feat(cli): add deep crawling options with configurable strategies and max pages. ref #874

Add comprehensive virtual scroll handling to capture all content from pages that use DOM recycling techniques (Twitter, Instagram, etc).

Key features:
- New VirtualScrollConfig class for configuring virtual scroll behavior
- Automatic detection of three scrolling scenarios: no change, content appended, content replaced
- Intelligent HTML chunk capture and merging with deduplication
- 100% content capture from virtual scroll pages
- Seamless integration with existing extraction strategies
- JavaScript-based detection and capture for performance
- Tree-based DOM merging with text-based deduplication

Documentation:
- Comprehensive guide at docs/md_v2/advanced/virtual-scroll.md
- API reference updates in parameters.md and page-interaction.md
- Blog article explaining the solution and techniques
- Complete examples with local test server

Testing:
- Full test suite achieving 100% capture of 1000 items
- Examples for Twitter timeline, Instagram grid scenarios
- Local test server with different scrolling behaviors

This enables scraping of modern websites that were previously impossible to fully capture with traditional scrolling techniques.

.claude/settings.local.json

@@ -0,0 +1,28 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(cd:*)",
+      "Bash(python3:*)",
+      "Bash(python:*)",
+      "Bash(grep:*)",
+      "Bash(mkdir:*)",
+      "Bash(cp:*)",
+      "Bash(rm:*)",
+      "Bash(true)",
+      "Bash(./package-extension.sh:*)",
+      "Bash(find:*)",
+      "Bash(chmod:*)",
+      "Bash(rg:*)",
+      "Bash(/Users/unclecode/.npm-global/lib/node_modules/@anthropic-ai/claude-code/vendor/ripgrep/arm64-darwin/rg -A 5 -B 5 \"Script Builder\" docs/md_v2/apps/crawl4ai-assistant/)",
+      "Bash(/Users/unclecode/.npm-global/lib/node_modules/@anthropic-ai/claude-code/vendor/ripgrep/arm64-darwin/rg -A 30 \"generateCode\\(events, format\\)\" docs/md_v2/apps/crawl4ai-assistant/content/content.js)",
+      "Bash(/Users/unclecode/.npm-global/lib/node_modules/@anthropic-ai/claude-code/vendor/ripgrep/arm64-darwin/rg \"<style>\" docs/md_v2/apps/crawl4ai-assistant/index.html -A 5)",
+      "Bash(git checkout:*)",
+      "Bash(docker logs:*)",
+      "Bash(curl:*)",
+      "Bash(docker compose:*)",
+      "Bash(./test-final-integration.sh:*)",
+      "Bash(mv:*)"
+    ]
+  },
+  "enableAllProjectMcpServers": false
+}

.gitignore

@@ -261,4 +261,10 @@ CLAUDE.md
 
 tests/**/test_site
 tests/**/reports
-tests/**/benchmark_reports
+tests/**/benchmark_reports
+
+docs/**/data
+.codecat/
+
+docs/apps/linkdin/debug*/
+docs/apps/linkdin/samples/insights/*

CHANGELOG.md

@@ -5,7 +5,81 @@ 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).
 
-## [0.6.0rc1] ‑ 2025‑04‑22
+## [0.7.x] - 2025-06-29
+
+### Added
+- **Virtual Scroll Support**: New `VirtualScrollConfig` for handling virtualized scrolling on modern websites
+  - Automatically detects and handles three scrolling scenarios:
+    - Content unchanged (continue scrolling)
+    - Content appended (traditional infinite scroll)
+    - Content replaced (true virtual scroll - Twitter/Instagram style)
+  - Captures ALL content from pages that replace DOM elements during scroll
+  - Intelligent deduplication based on normalized text content
+  - Configurable scroll amount, count, and wait times
+  - Seamless integration with existing extraction strategies
+  - Comprehensive examples including Twitter timeline, Instagram grid, and mixed content scenarios
+
+## [Unreleased]
+
+### Added
+- **AsyncUrlSeeder**: High-performance URL discovery system for intelligent crawling at scale
+  - Discover URLs from sitemaps and Common Crawl index
+  - Extract and analyze page metadata without full crawling
+  - BM25 relevance scoring for query-based URL filtering
+  - Multi-domain parallel discovery with `many_urls()` method
+  - Automatic caching with TTL for discovered URLs
+  - Rate limiting and concurrent request management
+  - Live URL validation with HEAD requests
+  - JSON-LD and Open Graph metadata extraction
+- **SeedingConfig**: Configuration class for URL seeding operations
+  - Support for multiple discovery sources (`sitemap`, `cc`, `sitemap+cc`)
+  - Pattern-based URL filtering with wildcards
+  - Configurable concurrency and rate limiting
+  - Query-based relevance scoring with BM25
+  - Score threshold filtering for quality control
+- Comprehensive documentation for URL seeding feature
+  - Detailed comparison with deep crawling approaches
+  - Complete API reference with examples
+  - Integration guide with AsyncWebCrawler
+  - Performance benchmarks and best practices
+- Example scripts demonstrating URL seeding:
+  - `url_seeder_demo.py`: Interactive Rich-based demonstration
+  - `url_seeder_quick_demo.py`: Screenshot-friendly examples
+- Test suite for URL seeding with BM25 scoring
+
+### Changed
+- Updated `__init__.py` to export AsyncUrlSeeder and SeedingConfig
+- Enhanced documentation with URL seeding integration examples
+
+### Fixed
+- Corrected examples to properly extract URLs from seeder results before passing to `arun_many()`
+- Fixed logger color compatibility issue (changed `lightblack` to `bright_black`)
+
+## [0.6.2] - 2025-05-02
+
+### Added
+- New `RegexExtractionStrategy` for fast pattern-based extraction without requiring LLM
+  - Built-in patterns for emails, URLs, phone numbers, dates, and more
+  - Support for custom regex patterns
+  - `generate_pattern` utility for LLM-assisted pattern creation (one-time use)
+- Added `fit_html` as a top-level field in `CrawlResult` for optimized HTML extraction
+- Added support for network response body capture in network request tracking
+
+### Changed
+- Updated documentation for no-LLM extraction strategies
+- Enhanced API reference to include RegexExtractionStrategy examples and usage
+- Improved HTML preprocessing with optimized performance for extraction strategies
+
+## [0.6.1] - 2025-04-24
+
+### Added
+- New dedicated `tables` field in `CrawlResult` model for better table extraction handling
+- Updated crypto_analysis_example.py to use the new tables field with backward compatibility
+
+### Changed
+- Improved playground UI in Docker deployment with better endpoint handling and UI feedback
+
+## [0.6.0] ‑ 2025‑04‑22
 
 ### Added
 - Browser pooling with page pre‑warming and fine‑grained **geolocation, locale, and timezone** controls  

README.md

@@ -21,9 +21,9 @@
 
 Crawl4AI is the #1 trending GitHub repository, actively maintained by a vibrant community. It delivers blazing-fast, AI-ready web crawling tailored for LLMs, AI agents, and data pipelines. Open source, flexible, and built for real-time performance, Crawl4AI empowers developers with unmatched speed, precision, and deployment ease.  
 
-[✨ Check out latest update v0.6.0rc1](#-recent-updates)
+[✨ Check out latest update v0.6.0](#-recent-updates)
 
-🎉 **Version 0.6.0rc1 is now available!** This release candidate introduces World-aware Crawling with geolocation and locale settings, Table-to-DataFrame extraction, Browser pooling with pre-warming, Network and console traffic capture, MCP integration for AI tools, and a completely revamped Docker deployment! [Read the release notes →](https://docs.crawl4ai.com/blog)
+🎉 **Version 0.6.0 is now available!** This release candidate introduces World-aware Crawling with geolocation and locale settings, Table-to-DataFrame extraction, Browser pooling with pre-warming, Network and console traffic capture, MCP integration for AI tools, and a completely revamped Docker deployment! [Read the release notes →](https://docs.crawl4ai.com/blog)
 
 <details>
 <summary>🤓 <strong>My Personal Story</strong></summary>
@@ -352,7 +352,7 @@ if __name__ == "__main__":
 ```python
 import asyncio
 from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 import json
 
 async def main():
@@ -426,7 +426,7 @@ if __name__ == "__main__":
 import os
 import asyncio
 from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode, LLMConfig
-from crawl4ai.extraction_strategy import LLMExtractionStrategy
+from crawl4ai import LLMExtractionStrategy
 from pydantic import BaseModel, Field
 
 class OpenAIModelFee(BaseModel):
@@ -505,7 +505,7 @@ async def test_news_crawl():
 
 ## ✨ Recent Updates
 
-### Version 0.6.0rc1 Release Highlights
+### Version 0.6.0 Release Highlights
 
 - **🌎 World-aware Crawling**: Set geolocation, language, and timezone for authentic locale-specific content:
   ```python
@@ -575,7 +575,7 @@ async def test_news_crawl():
 
 - **📱 Multi-stage Build System**: Optimized Dockerfile with platform-specific performance enhancements
 
-Read the full details in our [0.6.0rc1 Release Notes](https://docs.crawl4ai.com/blog/releases/0.6.0.html) or check the [CHANGELOG](https://github.com/unclecode/crawl4ai/blob/main/CHANGELOG.md).
+Read the full details in our [0.6.0 Release Notes](https://docs.crawl4ai.com/blog/releases/0.6.0.html) or check the [CHANGELOG](https://github.com/unclecode/crawl4ai/blob/main/CHANGELOG.md).
 
 ### Previous Version: 0.5.0 Major Release Highlights
 
@@ -606,7 +606,7 @@ We use different suffixes to indicate development stages:
 - `dev` (0.4.3dev1): Development versions, unstable
 - `a` (0.4.3a1): Alpha releases, experimental features
 - `b` (0.4.3b1): Beta releases, feature complete but needs testing
-- `rc` (0.4.3rc1): Release candidates, potential final version
+- `rc` (0.4.3): Release candidates, potential final version
 
 #### Installation
 - Regular installation (stable version):

crawl4ai/__init__.py

@@ -2,7 +2,8 @@
 import warnings
 
 from .async_webcrawler import AsyncWebCrawler, CacheMode
-from .async_configs import BrowserConfig, CrawlerRunConfig, HTTPCrawlerConfig, LLMConfig, ProxyConfig, GeolocationConfig
+# MODIFIED: Add SeedingConfig and VirtualScrollConfig here
+from .async_configs import BrowserConfig, CrawlerRunConfig, HTTPCrawlerConfig, LLMConfig, ProxyConfig, GeolocationConfig, SeedingConfig, VirtualScrollConfig
 
 from .content_scraping_strategy import (
     ContentScrapingStrategy,
@@ -23,7 +24,8 @@ from .extraction_strategy import (
     CosineStrategy,
     JsonCssExtractionStrategy,
     JsonXPathExtractionStrategy,
-    JsonLxmlExtractionStrategy
+    JsonLxmlExtractionStrategy,
+    RegexExtractionStrategy
 )
 from .chunking_strategy import ChunkingStrategy, RegexChunking
 from .markdown_generation_strategy import DefaultMarkdownGenerator
@@ -35,6 +37,7 @@ from .content_filter_strategy import (
 )
 from .models import CrawlResult, MarkdownGenerationResult, DisplayMode
 from .components.crawler_monitor import CrawlerMonitor
+from .link_preview import LinkPreview
 from .async_dispatcher import (
     MemoryAdaptiveDispatcher,
     SemaphoreDispatcher,
@@ -64,6 +67,23 @@ from .deep_crawling import (
     DFSDeepCrawlStrategy,
     DeepCrawlDecorator,
 )
+# NEW: Import AsyncUrlSeeder
+from .async_url_seeder import AsyncUrlSeeder
+
+# C4A Script Language Support
+from .script import (
+    compile as c4a_compile,
+    validate as c4a_validate,
+    compile_file as c4a_compile_file,
+    CompilationResult,
+    ValidationResult,
+    ErrorDetail
+)
+
+from .utils import (
+    start_colab_display_server,
+    setup_colab_environment
+)
 
 __all__ = [
     "AsyncLoggerBase",
@@ -72,6 +92,11 @@ __all__ = [
     "BrowserProfiler",
     "LLMConfig",
     "GeolocationConfig",
+    # NEW: Add SeedingConfig and VirtualScrollConfig
+    "SeedingConfig",
+    "VirtualScrollConfig",
+    # NEW: Add AsyncUrlSeeder
+    "AsyncUrlSeeder",
     "DeepCrawlStrategy",
     "BFSDeepCrawlStrategy",
     "BestFirstCrawlingStrategy",
@@ -105,6 +130,7 @@ __all__ = [
     "JsonCssExtractionStrategy",
     "JsonXPathExtractionStrategy",
     "JsonLxmlExtractionStrategy",
+    "RegexExtractionStrategy",
     "ChunkingStrategy",
     "RegexChunking",
     "DefaultMarkdownGenerator",
@@ -117,12 +143,22 @@ __all__ = [
     "SemaphoreDispatcher",
     "RateLimiter",
     "CrawlerMonitor",
+    "LinkPreview",
     "DisplayMode",
     "MarkdownGenerationResult",
     "Crawl4aiDockerClient",
     "ProxyRotationStrategy",
     "RoundRobinProxyStrategy",
-    "ProxyConfig"
+    "ProxyConfig",
+    "start_colab_display_server",
+    "setup_colab_environment",
+    # C4A Script additions
+    "c4a_compile",
+    "c4a_validate", 
+    "c4a_compile_file",
+    "CompilationResult",
+    "ValidationResult",
+    "ErrorDetail",
 ]
 
 
@@ -151,4 +187,4 @@ __all__ = [
 
 # Disable all Pydantic warnings
 warnings.filterwarnings("ignore", module="pydantic")
-# pydantic_warnings.filter_warnings()
+# pydantic_warnings.filter_warnings()

crawl4ai/__version__.py

@@ -1,3 +1,3 @@
 # crawl4ai/_version.py
-__version__ = "0.6.0"
+__version__ = "0.6.3"
 

crawl4ai/async_configs.py

@@ -1,4 +1,5 @@
 import os
+from typing import Union
 from .config import (
     DEFAULT_PROVIDER,
     DEFAULT_PROVIDER_API_KEY,
@@ -17,7 +18,7 @@ from .extraction_strategy import ExtractionStrategy, LLMExtractionStrategy
 from .chunking_strategy import ChunkingStrategy, RegexChunking
 
 from .markdown_generation_strategy import MarkdownGenerationStrategy, DefaultMarkdownGenerator
-from .content_scraping_strategy import ContentScrapingStrategy, WebScrapingStrategy
+from .content_scraping_strategy import ContentScrapingStrategy, WebScrapingStrategy, LXMLWebScrapingStrategy
 from .deep_crawling import DeepCrawlStrategy
 
 from .cache_context import CacheMode
@@ -207,7 +208,6 @@ class GeolocationConfig:
         config_dict.update(kwargs)
         return GeolocationConfig.from_dict(config_dict)
 
-
 class ProxyConfig:
     def __init__(
         self,
@@ -318,8 +318,6 @@ class ProxyConfig:
         config_dict.update(kwargs)
         return ProxyConfig.from_dict(config_dict)
 
-
-
 class BrowserConfig:
     """
     Configuration class for setting up a browser instance and its context in AsyncPlaywrightCrawlerStrategy.
@@ -427,7 +425,7 @@ 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
@@ -597,6 +595,145 @@ class BrowserConfig:
             return config
         return BrowserConfig.from_kwargs(config)
 
