bg)) !important; Dark text */
-    padding: 0.1em 0.4em;
-    border-radius: 4px;
-    font-size: 0.9em;
-}
-.ai-message pre {
-    background-color: var(--invert-font-color, var(--fallback-invert-font)) !important;
-    color: var(--background-color, var(--fallback-bg)) !important;
-    padding: 1em;
-    border-radius: 5px;
-    overflow-x: auto;
-    margin: 0.8em 0;
-    white-space: pre;
-}
-.ai-message pre code {
-    background-color: transparent !important;
-    padding: 0;
-    font-size: inherit;
-}
-
-/* Override white-space for specific elements generated by Markdown */
-.ai-message p,
-.ai-message ul,
-.ai-message ol,
-.ai-message blockquote {
-    white-space: normal; /* Allow standard wrapping for block elements */
-}
-
-/* --- Markdown Element Styling within Messages --- */
-.message p {
-    margin-top: 0;
-    margin-bottom: 0.5em;
-}
-.message p:last-child {
-    margin-bottom: 0;
-}
-.message ul,
-.message ol {
-    margin: 0.5em 0 0.5em 1.5em;
-    padding: 0;
-}
-.message li {
-    margin-bottom: 0.2em;
-}
-
-/* Code block styling (adjusts previous rules slightly) */
-.message code {
-    /* Inline code */
-    background-color: var(--invert-font-color, var(--fallback-invert-font)) !important;
-    color: var(--font-color);
-    padding: 0.1em 0.4em;
-    border-radius: 4px;
-    font-size: 0.9em;
-    /* Ensure inline code breaks nicely */
-    word-break: break-all;
-    white-space: normal; /* Allow inline code to wrap if needed */
-}
-.message pre {
-    /* Code block container */
-    background-color: var(--invert-font-color, var(--fallback-invert-font)) !important;
-    color: var(--background-color, var(--fallback-bg)) !important;
-    padding: 1em;
-    border-radius: 5px;
-    overflow-x: auto;
-    margin: 0.8em 0;
-    font-size: 0.9em; /* Slightly smaller code blocks */
-}
-.message pre code {
-    /* Code within code block */
-    background-color: transparent !important;
-    padding: 0;
-    font-size: inherit;
-    word-break: normal; /* Don't break words in code blocks */
-    white-space: pre; /* Preserve whitespace strictly in code blocks */
-}
-
-/* Thinking indicator */
-.message-thinking {
-    display: inline-block;
-    width: 5px;
-    height: 5px;
-    background-color: var(--primary-color, var(--fallback-primary));
-    border-radius: 50%;
-    margin-left: 8px;
-    vertical-align: middle;
-    animation: thinking 1s infinite ease-in-out;
-}
-@keyframes thinking {
-    0%,
-    100% {
-        opacity: 0.5;
-        transform: scale(0.8);
-    }
-    50% {
-        opacity: 1;
-        transform: scale(1.2);
-    }
-}
-
-/* --- Thinking Indicator (Blinking Cursor Style) --- */
-.thinking-indicator-cursor {
-    display: inline-block;
-    width: 10px; /* Width of the cursor */
-    height: 1.1em; /* Match line height */
-    background-color: var(--primary-color, var(--fallback-primary));
-    margin-left: 5px;
-    vertical-align: text-bottom; /* Align with text baseline */
-    animation: blink-cursor 1s step-end infinite;
-}
-
-@keyframes blink-cursor {
-    from,
-    to {
-        background-color: transparent;
-    }
-    50% {
-        background-color: var(--primary-color, var(--fallback-primary));
-    }
-}
-
-#chat-input-area {
-    flex-shrink: 0; /* Prevent input area from shrinking */
-    padding: 1em 1.5em;
-    display: flex;
-    align-items: flex-end; /* Align items to bottom */
-    gap: 10px;
-    background-color: var(--code-bg-color, var(--fallback-code-bg)); /* Match sidebars */
-}
-
-#chat-input-area textarea {
-    flex-grow: 1;
-    padding: 0.8em 1em;
-    border: 1px solid var(--progress-bar-background, var(--fallback-border));
-    background-color: var(--background-color, var(--fallback-bg));
-    color: var(--font-color, var(--fallback-font));
-    border-radius: 5px;
-    resize: none; /* Disable manual resize */
-    font-family: inherit;
-    font-size: 1em;
-    line-height: 1.4;
-    max-height: 150px; /* Limit excessive height */
-    overflow-y: auto;
-    /* rows: 2; */
-}
-
-#chat-input-area button {
-    /* Basic button styling - maybe inherit from main theme? */
-    padding: 0.6em 1.2em;
-    border: 1px solid var(--primary-dimmed-color, var(--fallback-primary-dimmed));
-    background-color: var(--primary-dimmed-color, var(--fallback-primary-dimmed));
-    color: var(--background-color, var(--fallback-bg));
-    border-radius: 5px;
-    cursor: pointer;
-    font-size: 0.9em;
-    transition: background-color 0.2s, border-color 0.2s;
-    height: min-content; /* Align with bottom of textarea */
-}
-
-#chat-input-area button:hover {
-    background-color: var(--primary-color, var(--fallback-primary));
-    border-color: var(--primary-color, var(--fallback-primary));
-}
-#chat-input-area button:disabled {
-    opacity: 0.6;
-    cursor: not-allowed;
-}
-
-.loading-indicator {
-    font-size: 0.9em;
-    color: var(--secondary-color, var(--fallback-secondary));
-    margin-right: 10px;
-    align-self: center;
-}
-
-/* --- Buttons --- */
-/* Inherit some button styles if possible */
-.btn.btn-sm {
-    color: var(--font-color, var(--fallback-font));
-    padding: 0.2em 0.5em;
-    font-size: 0.8em;
-    border: 1px solid var(--secondary-color, var(--fallback-secondary));
-    background: none;
-    border-radius: 3px;
-    cursor: pointer;
-}
-.btn.btn-sm:hover {
-    border-color: var(--font-color, var(--fallback-font));
-    background-color: var(--progress-bar-background, var(--fallback-border));
-}
-
-/* --- Basic Responsiveness --- */
-@media screen and (max-width: 900px) {
-    .left-sidebar {
-        flex-basis: 200px; /* Shrink history */
-    }
-    .right-sidebar {
-        flex-basis: 240px; /* Shrink citations */
-    }
-}
-
-@media screen and (max-width: 768px) {
-    /* Stack layout on mobile? Or hide sidebars? Hiding for now */
-    .sidebar {
-        display: none; /* Hide sidebars on small screens */
-    }
-    /* Could add toggle buttons later */
-}
-
-
-/* ==== File: docs/ask_ai/ask-ai.css (Updates V4 - Delete Button) ==== */
-
-
-.sidebar ul li {
-    /* Use flexbox to align link and delete button */
-    display: flex;
-    justify-content: space-between;
-    align-items: center;
-    padding: 0; /* Remove padding from li, add to link/button */
-    margin: 0.1em 0; /* Small vertical margin */
-}
-
-.sidebar ul li a {
-    /* Link takes most space */
-    flex-grow: 1;
-    padding: 0.3em 0.5em 0.3em 1em; /* Adjust padding */
-    /* Make ellipsis work for long titles */
-    white-space: nowrap;
-    overflow: hidden;
-    text-overflow: ellipsis;
-    /* Keep existing link styles */
-    color: var(--secondary-color, var(--fallback-secondary));
-    text-decoration: none;
-    display: block;
-    border-radius: 3px;
-    transition: background-color 0.2s, color 0.2s;
-}
-.sidebar ul li a:hover {
-    color: var(--primary-color, var(--fallback-primary));
-    background-color: rgba(80, 255, 255, 0.08);
-}
-
-/* Style for active history item's link */
-#history-list li.active a {
-    color: var(--primary-dimmed-color, var(--fallback-primary-dimmed));
-    font-weight: bold;
-    background-color: rgba(80, 255, 255, 0.12);
-}
-
-/* --- Delete Chat Button --- */
-.delete-chat-btn {
-    flex-shrink: 0; /* Don't shrink */
-    background: none;
-    border: none;
-    color: var(--secondary-color, var(--fallback-secondary));
-    cursor: pointer;
-    padding: 0.4em 0.8em; /* Padding around icon */
-    font-size: 0.9em;
-    opacity: 0.5; /* Dimmed by default */
-    transition: opacity 0.2s, color 0.2s;
-    margin-left: 5px; /* Space between link and button */
-    border-radius: 3px;
-}
-
-.sidebar ul li:hover .delete-chat-btn,
-.delete-chat-btn:hover {
-    opacity: 1; /* Show fully on hover */
-    color: var(--error-color, #ff3c74); /* Use error color on hover */
-}
-.delete-chat-btn:focus {
-    outline: 1px dashed var(--error-color, #ff3c74); /* Accessibility */
-     opacity: 1;
-}