+class VirtualScrollConfig:
+    """Configuration for virtual scroll handling.
+    
+    This config enables capturing content from pages with virtualized scrolling
+    (like Twitter, Instagram feeds) where DOM elements are recycled as user scrolls.
+    """
+    
+    def __init__(
+        self,
+        container_selector: str,
+        scroll_count: int = 10,
+        scroll_by: Union[str, int] = "container_height",
+        wait_after_scroll: float = 0.5,
+    ):
+        """
+        Initialize virtual scroll configuration.
+        
+        Args:
+            container_selector: CSS selector for the scrollable container
+            scroll_count: Maximum number of scrolls to perform
+            scroll_by: Amount to scroll - can be:
+                - "container_height": scroll by container's height
+                - "page_height": scroll by viewport height  
+                - int: fixed pixel amount
+            wait_after_scroll: Seconds to wait after each scroll for content to load
+        """
+        self.container_selector = container_selector
+        self.scroll_count = scroll_count
+        self.scroll_by = scroll_by
+        self.wait_after_scroll = wait_after_scroll
+    
+    def to_dict(self) -> dict:
+        """Convert to dictionary for serialization."""
+        return {
+            "container_selector": self.container_selector,
+            "scroll_count": self.scroll_count,
+            "scroll_by": self.scroll_by,
+            "wait_after_scroll": self.wait_after_scroll,
+        }
+    
+    @classmethod
+    def from_dict(cls, data: dict) -> "VirtualScrollConfig":
+        """Create instance from dictionary."""
+        return cls(**data)
+
+class LinkPreviewConfig:
+    """Configuration for link head extraction and scoring."""
+    
+    def __init__(
+        self,
+        include_internal: bool = True,
+        include_external: bool = False,
+        include_patterns: Optional[List[str]] = None,
+        exclude_patterns: Optional[List[str]] = None,
+        concurrency: int = 10,
+        timeout: int = 5,
+        max_links: int = 100,
+        query: Optional[str] = None,
+        score_threshold: Optional[float] = None,
+        verbose: bool = False
+    ):
+        """
+        Initialize link extraction configuration.
+        
+        Args:
+            include_internal: Whether to include same-domain links
+            include_external: Whether to include different-domain links  
+            include_patterns: List of glob patterns to include (e.g., ["*/docs/*", "*/api/*"])
+            exclude_patterns: List of glob patterns to exclude (e.g., ["*/login*", "*/admin*"])
+            concurrency: Number of links to process simultaneously
+            timeout: Timeout in seconds for each link's head extraction
+            max_links: Maximum number of links to process (prevents overload)
+            query: Query string for BM25 contextual scoring (optional)
+            score_threshold: Minimum relevance score to include links (0.0-1.0, optional)
+            verbose: Show detailed progress during extraction
+        """
+        self.include_internal = include_internal
+        self.include_external = include_external
+        self.include_patterns = include_patterns
+        self.exclude_patterns = exclude_patterns
+        self.concurrency = concurrency
+        self.timeout = timeout
+        self.max_links = max_links
+        self.query = query
+        self.score_threshold = score_threshold
+        self.verbose = verbose
+        
+        # Validation
+        if concurrency <= 0:
+            raise ValueError("concurrency must be positive")
+        if timeout <= 0:
+            raise ValueError("timeout must be positive")
+        if max_links <= 0:
+            raise ValueError("max_links must be positive")
+        if score_threshold is not None and not (0.0 <= score_threshold <= 1.0):
+            raise ValueError("score_threshold must be between 0.0 and 1.0")
+        if not include_internal and not include_external:
+            raise ValueError("At least one of include_internal or include_external must be True")
+    
+    @staticmethod
+    def from_dict(config_dict: Dict[str, Any]) -> "LinkPreviewConfig":
+        """Create LinkPreviewConfig from dictionary (for backward compatibility)."""
+        if not config_dict:
+            return None
+        
+        return LinkPreviewConfig(
+            include_internal=config_dict.get("include_internal", True),
+            include_external=config_dict.get("include_external", False),
+            include_patterns=config_dict.get("include_patterns"),
+            exclude_patterns=config_dict.get("exclude_patterns"),
+            concurrency=config_dict.get("concurrency", 10),
+            timeout=config_dict.get("timeout", 5),
+            max_links=config_dict.get("max_links", 100),
+            query=config_dict.get("query"),
+            score_threshold=config_dict.get("score_threshold"),
+            verbose=config_dict.get("verbose", False)
+        )
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary format."""
+        return {
+            "include_internal": self.include_internal,
+            "include_external": self.include_external,
+            "include_patterns": self.include_patterns,
+            "exclude_patterns": self.exclude_patterns,
+            "concurrency": self.concurrency,
+            "timeout": self.timeout,
+            "max_links": self.max_links,
+            "query": self.query,
+            "score_threshold": self.score_threshold,
+            "verbose": self.verbose
+        }
+    
+    def clone(self, **kwargs) -> "LinkPreviewConfig":
+        """Create a copy with updated values."""
+        config_dict = self.to_dict()
+        config_dict.update(kwargs)
+        return LinkPreviewConfig.from_dict(config_dict)
+
 
 class HTTPCrawlerConfig:
     """HTTP-specific crawler configuration"""
@@ -764,6 +901,9 @@ class CrawlerRunConfig():
                             Default: 60000 (60 seconds).
         wait_for (str or None): A CSS selector or JS condition to wait for before extracting content.
                                 Default: None.
+        wait_for_timeout (int or None): Specific timeout in ms for the wait_for condition.
+                                       If None, uses page_timeout instead.
+                                       Default: None.
         wait_for_images (bool): If True, wait for images to load before extracting content.
                                 Default: False.
         delay_before_return_html (float): Delay in seconds before retrieving final HTML.
@@ -817,6 +957,12 @@ class CrawlerRunConfig():
         table_score_threshold (int): Minimum score threshold for processing a table.
                                      Default: 7.
 
+        # Virtual Scroll Parameters
+        virtual_scroll_config (VirtualScrollConfig or dict or None): Configuration for handling virtual scroll containers.
+                                                                     Used for capturing content from pages with virtualized 
+                                                                     scrolling (e.g., Twitter, Instagram feeds).
+                                                                     Default: None.
+
         # Link and Domain Handling Parameters
         exclude_social_media_domains (list of str): List of domains to exclude for social media links.
                                                     Default: SOCIAL_MEDIA_DOMAINS (from config).
@@ -830,6 +976,9 @@ class CrawlerRunConfig():
                                        Default: [].
         exclude_internal_links (bool): If True, exclude internal links from the results.
                                        Default: False.
+        score_links (bool): If True, calculate intrinsic quality scores for all links using URL structure,
+                           text quality, and contextual relevance metrics. Separate from link_preview_config.
+                           Default: False.
 
         # Debugging and Logging Parameters
         verbose (bool): Enable verbose logging.
@@ -904,6 +1053,7 @@ class CrawlerRunConfig():
         wait_until: str = "domcontentloaded",
         page_timeout: int = PAGE_TIMEOUT,
         wait_for: str = None,
+        wait_for_timeout: int = None,
         wait_for_images: bool = False,
         delay_before_return_html: float = 0.1,
         mean_delay: float = 0.1,
@@ -911,6 +1061,7 @@ class CrawlerRunConfig():
         semaphore_count: int = 5,
         # Page Interaction Parameters
         js_code: Union[str, List[str]] = None,
+        c4a_script: Union[str, List[str]] = None,
         js_only: bool = False,
         ignore_body_visibility: bool = True,
         scan_full_page: bool = False,
@@ -938,6 +1089,7 @@ class CrawlerRunConfig():
         exclude_social_media_links: bool = False,
         exclude_domains: list = None,
         exclude_internal_links: bool = False,
+        score_links: bool = False,
         # Debugging and Logging Parameters
         verbose: bool = True,
         log_console: bool = False,
@@ -954,6 +1106,10 @@ class CrawlerRunConfig():
         user_agent_generator_config: dict = {},
         # Deep Crawl Parameters
         deep_crawl_strategy: Optional[DeepCrawlStrategy] = None,
+        # Link Extraction Parameters
+        link_preview_config: Union[LinkPreviewConfig, Dict[str, Any]] = None,
+        # Virtual Scroll Parameters
+        virtual_scroll_config: Union[VirtualScrollConfig, Dict[str, Any]] = None,
         # Experimental Parameters
         experimental: Dict[str, Any] = None,
     ):
@@ -975,7 +1131,7 @@ class CrawlerRunConfig():
         self.remove_forms = remove_forms
         self.prettiify = prettiify
         self.parser_type = parser_type
-        self.scraping_strategy = scraping_strategy or WebScrapingStrategy()
+        self.scraping_strategy = scraping_strategy or LXMLWebScrapingStrategy()
         self.proxy_config = proxy_config
         self.proxy_rotation_strategy = proxy_rotation_strategy
         
@@ -1000,6 +1156,7 @@ class CrawlerRunConfig():
         self.wait_until = wait_until
         self.page_timeout = page_timeout
         self.wait_for = wait_for
+        self.wait_for_timeout = wait_for_timeout
         self.wait_for_images = wait_for_images
         self.delay_before_return_html = delay_before_return_html
         self.mean_delay = mean_delay
@@ -1008,6 +1165,7 @@ class CrawlerRunConfig():
 
         # Page Interaction Parameters
         self.js_code = js_code
+        self.c4a_script = c4a_script
         self.js_only = js_only
         self.ignore_body_visibility = ignore_body_visibility
         self.scan_full_page = scan_full_page
@@ -1039,6 +1197,7 @@ class CrawlerRunConfig():
         self.exclude_social_media_links = exclude_social_media_links
         self.exclude_domains = exclude_domains or []
         self.exclude_internal_links = exclude_internal_links
+        self.score_links = score_links
 
         # Debugging and Logging Parameters
         self.verbose = verbose
@@ -1081,8 +1240,83 @@ class CrawlerRunConfig():
         # Deep Crawl Parameters
         self.deep_crawl_strategy = deep_crawl_strategy
         
+        # Link Extraction Parameters
+        if link_preview_config is None:
+            self.link_preview_config = None
+        elif isinstance(link_preview_config, LinkPreviewConfig):
+            self.link_preview_config = link_preview_config
+        elif isinstance(link_preview_config, dict):
+            # Convert dict to config object for backward compatibility
+            self.link_preview_config = LinkPreviewConfig.from_dict(link_preview_config)
+        else:
+            raise ValueError("link_preview_config must be LinkPreviewConfig object or dict")
+        
+        # Virtual Scroll Parameters
+        if virtual_scroll_config is None:
+            self.virtual_scroll_config = None
+        elif isinstance(virtual_scroll_config, VirtualScrollConfig):
+            self.virtual_scroll_config = virtual_scroll_config
+        elif isinstance(virtual_scroll_config, dict):
+            # Convert dict to config object for backward compatibility
+            self.virtual_scroll_config = VirtualScrollConfig.from_dict(virtual_scroll_config)
+        else:
+            raise ValueError("virtual_scroll_config must be VirtualScrollConfig object or dict")
+        
         # Experimental Parameters
         self.experimental = experimental or {}
+        
+        # Compile C4A scripts if provided
+        if self.c4a_script and not self.js_code:
+            self._compile_c4a_script()
+
+
+    def _compile_c4a_script(self):
+        """Compile C4A script to JavaScript"""
+        try:
+            # Try importing the compiler
+            try:
+                from .script import compile
+            except ImportError:
+                from crawl4ai.script import compile
+                
+            # Handle both string and list inputs
+            if isinstance(self.c4a_script, str):
+                scripts = [self.c4a_script]
+            else:
+                scripts = self.c4a_script
+                
+            # Compile each script
+            compiled_js = []
+            for i, script in enumerate(scripts):
+                result = compile(script)
+                
+                if result.success:
+                    compiled_js.extend(result.js_code)
+                else:
+                    # Format error message following existing patterns
+                    error = result.first_error
+                    error_msg = (
+                        f"C4A Script compilation error (script {i+1}):\n"
+                        f"  Line {error.line}, Column {error.column}: {error.message}\n"
+                        f"  Code: {error.source_line}"
+                    )
+                    if error.suggestions:
+                        error_msg += f"\n  Suggestion: {error.suggestions[0].message}"
+                        
+                    raise ValueError(error_msg)
+                    
+            self.js_code = compiled_js
+            
+        except ImportError:
+            raise ValueError(
+                "C4A script compiler not available. "
+                "Please ensure crawl4ai.script module is properly installed."
+            )
+        except Exception as e:
+            # Re-raise with context
+            if "compilation error" not in str(e).lower():
+                raise ValueError(f"Failed to compile C4A script: {str(e)}")
+            raise
 
 
     def __getattr__(self, name):
@@ -1141,6 +1375,7 @@ class CrawlerRunConfig():
             wait_until=kwargs.get("wait_until", "domcontentloaded"),
             page_timeout=kwargs.get("page_timeout", 60000),
             wait_for=kwargs.get("wait_for"),
+            wait_for_timeout=kwargs.get("wait_for_timeout"),
             wait_for_images=kwargs.get("wait_for_images", False),
             delay_before_return_html=kwargs.get("delay_before_return_html", 0.1),
             mean_delay=kwargs.get("mean_delay", 0.1),
@@ -1184,6 +1419,7 @@ class CrawlerRunConfig():
             exclude_social_media_links=kwargs.get("exclude_social_media_links", False),
             exclude_domains=kwargs.get("exclude_domains", []),
             exclude_internal_links=kwargs.get("exclude_internal_links", False),
+            score_links=kwargs.get("score_links", False),
             # Debugging and Logging Parameters
             verbose=kwargs.get("verbose", True),
             log_console=kwargs.get("log_console", False),
@@ -1199,6 +1435,8 @@ class CrawlerRunConfig():
             user_agent_generator_config=kwargs.get("user_agent_generator_config", {}),
             # Deep Crawl Parameters
             deep_crawl_strategy=kwargs.get("deep_crawl_strategy"),
+            # Link Extraction Parameters
+            link_preview_config=kwargs.get("link_preview_config"),
             url=kwargs.get("url"),
             # Experimental Parameters 
             experimental=kwargs.get("experimental"),
@@ -1250,6 +1488,7 @@ class CrawlerRunConfig():
             "wait_until": self.wait_until,
             "page_timeout": self.page_timeout,
             "wait_for": self.wait_for,
+            "wait_for_timeout": self.wait_for_timeout,
             "wait_for_images": self.wait_for_images,
             "delay_before_return_html": self.delay_before_return_html,
             "mean_delay": self.mean_delay,
@@ -1281,6 +1520,7 @@ class CrawlerRunConfig():
             "exclude_social_media_links": self.exclude_social_media_links,
             "exclude_domains": self.exclude_domains,
             "exclude_internal_links": self.exclude_internal_links,
+            "score_links": self.score_links,
             "verbose": self.verbose,
             "log_console": self.log_console,
             "capture_network_requests": self.capture_network_requests,
@@ -1292,6 +1532,7 @@ class CrawlerRunConfig():
             "user_agent_mode": self.user_agent_mode,
             "user_agent_generator_config": self.user_agent_generator_config,
             "deep_crawl_strategy": self.deep_crawl_strategy,
+            "link_preview_config": self.link_preview_config.to_dict() if self.link_preview_config else None,
             "url": self.url,
             "experimental": self.experimental,
         }
@@ -1322,14 +1563,13 @@ class CrawlerRunConfig():
         config_dict.update(kwargs)
         return CrawlerRunConfig.from_kwargs(config_dict)
 
-
 class LLMConfig:
     def __init__(
         self,
         provider: str = DEFAULT_PROVIDER,
         api_token: Optional[str] = None,
         base_url: Optional[str] = None,
-        temprature: Optional[float] = None,
+        temperature: Optional[float] = None,
         max_tokens: Optional[int] = None,
         top_p: Optional[float] = None,
         frequency_penalty: Optional[float] = None,
@@ -1357,7 +1597,7 @@ class LLMConfig:
                 self.provider = DEFAULT_PROVIDER
                 self.api_token = os.getenv(DEFAULT_PROVIDER_API_KEY)
         self.base_url = base_url
-        self.temprature = temprature
+        self.temperature = temperature
         self.max_tokens = max_tokens
         self.top_p = top_p
         self.frequency_penalty = frequency_penalty
@@ -1371,7 +1611,7 @@ class LLMConfig:
             provider=kwargs.get("provider", DEFAULT_PROVIDER),
             api_token=kwargs.get("api_token"),
             base_url=kwargs.get("base_url"),
-            temprature=kwargs.get("temprature"),
+            temperature=kwargs.get("temperature"),
             max_tokens=kwargs.get("max_tokens"),
             top_p=kwargs.get("top_p"),
             frequency_penalty=kwargs.get("frequency_penalty"),
@@ -1385,7 +1625,7 @@ class LLMConfig:
             "provider": self.provider,
             "api_token": self.api_token,
             "base_url": self.base_url,
-            "temprature": self.temprature,
+            "temperature": self.temperature,
             "max_tokens": self.max_tokens,
             "top_p": self.top_p,
             "frequency_penalty": self.frequency_penalty,
@@ -1407,4 +1647,53 @@ class LLMConfig:
         config_dict.update(kwargs)
         return LLMConfig.from_kwargs(config_dict)
 
+class SeedingConfig:
+    """
+    Configuration class for URL discovery and pre-validation via AsyncUrlSeeder.
+    """
+    def __init__(
+        self,
+        source: str = "sitemap+cc",  # Options: "sitemap", "cc", "sitemap+cc"
+        pattern: Optional[str] = "*", # URL pattern to filter discovered URLs (e.g., "*example.com/blog/*")
+        live_check: bool = False,    # Whether to perform HEAD requests to verify URL liveness
+        extract_head: bool = False,  # Whether to fetch and parse <head> section for metadata
+        max_urls: int = -1, # Maximum number of URLs to discover (default: -1 for no limit)
+        concurrency: int = 1000,      # Maximum concurrent requests for live checks/head extraction
+        hits_per_sec: int = 5,      # Rate limit in requests per second
+        force: bool = False, # If True, bypasses the AsyncUrlSeeder's internal .jsonl cache
+        base_directory: Optional[str] = None, # Base directory for UrlSeeder's cache files (.jsonl)
+        llm_config: Optional[LLMConfig] = None, # Forward LLM config for future use (e.g., relevance scoring)
+        verbose: Optional[bool] = None, # Override crawler's general verbose setting
+        query: Optional[str] = None,  # Search query for relevance scoring
+        score_threshold: Optional[float] = None,  # Minimum relevance score to include URL (0.0-1.0)
+        scoring_method: str = "bm25",  # Scoring method: "bm25" (default), future: "semantic"
+        filter_nonsense_urls: bool = True,  # Filter out utility URLs like robots.txt, sitemap.xml, etc.
+    ):
+        self.source = source
+        self.pattern = pattern
+        self.live_check = live_check
+        self.extract_head = extract_head
+        self.max_urls = max_urls
+        self.concurrency = concurrency
+        self.hits_per_sec = hits_per_sec
+        self.force = force
+        self.base_directory = base_directory
+        self.llm_config = llm_config
+        self.verbose = verbose
+        self.query = query
+        self.score_threshold = score_threshold
+        self.scoring_method = scoring_method
+        self.filter_nonsense_urls = filter_nonsense_urls
 
+    # Add to_dict, from_kwargs, and clone methods for consistency
+    def to_dict(self) -> Dict[str, Any]:
+        return {k: v for k, v in self.__dict__.items() if k != 'llm_config' or v is not None}
+
+    @staticmethod
+    def from_kwargs(kwargs: Dict[str, Any]) -> 'SeedingConfig':
+        return SeedingConfig(**kwargs)
+
+    def clone(self, **kwargs: Any) -> 'SeedingConfig':
+        config_dict = self.to_dict()
+        config_dict.update(kwargs)
+        return SeedingConfig.from_kwargs(config_dict)

crawl4ai/async_crawler_strategy.py

@@ -441,7 +441,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
         status_code = 200  # Default for local/raw HTML
         screenshot_data = None
 
-        if url.startswith(("http://", "https://")):
+        if url.startswith(("http://", "https://", "view-source:")):
             return await self._crawl_web(url, config)
 
         elif url.startswith("file://"):
@@ -571,6 +571,14 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
 
             async def handle_response_capture(response):
                 try:
+                    try:
+                        # body = await response.body()
+                        # json_body = await response.json()
+                        text_body = await response.text()
+                    except Exception as e:
+                        body = None
+                        # json_body = None
+                        # text_body = None
                     captured_requests.append({
                         "event_type": "response",
                         "url": response.url,
@@ -579,7 +587,12 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                         "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()
+                        "timestamp": time.time(),
+                        "body" : {
+                            # "raw": body,
+                            # "json": json_body,
+                            "text": text_body
+                        }
                     })
                 except Exception as e:
                     if self.logger:
@@ -771,7 +784,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
             except Error:
                 visibility_info = await self.check_visibility(page)
 
-                if self.config.verbose:
+                if self.browser_config.config.verbose:
                     self.logger.debug(
                         message="Body visibility info: {info}",
                         tag="DEBUG",
@@ -885,6 +898,10 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
             if config.scan_full_page:
                 await self._handle_full_page_scan(page, config.scroll_delay)
 
+            # Handle virtual scroll if configured
+            if config.virtual_scroll_config:
+                await self._handle_virtual_scroll(page, config.virtual_scroll_config)
+
             # Execute JavaScript if provided
             # if config.js_code:
             #     if isinstance(config.js_code, str):
@@ -924,8 +941,10 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
 
             if config.wait_for:
                 try:
+                    # Use wait_for_timeout if specified, otherwise fall back to page_timeout
+                    timeout = config.wait_for_timeout if config.wait_for_timeout is not None else config.page_timeout
                     await self.smart_wait(
-                        page, config.wait_for, timeout=config.page_timeout
+                        page, config.wait_for, timeout=timeout
                     )
                 except Exception as e:
                     raise RuntimeError(f"Wait condition failed: {str(e)}")
@@ -1050,7 +1069,13 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
 
         finally:
             # If no session_id is given we should close the page
-            if not config.session_id:
+            all_contexts = page.context.browser.contexts
+            total_pages = sum(len(context.pages) for context in all_contexts)                
+            if config.session_id:
+                pass
+            elif total_pages <= 1 and (self.browser_config.use_managed_browser or self.browser_config.headless):
+                pass
+            else:
                 # Detach listeners before closing to prevent potential errors during close
                 if config.capture_network_requests:
                     page.remove_listener("request", handle_request_capture)
@@ -1060,6 +1085,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                     page.remove_listener("console", handle_console_capture)
                     page.remove_listener("pageerror", handle_pageerror_capture)
                 
+                # Close the page
                 await page.close()
 
     async def _handle_full_page_scan(self, page: Page, scroll_delay: float = 0.1):
@@ -1127,6 +1153,177 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
             # await page.evaluate("window.scrollTo(0, document.body.scrollHeight)")
             await self.safe_scroll(page, 0, total_height)
 
+    async def _handle_virtual_scroll(self, page: Page, config: "VirtualScrollConfig"):
+        """
+        Handle virtual scroll containers (e.g., Twitter-like feeds) by capturing
+        content at different scroll positions and merging unique elements.
+        
+        Following the design:
+        1. Get container HTML
+        2. Scroll by container height
+        3. Wait and check if container HTML changed
+        4. Three cases:
+           - No change: continue scrolling
+           - New items added (appended): continue (items already in page)
+           - Items replaced: capture HTML chunk and add to list
+        5. After N scrolls, merge chunks if any were captured
+        
+        Args:
+            page: The Playwright page object
+            config: Virtual scroll configuration
+        """
+        try:
+            # Import VirtualScrollConfig to avoid circular import
+            from .async_configs import VirtualScrollConfig
+            
+            # Ensure config is a VirtualScrollConfig instance
+            if isinstance(config, dict):
+                config = VirtualScrollConfig.from_dict(config)
+            
+            self.logger.info(
+                message="Starting virtual scroll capture for container: {selector}",
+                tag="VSCROLL",
+                params={"selector": config.container_selector}
+            )
+            
+            # JavaScript function to handle virtual scroll capture
+            virtual_scroll_js = """
+            async (config) => {
+                const container = document.querySelector(config.container_selector);
+                if (!container) {
+                    throw new Error(`Container not found: ${config.container_selector}`);
+                }
+                
+                // List to store HTML chunks when content is replaced
+                const htmlChunks = [];
+                let previousHTML = container.innerHTML;
+                let scrollCount = 0;
+                
+                // Determine scroll amount
+                let scrollAmount;
+                if (typeof config.scroll_by === 'number') {
+                    scrollAmount = config.scroll_by;
+                } else if (config.scroll_by === 'page_height') {
+                    scrollAmount = window.innerHeight;
+                } else { // container_height
+                    scrollAmount = container.offsetHeight;
+                }
+                
+                // Perform scrolling
+                while (scrollCount < config.scroll_count) {
+                    // Scroll the container
+                    container.scrollTop += scrollAmount;
+                    
+                    // Wait for content to potentially load
+                    await new Promise(resolve => setTimeout(resolve, config.wait_after_scroll * 1000));
+                    
+                    // Get current HTML
+                    const currentHTML = container.innerHTML;
+                    
+                    // Determine what changed
+                    if (currentHTML === previousHTML) {
+                        // Case 0: No change - continue scrolling
+                        console.log(`Scroll ${scrollCount + 1}: No change in content`);
+                    } else if (currentHTML.startsWith(previousHTML)) {
+                        // Case 1: New items appended - content already in page
+                        console.log(`Scroll ${scrollCount + 1}: New items appended`);
+                    } else {
+                        // Case 2: Items replaced - capture the previous HTML
+                        console.log(`Scroll ${scrollCount + 1}: Content replaced, capturing chunk`);
+                        htmlChunks.push(previousHTML);
+                    }
+                    
+                    // Update previous HTML for next iteration
+                    previousHTML = currentHTML;
+                    scrollCount++;
+                    
+                    // Check if we've reached the end
+                    if (container.scrollTop + container.clientHeight >= container.scrollHeight - 10) {
+                        console.log(`Reached end of scrollable content at scroll ${scrollCount}`);
+                        // Capture final chunk if content was replaced
+                        if (htmlChunks.length > 0) {
+                            htmlChunks.push(currentHTML);
+                        }
+                        break;
+                    }
+                }
+                
+                // If we have chunks (case 2 occurred), merge them
+                if (htmlChunks.length > 0) {
+                    console.log(`Merging ${htmlChunks.length} HTML chunks`);
+                    
+                    // Parse all chunks to extract unique elements
+                    const tempDiv = document.createElement('div');
+                    const seenTexts = new Set();
+                    const uniqueElements = [];
+                    
+                    // Process each chunk
+                    for (const chunk of htmlChunks) {
+                        tempDiv.innerHTML = chunk;
+                        const elements = tempDiv.children;
+                        
+                        for (let i = 0; i < elements.length; i++) {
+                            const element = elements[i];
+                            // Normalize text for deduplication
+                            const normalizedText = element.innerText
+                                .toLowerCase()
+                                .replace(/[\\s\\W]/g, ''); // Remove spaces and symbols
+                            
+                            if (!seenTexts.has(normalizedText)) {
+                                seenTexts.add(normalizedText);
+                                uniqueElements.push(element.outerHTML);
+                            }
+                        }
+                    }
+                    
+                    // Replace container content with merged unique elements
+                    container.innerHTML = uniqueElements.join('\\n');
+                    console.log(`Merged ${uniqueElements.length} unique elements from ${htmlChunks.length} chunks`);
+                    
+                    return {
+                        success: true,
+                        chunksCount: htmlChunks.length,
+                        uniqueCount: uniqueElements.length,
+                        replaced: true
+                    };
+                } else {
+                    console.log('No content replacement detected, all content remains in page');
+                    return {
+                        success: true,
+                        chunksCount: 0,
+                        uniqueCount: 0,
+                        replaced: false
+                    };
+                }
+            }
+            """
+            
+            # Execute virtual scroll capture
+            result = await page.evaluate(virtual_scroll_js, config.to_dict())
+            
+            if result.get("replaced", False):
+                self.logger.success(
+                    message="Virtual scroll completed. Merged {unique} unique elements from {chunks} chunks",
+                    tag="VSCROLL",
+                    params={
+                        "unique": result.get("uniqueCount", 0),
+                        "chunks": result.get("chunksCount", 0)
+                    }
+                )
+            else:
+                self.logger.info(
+                    message="Virtual scroll completed. Content was appended, no merging needed",
+                    tag="VSCROLL"
+                )
+            
+        except Exception as e:
+            self.logger.error(
+                message="Virtual scroll capture failed: {error}",
+                tag="VSCROLL",
+                params={"error": str(e)}
+            )
+            # Continue with normal flow even if virtual scroll fails
+
     async def _handle_download(self, download):
         """
         Handle file downloads.
@@ -1454,8 +1651,8 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
             buffered = BytesIO()
             img.save(buffered, format="JPEG")
             return base64.b64encode(buffered.getvalue()).decode("utf-8")
-        finally:
-            await page.close()
+        # finally:
+        #     await page.close()
 
     async def take_screenshot_naive(self, page: Page) -> str:
         """
@@ -1488,8 +1685,8 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
             buffered = BytesIO()
             img.save(buffered, format="JPEG")
             return base64.b64encode(buffered.getvalue()).decode("utf-8")
-        finally:
-            await page.close()
+        # finally:
+        #     await page.close()
 
     async def export_storage_state(self, path: str = None) -> dict:
         """

crawl4ai/async_database.py

@@ -171,7 +171,10 @@ class AsyncDatabaseManager:
                             f"Code context:\n{error_context['code_context']}"
                         )
                         self.logger.error(
-                            message=create_box_message(error_message, type="error"),
+                            message="{error}",
+                            tag="ERROR",
+                            params={"error": str(error_message)},
+                            boxes=["error"],
                         )
 
                         raise
@@ -189,7 +192,10 @@ class AsyncDatabaseManager:
                 f"Code context:\n{error_context['code_context']}"
             )
             self.logger.error(
-                message=create_box_message(error_message, type="error"),
+                message="{error}",
+                tag="ERROR",
+                params={"error": str(error_message)},
+                boxes=["error"],
             )
             raise
         finally:

crawl4ai/async_dispatcher.py

@@ -126,6 +126,7 @@ class MemoryAdaptiveDispatcher(BaseDispatcher):
         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: Optional[float] = 600.0,
         rate_limiter: Optional[RateLimiter] = None,
         monitor: Optional[CrawlerMonitor] = None,
     ):
@@ -136,27 +137,46 @@ class MemoryAdaptiveDispatcher(BaseDispatcher):
         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.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
+        self._high_memory_start_time: Optional[float] = None
         
     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")
-            
+            if self.current_memory_percent >= self.memory_threshold_percent:
+                if not self.memory_pressure_mode:
+                    self.memory_pressure_mode = True
+                    self._high_memory_start_time = time.time()
+                    if self.monitor:
+                        self.monitor.update_memory_status("PRESSURE")
+                else:
+                    if self._high_memory_start_time is None:
+                        self._high_memory_start_time = time.time()
+                    if (
+                        self.memory_wait_timeout is not None
+                        and self._high_memory_start_time is not None
+                        and time.time() - self._high_memory_start_time >= self.memory_wait_timeout
+                    ):
+                        raise MemoryError(
+                            "Memory usage exceeded threshold for"
+                            f" {self.memory_wait_timeout} seconds"
+                        )
+
             # 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
+                self._high_memory_start_time = None
                 if self.monitor:
                     self.monitor.update_memory_status("NORMAL")
+            elif self.current_memory_percent < self.memory_threshold_percent:
+                self._high_memory_start_time = None
             
             # In critical mode, we might need to take more drastic action
             if self.current_memory_percent >= self.critical_threshold_percent:
@@ -307,7 +327,7 @@ class MemoryAdaptiveDispatcher(BaseDispatcher):
             self.monitor.start()
             
         results = []
-        
+
         try:
             # Initialize task queue
             for url in urls:
@@ -316,11 +336,18 @@ class MemoryAdaptiveDispatcher(BaseDispatcher):
                     self.monitor.add_task(task_id, url)
                 # Add to queue with initial priority 0, retry count 0, and current time
                 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_monitor.done():
+                    exc = memory_monitor.exception()
+                    if exc:
+                        for t in active_tasks:
+                            t.cancel()
+                        raise exc
+
                 # If memory pressure is low, start new tasks
                 if not self.memory_pressure_mode and len(active_tasks) < self.max_session_permit:
                     try:
@@ -465,8 +492,14 @@ class MemoryAdaptiveDispatcher(BaseDispatcher):
             active_tasks = []
             completed_count = 0
             total_urls = len(urls)
-            
+
             while completed_count < total_urls:
+                if memory_monitor.done():
+                    exc = memory_monitor.exception()
+                    if exc:
+                        for t in active_tasks:
+                            t.cancel()
+                        raise exc
                 # If memory pressure is low, start new tasks
                 if not self.memory_pressure_mode and len(active_tasks) < self.max_session_permit:
                     try:

crawl4ai/async_logger.py

@@ -1,10 +1,12 @@
 from abc import ABC, abstractmethod
 from enum import Enum
-from typing import Optional, Dict, Any
-from colorama import Fore, Style, init
+from typing import Optional, Dict, Any, List
 import os
 from datetime import datetime
 from urllib.parse import unquote
+from rich.console import Console
+from rich.text import Text
+from .utils import create_box_message
 
 
 class LogLevel(Enum):
@@ -21,6 +23,26 @@ class LogLevel(Enum):
     FATAL = 10
     
 
+    def __str__(self):
+        return self.name.lower()
+
+class LogColor(str, Enum):
+    """Enum for log colors."""
+
+    DEBUG = "bright_black"
+    INFO = "cyan"
+    SUCCESS = "green"
+    WARNING = "yellow"
+    ERROR = "red"
+    CYAN = "cyan"
+    GREEN = "green"
+    YELLOW = "yellow"
+    MAGENTA = "magenta"
+    DIM_MAGENTA = "dim magenta"
+
+    def __str__(self):
+        """Automatically convert rich color to string."""
+        return self.value
 
 
 class AsyncLoggerBase(ABC):
@@ -52,6 +74,7 @@ class AsyncLoggerBase(ABC):
     def error_status(self, url: str, error: str, tag: str = "ERROR", url_length: int = 100):
         pass
 
+
 class AsyncLogger(AsyncLoggerBase):
     """
     Asynchronous logger with support for colored console output and file logging.
@@ -79,17 +102,11 @@ class AsyncLogger(AsyncLoggerBase):
     }
 
     DEFAULT_COLORS = {
-        LogLevel.DEBUG: Fore.LIGHTBLACK_EX,
-        LogLevel.INFO: Fore.CYAN,
-        LogLevel.SUCCESS: Fore.GREEN,
-        LogLevel.WARNING: Fore.YELLOW,
-        LogLevel.ERROR: Fore.RED,
-        LogLevel.CRITICAL: Fore.RED + Style.BRIGHT,
-        LogLevel.ALERT: Fore.RED + Style.BRIGHT,
-        LogLevel.NOTICE: Fore.BLUE,
-        LogLevel.EXCEPTION: Fore.RED + Style.BRIGHT,
-        LogLevel.FATAL: Fore.RED + Style.BRIGHT,
-        LogLevel.DEFAULT: Fore.WHITE,
+        LogLevel.DEBUG: LogColor.DEBUG,
+        LogLevel.INFO: LogColor.INFO,
+        LogLevel.SUCCESS: LogColor.SUCCESS,
+        LogLevel.WARNING: LogColor.WARNING,
+        LogLevel.ERROR: LogColor.ERROR,
     }
 
     def __init__(
@@ -98,7 +115,7 @@ class AsyncLogger(AsyncLoggerBase):
         log_level: LogLevel = LogLevel.DEBUG,
         tag_width: int = 10,
         icons: Optional[Dict[str, str]] = None,
-        colors: Optional[Dict[LogLevel, str]] = None,
+        colors: Optional[Dict[LogLevel, LogColor]] = None,
         verbose: bool = True,
     ):
         """
@@ -112,13 +129,13 @@ class AsyncLogger(AsyncLoggerBase):
             colors: Custom colors for different log levels
             verbose: Whether to output to console
         """
-        init()  # Initialize colorama
         self.log_file = log_file
         self.log_level = log_level
         self.tag_width = tag_width
         self.icons = icons or self.DEFAULT_ICONS
         self.colors = colors or self.DEFAULT_COLORS
         self.verbose = verbose
+        self.console = Console()
 