docs/md_v2/ask_ai/ask-ai.js

@@ -1,603 +0,0 @@
-// ==== File: docs/ask_ai/ask-ai.js (Marked, Streaming, History) ====
-
-document.addEventListener("DOMContentLoaded", () => {
-    console.log("AI Assistant JS V2 Loaded");
-
-    // --- DOM Element Selectors ---
-    const historyList = document.getElementById("history-list");
-    const newChatButton = document.getElementById("new-chat-button");
-    const chatMessages = document.getElementById("chat-messages");
-    const chatInput = document.getElementById("chat-input");
-    const sendButton = document.getElementById("send-button");
-    const citationsList = document.getElementById("citations-list");
-
-    // --- Constants ---
-    const CHAT_INDEX_KEY = "aiAssistantChatIndex_v1";
-    const CHAT_PREFIX = "aiAssistantChat_v1_";
-
-    // --- State ---
-    let currentChatId = null;
-    let conversationHistory = []; // Holds message objects { sender: 'user'/'ai', text: '...' }
-    let isThinking = false;
-    let streamInterval = null; // To control the streaming interval
-
-    // --- Event Listeners ---
-    sendButton.addEventListener("click", handleSendMessage);
-    chatInput.addEventListener("keydown", handleInputKeydown);
-    newChatButton.addEventListener("click", handleNewChat);
-    chatInput.addEventListener("input", autoGrowTextarea);
-
-    // --- Initialization ---
-    loadChatHistoryIndex(); // Load history list on startup
-    const initialQuery = checkForInitialQuery(window.parent.location); // Check for query param
-    if (!initialQuery) {
-        loadInitialChat(); // Load normally if no query
-    }
-
-    // --- Core Functions ---
-
-    function handleSendMessage() {
-        const userMessageText = chatInput.value.trim();
-        if (!userMessageText || isThinking) return;
-
-        setThinking(true); // Start thinking state
-
-        // Add user message to state and UI
-        const userMessage = { sender: "user", text: userMessageText };
-        conversationHistory.push(userMessage);
-        addMessageToChat(userMessage, false); // Add user message without parsing markdown
-
-        chatInput.value = "";
-        autoGrowTextarea(); // Reset textarea height
-
-        // Prepare for AI response (create empty div)
-        const aiMessageDiv = addMessageToChat({ sender: "ai", text: "" }, true); // Add empty div with thinking indicator
-
-        // TODO: Generate fingerprint/JWT here
-
-        // TODO: Send `conversationHistory` + JWT to backend API
-        // Replace placeholder below with actual API call
-        // The backend should ideally return a stream of text tokens
-
-        // --- Placeholder Streaming Simulation ---
-        const simulatedFullResponse = `Okay, Here’s a minimal Python script that creates an AsyncWebCrawler, fetches a webpage, and prints the first 300 characters of its Markdown output:
-
-\`\`\`python
-import asyncio
-from crawl4ai import AsyncWebCrawler
-
-async def main():
-    async with AsyncWebCrawler() as crawler:
-        result = await crawler.arun("https://example.com")
-        print(result.markdown[:300])  # Print first 300 chars
-
-if __name__ == "__main__":
-    asyncio.run(main())
-\`\`\`
-
-A code snippet: \`crawler.run()\`. Check the [quickstart](/core/quickstart).`;
-
-        // Simulate receiving the response stream
-        streamSimulatedResponse(aiMessageDiv, simulatedFullResponse);
-
-        // // Simulate receiving citations *after* stream starts (or with first chunk)
-        // setTimeout(() => {
-        //     addCitations([
-        //         { title: "Simulated Doc 1", url: "#sim1" },
-        //         { title: "Another Concept", url: "#sim2" },
-        //     ]);
-        // }, 500); // Citations appear shortly after thinking starts
-    }
-
-    function handleInputKeydown(event) {
-        if (event.key === "Enter" && !event.shiftKey) {
-            event.preventDefault();
-            handleSendMessage();
-        }
-    }
-
-    function addMessageToChat(message, addThinkingIndicator = false) {
-        const messageDiv = document.createElement("div");
-        messageDiv.classList.add("message", `${message.sender}-message`);
-
-        // Parse markdown and set HTML
-        messageDiv.innerHTML = message.text ? marked.parse(message.text) : "";
-
-        if (message.sender === "ai") {
-            // Apply Syntax Highlighting AFTER setting innerHTML
-            messageDiv.querySelectorAll("pre code:not(.hljs)").forEach((block) => {
-                if (typeof hljs !== "undefined") {
-                    // Check if already highlighted to prevent double-highlighting issues
-                    if (!block.classList.contains("hljs")) {
-                        hljs.highlightElement(block);
-                    }
-                } else {
-                    console.warn("highlight.js (hljs) not found for syntax highlighting.");
-                }
-            });
-
-            // Add thinking indicator if needed (and not already present)
-            if (addThinkingIndicator && !message.text && !messageDiv.querySelector(".thinking-indicator-cursor")) {
-                const thinkingDiv = document.createElement("div");
-                thinkingDiv.className = "thinking-indicator-cursor";
-                messageDiv.appendChild(thinkingDiv);
-            }
-        } else {
-            // User messages remain plain text
-            // messageDiv.textContent = message.text;
-        }
-
-        // wrap each pre in a div.terminal
-        messageDiv.querySelectorAll("pre").forEach((block) => {
-            const wrapper = document.createElement("div");
-            wrapper.className = "terminal";
-            block.parentNode.insertBefore(wrapper, block);
-            wrapper.appendChild(block);
-        });
-
-        chatMessages.appendChild(messageDiv);
-        // Scroll only if user is near the bottom? (More advanced)
-        // Simple scroll for now:
-        scrollToBottom();
-        return messageDiv; // Return the created element
-    }
-
-    function streamSimulatedResponse(messageDiv, fullText) {
-        const thinkingIndicator = messageDiv.querySelector(".thinking-indicator-cursor");
-        if (thinkingIndicator) thinkingIndicator.remove();
-
-        const tokens = fullText.split(/(\s+)/);
-        let currentText = "";
-        let tokenIndex = 0;
-        // Clear previous interval just in case
-        if (streamInterval) clearInterval(streamInterval);
-
-        streamInterval = setInterval(() => {
-            const cursorSpan = '<span class="thinking-indicator-cursor"></span>'; // Cursor for streaming
-            if (tokenIndex < tokens.length) {
-                currentText += tokens[tokenIndex];
-                // Render intermediate markdown + cursor
-                messageDiv.innerHTML = marked.parse(currentText + cursorSpan);
-                // Re-highlight code blocks on each stream update - might be slightly inefficient
-                // but ensures partial code blocks look okay. Highlight only final on completion.
-                // messageDiv.querySelectorAll('pre code:not(.hljs)').forEach((block) => {
-                //     hljs.highlightElement(block);
-                // });
-                scrollToBottom(); // Keep scrolling as content streams
-                tokenIndex++;
-            } else {
-                // Streaming finished
-                clearInterval(streamInterval);
-                streamInterval = null;
-
-                // Final render without cursor
-                messageDiv.innerHTML = marked.parse(currentText);
-
-                // === Final Syntax Highlighting ===
-                messageDiv.querySelectorAll("pre code:not(.hljs)").forEach((block) => {
-                    if (typeof hljs !== "undefined" && !block.classList.contains("hljs")) {
-                        hljs.highlightElement(block);
-                    }
-                });
-
-                // === Extract Citations ===
-                const citations = extractMarkdownLinks(currentText);
-
-                // Wrap each pre in a div.terminal
-                messageDiv.querySelectorAll("pre").forEach((block) => {
-                    const wrapper = document.createElement("div");
-                    wrapper.className = "terminal";
-                    block.parentNode.insertBefore(wrapper, block);
-                    wrapper.appendChild(block);
-                });
-
-                const aiMessage = { sender: "ai", text: currentText, citations: citations };
-                conversationHistory.push(aiMessage);
-                updateCitationsDisplay();
-                saveCurrentChat();
-                setThinking(false);
-            }
-        }, 50); // Adjust speed
-    }
-
-    // === NEW Function to Extract Links ===
-    function extractMarkdownLinks(markdownText) {
-        const regex = /\[([^\]]+)\]\(([^)]+)\)/g; // [text](url)
-        const citations = [];
-        let match;
-        while ((match = regex.exec(markdownText)) !== null) {
-            // Avoid adding self-links from within the citations list if AI includes them
-            if (!match[2].startsWith("#citation-")) {
-                citations.push({
-                    title: match[1].trim(),
-                    url: match[2].trim(),
-                });
-            }
-        }
-        // Optional: Deduplicate links based on URL
-        const uniqueCitations = citations.filter(
-            (citation, index, self) => index === self.findIndex((c) => c.url === citation.url)
-        );
-        return uniqueCitations;
-    }
-
-    // === REVISED Function to Display Citations ===
-    function updateCitationsDisplay() {
-        let lastCitations = null;
-        // Find the most recent AI message with citations
-        for (let i = conversationHistory.length - 1; i >= 0; i--) {
-            if (
-                conversationHistory[i].sender === "ai" &&
-                conversationHistory[i].citations &&
-                conversationHistory[i].citations.length > 0
-            ) {
-                lastCitations = conversationHistory[i].citations;
-                break; // Found the latest citations
-            }
-        }
-
-        citationsList.innerHTML = ""; // Clear previous
-        if (!lastCitations) {
-            citationsList.innerHTML = '<li class="no-citations">No citations available.</li>';
-            return;
-        }
-
-        lastCitations.forEach((citation, index) => {
-            const li = document.createElement("li");
-            const a = document.createElement("a");
-            // Generate a unique ID for potential internal linking if needed
-            // a.id = `citation-${index}`;
-            a.href = citation.url || "#";
-            a.textContent = citation.title;
-            a.target = "_top"; // Open in main window
-            li.appendChild(a);
-            citationsList.appendChild(li);
-        });
-    }
-
-    function addCitations(citations) {
-        citationsList.innerHTML = ""; // Clear
-        if (!citations || citations.length === 0) {
-            citationsList.innerHTML = '<li class="no-citations">No citations available.</li>';
-            return;
-        }
-        citations.forEach((citation) => {
-            const li = document.createElement("li");
-            const a = document.createElement("a");
-            a.href = citation.url || "#";
-            a.textContent = citation.title;
-            a.target = "_top"; // Open in main window
-            li.appendChild(a);
-            citationsList.appendChild(li);
-        });
-    }
-
-    function setThinking(thinking) {
-        isThinking = thinking;
-        sendButton.disabled = thinking;
-        chatInput.disabled = thinking;
-        chatInput.placeholder = thinking ? "AI is responding..." : "Ask about Crawl4AI...";
-        // Stop any existing stream if we start thinking again (e.g., rapid resend)
-        if (thinking && streamInterval) {
-            clearInterval(streamInterval);
-            streamInterval = null;
-        }
-    }
-
-    function autoGrowTextarea() {
-        chatInput.style.height = "auto";
-        chatInput.style.height = `${chatInput.scrollHeight}px`;
-    }
-
-    function scrollToBottom() {
-        chatMessages.scrollTop = chatMessages.scrollHeight;
-    }
-
-    // --- Query Parameter Handling ---
-    function checkForInitialQuery(locationToCheck) {
-        // <-- Receive location object
-        if (!locationToCheck) {
-            console.warn("Ask AI: Could not access parent window location.");
-            return false;
-        }
-        const urlParams = new URLSearchParams(locationToCheck.search); // <-- Use passed location's search string