         # Create log file directory if needed
         if log_file:
@@ -143,16 +160,11 @@ class AsyncLogger(AsyncLoggerBase):
     def _write_to_file(self, message: str):
         """Write a message to the log file if configured."""
         if self.log_file:
+            text = Text.from_markup(message)
+            plain_text = text.plain
             timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S.%f")[:-3]
             with open(self.log_file, "a", encoding="utf-8") as f:
-                # Strip ANSI color codes for file output
-                clean_message = message.replace(Fore.RESET, "").replace(
-                    Style.RESET_ALL, ""
-                )
-                for color in vars(Fore).values():
-                    if isinstance(color, str):
-                        clean_message = clean_message.replace(color, "")
-                f.write(f"[{timestamp}] {clean_message}\n")
+                f.write(f"[{timestamp}] {plain_text}\n")
 
     def _log(
         self,
@@ -160,8 +172,9 @@ class AsyncLogger(AsyncLoggerBase):
         message: str,
         tag: str,
         params: Optional[Dict[str, Any]] = None,
-        colors: Optional[Dict[str, str]] = None,
-        base_color: Optional[str] = None,
+        colors: Optional[Dict[str, LogColor]] = None,
+        boxes: Optional[List[str]] = None,
+        base_color: Optional[LogColor] = None,
         **kwargs,
     ):
         """
@@ -173,55 +186,44 @@ class AsyncLogger(AsyncLoggerBase):
             tag: Tag for the message
             params: Parameters to format into the message
             colors: Color overrides for specific parameters
+            boxes: Box overrides for specific parameters
             base_color: Base color for the entire message
         """
         if level.value < self.log_level.value:
             return
 
-        # Format the message with parameters if provided
+        # avoid conflict with rich formatting
+        parsed_message = message.replace("[", "[[").replace("]", "]]")
         if params:
-            try:
-                # First format the message with raw parameters
-                formatted_message = message.format(**params)
+            # FIXME: If there are formatting strings in floating point format, 
+            # this may result in colors and boxes not being applied properly.
+            # such as {value:.2f}, the value is 0.23333 format it to 0.23,
+            # but we replace("0.23333", "[color]0.23333[/color]")
+            formatted_message = parsed_message.format(**params)
+            for key, value in params.items():
+                # value_str may discard `[` and `]`, so we need to replace it. 
+                value_str = str(value).replace("[", "[[").replace("]", "]]")
+                # check is need apply color
+                if colors and key in colors:
+                    color_str = f"[{colors[key]}]{value_str}[/{colors[key]}]"
+                    formatted_message = formatted_message.replace(value_str, color_str)
+                    value_str = color_str
 
-                # 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(
-                                value_str, f"{color}{value_str}{Style.RESET_ALL}"
-                            )
+                # check is need apply box
+                if boxes and key in boxes:
+                    formatted_message = formatted_message.replace(value_str,
+                        create_box_message(value_str, type=str(level)))
 
-            except KeyError as e:
-                formatted_message = (
-                    f"LOGGING ERROR: Missing parameter {e} in message template"
-                )
-                level = LogLevel.ERROR
         else:
-            formatted_message = message
+            formatted_message = parsed_message
 
         # Construct the full log line
-        color = base_color or self.colors[level]
-        log_line = f"{color}{self._format_tag(tag)} {self._get_icon(tag)} {formatted_message}{Style.RESET_ALL}"
+        color: LogColor = base_color or self.colors[level]
+        log_line = f"[{color}]{self._format_tag(tag)} {self._get_icon(tag)} {formatted_message} [/{color}]"
 
         # Output to console if verbose
         if self.verbose or kwargs.get("force_verbose", False):
-            print(log_line)
+            self.console.print(log_line)
 
         # Write to file if configured
         self._write_to_file(log_line)
@@ -292,8 +294,8 @@ class AsyncLogger(AsyncLoggerBase):
                 "timing": timing,
             },
             colors={
-                "status": Fore.GREEN if success else Fore.RED,
-                "timing": Fore.YELLOW,
+                "status": LogColor.SUCCESS if success else LogColor.ERROR,
+                "timing": LogColor.WARNING,
             },
         )
 

crawl4ai/async_webcrawler.py

@@ -2,7 +2,6 @@ from .__version__ import __version__ as crawl4ai_version
 import os
 import sys
 import time
-from colorama import Fore
 from pathlib import Path
 from typing import Optional, List
 import json
@@ -36,15 +35,15 @@ from .markdown_generation_strategy import (
 )
 from .deep_crawling import DeepCrawlDecorator
 from .async_logger import AsyncLogger, AsyncLoggerBase
-from .async_configs import BrowserConfig, CrawlerRunConfig, ProxyConfig
+from .async_configs import BrowserConfig, CrawlerRunConfig, ProxyConfig, SeedingConfig
 from .async_dispatcher import *  # noqa: F403
 from .async_dispatcher import BaseDispatcher, MemoryAdaptiveDispatcher, RateLimiter
+from .async_url_seeder import AsyncUrlSeeder
 
 from .utils import (
     sanitize_input_encode,
     InvalidCSSSelectorError,
     fast_format_html,
-    create_box_message,
     get_error_context,
     RobotsParser,
     preprocess_html_for_schema,
@@ -165,6 +164,8 @@ class AsyncWebCrawler:
         # Decorate arun method with deep crawling capabilities
         self._deep_handler = DeepCrawlDecorator(self)
         self.arun = self._deep_handler(self.arun)
+        
+        self.url_seeder: Optional[AsyncUrlSeeder] = None
 
     async def start(self):
         """
@@ -419,7 +420,7 @@ class AsyncWebCrawler:
 
                 self.logger.error_status(
                     url=url,
-                    error=create_box_message(error_message, type="error"),
+                    error=error_message,
                     tag="ERROR",
                 )
 
@@ -496,13 +497,20 @@ class AsyncWebCrawler:
             cleaned_html = sanitize_input_encode(
                 result.get("cleaned_html", ""))
             media = result.get("media", {})
+            tables = media.pop("tables", []) if isinstance(media, dict) else []
             links = result.get("links", {})
             metadata = result.get("metadata", {})
         else:
             cleaned_html = sanitize_input_encode(result.cleaned_html)
-            media = result.media.model_dump()
-            links = result.links.model_dump()
+            # media = result.media.model_dump()
+            # tables = media.pop("tables", [])
+            # links = result.links.model_dump()
+            media = result.media.model_dump() if hasattr(result.media, 'model_dump') else result.media
+            tables = media.pop("tables", []) if isinstance(media, dict) else []
+            links = result.links.model_dump() if hasattr(result.links, 'model_dump') else result.links
             metadata = result.metadata
+            
+        fit_html = preprocess_html_for_schema(html_content=html, text_threshold= 500, max_size= 300_000)
 
         ################################
         # Generate Markdown            #
@@ -519,7 +527,7 @@ class AsyncWebCrawler:
         html_source_selector = {
             "raw_html": lambda: html,  # The original raw HTML
             "cleaned_html": lambda: cleaned_html,  # The HTML after scraping strategy
-            "fit_html": lambda: preprocess_html_for_schema(html_content=html),  # Preprocessed raw HTML
+            "fit_html": lambda: fit_html,  # The HTML after preprocessing for schema
         }
 
         markdown_input_html = cleaned_html  # Default to cleaned_html
@@ -593,6 +601,7 @@ class AsyncWebCrawler:
             content = {
                 "markdown": markdown_result.raw_markdown,
                 "html": html,
+                "fit_html": fit_html,
                 "cleaned_html": cleaned_html,
                 "fit_markdown": markdown_result.fit_markdown,
             }.get(content_format, markdown_result.raw_markdown)
@@ -600,7 +609,7 @@ class AsyncWebCrawler:
             # Use IdentityChunking for HTML input, otherwise use provided chunking strategy
             chunking = (
                 IdentityChunking()
-                if content_format in ["html", "cleaned_html"]
+                if content_format in ["html", "cleaned_html", "fit_html"]
                 else config.chunking_strategy
             )
             sections = chunking.chunk(content)
@@ -624,9 +633,11 @@ class AsyncWebCrawler:
         return CrawlResult(
             url=url,
             html=html,
+            fit_html=fit_html,
             cleaned_html=cleaned_html,
             markdown=markdown_result,
             media=media,
+            tables=tables,                       # NEW
             links=links,
             metadata=metadata,
             screenshot=screenshot_data,
@@ -739,3 +750,94 @@ class AsyncWebCrawler:
         else:
             _results = await dispatcher.run_urls(crawler=self, urls=urls, config=config)
             return [transform_result(res) for res in _results]
+
+    async def aseed_urls(
+        self,
+        domain_or_domains: Union[str, List[str]],
+        config: Optional[SeedingConfig] = None,
+        **kwargs
+    ) -> Union[List[str], Dict[str, List[Union[str, Dict[str, Any]]]]]:
+        """
+        Discovers, filters, and optionally validates URLs for a given domain(s)
+        using sitemaps and Common Crawl archives.
+
+        Args:
+            domain_or_domains: A single domain string (e.g., "iana.org") or a list of domains.
+            config: A SeedingConfig object to control the seeding process.
+                    Parameters passed directly via kwargs will override those in 'config'.
+            **kwargs: Additional parameters (e.g., `source`, `live_check`, `extract_head`,
+                      `pattern`, `concurrency`, `hits_per_sec`, `force_refresh`, `verbose`)
+                      that will be used to construct or update the SeedingConfig.
+
+        Returns:
+            If `extract_head` is False:
+                - For a single domain: `List[str]` of discovered URLs.
+                - For multiple domains: `Dict[str, List[str]]` mapping each domain to its URLs.
+            If `extract_head` is True:
+                - For a single domain: `List[Dict[str, Any]]` where each dict contains 'url'
+                  and 'head_data' (parsed <head> metadata).
+                - For multiple domains: `Dict[str, List[Dict[str, Any]]]` mapping each domain
+                  to a list of URL data dictionaries.
+
+        Raises:
+            ValueError: If `domain_or_domains` is not a string or a list of strings.
+            Exception: Any underlying exceptions from AsyncUrlSeeder or network operations.
+
+        Example:
+            >>> # Discover URLs from sitemap with live check for 'example.com'
+            >>> result = await crawler.aseed_urls("example.com", source="sitemap", live_check=True, hits_per_sec=10)
+
+            >>> # Discover URLs from Common Crawl, extract head data for 'example.com' and 'python.org'
+            >>> multi_domain_result = await crawler.aseed_urls(
+            >>>     ["example.com", "python.org"],
+            >>>     source="cc", extract_head=True, concurrency=200, hits_per_sec=50
+            >>> )
+        """
+        # Initialize AsyncUrlSeeder here if it hasn't been already
+        if not self.url_seeder:
+            # Pass the crawler's base_directory for seeder's cache management
+            # Pass the crawler's logger for consistent logging
+            self.url_seeder = AsyncUrlSeeder(
+                base_directory=self.crawl4ai_folder,
+                logger=self.logger
+            )                    
+
+        # Merge config object with direct kwargs, giving kwargs precedence
+        seeding_config = config.clone(**kwargs) if config else SeedingConfig.from_kwargs(kwargs)
+        
+        # Ensure base_directory is set for the seeder's cache
+        seeding_config.base_directory = seeding_config.base_directory or self.crawl4ai_folder        
+        # Ensure the seeder uses the crawler's logger (if not already set)
+        if not self.url_seeder.logger:
+            self.url_seeder.logger = self.logger
+
+        # Pass verbose setting if explicitly provided in SeedingConfig or kwargs
+        if seeding_config.verbose is not None:
+            self.url_seeder.logger.verbose = seeding_config.verbose
+        else: # Default to crawler's verbose setting
+            self.url_seeder.logger.verbose = self.logger.verbose
+
+
+        if isinstance(domain_or_domains, str):
+            self.logger.info(
+                message="Starting URL seeding for domain: {domain}",
+                tag="SEED",
+                params={"domain": domain_or_domains}
+            )
+            return await self.url_seeder.urls(
+                domain_or_domains,
+                seeding_config
+            )
+        elif isinstance(domain_or_domains, (list, tuple)):
+            self.logger.info(
+                message="Starting URL seeding for {count} domains",
+                tag="SEED",
+                params={"count": len(domain_or_domains)}
+            )
+            # AsyncUrlSeeder.many_urls directly accepts a list of domains and individual params.
+            return await self.url_seeder.many_urls(
+                domain_or_domains,
+                seeding_config
+            )
+        else:
+            raise ValueError("`domain_or_domains` must be a string or a list of strings.")

crawl4ai/browser_manager.py

@@ -5,7 +5,10 @@ import os
 import sys
 import shutil
 import tempfile
+import psutil  
+import signal
 import subprocess
+import shlex
 from playwright.async_api import BrowserContext
 import hashlib
 from .js_snippet import load_js_script
@@ -193,6 +196,45 @@ class ManagedBrowser:
         
         if self.browser_config.extra_args:
             args.extend(self.browser_config.extra_args)
+            
+
+        # ── make sure no old Chromium instance is owning the same port/profile ──
+        try:
+            if sys.platform == "win32":
+                if psutil is None:
+                    raise RuntimeError("psutil not available, cannot clean old browser")
+                for p in psutil.process_iter(["pid", "name", "cmdline"]):
+                    cl = " ".join(p.info.get("cmdline") or [])
+                    if (
+                        f"--remote-debugging-port={self.debugging_port}" in cl
+                        and f"--user-data-dir={self.user_data_dir}" in cl
+                    ):
+                        p.kill()
+                        p.wait(timeout=5)
+            else:  # macOS / Linux
+                # kill any process listening on the same debugging port
+                pids = (
+                    subprocess.check_output(shlex.split(f"lsof -t -i:{self.debugging_port}"))
+                    .decode()
+                    .strip()
+                    .splitlines()
+                )
+                for pid in pids:
+                    try:
+                        os.kill(int(pid), signal.SIGTERM)
+                    except ProcessLookupError:
+                        pass
+
+                # remove Chromium singleton locks, or new launch exits with
+                # “Opening in existing browser session.”
+                for f in ("SingletonLock", "SingletonSocket", "SingletonCookie"):
+                    fp = os.path.join(self.user_data_dir, f)
+                    if os.path.exists(fp):
+                        os.remove(fp)
+        except Exception as _e:
+            # non-fatal — we'll try to start anyway, but log what happened
+            self.logger.warning(f"pre-launch cleanup failed: {_e}", tag="BROWSER")            
+            
 
         # Start browser process
         try:
@@ -213,6 +255,13 @@ class ManagedBrowser:
                     preexec_fn=os.setpgrp  # Start in a new process group
                 )
                 
+            # If verbose is True print args used to run the process
+            if self.logger and self.browser_config.verbose:
+                self.logger.debug(
+                    f"Starting browser with args: {' '.join(args)}",
+                    tag="BROWSER"
+                )    
+                
             # 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()
@@ -469,6 +518,56 @@ class ManagedBrowser:
         return profiler.delete_profile(profile_name_or_path)
 
 
+async def clone_runtime_state(
+    src: BrowserContext,
+    dst: BrowserContext,
+    crawlerRunConfig: CrawlerRunConfig | None = None,
+    browserConfig: BrowserConfig | None = None,
+) -> None:
+    """
+    Bring everything that *can* be changed at runtime from `src` → `dst`.
+
+    1. Cookies
+    2. localStorage (and sessionStorage, same API)
+    3. Extra headers, permissions, geolocation if supplied in configs
+    """
+
+    # ── 1. cookies ────────────────────────────────────────────────────────────
+    cookies = await src.cookies()
+    if cookies:
+        await dst.add_cookies(cookies)
+
+    # ── 2. localStorage / sessionStorage ──────────────────────────────────────
+    state = await src.storage_state()
+    for origin in state.get("origins", []):
+        url = origin["origin"]
+        kvs = origin.get("localStorage", [])
+        if not kvs:
+            continue
+
+        page = dst.pages[0] if dst.pages else await dst.new_page()
+        await page.goto(url, wait_until="domcontentloaded")
+        for k, v in kvs:
+            await page.evaluate("(k,v)=>localStorage.setItem(k,v)", k, v)
+
+    # ── 3. runtime-mutable extras from configs ────────────────────────────────
+    # headers
+    if browserConfig and browserConfig.headers:
+        await dst.set_extra_http_headers(browserConfig.headers)
+
+    # geolocation
+    if crawlerRunConfig and crawlerRunConfig.geolocation:
+        await dst.grant_permissions(["geolocation"])
+        await dst.set_geolocation(
+            {
+                "latitude": crawlerRunConfig.geolocation.latitude,
+                "longitude": crawlerRunConfig.geolocation.longitude,
+                "accuracy": crawlerRunConfig.geolocation.accuracy,
+            }
+        )
+        
+    return dst
+
 
 
 class BrowserManager:
@@ -918,11 +1017,17 @@ class BrowserManager:
 
         # If using a managed browser, just grab the shared default_context
         if self.config.use_managed_browser:
-            context = self.default_context
-            pages = context.pages
-            page = next((p for p in pages if p.url == crawlerRunConfig.url), None)
-            if not page:
-                page = await context.new_page()
+            if self.config.storage_state:
+                context = await self.create_browser_context(crawlerRunConfig)
+                ctx = self.default_context        # default context, one window only
+                ctx = await clone_runtime_state(context, ctx, crawlerRunConfig, self.config)
+                page = await ctx.new_page()
+            else:
+                context = self.default_context
+                pages = context.pages
+                page = next((p for p in pages if p.url == crawlerRunConfig.url), None)
+                if not page:
+                    page = context.pages[0] # await context.new_page()
         else:
             # Otherwise, check if we have an existing context for this config
             config_signature = self._make_config_signature(crawlerRunConfig)

crawl4ai/browser_profiler.py

@@ -15,12 +15,12 @@ import shutil
 import json
 import subprocess
 import time
-from typing import List, Dict, Optional, Any, Tuple
-from colorama import Fore, Style, init
+from typing import List, Dict, Optional, Any
+from rich.console import Console
 
 from .async_configs import BrowserConfig
 from .browser_manager import ManagedBrowser
-from .async_logger import AsyncLogger, AsyncLoggerBase
+from .async_logger import AsyncLogger, AsyncLoggerBase, LogColor
 from .utils import get_home_folder
 
 
@@ -45,8 +45,8 @@ class BrowserProfiler:
             logger (AsyncLoggerBase, optional): Logger for outputting messages.
                 If None, a default AsyncLogger will be created.
         """
-        # Initialize colorama for colorful terminal output
-        init()
+        # Initialize rich console for colorful input prompts
+        self.console = Console()
         
         # Create a logger if not provided
         if logger is None:
@@ -127,26 +127,30 @@ class BrowserProfiler:
         profile_path = os.path.join(self.profiles_dir, profile_name)
         os.makedirs(profile_path, exist_ok=True)
         
-        # Print instructions for the user with colorama formatting
-        border = f"{Fore.CYAN}{'='*80}{Style.RESET_ALL}"
-        self.logger.info(f"\n{border}", tag="PROFILE")
-        self.logger.info(f"Creating browser profile: {Fore.GREEN}{profile_name}{Style.RESET_ALL}", tag="PROFILE")
-        self.logger.info(f"Profile directory: {Fore.YELLOW}{profile_path}{Style.RESET_ALL}", tag="PROFILE")
+        # Print instructions for the user with rich formatting
+        border = f"{'='*80}"
+        self.logger.info("{border}", tag="PROFILE", params={"border": f"\n{border}"}, colors={"border": LogColor.CYAN})
+        self.logger.info("Creating browser profile: {profile_name}", tag="PROFILE", params={"profile_name": profile_name}, colors={"profile_name": LogColor.GREEN})
+        self.logger.info("Profile directory: {profile_path}", tag="PROFILE", params={"profile_path": profile_path}, colors={"profile_path": LogColor.YELLOW})
         
         self.logger.info("\nInstructions:", tag="PROFILE")
         self.logger.info("1. A browser window will open for you to set up your profile.", tag="PROFILE")
-        self.logger.info(f"2. {Fore.CYAN}Log in to websites{Style.RESET_ALL}, configure settings, etc. as needed.", tag="PROFILE")
-        self.logger.info(f"3. When you're done, {Fore.YELLOW}press 'q' in this terminal{Style.RESET_ALL} to close the browser.", tag="PROFILE")
+        self.logger.info("{segment}, configure settings, etc. as needed.", tag="PROFILE", params={"segment": "2. Log in to websites"}, colors={"segment": LogColor.CYAN})
+        self.logger.info("3. When you're done, {segment} to close the browser.", tag="PROFILE", params={"segment": "press 'q' in this terminal"}, colors={"segment": LogColor.YELLOW})
         self.logger.info("4. The profile will be saved and ready to use with Crawl4AI.", tag="PROFILE")
-        self.logger.info(f"{border}\n", tag="PROFILE")
+        self.logger.info("{border}", tag="PROFILE", params={"border": f"{border}\n"}, colors={"border": LogColor.CYAN})
+        
+        browser_config.headless = False
+        browser_config.user_data_dir = profile_path
+        
         
         # Create managed browser instance
         managed_browser = ManagedBrowser(
-            browser_type=browser_config.browser_type,
-            user_data_dir=profile_path,
-            headless=False,  # Must be visible
+            browser_config=browser_config,
+            # user_data_dir=profile_path,
+            # headless=False,  # Must be visible
             logger=self.logger,
-            debugging_port=browser_config.debugging_port
+            # debugging_port=browser_config.debugging_port
         )
         
         # Set up signal handlers to ensure cleanup on interrupt
@@ -181,7 +185,7 @@ class BrowserProfiler:
             import select
             
             # First output the prompt
-            self.logger.info(f"{Fore.CYAN}Press '{Fore.WHITE}q{Fore.CYAN}' when you've finished using the browser...{Style.RESET_ALL}", tag="PROFILE")
+            self.logger.info("Press 'q' when you've finished using the browser...", tag="PROFILE")
             
             # Save original terminal settings
             fd = sys.stdin.fileno()
@@ -197,7 +201,7 @@ class BrowserProfiler:
                     if readable:
                         key = sys.stdin.read(1)
                         if key.lower() == 'q':
-                            self.logger.info(f"{Fore.GREEN}Closing browser and saving profile...{Style.RESET_ALL}", tag="PROFILE")
+                            self.logger.info("Closing browser and saving profile...", tag="PROFILE", base_color=LogColor.GREEN)
                             user_done_event.set()
                             return
                     
@@ -214,8 +218,18 @@ class BrowserProfiler:
                 termios.tcsetattr(fd, termios.TCSADRAIN, old_settings)
         
         try:
+            from playwright.async_api import async_playwright
+
             # Start the browser
-            await managed_browser.start()
+            # await managed_browser.start()
+            # 1. ── Start the browser ─────────────────────────────────────────
+            cdp_url = await managed_browser.start()
+
+            # 2. ── Attach Playwright to that running Chrome ──────────────────
+            pw       = await async_playwright().start()
+            browser  = await pw.chromium.connect_over_cdp(cdp_url)
+            # Grab the existing default context (there is always one)
+            context  = browser.contexts[0]
             
             # Check if browser started successfully
             browser_process = managed_browser.browser_process
@@ -223,7 +237,7 @@ class BrowserProfiler:
                 self.logger.error("Failed to start browser process.", tag="PROFILE")
                 return None
             
-            self.logger.info(f"Browser launched. {Fore.CYAN}Waiting for you to finish...{Style.RESET_ALL}", tag="PROFILE") 
+            self.logger.info("Browser launched. Waiting for you to finish...", tag="PROFILE") 
             
             # Start listening for keyboard input
             listener_task = asyncio.create_task(listen_for_quit_command())
@@ -240,15 +254,27 @@ class BrowserProfiler:
                 except asyncio.CancelledError:
                     pass
             
+            # 3. ── Persist storage state *before* we kill Chrome ─────────────
+            state_file = os.path.join(profile_path, "storage_state.json")
+            try:
+                await context.storage_state(path=state_file)
+                self.logger.info(f"[PROFILE].i  storage_state saved → {state_file}", tag="PROFILE")
+            except Exception as e:
+                self.logger.warning(f"[PROFILE].w  failed to save storage_state: {e}", tag="PROFILE")
+
+            # 4. ── Close everything cleanly ──────────────────────────────────
+            await browser.close()
+            await pw.stop()
+
             # If the browser is still running and the user pressed 'q', terminate it
             if browser_process.poll() is None and user_done_event.is_set():
                 self.logger.info("Terminating browser process...", tag="PROFILE")
                 await managed_browser.cleanup()
             
-            self.logger.success(f"Browser closed. Profile saved at: {Fore.GREEN}{profile_path}{Style.RESET_ALL}", tag="PROFILE")
+            self.logger.success(f"Browser closed. Profile saved at: {profile_path}", tag="PROFILE")
                 
         except Exception as e:
-            self.logger.error(f"Error creating profile: {str(e)}", tag="PROFILE")
+            self.logger.error(f"Error creating profile: {e!s}", tag="PROFILE")
             await managed_browser.cleanup()
             return None
         finally:
@@ -440,25 +466,27 @@ class BrowserProfiler:
             ```
         """
         while True:
-            self.logger.info(f"\n{Fore.CYAN}Profile Management Options:{Style.RESET_ALL}", tag="MENU")
-            self.logger.info(f"1. {Fore.GREEN}Create a new profile{Style.RESET_ALL}", tag="MENU")
-            self.logger.info(f"2. {Fore.YELLOW}List available profiles{Style.RESET_ALL}", tag="MENU")
-            self.logger.info(f"3. {Fore.RED}Delete a profile{Style.RESET_ALL}", tag="MENU")
+            self.logger.info("\nProfile Management Options:", tag="MENU")
+            self.logger.info("1. Create a new profile", tag="MENU", base_color=LogColor.GREEN)
+            self.logger.info("2. List available profiles", tag="MENU", base_color=LogColor.YELLOW)
+            self.logger.info("3. Delete a profile", tag="MENU", base_color=LogColor.RED)
             
             # Only show crawl option if callback provided
             if crawl_callback:
-                self.logger.info(f"4. {Fore.CYAN}Use a profile to crawl a website{Style.RESET_ALL}", tag="MENU")
-                self.logger.info(f"5. {Fore.MAGENTA}Exit{Style.RESET_ALL}", tag="MENU")
+                self.logger.info("4. Use a profile to crawl a website", tag="MENU", base_color=LogColor.CYAN)
+                self.logger.info("5. Exit", tag="MENU", base_color=LogColor.MAGENTA)
                 exit_option = "5"
             else:
-                self.logger.info(f"4. {Fore.MAGENTA}Exit{Style.RESET_ALL}", tag="MENU")
+                self.logger.info("4. Exit", tag="MENU", base_color=LogColor.MAGENTA)
                 exit_option = "4"
             
-            choice = input(f"\n{Fore.CYAN}Enter your choice (1-{exit_option}): {Style.RESET_ALL}")
+            self.logger.print(f"\n[cyan]Enter your choice (1-{exit_option}): [/cyan]", end="")
+            choice = input()
             
             if choice == "1":
                 # Create new profile
-                name = input(f"{Fore.GREEN}Enter a name for the new profile (or press Enter for auto-generated name): {Style.RESET_ALL}")
+                self.console.print("[green]Enter a name for the new profile (or press Enter for auto-generated name): [/green]", end="")
+                name = input()
                 await self.create_profile(name or None)
                 
             elif choice == "2":
@@ -469,11 +497,11 @@ class BrowserProfiler:
                     self.logger.warning("  No profiles found. Create one first with option 1.", tag="PROFILES")
                     continue
                 
-                # Print profile information with colorama formatting
+                # Print profile information 
                 self.logger.info("\nAvailable profiles:", tag="PROFILES")
                 for i, profile in enumerate(profiles):
-                    self.logger.info(f"[{i+1}] {Fore.CYAN}{profile['name']}{Style.RESET_ALL}", tag="PROFILES")
-                    self.logger.info(f"    Path: {Fore.YELLOW}{profile['path']}{Style.RESET_ALL}", tag="PROFILES")
+                    self.logger.info(f"[{i+1}] {profile['name']}", tag="PROFILES")
+                    self.logger.info(f"    Path: {profile['path']}", tag="PROFILES", base_color=LogColor.YELLOW)
                     self.logger.info(f"    Created: {profile['created'].strftime('%Y-%m-%d %H:%M:%S')}", tag="PROFILES")
                     self.logger.info(f"    Browser type: {profile['type']}", tag="PROFILES")
                     self.logger.info("", tag="PROFILES")  # Empty line for spacing
@@ -486,12 +514,13 @@ class BrowserProfiler:
                     continue
                     
                 # Display numbered list
-                self.logger.info(f"\n{Fore.YELLOW}Available profiles:{Style.RESET_ALL}", tag="PROFILES")
+                self.logger.info("\nAvailable profiles:", tag="PROFILES", base_color=LogColor.YELLOW)
                 for i, profile in enumerate(profiles):
                     self.logger.info(f"[{i+1}] {profile['name']}", tag="PROFILES")
                     
                 # Get profile to delete
-                profile_idx = input(f"{Fore.RED}Enter the number of the profile to delete (or 'c' to cancel): {Style.RESET_ALL}")
+                self.console.print("[red]Enter the number of the profile to delete (or 'c' to cancel): [/red]", end="")
+                profile_idx = input()
                 if profile_idx.lower() == 'c':
                     continue
                     
@@ -499,17 +528,18 @@ class BrowserProfiler:
                     idx = int(profile_idx) - 1
                     if 0 <= idx < len(profiles):
                         profile_name = profiles[idx]["name"]
-                        self.logger.info(f"Deleting profile: {Fore.YELLOW}{profile_name}{Style.RESET_ALL}", tag="PROFILES")
+                        self.logger.info(f"Deleting profile: [yellow]{profile_name}[/yellow]", tag="PROFILES")
                         
                         # Confirm deletion
-                        confirm = input(f"{Fore.RED}Are you sure you want to delete this profile? (y/n): {Style.RESET_ALL}")
+                        self.console.print("[red]Are you sure you want to delete this profile? (y/n): [/red]", end="")
+                        confirm = input()
                         if confirm.lower() == 'y':
                             success = self.delete_profile(profiles[idx]["path"])
                             
                             if success:
-                                self.logger.success(f"Profile {Fore.GREEN}{profile_name}{Style.RESET_ALL} deleted successfully", tag="PROFILES")
+                                self.logger.success(f"Profile {profile_name} deleted successfully", tag="PROFILES")
                             else:
-                                self.logger.error(f"Failed to delete profile {Fore.RED}{profile_name}{Style.RESET_ALL}", tag="PROFILES")
+                                self.logger.error(f"Failed to delete profile {profile_name}", tag="PROFILES")
                     else:
                         self.logger.error("Invalid profile number", tag="PROFILES")
                 except ValueError:
@@ -523,12 +553,13 @@ class BrowserProfiler:
                     continue
                     
                 # Display numbered list
-                self.logger.info(f"\n{Fore.YELLOW}Available profiles:{Style.RESET_ALL}", tag="PROFILES")
+                self.logger.info("\nAvailable profiles:", tag="PROFILES", base_color=LogColor.YELLOW)
                 for i, profile in enumerate(profiles):
                     self.logger.info(f"[{i+1}] {profile['name']}", tag="PROFILES")
                     
                 # Get profile to use
-                profile_idx = input(f"{Fore.CYAN}Enter the number of the profile to use (or 'c' to cancel): {Style.RESET_ALL}")
+                self.console.print("[cyan]Enter the number of the profile to use (or 'c' to cancel): [/cyan]", end="")
+                profile_idx = input()
                 if profile_idx.lower() == 'c':
                     continue
                     
@@ -536,7 +567,8 @@ class BrowserProfiler:
                     idx = int(profile_idx) - 1
                     if 0 <= idx < len(profiles):
                         profile_path = profiles[idx]["path"]
-                        url = input(f"{Fore.CYAN}Enter the URL to crawl: {Style.RESET_ALL}")
+                        self.console.print("[cyan]Enter the URL to crawl: [/cyan]", end="")
+                        url = input()
                         if url:
                             # Call the provided crawl callback
                             await crawl_callback(profile_path, url)
@@ -597,13 +629,13 @@ class BrowserProfiler:
             os.makedirs(profile_path, exist_ok=True)
         
         # Print initial information
-        border = f"{Fore.CYAN}{'='*80}{Style.RESET_ALL}"
-        self.logger.info(f"\n{border}", tag="CDP")
-        self.logger.info(f"Launching standalone browser with CDP debugging", tag="CDP")
-        self.logger.info(f"Browser type: {Fore.GREEN}{browser_type}{Style.RESET_ALL}", tag="CDP")
-        self.logger.info(f"Profile path: {Fore.YELLOW}{profile_path}{Style.RESET_ALL}", tag="CDP")
-        self.logger.info(f"Debugging port: {Fore.CYAN}{debugging_port}{Style.RESET_ALL}", tag="CDP")
-        self.logger.info(f"Headless mode: {Fore.CYAN}{headless}{Style.RESET_ALL}", tag="CDP")
+        border = f"{'='*80}"
+        self.logger.info("{border}", tag="CDP", params={"border": border}, colors={"border": LogColor.CYAN})
+        self.logger.info("Launching standalone browser with CDP debugging", tag="CDP")
+        self.logger.info("Browser type: {browser_type}", tag="CDP", params={"browser_type": browser_type}, colors={"browser_type": LogColor.CYAN})
+        self.logger.info("Profile path: {profile_path}", tag="CDP", params={"profile_path": profile_path}, colors={"profile_path": LogColor.YELLOW})
+        self.logger.info(f"Debugging port: {debugging_port}", tag="CDP")
+        self.logger.info(f"Headless mode: {headless}", tag="CDP")
         