-        const encodedQuery = urlParams.get("qq"); // <-- Use 'qq'
-
-        if (encodedQuery) {
-            console.log("Initial query found (qq):", encodedQuery);
-            try {
-                const decodedText = decodeURIComponent(escape(atob(encodedQuery)));
-                console.log("Decoded query:", decodedText);
-
-                // Start new chat immediately
-                handleNewChat(true);
-
-                // Delay setting input and sending message slightly
-                setTimeout(() => {
-                    chatInput.value = decodedText;
-                    autoGrowTextarea();
-                    handleSendMessage();
-
-                    // Clean the PARENT window's URL
-                    try {
-                        const cleanUrl = locationToCheck.pathname;
-                        // Use parent's history object
-                        window.parent.history.replaceState({}, window.parent.document.title, cleanUrl);
-                    } catch (e) {
-                        console.warn("Ask AI: Could not clean parent URL using replaceState.", e);
-                        // This might fail due to cross-origin restrictions if served differently,
-                        // but should work fine with mkdocs serve on the same origin.
-                    }
-                }, 100);
-
-                return true; // Query processed
-            } catch (e) {
-                console.error("Error decoding initial query (qq):", e);
-                // Clean the PARENT window's URL even on error
-                try {
-                    const cleanUrl = locationToCheck.pathname;
-                    window.parent.history.replaceState({}, window.parent.document.title, cleanUrl);
-                } catch (cleanError) {
-                    console.warn("Ask AI: Could not clean parent URL after decode error.", cleanError);
-                }
-                return false;
-            }
-        }
-        return false; // No 'qq' query found
-    }
-
-    // --- History Management ---
-
-    function handleNewChat(isFromQuery = false) {
-        if (isThinking) return; // Don't allow new chat while responding
-
-        // Only save if NOT triggered immediately by a query parameter load
-        if (!isFromQuery) {
-            saveCurrentChat();
-        }
-
-        currentChatId = `chat_${Date.now()}`;
-        conversationHistory = []; // Clear message history state
-        chatMessages.innerHTML = ""; // Start with clean slate for query
-        if (!isFromQuery) {
-            // Show welcome only if manually started
-            chatMessages.innerHTML =
-                '<div class="message ai-message welcome-message">Started a new chat! Ask me anything about Crawl4AI.</div>';
-        }
-        addCitations([]); // Clear citations
-        updateCitationsDisplay(); // Clear UI
-
-        // Add to index and save
-        let index = loadChatIndex();
-        // Generate a generic title initially, update later
-        const newTitle = isFromQuery ? "Chat from Selection" : `Chat ${new Date().toLocaleString()}`;
-        // index.unshift({ id: currentChatId, title: `Chat ${new Date().toLocaleString()}` }); // Add to start
-        index.unshift({ id: currentChatId, title: newTitle });
-        saveChatIndex(index);
-
-        renderHistoryList(index); // Update UI
-        setActiveHistoryItem(currentChatId);
-        saveCurrentChat(); // Save the empty new chat state
-    }
-
-    function loadChat(chatId) {
-        if (isThinking || chatId === currentChatId) return;
-
-        // Check if chat data actually exists before proceeding
-        const storedChat = localStorage.getItem(CHAT_PREFIX + chatId);
-        if (storedChat === null) {
-            console.warn(`Attempted to load non-existent chat: ${chatId}. Removing from index.`);
-            deleteChatData(chatId); // Clean up index
-            loadChatHistoryIndex(); // Reload history list
-            loadInitialChat(); // Load next available chat
-            return;
-        }
-
-        console.log(`Loading chat: ${chatId}`);
-        saveCurrentChat(); // Save current before switching
-
-        try {
-            conversationHistory = JSON.parse(storedChat);
-            currentChatId = chatId;
-            renderChatMessages(conversationHistory);
-            updateCitationsDisplay();
-            setActiveHistoryItem(chatId);
-        } catch (e) {
-            console.error("Error loading chat:", chatId, e);
-            alert("Failed to load chat data.");
-            conversationHistory = [];
-            renderChatMessages(conversationHistory);
-            updateCitationsDisplay();
-        }
-    }
-
-    function saveCurrentChat() {
-        if (currentChatId && conversationHistory.length > 0) {
-            try {
-                localStorage.setItem(CHAT_PREFIX + currentChatId, JSON.stringify(conversationHistory));
-                console.log(`Chat ${currentChatId} saved.`);
-
-                // Update title in index (e.g., use first user message)
-                let index = loadChatIndex();
-                const currentItem = index.find((item) => item.id === currentChatId);
-                if (
-                    currentItem &&
-                    conversationHistory[0]?.sender === "user" &&
-                    !currentItem.title.startsWith("Chat about:")
-                ) {
-                    currentItem.title = `Chat about: ${conversationHistory[0].text.substring(0, 30)}...`;
-                    saveChatIndex(index);
-                    // Re-render history list if title changed - small optimization needed here maybe
-                    renderHistoryList(index);
-                    setActiveHistoryItem(currentChatId); // Re-set active after re-render
-                }
-            } catch (e) {
-                console.error("Error saving chat:", currentChatId, e);
-                // Handle potential storage full errors
-                if (e.name === "QuotaExceededError") {
-                    alert("Local storage is full. Cannot save chat history.");
-                    // Consider implementing history pruning logic here
-                }
-            }
-        } else if (currentChatId) {
-            // Save empty state for newly created chats if needed, or remove?
-            localStorage.setItem(CHAT_PREFIX + currentChatId, JSON.stringify([]));
-        }
-    }
-
-    function loadChatIndex() {
-        try {
-            const storedIndex = localStorage.getItem(CHAT_INDEX_KEY);
-            return storedIndex ? JSON.parse(storedIndex) : [];
-        } catch (e) {
-            console.error("Error loading chat index:", e);
-            return []; // Return empty array on error
-        }
-    }
-
-    function saveChatIndex(indexArray) {
-        try {
-            localStorage.setItem(CHAT_INDEX_KEY, JSON.stringify(indexArray));
-        } catch (e) {
-            console.error("Error saving chat index:", e);
-        }
-    }
-
-    function renderHistoryList(indexArray) {
-        historyList.innerHTML = ""; // Clear existing
-        if (!indexArray || indexArray.length === 0) {
-            historyList.innerHTML = '<li class="no-history">No past chats found.</li>';
-            return;
-        }
-        indexArray.forEach((item) => {
-            const li = document.createElement("li");
-            li.dataset.chatId = item.id; // Add ID to li for easier selection
-
-            const a = document.createElement("a");
-            a.href = "#";
-            a.dataset.chatId = item.id;
-            a.textContent = item.title || `Chat ${item.id.split("_")[1] || item.id}`;
-            a.title = a.textContent; // Tooltip for potentially long titles
-            a.addEventListener("click", (e) => {
-                e.preventDefault();
-                loadChat(item.id);
-            });
-
-            // === Add Delete Button ===
-            const deleteBtn = document.createElement("button");
-            deleteBtn.className = "delete-chat-btn";
-            deleteBtn.innerHTML = "✕"; // Trash can emoji/icon (or use text/SVG/FontAwesome)
-            deleteBtn.title = "Delete Chat";
-            deleteBtn.dataset.chatId = item.id; // Store ID on button too
-            deleteBtn.addEventListener("click", handleDeleteChat);
-
-            li.appendChild(a);
-            li.appendChild(deleteBtn); // Append button to the list item
-            historyList.appendChild(li);
-        });
-    }
-
-    function renderChatMessages(messages) {
-        chatMessages.innerHTML = ""; // Clear existing messages
-        messages.forEach((message) => {
-            // Ensure highlighting is applied when loading from history
-            addMessageToChat(message, false);
-        });
-        if (messages.length === 0) {
-            chatMessages.innerHTML =
-                '<div class="message ai-message welcome-message">Chat history loaded. Ask a question!</div>';
-        }
-        // Scroll to bottom after loading messages
-        scrollToBottom();
-    }
-
-    function setActiveHistoryItem(chatId) {
-        document.querySelectorAll("#history-list li").forEach((li) => li.classList.remove("active"));
-        // Select the LI element directly now
-        const activeLi = document.querySelector(`#history-list li[data-chat-id="${chatId}"]`);
-        if (activeLi) {
-            activeLi.classList.add("active");
-        }
-    }
-
-    function loadInitialChat() {
-        const index = loadChatIndex();
-        if (index.length > 0) {
-            loadChat(index[0].id);
-        } else {
-            // Check if handleNewChat wasn't already called by query handler
-            if (!currentChatId) {
-                handleNewChat();
-            }
-        }
-    }
-
-    function loadChatHistoryIndex() {
-        const index = loadChatIndex();
-        renderHistoryList(index);
-        if (currentChatId) setActiveHistoryItem(currentChatId);
-    }
-
-    // === NEW Function to Handle Delete Click ===
-    function handleDeleteChat(event) {
-        event.stopPropagation(); // Prevent triggering loadChat on the link behind it
-        const button = event.currentTarget;
-        const chatIdToDelete = button.dataset.chatId;
-
-        if (!chatIdToDelete) return;
-
-        // Confirmation dialog
-        if (
-            window.confirm(
-                `Are you sure you want to delete this chat session?\n"${
-                    button.previousElementSibling?.textContent || "Chat " + chatIdToDelete
-                }"`
-            )
-        ) {
-            console.log(`Deleting chat: ${chatIdToDelete}`);
-
-            // Perform deletion
-            const updatedIndex = deleteChatData(chatIdToDelete);
-
-            // If the deleted chat was the currently active one, load another chat
-            if (currentChatId === chatIdToDelete) {
-                currentChatId = null; // Reset current ID
-                conversationHistory = []; // Clear state
-                if (updatedIndex.length > 0) {
-                    // Load the new top chat (most recent remaining)
-                    loadChat(updatedIndex[0].id);
-                } else {
-                    // No chats left, start a new one
-                    handleNewChat();
-                }
-            } else {
-                // If a different chat was deleted, just re-render the list
-                renderHistoryList(updatedIndex);
-                // Re-apply active state in case IDs shifted (though they shouldn't)
-                setActiveHistoryItem(currentChatId);
-            }
-        }
-    }
-
-    // === NEW Function to Delete Chat Data ===
-    function deleteChatData(chatId) {
-        // Remove chat data
-        localStorage.removeItem(CHAT_PREFIX + chatId);
-
-        // Update index
-        let index = loadChatIndex();
-        index = index.filter((item) => item.id !== chatId);
-        saveChatIndex(index);
-
-        console.log(`Chat ${chatId} data and index entry removed.`);
-        return index; // Return the updated index
-    }
-
-    // --- Virtual Scrolling Placeholder ---
-    // NOTE: Virtual scrolling is complex. For now, we do direct rendering.
-    // If performance becomes an issue with very long chats/history,
-    // investigate libraries like 'simple-virtual-scroll' or 'virtual-scroller'.
-    // You would replace parts of `renderChatMessages` and `renderHistoryList`
-    // to work with the chosen library's API (providing data and item renderers).
-    console.warn("Virtual scrolling not implemented. Performance may degrade with very long chat histories.");
-});

docs/md_v2/ask_ai/index.html

@@ -1,64 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
-    <meta charset="UTF-8">
-    <meta name="viewport" content="width=device-width, initial-scale=1.0">
-    <title>Crawl4AI Assistant</title>
-    <!-- Link main styles first for variable access -->
-    <link rel="stylesheet" href="../assets/layout.css">
-    <link rel="stylesheet" href="../assets/styles.css">
-    <!-- Link specific AI styles -->
-    <link rel="stylesheet" href="../assets/highlight.css">
-    <link rel="stylesheet" href="ask-ai.css">
-</head>
-<body>
-    <div class="ai-assistant-container">
-
-        <!-- Left Sidebar: Conversation History -->
-        <aside id="history-panel" class="sidebar left-sidebar">
-            <header>
-                <h3>History</h3>
-                <button id="new-chat-button" class="btn btn-sm">New Chat</button>
-            </header>
-            <ul id="history-list">
-                <!-- History items populated by JS -->
-            </ul>
-        </aside>
-
-        <!-- Main Area: Chat Interface -->
-        <main id="chat-panel">
-            <div id="chat-messages">
-                <!-- Chat messages populated by JS -->
-                 <div class="message ai-message welcome-message">
-                    Welcome to the Crawl4AI Assistant! How can I help you today?
-                 </div>
-            </div>
-            <div id="chat-input-area">
-                <!-- Loading indicator for general waiting (optional) -->
-                <!-- <div class="loading-indicator" style="display: none;">Thinking...</div> -->
-                <textarea id="chat-input" placeholder="Ask about Crawl4AI..." rows="2"></textarea> 
-                <button id="send-button">Send</button>
-            </div>
-        </main>
-
-        <!-- Right Sidebar: Citations / Context -->
-        <aside id="citations-panel" class="sidebar right-sidebar">
-            <header>
-                <h3>Citations</h3>
-            </header>
-            <ul id="citations-list">
-                <!-- Citations populated by JS -->
-                <li class="no-citations">No citations for this response yet.</li>
-            </ul>
-        </aside>
-
-    </div>
-
-    <!-- Include Marked.js library -->
-    <script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script>
-    <script src="../assets/highlight.min.js"></script> 
-
-    <!-- Your AI Assistant Logic -->
-    <script src="ask-ai.js"></script>
-</body>
-</html>

docs/md_v2/assets/copy_code.js

@@ -1,62 +0,0 @@
-// ==== File: docs/assets/copy_code.js ====
-
-document.addEventListener('DOMContentLoaded', () => {
-    // Target specifically code blocks within the main content area
-    const codeBlocks = document.querySelectorAll('#terminal-mkdocs-main-content pre > code');
-
-    codeBlocks.forEach((codeElement) => {
-        const preElement = codeElement.parentElement; // The <pre> tag
-
-        // Ensure the <pre> tag can contain a positioned button
-        if (window.getComputedStyle(preElement).position === 'static') {
-            preElement.style.position = 'relative';
-        }
-
-        // Create the button
-        const copyButton = document.createElement('button');
-        copyButton.className = 'copy-code-button';
-        copyButton.type = 'button';
-        copyButton.setAttribute('aria-label', 'Copy code to clipboard');
-        copyButton.title = 'Copy code to clipboard';
-        copyButton.innerHTML = 'Copy'; // Or use an icon like an SVG or FontAwesome class
-
-        // Append the button to the <pre> element
-        preElement.appendChild(copyButton);
-
-        // Add click event listener
-        copyButton.addEventListener('click', () => {
-            copyCodeToClipboard(codeElement, copyButton);
-        });
-    });
-
-    async function copyCodeToClipboard(codeElement, button) {
-        // Use innerText to get the rendered text content, preserving line breaks
-        const textToCopy = codeElement.innerText;
-
-        try {
-            await navigator.clipboard.writeText(textToCopy);
-
-            // Visual feedback
-            button.innerHTML = 'Copied!';
-            button.classList.add('copied');
-            button.disabled = true; // Temporarily disable
-
-            // Revert button state after a short delay
-            setTimeout(() => {
-                button.innerHTML = 'Copy';
-                button.classList.remove('copied');
-                button.disabled = false;
-            }, 2000); // Show "Copied!" for 2 seconds
-
-        } catch (err) {
-            console.error('Failed to copy code: ', err);
-            // Optional: Provide error feedback on the button
-            button.innerHTML = 'Error';
-            setTimeout(() => {
-                button.innerHTML = 'Copy';
-            }, 2000);
-        }
-    }
-
-    console.log("Copy Code Button script loaded.");
-});