         # Create managed browser instance
         managed_browser = ManagedBrowser(
@@ -646,7 +678,7 @@ class BrowserProfiler:
             import select
             
             # First output the prompt
-            self.logger.info(f"{Fore.CYAN}Press '{Fore.WHITE}q{Fore.CYAN}' to stop the browser and exit...{Style.RESET_ALL}", tag="CDP")
+            self.logger.info("Press 'q' to stop the browser and exit...", tag="CDP")
             
             # Save original terminal settings
             fd = sys.stdin.fileno()
@@ -662,7 +694,7 @@ class BrowserProfiler:
                     if readable:
                         key = sys.stdin.read(1)
                         if key.lower() == 'q':
-                            self.logger.info(f"{Fore.GREEN}Closing browser...{Style.RESET_ALL}", tag="CDP")
+                            self.logger.info("Closing browser...", tag="CDP")
                             user_done_event.set()
                             return
                     
@@ -716,20 +748,20 @@ class BrowserProfiler:
                 self.logger.error("Failed to start browser process.", tag="CDP")
                 return None
             
-            self.logger.info(f"Browser launched successfully. Retrieving CDP information...", tag="CDP") 
+            self.logger.info("Browser launched successfully. Retrieving CDP information...", tag="CDP") 
             
             # Get CDP URL and JSON config
             cdp_url, config_json = await get_cdp_json(debugging_port)
             
             if cdp_url:
-                self.logger.success(f"CDP URL: {Fore.GREEN}{cdp_url}{Style.RESET_ALL}", tag="CDP")
+                self.logger.success(f"CDP URL: {cdp_url}", tag="CDP")
                 
                 if config_json:
                     # Display relevant CDP information
-                    self.logger.info(f"Browser: {Fore.CYAN}{config_json.get('Browser', 'Unknown')}{Style.RESET_ALL}", tag="CDP")
-                    self.logger.info(f"Protocol Version: {config_json.get('Protocol-Version', 'Unknown')}", tag="CDP")
+                    self.logger.info(f"Browser: {config_json.get('Browser', 'Unknown')}", tag="CDP", colors={"Browser": LogColor.CYAN})
+                    self.logger.info(f"Protocol Version: {config_json.get('Protocol-Version', 'Unknown')}", tag="CDP", colors={"Protocol-Version": LogColor.CYAN})
                     if 'webSocketDebuggerUrl' in config_json:
-                        self.logger.info(f"WebSocket URL: {Fore.GREEN}{config_json['webSocketDebuggerUrl']}{Style.RESET_ALL}", tag="CDP")
+                        self.logger.info("WebSocket URL: {webSocketDebuggerUrl}", tag="CDP", params={"webSocketDebuggerUrl": config_json['webSocketDebuggerUrl']}, colors={"webSocketDebuggerUrl": LogColor.GREEN})
                 else:
                     self.logger.warning("Could not retrieve CDP configuration JSON", tag="CDP")
             else:
@@ -757,7 +789,7 @@ class BrowserProfiler:
                 self.logger.info("Terminating browser process...", tag="CDP")
                 await managed_browser.cleanup()
             
-            self.logger.success(f"Browser closed.", tag="CDP")
+            self.logger.success("Browser closed.", tag="CDP")
                 
         except Exception as e:
             self.logger.error(f"Error launching standalone browser: {str(e)}", tag="CDP")
@@ -972,3 +1004,30 @@ class BrowserProfiler:
             'info': browser_info
         }
 
+
+if __name__ == "__main__":
+    # Example usage
+    profiler = BrowserProfiler()
+    
+    # Create a new profile
+    import os
+    from pathlib import Path
+    home_dir = Path.home()
+    profile_path = asyncio.run(profiler.create_profile( str(home_dir / ".crawl4ai/profiles/test-profile")))
+
+        
+            
+    # Launch a standalone browser
+    asyncio.run(profiler.launch_standalone_browser())
+    
+    # List profiles
+    profiles = profiler.list_profiles()
+    for profile in profiles:
+        print(f"Profile: {profile['name']}, Path: {profile['path']}")
+    
+    # Delete a profile
+    success = profiler.delete_profile("my-profile")
+    if success:
+        print("Profile deleted successfully")
+    else:
+        print("Failed to delete profile")

crawl4ai/cli.py

@@ -27,7 +27,10 @@ from crawl4ai import (
     PruningContentFilter,
     BrowserProfiler,
     DefaultMarkdownGenerator,
-    LLMConfig
+    LLMConfig,
+    BFSDeepCrawlStrategy,
+    DFSDeepCrawlStrategy,
+    BestFirstCrawlingStrategy,
 )
 from crawl4ai.config import USER_SETTINGS
 from litellm import completion
@@ -1010,13 +1013,15 @@ def cdp_cmd(user_data_dir: Optional[str], port: int, browser_type: str, headless
 @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", "-b", is_flag=True, default=True, help="Bypass cache when crawling")
+@click.option("--bypass-cache", "-bc", 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)")
+@click.option("--deep-crawl", type=click.Choice(["bfs", "dfs", "best-first"]), help="Enable deep crawling with specified strategy (bfs, dfs, or best-first)")
+@click.option("--max-pages", type=int, default=10, help="Maximum number of pages to crawl in deep crawl mode")
 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,
-           output: str, output_file: str, bypass_cache: bool, question: str, verbose: bool, profile: str):
+           output: str, output_file: str, bypass_cache: bool, question: str, verbose: bool, profile: str, deep_crawl: str, max_pages: int):
     """Crawl a website and extract content
     
     Simple Usage:
@@ -1073,7 +1078,8 @@ def crawl_cmd(url: str, browser_config: str, crawler_config: str, filter_config:
                 crawler_cfg.markdown_generator = DefaultMarkdownGenerator(
                     content_filter = BM25ContentFilter(
                         user_query=filter_conf.get("query"),
-                        bm25_threshold=filter_conf.get("threshold", 1.0)
+                        bm25_threshold=filter_conf.get("threshold", 1.0),
+                        use_stemming=filter_conf.get("use_stemming", True),
                     )
                 )
             elif filter_conf["type"] == "pruning":
@@ -1155,6 +1161,27 @@ Always return valid, properly formatted JSON."""
 
         crawler_cfg.scraping_strategy = LXMLWebScrapingStrategy()    
 
+        # Handle deep crawling configuration
+        if deep_crawl:
+            if deep_crawl == "bfs":
+                crawler_cfg.deep_crawl_strategy = BFSDeepCrawlStrategy(
+                    max_depth=3,
+                    max_pages=max_pages
+                )
+            elif deep_crawl == "dfs":
+                crawler_cfg.deep_crawl_strategy = DFSDeepCrawlStrategy(
+                    max_depth=3,
+                    max_pages=max_pages
+                )
+            elif deep_crawl == "best-first":
+                crawler_cfg.deep_crawl_strategy = BestFirstCrawlingStrategy(
+                    max_depth=3,
+                    max_pages=max_pages
+                )
+            
+            if verbose:
+                console.print(f"[green]Deep crawling enabled:[/green] {deep_crawl} strategy, max {max_pages} pages")
+
         config = get_global_config()
         
         browser_cfg.verbose = config.get("VERBOSE", False)
@@ -1169,39 +1196,60 @@ Always return valid, properly formatted JSON."""
             verbose
         )
 
+        # Handle deep crawl results (list) vs single result
+        if isinstance(result, list):
+            if len(result) == 0:
+                click.echo("No results found during deep crawling")
+                return
+            # Use the first result for question answering and output
+            main_result = result[0]
+            all_results = result
+        else:
+            # Single result from regular crawling
+            main_result = result
+            all_results = [result]
+
         # Handle question
         if question:
             provider, token = setup_llm_config()
-            markdown = result.markdown.raw_markdown
+            markdown = main_result.markdown.raw_markdown
             anyio.run(stream_llm_response, url, markdown, question, provider, token)
             return
         
         # Handle output
         if not output_file:
             if output == "all":
-                click.echo(json.dumps(result.model_dump(), indent=2))
+                if isinstance(result, list):
+                    output_data = [r.model_dump() for r in all_results]
+                    click.echo(json.dumps(output_data, indent=2))
+                else:
+                    click.echo(json.dumps(main_result.model_dump(), indent=2))
             elif output == "json":
-                print(result.extracted_content)
-                extracted_items = json.loads(result.extracted_content)
+                print(main_result.extracted_content)
+                extracted_items = json.loads(main_result.extracted_content)
                 click.echo(json.dumps(extracted_items, indent=2))
                 
             elif output in ["markdown", "md"]:
-                click.echo(result.markdown.raw_markdown)
+                click.echo(main_result.markdown.raw_markdown)
             elif output in ["markdown-fit", "md-fit"]:
-                click.echo(result.markdown.fit_markdown)
+                click.echo(main_result.markdown.fit_markdown)
         else:
             if output == "all":
                 with open(output_file, "w") as f:
-                    f.write(json.dumps(result.model_dump(), indent=2))
+                    if isinstance(result, list):
+                        output_data = [r.model_dump() for r in all_results]
+                        f.write(json.dumps(output_data, indent=2))
+                    else:
+                        f.write(json.dumps(main_result.model_dump(), indent=2))
             elif output == "json":
                 with open(output_file, "w") as f:
-                    f.write(result.extracted_content)
+                    f.write(main_result.extracted_content)
             elif output in ["markdown", "md"]:
                 with open(output_file, "w") as f:
-                    f.write(result.markdown.raw_markdown)
+                    f.write(main_result.markdown.raw_markdown)
             elif output in ["markdown-fit", "md-fit"]:
                 with open(output_file, "w") as f:
-                    f.write(result.markdown.fit_markdown)
+                    f.write(main_result.markdown.fit_markdown)
             
     except Exception as e:
         raise click.ClickException(str(e))
@@ -1353,9 +1401,11 @@ def profiles_cmd():
 @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)")
+@click.option("--deep-crawl", type=click.Choice(["bfs", "dfs", "best-first"]), help="Enable deep crawling with specified strategy")
+@click.option("--max-pages", type=int, default=10, help="Maximum number of pages to crawl in deep crawl mode")
 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,
-        output: str, bypass_cache: bool, question: str, verbose: bool, profile: str):
+        output: str, bypass_cache: bool, question: str, verbose: bool, profile: str, deep_crawl: str, max_pages: int):
     """Crawl4AI CLI - Web content extraction tool
 
     Simple Usage:
@@ -1405,7 +1455,9 @@ def default(url: str, example: bool, browser_config: str, crawler_config: str, f
         bypass_cache=bypass_cache,
         question=question,
         verbose=verbose,
-        profile=profile
+        profile=profile,
+        deep_crawl=deep_crawl,
+        max_pages=max_pages
     )
 
 def main():

crawl4ai/content_filter_strategy.py

@@ -27,8 +27,7 @@ import json
 import hashlib
 from pathlib import Path
 from concurrent.futures import ThreadPoolExecutor
-from .async_logger import AsyncLogger, LogLevel
-from colorama import Fore, Style
+from .async_logger import AsyncLogger, LogLevel, LogColor
 
 
 class RelevantContentFilter(ABC):
@@ -406,6 +405,7 @@ class BM25ContentFilter(RelevantContentFilter):
         user_query: str = None,
         bm25_threshold: float = 1.0,
         language: str = "english",
+        use_stemming: bool = True,
     ):
         """
         Initializes the BM25ContentFilter class, if not provided, falls back to page metadata.
@@ -417,9 +417,11 @@ class BM25ContentFilter(RelevantContentFilter):
             user_query (str): User query for filtering (optional).
             bm25_threshold (float): BM25 threshold for filtering (default: 1.0).
             language (str): Language for stemming (default: 'english').
+            use_stemming (bool): Whether to apply stemming (default: True).
         """
         super().__init__(user_query=user_query)
         self.bm25_threshold = bm25_threshold
+        self.use_stemming = use_stemming
         self.priority_tags = {
             "h1": 5.0,
             "h2": 4.0,
@@ -433,7 +435,7 @@ class BM25ContentFilter(RelevantContentFilter):
             "pre": 1.5,
             "th": 1.5,  # Table headers
         }
-        self.stemmer = stemmer(language)
+        self.stemmer = stemmer(language) if use_stemming else None
 
     def filter_content(self, html: str, min_word_threshold: int = None) -> List[str]:
         """
@@ -480,13 +482,19 @@ class BM25ContentFilter(RelevantContentFilter):
         #                 for _, chunk, _, _ in candidates]
         # tokenized_query = [ps.stem(word) for word in query.lower().split()]
 
-        tokenized_corpus = [
-            [self.stemmer.stemWord(word) for word in chunk.lower().split()]
-            for _, chunk, _, _ in candidates
-        ]
-        tokenized_query = [
-            self.stemmer.stemWord(word) for word in query.lower().split()
-        ]
+        if self.use_stemming:
+            tokenized_corpus = [
+                [self.stemmer.stemWord(word) for word in chunk.lower().split()]
+                for _, chunk, _, _ in candidates
+            ]
+            tokenized_query = [
+                self.stemmer.stemWord(word) for word in query.lower().split()
+            ]
+        else:
+            tokenized_corpus = [
+                chunk.lower().split() for _, chunk, _, _ in candidates
+            ]
+            tokenized_query = query.lower().split()
 
         # tokenized_corpus = [[self.stemmer.stemWord(word) for word in tokenize_text(chunk.lower())]
         #            for _, chunk, _, _ in candidates]
@@ -846,8 +854,7 @@ class LLMContentFilter(RelevantContentFilter):
                 },
                 colors={
                     **AsyncLogger.DEFAULT_COLORS,
-                    LogLevel.INFO: Fore.MAGENTA
-                    + Style.DIM,  # Dimmed purple for LLM ops
+                    LogLevel.INFO: LogColor.DIM_MAGENTA  # Dimmed purple for LLM ops
                 },
             )
         else:
@@ -892,7 +899,7 @@ class LLMContentFilter(RelevantContentFilter):
                 "Starting LLM markdown content filtering process",
                 tag="LLM",
                 params={"provider": self.llm_config.provider},
-                colors={"provider": Fore.CYAN},
+                colors={"provider": LogColor.CYAN},
             )
 
         # Cache handling
@@ -929,7 +936,7 @@ class LLMContentFilter(RelevantContentFilter):
                 "LLM markdown: Split content into {chunk_count} chunks",
                 tag="CHUNK",
                 params={"chunk_count": len(html_chunks)},
-                colors={"chunk_count": Fore.YELLOW},
+                colors={"chunk_count": LogColor.YELLOW},
             )
 
         start_time = time.time()
@@ -1038,7 +1045,7 @@ class LLMContentFilter(RelevantContentFilter):
                 "LLM markdown: Completed processing in {time:.2f}s",
                 tag="LLM",
                 params={"time": end_time - start_time},
-                colors={"time": Fore.YELLOW},
+                colors={"time": LogColor.YELLOW},
             )
 
         result = ordered_results if ordered_results else []

crawl4ai/content_scraping_strategy.py

@@ -23,6 +23,8 @@ from .utils import (
     is_external_url,
     get_base_domain,
     extract_metadata_using_lxml,
+    extract_page_context,
+    calculate_link_intrinsic_score,
 )
 from lxml import etree
 from lxml import html as lhtml
@@ -944,6 +946,72 @@ class WebScrapingStrategy(ContentScrapingStrategy):
         # Update the links dictionary with unique links
         links["internal"] = list(internal_links_dict.values())
         links["external"] = list(external_links_dict.values())
+        
+        # Extract head content for links if configured
+        link_preview_config = kwargs.get("link_preview_config")
+        if link_preview_config is not None:
+            try:
+                import asyncio
+                from .link_preview import LinkPreview
+                from .models import Links, Link
+                
+                verbose = link_preview_config.verbose
+                
+                if verbose:
+                    self._log("info", "Starting link head extraction for {internal} internal and {external} external links",
+                              params={"internal": len(links["internal"]), "external": len(links["external"])}, tag="LINK_EXTRACT")
+                
+                # Convert dict links to Link objects
+                internal_links = [Link(**link_data) for link_data in links["internal"]]
+                external_links = [Link(**link_data) for link_data in links["external"]]
+                links_obj = Links(internal=internal_links, external=external_links)
+                
+                # Create a config object for LinkPreview  
+                class TempCrawlerRunConfig:
+                    def __init__(self, link_config, score_links):
+                        self.link_preview_config = link_config
+                        self.score_links = score_links
+                
+                config = TempCrawlerRunConfig(link_preview_config, kwargs.get("score_links", False))
+                
+                # Extract head content (run async operation in sync context)
+                async def extract_links():
+                    async with LinkPreview(self.logger) as extractor:
+                        return await extractor.extract_link_heads(links_obj, config)
+                
+                # Run the async operation
+                try:
+                    # Check if we're already in an async context
+                    loop = asyncio.get_running_loop()
+                    # If we're in an async context, we need to run in a thread
+                    import concurrent.futures
+                    with concurrent.futures.ThreadPoolExecutor() as executor:
+                        future = executor.submit(asyncio.run, extract_links())
+                        updated_links = future.result()
+                except RuntimeError:
+                    # No running loop, we can use asyncio.run directly
+                    updated_links = asyncio.run(extract_links())
+                
+                # Convert back to dict format
+                links["internal"] = [link.dict() for link in updated_links.internal]
+                links["external"] = [link.dict() for link in updated_links.external]
+                
+                if verbose:
+                    successful_internal = len([l for l in updated_links.internal if l.head_extraction_status == "valid"])
+                    successful_external = len([l for l in updated_links.external if l.head_extraction_status == "valid"])
+                    self._log("info", "Link head extraction completed: {internal_success}/{internal_total} internal, {external_success}/{external_total} external",
+                              params={
+                                  "internal_success": successful_internal,
+                                  "internal_total": len(updated_links.internal),
+                                  "external_success": successful_external,
+                                  "external_total": len(updated_links.external)
+                              }, tag="LINK_EXTRACT")
+                else:
+                    self._log("info", "Link head extraction completed successfully", tag="LINK_EXTRACT")
+                
+            except Exception as e:
+                self._log("error", f"Link head extraction failed: {str(e)}", tag="LINK_EXTRACT")
+                # Continue with original links if extraction fails
 