docs/md_v2/assets/floating_ask_ai_button.js

@@ -1,39 +0,0 @@
-// ==== File: docs/assets/floating_ask_ai_button.js ====
-
-document.addEventListener('DOMContentLoaded', () => {
-    const askAiPagePath = '/core/ask-ai/'; // IMPORTANT: Adjust this path if needed!
-    const currentPath = window.location.pathname;
-
-    // Determine the base URL for constructing the link correctly,
-    // especially if deployed in a sub-directory.
-    // This assumes a simple structure; adjust if needed.
-    const baseUrl = window.location.origin + (currentPath.startsWith('/core/') ? '../..' : '');
-
-
-    // Check if the current page IS the Ask AI page
-    // Use includes() for flexibility (handles trailing slash or .html)
-    if (currentPath.includes(askAiPagePath.replace(/\/$/, ''))) { // Remove trailing slash for includes check
-        console.log("Floating Ask AI Button: Not adding button on the Ask AI page itself.");
-        return; // Don't add the button on the target page
-    }
-
-    // --- Create the button ---
-    const fabLink = document.createElement('a');
-    fabLink.className = 'floating-ask-ai-button';
-    fabLink.href = askAiPagePath; // Construct the correct URL
-    fabLink.title = 'Ask Crawl4AI Assistant';
-    fabLink.setAttribute('aria-label', 'Ask Crawl4AI Assistant');
-
-    // Add content (using SVG icon for better visuals)
-    fabLink.innerHTML = `
-        <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" width="24" height="24" fill="currentColor">
-            <path d="M20 2H4c-1.1 0-2 .9-2 2v12c0 1.1.9 2 2 2h14l4 4V4c0-1.1-.9-2-2-2zm-2 12H6v-2h12v2zm0-3H6V9h12v2zm0-3H6V6h12v2z"/>
-        </svg>
-        <span>Ask AI</span>
-    `;
-
-    // Append to body
-    document.body.appendChild(fabLink);
-
-    console.log("Floating Ask AI Button added.");
-});

docs/md_v2/assets/github_stats.js

@@ -1,119 +0,0 @@
-// ==== File: assets/github_stats.js ====
-
-document.addEventListener('DOMContentLoaded', async () => {
-    // --- Configuration ---
-    const targetHeaderSelector = '.terminal .container:first-child'; // Selector for your header container
-    const insertBeforeSelector = '.terminal-nav'; // Selector for the element to insert the badge BEFORE (e.g., the main nav)
-                                                  // Or set to null to append at the end of the header.
-
-    // --- Find elements ---
-    const headerContainer = document.querySelector(targetHeaderSelector);
-    if (!headerContainer) {
-        console.warn('GitHub Stats: Header container not found with selector:', targetHeaderSelector);
-        return;
-    }
-
-    const repoLinkElement = headerContainer.querySelector('a[href*="github.com/"]'); // Find the existing GitHub link
-    let repoUrl = 'https://github.com/unclecode/crawl4ai';
-    // if (repoLinkElement) {
-    //     repoUrl = repoLinkElement.href;
-    // } else {
-    //     // Fallback: Try finding from config (requires template injection - harder)
-    //     // Or hardcode if necessary, but reading from the link is better.
-    //      console.warn('GitHub Stats: GitHub repo link not found in header.');
-    //      // Try to get repo_url from mkdocs config if available globally (less likely)
-    //      // repoUrl = window.mkdocs_config?.repo_url; // Requires setting this variable
-    //      // if (!repoUrl) return; // Exit if still no URL
-    //      return; // Exit for now if link isn't found
-    // }
-
-
-    // --- Extract Repo Owner/Name ---
-    let owner = '';
-    let repo = '';
-    try {
-        const url = new URL(repoUrl);
-        const pathParts = url.pathname.split('/').filter(part => part.length > 0);
-        if (pathParts.length >= 2) {
-            owner = pathParts[0];
-            repo = pathParts[1];
-        }
-    } catch (e) {
-        console.error('GitHub Stats: Could not parse repository URL:', repoUrl, e);
-        return;
-    }
-
-    if (!owner || !repo) {
-        console.warn('GitHub Stats: Could not extract owner/repo from URL:', repoUrl);
-        return;
-    }
-
-    // --- Get Version (Attempt to extract from site title) ---
-    let version = '';
-    const siteTitleElement = headerContainer.querySelector('.terminal-title, .site-title'); // Adjust selector based on theme's title element
-    // Example title: "Crawl4AI Documentation (v0.5.x)"
-    if (siteTitleElement) {
-         const match = siteTitleElement.textContent.match(/\((v?[^)]+)\)/); // Look for text in parentheses starting with 'v' (optional)
-         if (match && match[1]) {
-             version = match[1].trim();
-         }
-    }
-     if (!version) {
-        console.info('GitHub Stats: Could not extract version from title. You might need to adjust the selector or regex.');
-        // You could fallback to config.extra.version if injected into JS
-        // version = window.mkdocs_config?.extra?.version || 'N/A';
-     }
-
-
-    // --- Fetch GitHub API Data ---
-    let stars = '...';
-    let forks = '...';
-    try {
-        const apiUrl = `https://api.github.com/repos/${owner}/${repo}`;
-        const response = await fetch(apiUrl);
-
-        if (response.ok) {
-            const data = await response.json();
-            // Format large numbers (optional)
-            stars = data.stargazers_count > 1000 ? `${(data.stargazers_count / 1000).toFixed(1)}k` : data.stargazers_count;
-            forks = data.forks_count > 1000 ? `${(data.forks_count / 1000).toFixed(1)}k` : data.forks_count;
-        } else {
-            console.warn(`GitHub Stats: API request failed with status ${response.status}. Rate limit exceeded?`);
-            stars = 'N/A';
-            forks = 'N/A';
-        }
-    } catch (error) {
-        console.error('GitHub Stats: Error fetching repository data:', error);
-        stars = 'N/A';
-        forks = 'N/A';
-    }
-
-    // --- Create Badge HTML ---
-    const badgeContainer = document.createElement('div');
-    badgeContainer.className = 'github-stats-badge';
-
-    // Use innerHTML for simplicity, including potential icons (requires FontAwesome or similar)
-    // Ensure your theme loads FontAwesome or add it yourself if you want icons.
-    badgeContainer.innerHTML = `
-        <a href="${repoUrl}" target="_blank" rel="noopener">
-            <!-- Optional Icon (FontAwesome example) -->
-            <!-- <i class="fab fa-github"></i> -->
-             <span class="repo-name">${owner}/${repo}</span>
-             ${version ? `<span class="stat version"><i class="fas fa-tag"></i> ${version}</span>` : ''}
-            <span class="stat stars"><i class="fas fa-star"></i> ${stars}</span>
-            <span class="stat forks"><i class="fas fa-code-branch"></i> ${forks}</span>
-        </a>
-    `;
-
-    // --- Inject Badge into Header ---
-    const insertBeforeElement = insertBeforeSelector ? headerContainer.querySelector(insertBeforeSelector) : null;
-    if (insertBeforeElement) {
-        // headerContainer.insertBefore(badgeContainer, insertBeforeElement);
-        headerContainer.querySelector(insertBeforeSelector).appendChild(badgeContainer); 
-    } else {
-        headerContainer.appendChild(badgeContainer); 
-    }
-
-     console.info('GitHub Stats: Badge added to header.');
-
-});

docs/md_v2/assets/layout.css

@@ -1,441 +0,0 @@
-/* ==== File: assets/layout.css (Non-Fluid Centered Layout) ==== */
-
-:root {
-    --header-height: 55px; /* Adjust if needed */
-    --sidebar-width: 280px; /* Adjust if needed */
-    --toc-width: 340px; /* As specified */
-    --content-max-width: 90em; /* Max width for the centered content */
-    --layout-transition-speed: 0.2s;
-    --global-space: 10px;
-}
-
-/* --- Basic Setup --- */
-html {
-    scroll-behavior: smooth;
-    scroll-padding-top: calc(var(--header-height) + 15px);
-    box-sizing: border-box;
-}
-*, *:before, *:after {
-    box-sizing: inherit;
-}
-
-body {
-    padding-top: 0;
-    padding-bottom: 0;
-    background-color: var(--background-color);
-    color: var(--font-color);
-    /* Prevents horizontal scrollbars during transitions */
-    overflow-x: hidden;
-}
-
-/* --- Fixed Header --- */
-/* Full width, fixed header */
-.terminal .container:first-child { /* Assuming this targets the header container */
-    position: fixed;
-    top: 0;
-    left: 0;
-    right: 0;
-    height: var(--header-height);
-    background-color: var(--background-color);
-    z-index: 1000;
-    border-bottom: 1px solid var(--progress-bar-background);
-    max-width: none; /* Override any container max-width */
-    padding: 0 calc(var(--global-space) * 2);
-}
-
-/* --- Main Layout Container (Below Header) --- */
-/* This container just provides space for the fixed header */
-.container:has(.terminal-mkdocs-main-grid) {
-    margin: 0 auto;
-    padding: 0;
-    padding-top: var(--header-height); /* Space for fixed header */
-}
-
-/* --- Flex Container: Grid holding content and toc (CENTERED) --- */
-/* THIS is the main centered block */
-.terminal-mkdocs-main-grid {
-    display: flex;
-    align-items: flex-start;
-    /* Enforce max-width and center */
-    max-width: var(--content-max-width);
-    margin-left: auto;
-    margin-right: auto;
-    position: relative;
-    /* Apply side padding within the centered block */
-    padding-left: calc(var(--global-space) * 2);
-    padding-right: calc(var(--global-space) * 2);
-    /* Add margin-left to clear the fixed sidebar */
-    margin-left: var(--sidebar-width);
-}
-
-/* --- 1. Fixed Left Sidebar (Viewport Relative) --- */
-#terminal-mkdocs-side-panel {
-    position: fixed;
-    top: var(--header-height);
-    left: max(0px, calc((90vw - var(--content-max-width)) / 2)); 
-    bottom: 0;
-    width: var(--sidebar-width);
-    background-color: var(--background-color);
-    border-right: 1px solid var(--progress-bar-background);
-    overflow-y: auto;
-    z-index: 900;
-    padding: 1em calc(var(--global-space) * 2);
-    padding-bottom: 2em;
-    /* transition: left var(--layout-transition-speed) ease-in-out; */
-}
-
-/* --- 2. Main Content Area (Within Centered Grid) --- */
-#terminal-mkdocs-main-content {
-    flex-grow: 1;
-    flex-shrink: 1;
-    min-width: 0; /* Flexbox shrink fix */
-
-    /* No left/right margins needed here - handled by parent grid */
-    margin-left: 0;
-    margin-right: 0;
-
-    /* Internal Padding */
-    padding: 1.5em 2em;
-
-    position: relative;
-    z-index: 1;
-}
-
-/* --- 3. Right Table of Contents (Sticky, Within Centered Grid) --- */
-#toc-sidebar {
-    flex-basis: var(--toc-width);
-    flex-shrink: 0;
-    width: var(--toc-width);
-
-    position: sticky; /* Sticks within the centered grid */
-    top: var(--header-height);
-    align-self: stretch;
-    height: calc(100vh - var(--header-height));
-    overflow-y: auto;
-
-    padding: 1.5em 1em;
-    font-size: 0.85em;
-    border-left: 1px solid var(--progress-bar-background);
-    z-index: 800;
-    /* display: none; /* JS handles */
-}
-
-/* (ToC link styles remain the same) */
-#toc-sidebar h4 { margin-top: 0; margin-bottom: 1em; font-size: 1.1em; color: var(--secondary-color); padding-left: 0.8em; }
-#toc-sidebar ul { list-style: none; padding: 0; margin: 0; }
-#toc-sidebar ul li a { display: block; padding: 0.3em 0; color: var(--secondary-color); text-decoration: none; border-left: 3px solid transparent; padding-left: 0.8em; transition: all 0.1s ease-in-out; line-height: 1.4; word-break: break-word; }
-#toc-sidebar ul li.toc-level-3 a { padding-left: 1.8em; }
-#toc-sidebar ul li.toc-level-4 a { padding-left: 2.8em; }
-#toc-sidebar ul li a:hover { color: var(--font-color); background-color: rgba(255, 255, 255, 0.05); }
-#toc-sidebar ul li a.active { color: var(--primary-color); border-left-color: var(--primary-color); background-color: rgba(80, 255, 255, 0.08); }
-
-
-/* --- Footer Styling (Respects Centered Layout) --- */
-footer {
-    background-color: var(--code-bg-color);
-    color: var(--secondary-color);
-    position: relative;
-    z-index: 10;
-    margin-top: 2em;
-
-    /* Apply margin-left to clear the fixed sidebar */
-    margin-left: var(--sidebar-width);
-
-    /* Constrain width relative to the centered grid it follows */
-    max-width: calc(var(--content-max-width) - var(--sidebar-width));
-    margin-right: auto; /* Keep it left-aligned within the space next to sidebar */
-
-    /* Use padding consistent with the grid */
-    padding: 2em calc(var(--global-space) * 2);
-}
-
-/* Adjust footer grid if needed */
-.terminal-mkdocs-footer-grid {
-    display: grid;
-    grid-template-columns: 1fr auto;
-    gap: 1em;
-    align-items: center;
-}
-
-/* ==========================================================================
-   RESPONSIVENESS (Adapting the Non-Fluid Layout)
-   ========================================================================== */
-
-/* --- Medium screens: Hide ToC --- */
-@media screen and (max-width: 1200px) {
-    #toc-sidebar {
-        display: none;
-    }
-
-    .terminal-mkdocs-main-grid {
-        /* Grid adjusts automatically as ToC is removed */
-        /* Ensure grid padding remains */
-         padding-left: calc(var(--global-space) * 2);
-         padding-right: calc(var(--global-space) * 2);
-    }
-
-    #terminal-mkdocs-main-content {
-        /* Content area naturally expands */
-    }
-
-    footer {
-        /* Footer still respects the left sidebar and overall max width */
-        margin-left: var(--sidebar-width);
-        max-width: calc(var(--content-max-width) - var(--sidebar-width));
-        /* Padding remains consistent */
-         padding-left: calc(var(--global-space) * 2);
-         padding-right: calc(var(--global-space) * 2);
-    }
-}
-
-/* --- Small screens: Hide left sidebar, full width content & footer --- */
-@media screen and (max-width: 768px) {
-
-    #terminal-mkdocs-side-panel {
-        left: calc(-1 * var(--sidebar-width));
-        z-index: 1100;
-        box-shadow: 2px 0 10px rgba(0,0,0,0.3);
-    }
-    #terminal-mkdocs-side-panel.sidebar-visible {
-        left: 0;
-    }
-
-    .terminal-mkdocs-main-grid {
-        /* Grid now takes full width (minus body padding) */
-        margin-left: 0; /* Override sidebar margin */
-        margin-right: 0; /* Override auto margin */
-        max-width: 100%; /* Allow full width */
-        padding-left: var(--global-space); /* Reduce padding */
-        padding-right: var(--global-space);
-    }
-
-    #terminal-mkdocs-main-content {
-        padding: 1.5em 1em; /* Adjust internal padding */
-    }
-
-    footer {
-        margin-left: 0; /* Full width footer */
-        max-width: 100%; /* Allow full width */
-        padding: 2em 1em; /* Adjust internal padding */
-    }
-
-    .terminal-mkdocs-footer-grid {
-         grid-template-columns: 1fr; /* Stack footer items */
-         text-align: center;
-         gap: 0.5em;
-    }
-    /* Remember JS for toggle button & overlay */
-}
-
-
-/* ==== GitHub Stats Badge Styling ==== */
-
-.github-stats-badge {
-    display: inline-block; /* Or flex if needed */
-    margin-left: 2em; /* Adjust spacing */
-    vertical-align: middle; /* Align with other header items */
-    font-size: 0.9em; /* Slightly smaller font */
-}
-
-.github-stats-badge a {
-    color: var(--secondary-color); /* Use secondary color */
-    text-decoration: none;
-    display: flex; /* Use flex for alignment */
-    align-items: center;
-    gap: 0.8em; /* Space between items */
-    padding: 0.2em 0.5em;
-    border: 1px solid var(--progress-bar-background); /* Subtle border */
-    border-radius: 4px;
-    transition: color 0.2s, background-color 0.2s;
-}
-
-.github-stats-badge a:hover {
-    color: var(--font-color); /* Brighter color on hover */
-    background-color: var(--progress-bar-background); /* Subtle background on hover */
-}
-
-.github-stats-badge .repo-name {
-    color: var(--font-color); /* Make repo name stand out slightly */
-    font-weight: 500; /* Optional bolder weight */
-}
-
-.github-stats-badge .stat {
-    /* Styles for individual stats (version, stars, forks) */
-    white-space: nowrap; /* Prevent wrapping */
-}
-
-.github-stats-badge .stat i {
-    /* Optional: Style for FontAwesome icons */
-    margin-right: 0.3em;
-    color: var(--secondary-dimmed-color); /* Dimmer color for icons */
-}
-
-
-/* Adjust positioning relative to search/nav if needed */
-/* Example: If search is floated right */
-/* .terminal-nav { float: left; } */
-/* .github-stats-badge { float: left; } */
-/* #mkdocs-search-query { float: right; } */
-
-/* --- Responsive adjustments --- */
-@media screen and (max-width: 900px) { /* Example breakpoint */
-    .github-stats-badge .repo-name {
-        display: none; /* Hide full repo name on smaller screens */
-    }
-    .github-stats-badge {
-        margin-left: 1em;
-    }
-     .github-stats-badge a {
-        gap: 0.5em;
-    }
-}
-@media screen and (max-width: 768px) {
-    /* Further hide or simplify on mobile if needed */
-     .github-stats-badge {
-        display: none; /* Example: Hide completely on smallest screens */
-     }
-}
-
-/* --- Ask AI Selection Button --- */
-.ask-ai-selection-button {
-    background-color: var(--primary-dimmed-color, #09b5a5);
-    color: var(--background-color, #070708);
-    border: none;
-    padding: 4px 8px;
-    font-size: 0.8em;
-    border-radius: 4px;
-    cursor: pointer;
-    box-shadow: 0 2px 5px rgba(0, 0, 0, 0.3);
-    transition: background-color 0.2s ease;
-    white-space: nowrap;
-}
-
-.ask-ai-selection-button:hover {
-    background-color: var(--primary-color, #50ffff);
-}
-
-/* ==== File: docs/assets/layout.css (Additions) ==== */
-
-/* ... (keep all existing layout CSS) ... */
-
-/* --- Copy Code Button Styling --- */
-
-/* Ensure the parent <pre> can contain the absolutely positioned button */
-#terminal-mkdocs-main-content pre {
-    position: relative; /* Needed for absolute positioning of child */
-    /* Add a little padding top/right to make space for the button */
-    padding-top: 2.5em;
-    padding-right: 1em; /* Ensure padding is sufficient */
-}
-
-.copy-code-button {
-    position: absolute;
-    top: 0.5em; /* Adjust spacing from top */
-    left: 0.5em; /* Adjust spacing from left */
-    z-index: 1; /* Sit on top of code */
-
-    background-color: var(--progress-bar-background, #444); /* Use a background */
-    color: var(--font-color, #eaeaea);
-    border: 1px solid var(--secondary-color, #727578);
-    padding: 3px 8px;
-    font-size: 0.8em;
-    font-family: var(--font-stack, monospace);
-    border-radius: 4px;
-    cursor: pointer;
-    opacity: 0; /* Hidden by default */
-    transition: opacity 0.2s ease-in-out, background-color 0.2s ease, color 0.2s ease;
-    white-space: nowrap;
-}
-
-/* Show button on hover of the <pre> container */
-#terminal-mkdocs-main-content pre:hover .copy-code-button {
-    opacity: 0.8; /* Show partially */
-}
-
-.copy-code-button:hover {
-    opacity: 1; /* Fully visible on button hover */
-    background-color: var(--secondary-color, #727578);
-}
-
-.copy-code-button:focus {
-     opacity: 1; /* Ensure visible when focused */
-     outline: 1px dashed var(--primary-color);
-}
-
-
-/* Style for "Copied!" state */
-.copy-code-button.copied {
-    background-color: var(--primary-dimmed-color, #09b5a5);
-    color: var(--background-color, #070708);
-    border-color: var(--primary-dimmed-color, #09b5a5);
-    opacity: 1; /* Ensure visible */
-}
-.copy-code-button.copied:hover {
-     background-color: var(--primary-dimmed-color, #09b5a5); /* Prevent hover change */
-}
-
-/* ==== File: docs/assets/layout.css (Additions) ==== */
-
-/* ... (keep all existing layout CSS) ... */
-
-/* --- Floating Ask AI Button --- */
-.floating-ask-ai-button {
-    position: fixed;
-    bottom: 25px;
-    right: 25px;
-    z-index: 1050; /* Below modals, above most content */
-
-    background-color: var(--primary-dimmed-color, #09b5a5);
-    color: var(--background-color, #070708);
-    border: none;
-    border-radius: 50%; /* Make it circular */
-    width: 60px; /* Adjust size */
-    height: 60px; /* Adjust size */
-    padding: 10px; /* Adjust padding */
-    box-shadow: 0 4px 10px rgba(0, 0, 0, 0.4);
-    cursor: pointer;
-    transition: background-color 0.2s ease, transform 0.2s ease;
-
-    display: flex;
-    flex-direction: column; /* Stack icon and text */
-    align-items: center;
-    justify-content: center;
-    text-decoration: none;
-    text-align: center;
-}
-
-.floating-ask-ai-button svg {
-    width: 24px; /* Control icon size */
-    height: 24px;
-}
-
-.floating-ask-ai-button span {
-    font-size: 0.7em;
-    margin-top: 2px; /* Space between icon and text */
-    display: block; /* Ensure it takes space */
-     line-height: 1;
-}
-
-
-.floating-ask-ai-button:hover {
-    background-color: var(--primary-color, #50ffff);
-    transform: scale(1.05); /* Slight grow effect */
-}
-
-.floating-ask-ai-button:focus {
-     outline: 2px solid var(--primary-color);
-     outline-offset: 2px;
-}
-
-/* Optional: Hide text on smaller screens if needed */
-@media screen and (max-width: 768px) {
-     .floating-ask-ai-button span {
-        /* display: none; */ /* Uncomment to hide text */
-     }
-     .floating-ask-ai-button {
-        width: 55px;
-        height: 55px;
-        bottom: 20px;
-        right: 20px;
-     }
-}