         # # Process images using ThreadPoolExecutor
         imgs = body.find_all("img")
@@ -1037,6 +1105,7 @@ class LXMLWebScrapingStrategy(WebScrapingStrategy):
         media: Dict[str, List],
         internal_links_dict: Dict[str, Any],
         external_links_dict: Dict[str, Any],
+        page_context: dict = None,
         **kwargs,
     ) -> bool:
         base_domain = kwargs.get("base_domain", get_base_domain(url))
@@ -1056,6 +1125,25 @@ class LXMLWebScrapingStrategy(WebScrapingStrategy):
                     "title": link.get("title", "").strip(),
                     "base_domain": base_domain,
                 }
+                
+                # Add intrinsic scoring if enabled
+                if kwargs.get("score_links", False) and page_context is not None:
+                    try:
+                        intrinsic_score = calculate_link_intrinsic_score(
+                            link_text=link_data["text"],
+                            url=normalized_href,
+                            title_attr=link_data["title"],
+                            class_attr=link.get("class", ""),
+                            rel_attr=link.get("rel", ""),
+                            page_context=page_context
+                        )
+                        link_data["intrinsic_score"] = intrinsic_score
+                    except Exception:
+                        # Fail gracefully - assign default score
+                        link_data["intrinsic_score"] = float('inf')
+                else:
+                    # No scoring enabled - assign infinity (all links equal priority)
+                    link_data["intrinsic_score"] = float('inf')
 
                 is_external = is_external_url(normalized_href, base_domain)
                 if is_external:
@@ -1491,6 +1579,33 @@ class LXMLWebScrapingStrategy(WebScrapingStrategy):
 
             base_domain = get_base_domain(url)
             
+            # Extract page context for link scoring (if enabled) - do this BEFORE any removals
+            page_context = None
+            if kwargs.get("score_links", False):
+                try:
+                    # Extract title
+                    title_elements = doc.xpath('//title')
+                    page_title = title_elements[0].text_content() if title_elements else ""
+                    
+                    # Extract headlines
+                    headlines = []
+                    for tag in ['h1', 'h2', 'h3']:
+                        elements = doc.xpath(f'//{tag}')
+                        for el in elements:
+                            text = el.text_content().strip()
+                            if text:
+                                headlines.append(text)
+                    headlines_text = ' '.join(headlines)
+                    
+                    # Extract meta description
+                    meta_desc_elements = doc.xpath('//meta[@name="description"]/@content')
+                    meta_description = meta_desc_elements[0] if meta_desc_elements else ""
+                    
+                    # Create page context
+                    page_context = extract_page_context(page_title, headlines_text, meta_description, url)
+                except Exception:
+                    page_context = {}  # Fail gracefully
+            
             # 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):
@@ -1579,6 +1694,7 @@ class LXMLWebScrapingStrategy(WebScrapingStrategy):
                 media,
                 internal_links_dict,
                 external_links_dict,
+                page_context=page_context,
                 base_domain=base_domain,
                 **kwargs,
             )
@@ -1623,14 +1739,84 @@ class LXMLWebScrapingStrategy(WebScrapingStrategy):
                 method="html",
                 with_tail=False,
             ).strip()
+            
+            # Create links dictionary in the format expected by LinkPreview
+            links = {
+                "internal": list(internal_links_dict.values()),
+                "external": list(external_links_dict.values()),
+            }
+            
+            # Extract head content for links if configured
+            link_preview_config = kwargs.get("link_preview_config")
+            if link_preview_config is not None:
+                try:
+                    import asyncio
+                    from .link_preview import LinkPreview
+                    from .models import Links, Link
+                    
+                    verbose = link_preview_config.verbose
+                    
+                    if verbose:
+                        self._log("info", "Starting link head extraction for {internal} internal and {external} external links",
+                                  params={"internal": len(links["internal"]), "external": len(links["external"])}, tag="LINK_EXTRACT")
+                    
+                    # Convert dict links to Link objects
+                    internal_links = [Link(**link_data) for link_data in links["internal"]]
+                    external_links = [Link(**link_data) for link_data in links["external"]]
+                    links_obj = Links(internal=internal_links, external=external_links)
+                    
+                    # Create a config object for LinkPreview
+                    class TempCrawlerRunConfig:
+                        def __init__(self, link_config, score_links):
+                            self.link_preview_config = link_config
+                            self.score_links = score_links
+                    
+                    config = TempCrawlerRunConfig(link_preview_config, kwargs.get("score_links", False))
+                    
+                    # Extract head content (run async operation in sync context)
+                    async def extract_links():
+                        async with LinkPreview(self.logger) as extractor:
+                            return await extractor.extract_link_heads(links_obj, config)
+                    
+                    # Run the async operation
+                    try:
+                        # Check if we're already in an async context
+                        loop = asyncio.get_running_loop()
+                        # If we're in an async context, we need to run in a thread
+                        import concurrent.futures
+                        with concurrent.futures.ThreadPoolExecutor() as executor:
+                            future = executor.submit(asyncio.run, extract_links())
+                            updated_links = future.result()
+                    except RuntimeError:
+                        # No running loop, we can use asyncio.run directly
+                        updated_links = asyncio.run(extract_links())
+                    
+                    # Convert back to dict format
+                    links["internal"] = [link.dict() for link in updated_links.internal]
+                    links["external"] = [link.dict() for link in updated_links.external]
+                    
+                    if verbose:
+                        successful_internal = len([l for l in updated_links.internal if l.head_extraction_status == "valid"])
+                        successful_external = len([l for l in updated_links.external if l.head_extraction_status == "valid"])
+                        self._log("info", "Link head extraction completed: {internal_success}/{internal_total} internal, {external_success}/{external_total} external",
+                                  params={
+                                      "internal_success": successful_internal,
+                                      "internal_total": len(updated_links.internal),
+                                      "external_success": successful_external,
+                                      "external_total": len(updated_links.external)
+                                  }, tag="LINK_EXTRACT")
+                    else:
+                        self._log("info", "Link head extraction completed successfully", tag="LINK_EXTRACT")
+                        
+                except Exception as e:
+                    self._log("error", f"Error during link head extraction: {str(e)}", tag="LINK_EXTRACT")
+                    # Continue with original links if head extraction fails
+            
             return {
                 "cleaned_html": cleaned_html,
                 "success": success,
                 "media": media,
-                "links": {
-                    "internal": list(internal_links_dict.values()),
-                    "external": list(external_links_dict.values()),
-                },
+                "links": links,
                 "metadata": meta,
             }
 

crawl4ai/crawlers/google_search/crawler.py

@@ -1,7 +1,7 @@
 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.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 from pathlib import Path
 import json
 import os

crawl4ai/extraction_strategy.py

@@ -1,9 +1,10 @@
 from abc import ABC, abstractmethod
 import inspect
-from typing import Any, List, Dict, Optional
+from typing import Any, List, Dict, Optional, Tuple, Pattern, Union
 from concurrent.futures import ThreadPoolExecutor, as_completed
 import json
 import time
+from enum import IntFlag, auto
 
 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 .config import (
@@ -540,7 +541,7 @@ class LLMExtractionStrategy(ExtractionStrategy):
             api_token: The API token for the provider.
             base_url: The base URL for the API request.
             api_base: The base URL for the API request.
-            extra_args: Additional arguments for the API request, such as temprature, max_tokens, etc.
+            extra_args: Additional arguments for the API request, such as temperature, max_tokens, etc.
         """
         super().__init__( input_format=input_format, **kwargs)
         self.llm_config = llm_config
@@ -1167,7 +1168,11 @@ In this scenario, use your best judgment to generate the schema. You need to exa
         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: 
+        0/ 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.
+        1/ DO NOT USE use base64 kind of classes, they are temporary and not reliable.
+        2/ Every selector must refer to only one unique element. You should ensure your selector points to a single element and is unique to the place that contains the information. You have to use available techniques based on CSS or XPATH requested schema to make sure your selector is unique and also not fragile, meaning if we reload the page now or in the future, the selector should remain reliable.
+        3/ Do not use Regex as much as possible.
 
         Analyze the HTML and generate a JSON schema that follows the specified format. Only output valid JSON schema, nothing else.
         """
@@ -1668,3 +1673,303 @@ class JsonXPathExtractionStrategy(JsonElementExtractionStrategy):
     def _get_element_attribute(self, element, attribute: str):
         return element.get(attribute)
 
+"""
+RegexExtractionStrategy
+Fast, zero-LLM extraction of common entities via regular expressions.
+"""
+
+_CTRL = {c: rf"\x{ord(c):02x}" for c in map(chr, range(32)) if c not in "\t\n\r"}
+
+_WB_FIX = re.compile(r"\x08")               # stray back-space   →   word-boundary
+_NEEDS_ESCAPE = re.compile(r"(?<!\\)\\(?![\\u])")   # lone backslash
+
+def _sanitize_schema(schema: Dict[str, str]) -> Dict[str, str]:
+    """Fix common JSON-escape goofs coming from LLMs or manual edits."""
+    safe = {}
+    for label, pat in schema.items():
+        # 1️⃣ replace accidental control chars (inc. the infamous back-space)
+        pat = _WB_FIX.sub(r"\\b", pat).translate(_CTRL)
+
+        # 2️⃣ double any single backslash that JSON kept single
+        pat = _NEEDS_ESCAPE.sub(r"\\\\", pat)
+
+        # 3️⃣ quick sanity compile
+        try:
+            re.compile(pat)
+        except re.error as e:
+            raise ValueError(f"Regex for '{label}' won’t compile after fix: {e}") from None
+
+        safe[label] = pat
+    return safe
+
+
+class RegexExtractionStrategy(ExtractionStrategy):
+    """
+    A lean strategy that finds e-mails, phones, URLs, dates, money, etc.,
+    using nothing but pre-compiled regular expressions.
+
+    Extraction returns::
+
+        {
+            "url":   "<page-url>",
+            "label": "<pattern-label>",
+            "value": "<matched-string>",
+            "span":  [start, end]
+        }
+
+    Only `generate_schema()` touches an LLM, extraction itself is pure Python.
+    """
+
+    # -------------------------------------------------------------- #
+    # Built-in patterns exposed as IntFlag so callers can bit-OR them
+    # -------------------------------------------------------------- #
+    class _B(IntFlag):
+        EMAIL           = auto()
+        PHONE_INTL      = auto()
+        PHONE_US        = auto()
+        URL             = auto()
+        IPV4            = auto()
+        IPV6            = auto()
+        UUID            = auto()
+        CURRENCY        = auto()
+        PERCENTAGE      = auto()
+        NUMBER          = auto()
+        DATE_ISO        = auto()
+        DATE_US         = auto()
+        TIME_24H        = auto()
+        POSTAL_US       = auto()
+        POSTAL_UK       = auto()
+        HTML_COLOR_HEX  = auto()
+        TWITTER_HANDLE  = auto()
+        HASHTAG         = auto()
+        MAC_ADDR        = auto()
+        IBAN            = auto()
+        CREDIT_CARD     = auto()
+        NOTHING         = auto()
+        ALL             = (
+            EMAIL | PHONE_INTL | PHONE_US | URL | IPV4 | IPV6 | UUID
+            | CURRENCY | PERCENTAGE | NUMBER | DATE_ISO | DATE_US | TIME_24H
+            | POSTAL_US | POSTAL_UK | HTML_COLOR_HEX | TWITTER_HANDLE
+            | HASHTAG | MAC_ADDR | IBAN | CREDIT_CARD
+        )
+
+    # user-friendly aliases  (RegexExtractionStrategy.Email, .IPv4, …)
+    Email          = _B.EMAIL
+    PhoneIntl      = _B.PHONE_INTL
+    PhoneUS        = _B.PHONE_US
+    Url            = _B.URL
+    IPv4           = _B.IPV4
+    IPv6           = _B.IPV6
+    Uuid           = _B.UUID
+    Currency       = _B.CURRENCY
+    Percentage     = _B.PERCENTAGE
+    Number         = _B.NUMBER
+    DateIso        = _B.DATE_ISO
+    DateUS         = _B.DATE_US
+    Time24h        = _B.TIME_24H
+    PostalUS       = _B.POSTAL_US
+    PostalUK       = _B.POSTAL_UK
+    HexColor       = _B.HTML_COLOR_HEX
+    TwitterHandle  = _B.TWITTER_HANDLE
+    Hashtag        = _B.HASHTAG
+    MacAddr        = _B.MAC_ADDR
+    Iban           = _B.IBAN
+    CreditCard     = _B.CREDIT_CARD
+    All            = _B.ALL
+    Nothing        = _B(0)  # no patterns
+
+    # ------------------------------------------------------------------ #
+    # Built-in pattern catalog
+    # ------------------------------------------------------------------ #
+    DEFAULT_PATTERNS: Dict[str, str] = {
+        # Communication
+        "email":           r"[\w.+-]+@[\w-]+\.[\w.-]+",
+        "phone_intl":      r"\+?\d[\d .()-]{7,}\d",
+        "phone_us":        r"\(?\d{3}\)?[ -. ]?\d{3}[ -. ]?\d{4}",
+        # Web
+        "url":             r"https?://[^\s\"'<>]+",
+        "ipv4":            r"(?:\d{1,3}\.){3}\d{1,3}",
+        "ipv6":            r"[A-F0-9]{1,4}(?::[A-F0-9]{1,4}){7}",
+        # IDs
+        "uuid":            r"[0-9a-f]{8}-[0-9a-f]{4}-[1-5][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}",
+        # Money / numbers
+        "currency":        r"(?:USD|EUR|RM|\$|€|£)\s?\d+(?:[.,]\d{2})?",
+        "percentage":      r"\d+(?:\.\d+)?%",
+        "number":          r"\b\d{1,3}(?:[,.\s]\d{3})*(?:\.\d+)?\b",
+        # Dates / Times
+        "date_iso":        r"\d{4}-\d{2}-\d{2}",
+        "date_us":         r"\d{1,2}/\d{1,2}/\d{2,4}",
+        "time_24h":        r"\b(?:[01]?\d|2[0-3]):[0-5]\d(?:[:.][0-5]\d)?\b",
+        # Misc
+        "postal_us":       r"\b\d{5}(?:-\d{4})?\b",
+        "postal_uk":       r"\b[A-Z]{1,2}\d[A-Z\d]? ?\d[A-Z]{2}\b",
+        "html_color_hex":  r"#[0-9A-Fa-f]{6}\b",
+        "twitter_handle":  r"@[\w]{1,15}",
+        "hashtag":         r"#[\w-]+",
+        "mac_addr":        r"(?:[0-9A-Fa-f]{2}:){5}[0-9A-Fa-f]{2}",
+        "iban":            r"[A-Z]{2}\d{2}[A-Z0-9]{11,30}",
+        "credit_card":     r"\b(?:4\d{12}(?:\d{3})?|5[1-5]\d{14}|3[47]\d{13}|6(?:011|5\d{2})\d{12})\b",
+    }
+
+    _FLAGS = re.IGNORECASE | re.MULTILINE
+    _UNWANTED_PROPS = {
+        "provider": "Use llm_config instead",
+        "api_token": "Use llm_config instead",
+    }
+
+    # ------------------------------------------------------------------ #
+    # Construction
+    # ------------------------------------------------------------------ #
+    def __init__(
+        self,
+        pattern: "_B" = _B.NOTHING,
+        *,
+        custom: Optional[Union[Dict[str, str], List[Tuple[str, str]]]] = None,
+        input_format: str = "fit_html",
+        **kwargs,
+    ) -> None:
+        """
+        Args:
+            patterns: Custom patterns overriding or extending defaults.
+                      Dict[label, regex] or list[tuple(label, regex)].
+            input_format: "html", "markdown" or "text".
+            **kwargs: Forwarded to ExtractionStrategy.
+        """
+        super().__init__(input_format=input_format, **kwargs)
+
+        # 1️⃣  take only the requested built-ins
+        merged: Dict[str, str] = {
+            key: rx
+            for key, rx in self.DEFAULT_PATTERNS.items()
+            if getattr(self._B, key.upper()).value & pattern
+        }
+
+        # 2️⃣  apply user overrides / additions
+        if custom:
+            if isinstance(custom, dict):
+                merged.update(custom)
+            else:  # iterable of (label, regex)
+                merged.update({lbl: rx for lbl, rx in custom})
+
+        self._compiled: Dict[str, Pattern] = {
+            lbl: re.compile(rx, self._FLAGS) for lbl, rx in merged.items()
+        }
+
+    # ------------------------------------------------------------------ #
+    # Extraction
+    # ------------------------------------------------------------------ #
+    def extract(self, url: str, content: str, *q, **kw) -> List[Dict[str, Any]]:
+        # text = self._plain_text(html)
+        out: List[Dict[str, Any]] = []
+
+        for label, cre in self._compiled.items():
+            for m in cre.finditer(content):
+                out.append(
+                    {
+                        "url": url,
+                        "label": label,
+                        "value": m.group(0),
+                        "span": [m.start(), m.end()],
+                    }
+                )
+        return out
+
+    # ------------------------------------------------------------------ #
+    # Helpers
+    # ------------------------------------------------------------------ #
+    def _plain_text(self, content: str) -> str:
+        if self.input_format == "text":
+            return content
+        return BeautifulSoup(content, "lxml").get_text(" ", strip=True)
+
+    # ------------------------------------------------------------------ #
+    # LLM-assisted pattern generator
+    # ------------------------------------------------------------------ #
+    # ------------------------------------------------------------------ #
+    # LLM-assisted one-off pattern builder
+    # ------------------------------------------------------------------ #
+    @staticmethod
+    def generate_pattern(
+        label: str,
+        html: str,
+        *,
+        query: Optional[str] = None,
+        examples: Optional[List[str]] = None,
+        llm_config: Optional[LLMConfig] = None,
+        **kwargs,
+    ) -> Dict[str, str]:
+        """
+        Ask an LLM for a single page-specific regex and return
+            {label: pattern}   ── ready for RegexExtractionStrategy(custom=…)
+        """
+
+        # ── guard deprecated kwargs
+        for k in RegexExtractionStrategy._UNWANTED_PROPS:
+            if k in kwargs:
+                raise AttributeError(
+                    f"{k} is deprecated, {RegexExtractionStrategy._UNWANTED_PROPS[k]}"
+                )
+
+        # ── default LLM config
+        if llm_config is None:
+            llm_config = create_llm_config()
+
+        # ── system prompt – hardened
+        system_msg = (
+            "You are an expert Python-regex engineer.\n"
+            f"Return **one** JSON object whose single key is exactly \"{label}\", "
+            "and whose value is a raw-string regex pattern that works with "
+            "the standard `re` module in Python.\n\n"
+            "Strict rules (obey every bullet):\n"
+            "• If a *user query* is supplied, treat it as the precise semantic target and optimise the "
+            "  pattern to capture ONLY text that answers that query. If the query conflicts with the "
+            "  sample HTML, the HTML wins.\n"
+            "• Tailor the pattern to the *sample HTML* – reproduce its exact punctuation, spacing, "
+            "  symbols, capitalisation, etc. Do **NOT** invent a generic form.\n"
+            "• Keep it minimal and fast: avoid unnecessary capturing, prefer non-capturing `(?: … )`, "
+            "  and guard against catastrophic backtracking.\n"
+            "• Anchor with `^`, `$`, or `\\b` only when it genuinely improves precision.\n"
+            "• Use inline flags like `(?i)` when needed; no verbose flag comments.\n"
+            "• Output must be valid JSON – no markdown, code fences, comments, or extra keys.\n"
+            "• The regex value must be a Python string literal: **double every backslash** "
+            "(e.g. `\\\\b`, `\\\\d`, `\\\\\\\\`).\n\n"
+            "Example valid output:\n"
+            f"{{\"{label}\": \"(?:RM|rm)\\\\s?\\\\d{{1,3}}(?:,\\\\d{{3}})*(?:\\\\.\\\\d{{2}})?\"}}"
+        )
+
+        # ── user message: cropped HTML + optional hints
+        user_parts = ["```html", html[:5000], "```"]  # protect token budget
+        if query:
+            user_parts.append(f"\n\n## Query\n{query.strip()}")
+        if examples:
+            user_parts.append("## Examples\n" + "\n".join(examples[:20]))
+        user_msg = "\n\n".join(user_parts)
+
+        # ── LLM call (with retry/backoff)
+        resp = perform_completion_with_backoff(
+            provider=llm_config.provider,
+            prompt_with_variables="\n\n".join([system_msg, user_msg]),
+            json_response=True,
+            api_token=llm_config.api_token,
+            base_url=llm_config.base_url,
+            extra_args=kwargs,
+        )
+
+        # ── clean & load JSON (fix common escape mistakes *before* json.loads)
+        raw = resp.choices[0].message.content
+        raw = raw.replace("\x08", "\\b")                     # stray back-space → \b
+        raw = re.sub(r'(?<!\\)\\(?![\\u"])', r"\\\\", raw)   # lone \ → \\
+
+        try:
+            pattern_dict = json.loads(raw)
+        except Exception as exc:
+            raise ValueError(f"LLM did not return valid JSON: {raw}") from exc
+
+        # quick sanity-compile
+        for lbl, pat in pattern_dict.items():
+            try:
+                re.compile(pat)
+            except re.error as e:
+                raise ValueError(f"Invalid regex for '{lbl}': {e}") from None
+
+        return pattern_dict