docs/md_v2/assets/selection_ask_ai.js

@@ -1,109 +0,0 @@
-// ==== File: docs/assets/selection_ask_ai.js ====
-
-document.addEventListener('DOMContentLoaded', () => {
-    let askAiButton = null;
-    const askAiPageUrl = '/core/ask-ai/'; // Adjust if your Ask AI page path is different
-
-    function createAskAiButton() {
-        const button = document.createElement('button');
-        button.id = 'ask-ai-selection-btn';
-        button.className = 'ask-ai-selection-button';
-        button.textContent = 'Ask AI'; // Or use an icon
-        button.style.display = 'none'; // Initially hidden
-        button.style.position = 'absolute';
-        button.style.zIndex = '1500'; // Ensure it's on top
-        document.body.appendChild(button);
-
-        button.addEventListener('click', handleAskAiClick);
-        return button;
-    }
-
-    function getSafeSelectedText() {
-        const selection = window.getSelection();
-        if (!selection || selection.rangeCount === 0) {
-            return null;
-        }
-        // Avoid selecting text within the button itself if it was somehow selected
-        const container = selection.getRangeAt(0).commonAncestorContainer;
-        if (askAiButton && askAiButton.contains(container)) {
-             return null;
-        }
-
-        const text = selection.toString().trim();
-        return text.length > 0 ? text : null;
-    }
-
-    function positionButton(event) {
-         const selection = window.getSelection();
-         if (!selection || selection.rangeCount === 0 || selection.isCollapsed) {
-             hideButton();
-             return;
-         }
-
-        const range = selection.getRangeAt(0);
-        const rect = range.getBoundingClientRect();
-
-        // Calculate position: top-right of the selection
-        const scrollX = window.scrollX;
-        const scrollY = window.scrollY;
-        const buttonTop = rect.top + scrollY - askAiButton.offsetHeight - 5; // 5px above
-        const buttonLeft = rect.right + scrollX + 5; // 5px to the right
-
-        askAiButton.style.top = `${buttonTop}px`;
-        askAiButton.style.left = `${buttonLeft}px`;
-        askAiButton.style.display = 'block'; // Show the button
-    }
-
-    function hideButton() {
-        if (askAiButton) {
-            askAiButton.style.display = 'none';
-        }
-    }
-
-    function handleAskAiClick(event) {
-        event.stopPropagation(); // Prevent mousedown from hiding button immediately
-        const selectedText = getSafeSelectedText();
-        if (selectedText) {
-            console.log("Selected Text:", selectedText);
-            // Base64 encode for URL safety (handles special chars, line breaks)
-            // Use encodeURIComponent first for proper Unicode handling before btoa
-            const encodedText = btoa(unescape(encodeURIComponent(selectedText)));
-            const targetUrl = `${askAiPageUrl}?qq=${encodedText}`;
-            console.log("Navigating to:", targetUrl);
-            window.location.href = targetUrl; // Navigate to Ask AI page
-        }
-        hideButton(); // Hide after click
-    }
-
-    // --- Event Listeners ---
-
-    // Show button on mouse up after selection
-    document.addEventListener('mouseup', (event) => {
-        // Slight delay to ensure selection is registered
-        setTimeout(() => {
-            const selectedText = getSafeSelectedText();
-            if (selectedText) {
-                if (!askAiButton) {
-                    askAiButton = createAskAiButton();
-                }
-                // Don't position if the click was ON the button itself
-                if (event.target !== askAiButton) {
-                     positionButton(event);
-                }
-            } else {
-                hideButton();
-            }
-        }, 10); // Small delay
-    });
-
-    // Hide button on scroll or click elsewhere
-    document.addEventListener('mousedown', (event) => {
-        // Hide if clicking anywhere EXCEPT the button itself
-        if (askAiButton && event.target !== askAiButton) {
-            hideButton();
-        }
-    });
-    document.addEventListener('scroll', hideButton, true); // Capture scroll events
-
-    console.log("Selection Ask AI script loaded.");
-});

docs/md_v2/assets/styles.css

@@ -6,8 +6,8 @@
 }
 
 :root {
-    --global-font-size: 14px;
+    --global-font-size: 16px;
-    --global-code-font-size: 13px;
+    --global-code-font-size: 16px;
     --global-line-height: 1.5em;
     --global-space: 10px;
     --font-stack: Menlo, Monaco, Lucida Console, Liberation Mono, DejaVu Sans Mono, Bitstream Vera Sans Mono,
@@ -50,17 +50,8 @@
     --display-h1-decoration: none;
 
     --display-h1-decoration: none;
-
-    --header-height: 65px; /* Adjust based on your actual header height */
-    --sidebar-width: 280px; /* Adjust based on your desired sidebar width */
-    --toc-width: 240px; /* Adjust based on your desired ToC width */
-    --layout-transition-speed: 0.2s; /* For potential future animations */
-
-    --page-width : 100em; /* Adjust based on your design */
 }
 
-
-
 /* body {
     background-color: var(--background-color);
     color: var(--font-color);
@@ -265,6 +256,4 @@ div.badges a {
 }
 div.badges a > img {
     width: auto;
-}
+}
-
-

docs/md_v2/assets/toc.js

@@ -1,144 +0,0 @@
-// ==== File: assets/toc.js ====
-
-document.addEventListener('DOMContentLoaded', () => {
-    const mainContent = document.getElementById('terminal-mkdocs-main-content');
-    const tocContainer = document.getElementById('toc-sidebar');
-    const mainGrid = document.querySelector('.terminal-mkdocs-main-grid'); // Get the flex container
-
-    if (!mainContent) {
-        console.warn("TOC Generator: Main content area '#terminal-mkdocs-main-content' not found.");
-        return;
-    }
-
-    // --- Create ToC container if it doesn't exist ---
-    let tocElement = tocContainer;
-    if (!tocElement) {
-        if (!mainGrid) {
-            console.warn("TOC Generator: Flex container '.terminal-mkdocs-main-grid' not found to append ToC.");
-            return;
-        }
-        tocElement = document.createElement('aside');
-        tocElement.id = 'toc-sidebar';
-        tocElement.style.display = 'none'; // Keep hidden initially
-        // Append it as the last child of the flex grid
-        mainGrid.appendChild(tocElement);
-        console.info("TOC Generator: Created '#toc-sidebar' element.");
-    }
-
-    // --- Find Headings (h2, h3, h4 are common for ToC) ---
-    const headings = mainContent.querySelectorAll('h2, h3, h4');
-    if (headings.length === 0) {
-        console.info("TOC Generator: No headings found on this page. ToC not generated.");
-        tocElement.style.display = 'none'; // Ensure it's hidden
-        return;
-    }
-
-    // --- Generate ToC List ---
-    const tocList = document.createElement('ul');
-    const observerTargets = []; // Store headings for IntersectionObserver
-
-    headings.forEach((heading, index) => {
-        // Ensure heading has an ID for linking
-        if (!heading.id) {
-            // Create a simple slug-like ID
-            heading.id = `toc-heading-${index}-${heading.textContent.toLowerCase().replace(/\s+/g, '-').replace(/[^a-z0-9-]/g, '')}`;
-        }
-
-        const listItem = document.createElement('li');
-        const link = document.createElement('a');
-
-        link.href = `#${heading.id}`;
-        link.textContent = heading.textContent;
-
-        // Add class for styling based on heading level
-        const level = parseInt(heading.tagName.substring(1), 10); // Get 2, 3, or 4
-        listItem.classList.add(`toc-level-${level}`);
-
-        listItem.appendChild(link);
-        tocList.appendChild(listItem);
-        observerTargets.push(heading); // Add to observer list
-    });
-
-    // --- Populate and Show ToC ---
-    // Optional: Add a title
-    const tocTitle = document.createElement('h4');
-    tocTitle.textContent = 'On this page'; // Customize title if needed
-
-    tocElement.innerHTML = ''; // Clear previous content if any
-    tocElement.appendChild(tocTitle);
-    tocElement.appendChild(tocList);
-    tocElement.style.display = ''; // Show the ToC container
-
-    console.info(`TOC Generator: Generated ToC with ${headings.length} items.`);
-
-    // --- Scroll Spy using Intersection Observer ---
-    const tocLinks = tocElement.querySelectorAll('a');
-    let activeLink = null; // Keep track of the current active link
-
-    const observerOptions = {
-        // Observe changes relative to the viewport, offset by the header height
-        // Negative top margin pushes the intersection trigger point down
-        // Negative bottom margin ensures elements low on the screen can trigger before they exit
-        rootMargin: `-${getComputedStyle(document.documentElement).getPropertyValue('--header-height').trim()} 0px -60% 0px`,
-        threshold: 0 // Trigger as soon as any part enters/exits the boundary
-    };
-
-    const observerCallback = (entries) => {
-        let topmostVisibleHeading = null;
-
-        entries.forEach(entry => {
-            const link = tocElement.querySelector(`a[href="#${entry.target.id}"]`);
-            if (!link) return;
-
-            // Check if the heading is intersecting (partially or fully visible within rootMargin)
-            if (entry.isIntersecting) {
-                 // Among visible headings, find the one closest to the top edge (within the rootMargin)
-                if (!topmostVisibleHeading || entry.boundingClientRect.top < topmostVisibleHeading.boundingClientRect.top) {
-                    topmostVisibleHeading = entry.target;
-                 }
-            }
-        });
-
-        // If we found a topmost visible heading, activate its link
-        if (topmostVisibleHeading) {
-            const newActiveLink = tocElement.querySelector(`a[href="#${topmostVisibleHeading.id}"]`);
-            if (newActiveLink && newActiveLink !== activeLink) {
-                 // Remove active class from previous link
-                 if (activeLink) {
-                     activeLink.classList.remove('active');
-                     activeLink.parentElement.classList.remove('active-parent'); // Optional parent styling
-                 }
-                 // Add active class to the new link
-                 newActiveLink.classList.add('active');
-                 newActiveLink.parentElement.classList.add('active-parent'); // Optional parent styling
-                 activeLink = newActiveLink;
-
-                 // Optional: Scroll the ToC sidebar to keep the active link visible
-                 // newActiveLink.scrollIntoView({ behavior: 'smooth', block: 'nearest' });
-            }
-        }
-        // If no headings are intersecting (scrolled past the last one?), maybe deactivate all
-        // Or keep the last one active - depends on desired behavior. Current logic keeps last active.
-    };
-
-    const observer = new IntersectionObserver(observerCallback, observerOptions);
-
-    // Observe all target headings
-    observerTargets.forEach(heading => observer.observe(heading));
-
-    // Initial check in case a heading is already in view on load
-    // (Requires slight delay for accurate layout calculation)
-    setTimeout(() => {
-        observerCallback(observer.takeRecords()); // Process initial state
-    }, 100);
-
-    // move footer and the hr before footer to the end of the main content
-    const footer = document.querySelector('footer');
-    const hr = footer.previousElementSibling;
-    if (hr && hr.tagName === 'HR') {
-        mainContent.appendChild(hr);
-    }
-    mainContent.appendChild(footer);
-    console.info("TOC Generator: Footer moved to the end of the main content.");
-
-});

docs/md_v2/core/ask-ai.md

@@ -1,74 +0,0 @@
-<div class="ask-ai-container">
-<iframe id="ask-ai-frame" src="../../ask_ai/index.html" width="100%" style="border:none; display: block;" title="Crawl4AI Assistant"></iframe>
-</div>
-
-<script>
-// Iframe height adjustment
-function resizeAskAiIframe() {
-  const iframe = document.getElementById('ask-ai-frame');
-  if (iframe) {
-    const headerHeight = parseFloat(getComputedStyle(document.documentElement).getPropertyValue('--header-height') || '55');
-    // Footer is removed by JS below, so calculate height based on header + small buffer
-    const topOffset = headerHeight + 20; // Header + buffer/margin
-
-    const availableHeight = window.innerHeight - topOffset;
-    iframe.style.height = Math.max(600, availableHeight) + 'px'; // Min height 600px
-  }
-}
-
-// Run immediately and on resize/load
-resizeAskAiIframe(); // Initial call
-let resizeTimer;
-window.addEventListener('load', resizeAskAiIframe);
-window.addEventListener('resize', () => {
-    clearTimeout(resizeTimer);
-    resizeTimer = setTimeout(resizeAskAiIframe, 150);
-});
-
-// Remove Footer & HR from parent page (DOM Ready might be safer)
-document.addEventListener('DOMContentLoaded', () => {
-    setTimeout(() => { // Add slight delay just in case elements render slowly
-        const footer = window.parent.document.querySelector('footer'); // Target parent document
-        if (footer) {
-            const hrBeforeFooter = footer.previousElementSibling;
-            if (hrBeforeFooter && hrBeforeFooter.tagName === 'HR') {
-                hrBeforeFooter.remove();
-            }
-            footer.remove();
-            // Trigger resize again after removing footer
-            resizeAskAiIframe();
-        } else {
-             console.warn("Ask AI Page: Could not find footer in parent document to remove.");
-        }
-    }, 100); // Shorter delay
-});
-</script>
-
-<style>
-#terminal-mkdocs-main-content {
-    padding: 0 !important;
-    margin: 0;
-    width: 100%;
-    height: 100%;
-    overflow: hidden; /* Prevent body scrollbars, panels handle scroll */
-}
-
-/* Ensure iframe container takes full space */
-#terminal-mkdocs-main-content .ask-ai-container {
-    /* Remove negative margins if footer removal handles space */
-     margin: 0;
-    padding: 0;
-    max-width: none;
-    /* Let the JS set the height */
-    /* height: 600px; Initial fallback height */
-    overflow: hidden; /* Hide potential overflow before JS resize */
-}
-
-/* Hide title/paragraph if they were part of the markdown */
-/* Alternatively, just remove them from the .md file directly */
-/* #terminal-mkdocs-main-content > h1,
-#terminal-mkdocs-main-content > p:first-of-type {
-    display: none;
-} */
-
-</style>

docs/md_v2/core/browser-crawler-config.md

@@ -136,7 +136,6 @@ class CrawlerRunConfig:
         wait_for=None,
         screenshot=False,
         pdf=False,
-        capture_mhtml=False,
         enable_rate_limiting=False,
         rate_limit_config=None,
         memory_threshold_percent=70.0,
@@ -176,9 +175,10 @@ class CrawlerRunConfig:
    - A CSS or JS expression to wait for before extracting content.  
    - Common usage: `wait_for="css:.main-loaded"` or `wait_for="js:() => window.loaded === true"`.
 
-7. **`screenshot`**, **`pdf`**, & **`capture_mhtml`**:  
+7. **`screenshot`** & **`pdf`**:  
-   - If `True`, captures a screenshot, PDF, or MHTML snapshot after the page is fully loaded.  
+   - If `True`, captures a screenshot or PDF after the page is fully loaded.  
-   - The results go to `result.screenshot` (base64), `result.pdf` (bytes), or `result.mhtml` (string).
+   - The results go to `result.screenshot` (base64) or `result.pdf` (bytes).
+
 8. **`verbose`**:  
    - Logs additional runtime details.  
    - Overlaps with the browser’s verbosity if also set to `True` in `BrowserConfig`.