crawl4ai/link_preview.py

@@ -0,0 +1,395 @@
+"""
+Link Extractor for Crawl4AI
+
+Extracts head content from links discovered during crawling using URLSeeder's
+efficient parallel processing and caching infrastructure.
+"""
+
+import asyncio
+import fnmatch
+from typing import Dict, List, Optional, Any
+from .async_logger import AsyncLogger
+from .async_url_seeder import AsyncUrlSeeder
+from .async_configs import SeedingConfig, CrawlerRunConfig
+from .models import Links, Link
+from .utils import calculate_total_score
+
+
+class LinkPreview:
+    """
+    Extracts head content from links using URLSeeder's parallel processing infrastructure.
+    
+    This class provides intelligent link filtering and head content extraction with:
+    - Pattern-based inclusion/exclusion filtering
+    - Parallel processing with configurable concurrency
+    - Caching for performance
+    - BM25 relevance scoring
+    - Memory-safe processing for large link sets
+    """
+    
+    def __init__(self, logger: Optional[AsyncLogger] = None):
+        """
+        Initialize the LinkPreview.
+        
+        Args:
+            logger: Optional logger instance for recording events
+        """
+        self.logger = logger
+        self.seeder: Optional[AsyncUrlSeeder] = None
+        self._owns_seeder = False
+    
+    async def __aenter__(self):
+        """Async context manager entry."""
+        await self.start()
+        return self
+    
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
+        """Async context manager exit."""
+        await self.close()
+    
+    async def start(self):
+        """Initialize the URLSeeder instance."""
+        if not self.seeder:
+            self.seeder = AsyncUrlSeeder(logger=self.logger)
+            await self.seeder.__aenter__()
+            self._owns_seeder = True
+    
+    async def close(self):
+        """Clean up resources."""
+        if self.seeder and self._owns_seeder:
+            await self.seeder.__aexit__(None, None, None)
+            self.seeder = None
+            self._owns_seeder = False
+    
+    def _log(self, level: str, message: str, tag: str = "LINK_EXTRACT", **kwargs):
+        """Helper method to safely log messages."""
+        if self.logger:
+            log_method = getattr(self.logger, level, None)
+            if log_method:
+                log_method(message=message, tag=tag, params=kwargs.get('params', {}))
+    
+    async def extract_link_heads(
+        self, 
+        links: Links, 
+        config: CrawlerRunConfig
+    ) -> Links:
+        """
+        Extract head content for filtered links and attach to Link objects.
+        
+        Args:
+            links: Links object containing internal and external links
+            config: CrawlerRunConfig with link_preview_config settings
+            
+        Returns:
+            Links object with head_data attached to filtered Link objects
+        """
+        link_config = config.link_preview_config
+        
+        # Ensure seeder is initialized
+        await self.start()
+        
+        # Filter links based on configuration
+        filtered_urls = self._filter_links(links, link_config)
+        
+        if not filtered_urls:
+            self._log("info", "No links matched filtering criteria")
+            return links
+        
+        self._log("info", "Extracting head content for {count} filtered links",
+                  params={"count": len(filtered_urls)})
+        
+        # Extract head content using URLSeeder
+        head_results = await self._extract_heads_parallel(filtered_urls, link_config)
+        
+        # Merge results back into Link objects
+        updated_links = self._merge_head_data(links, head_results, config)
+        
+        self._log("info", "Completed head extraction for links, {success} successful",
+                  params={"success": len([r for r in head_results if r.get("status") == "valid"])})
+        
+        return updated_links
+    
+    def _filter_links(self, links: Links, link_config: Dict[str, Any]) -> List[str]:
+        """
+        Filter links based on configuration parameters.
+        
+        Args:
+            links: Links object containing internal and external links
+            link_config: Configuration dictionary for link extraction
+            
+        Returns:
+            List of filtered URL strings
+        """
+        filtered_urls = []
+        
+        # Include internal links if configured
+        if link_config.include_internal:
+            filtered_urls.extend([link.href for link in links.internal if link.href])
+            self._log("debug", "Added {count} internal links",
+                      params={"count": len(links.internal)})
+        
+        # Include external links if configured
+        if link_config.include_external:
+            filtered_urls.extend([link.href for link in links.external if link.href])
+            self._log("debug", "Added {count} external links",
+                      params={"count": len(links.external)})
+        
+        # Apply include patterns
+        include_patterns = link_config.include_patterns
+        if include_patterns:
+            filtered_urls = [
+                url for url in filtered_urls
+                if any(fnmatch.fnmatch(url, pattern) for pattern in include_patterns)
+            ]
+            self._log("debug", "After include patterns: {count} links remain",
+                      params={"count": len(filtered_urls)})
+        
+        # Apply exclude patterns
+        exclude_patterns = link_config.exclude_patterns
+        if exclude_patterns:
+            filtered_urls = [
+                url for url in filtered_urls
+                if not any(fnmatch.fnmatch(url, pattern) for pattern in exclude_patterns)
+            ]
+            self._log("debug", "After exclude patterns: {count} links remain",
+                      params={"count": len(filtered_urls)})
+        
+        # Limit number of links
+        max_links = link_config.max_links
+        if max_links > 0 and len(filtered_urls) > max_links:
+            filtered_urls = filtered_urls[:max_links]
+            self._log("debug", "Limited to {max_links} links",
+                      params={"max_links": max_links})
+        
+        # Remove duplicates while preserving order
+        seen = set()
+        unique_urls = []
+        for url in filtered_urls:
+            if url not in seen:
+                seen.add(url)
+                unique_urls.append(url)
+        
+        self._log("debug", "Final filtered URLs: {count} unique links",
+                  params={"count": len(unique_urls)})
+        
+        return unique_urls
+    
+    async def _extract_heads_parallel(
+        self, 
+        urls: List[str], 
+        link_config: Dict[str, Any]
+    ) -> List[Dict[str, Any]]:
+        """
+        Extract head content for URLs using URLSeeder's parallel processing.
+        
+        Args:
+            urls: List of URLs to process
+            link_config: Configuration dictionary for link extraction
+            
+        Returns:
+            List of dictionaries with url, status, head_data, and optional relevance_score
+        """
+        verbose = link_config.verbose
+        concurrency = link_config.concurrency
+        
+        if verbose:
+            self._log("info", "Starting batch processing: {total} links with {concurrency} concurrent workers",
+                      params={"total": len(urls), "concurrency": concurrency})
+        
+        # Create SeedingConfig for URLSeeder
+        seeding_config = SeedingConfig(
+            extract_head=True,
+            concurrency=concurrency,
+            hits_per_sec=getattr(link_config, 'hits_per_sec', None),
+            query=link_config.query,
+            score_threshold=link_config.score_threshold,
+            scoring_method="bm25" if link_config.query else None,
+            verbose=verbose
+        )
+        
+        # Use URLSeeder's extract_head_for_urls method with progress tracking
+        if verbose:
+            # Create a wrapper to track progress
+            results = await self._extract_with_progress(urls, seeding_config, link_config)
+        else:
+            results = await self.seeder.extract_head_for_urls(
+                urls=urls,
+                config=seeding_config,
+                concurrency=concurrency,
+                timeout=link_config.timeout
+            )
+        
+        return results
+    
+    async def _extract_with_progress(
+        self, 
+        urls: List[str], 
+        seeding_config: SeedingConfig, 
+        link_config: Dict[str, Any]
+    ) -> List[Dict[str, Any]]:
+        """Extract head content with progress reporting."""
+        
+        total_urls = len(urls)
+        concurrency = link_config.concurrency
+        batch_size = max(1, total_urls // 10)  # Report progress every 10%
+        
+        # Process URLs and track progress
+        completed = 0
+        successful = 0
+        failed = 0
+        
+        # Create a custom progress tracking version
+        # We'll modify URLSeeder's method to include progress callbacks
+        
+        # For now, let's use the existing method and report at the end
+        # In a production version, we would modify URLSeeder to accept progress callbacks
+        
+        self._log("info", "Processing links in batches...")
+        
+        # Use existing method
+        results = await self.seeder.extract_head_for_urls(
+            urls=urls,
+            config=seeding_config,
+            concurrency=concurrency,
+            timeout=link_config.timeout
+        )
+        
+        # Count results
+        for result in results:
+            completed += 1
+            if result.get("status") == "valid":
+                successful += 1
+            else:
+                failed += 1
+        
+        # Final progress report
+        self._log("info", "Batch processing completed: {completed}/{total} processed, {successful} successful, {failed} failed",
+                  params={
+                      "completed": completed,
+                      "total": total_urls,
+                      "successful": successful,
+                      "failed": failed
+                  })
+        
+        return results
+    
+    def _merge_head_data(
+        self, 
+        original_links: Links, 
+        head_results: List[Dict[str, Any]],
+        config: CrawlerRunConfig
+    ) -> Links:
+        """
+        Merge head extraction results back into Link objects.
+        
+        Args:
+            original_links: Original Links object
+            head_results: Results from head extraction
+            
+        Returns:
+            Links object with head_data attached to matching links
+        """
+        # Create URL to head_data mapping
+        url_to_head_data = {}
+        for result in head_results:
+            url = result.get("url")
+            if url:
+                url_to_head_data[url] = {
+                    "head_data": result.get("head_data", {}),
+                    "status": result.get("status", "unknown"),
+                    "error": result.get("error"),
+                    "relevance_score": result.get("relevance_score")
+                }
+        
+        # Update internal links
+        updated_internal = []
+        for link in original_links.internal:
+            if link.href in url_to_head_data:
+                head_info = url_to_head_data[link.href]
+                # Create new Link object with head data and scoring
+                contextual_score = head_info.get("relevance_score")
+                
+                updated_link = Link(
+                    href=link.href,
+                    text=link.text,
+                    title=link.title,
+                    base_domain=link.base_domain,
+                    head_data=head_info["head_data"],
+                    head_extraction_status=head_info["status"],
+                    head_extraction_error=head_info.get("error"),
+                    intrinsic_score=getattr(link, 'intrinsic_score', None),
+                    contextual_score=contextual_score
+                )
+                
+                # Add relevance score to head_data for backward compatibility
+                if contextual_score is not None:
+                    updated_link.head_data = updated_link.head_data or {}
+                    updated_link.head_data["relevance_score"] = contextual_score
+                
+                # Calculate total score combining intrinsic and contextual scores
+                updated_link.total_score = calculate_total_score(
+                    intrinsic_score=updated_link.intrinsic_score,
+                    contextual_score=updated_link.contextual_score,
+                    score_links_enabled=getattr(config, 'score_links', False),
+                    query_provided=bool(config.link_preview_config.query)
+                )
+                
+                updated_internal.append(updated_link)
+            else:
+                # Keep original link unchanged
+                updated_internal.append(link)
+        
+        # Update external links
+        updated_external = []
+        for link in original_links.external:
+            if link.href in url_to_head_data:
+                head_info = url_to_head_data[link.href]
+                # Create new Link object with head data and scoring
+                contextual_score = head_info.get("relevance_score")
+                
+                updated_link = Link(
+                    href=link.href,
+                    text=link.text,
+                    title=link.title,
+                    base_domain=link.base_domain,
+                    head_data=head_info["head_data"],
+                    head_extraction_status=head_info["status"],
+                    head_extraction_error=head_info.get("error"),
+                    intrinsic_score=getattr(link, 'intrinsic_score', None),
+                    contextual_score=contextual_score
+                )
+                
+                # Add relevance score to head_data for backward compatibility
+                if contextual_score is not None:
+                    updated_link.head_data = updated_link.head_data or {}
+                    updated_link.head_data["relevance_score"] = contextual_score
+                
+                # Calculate total score combining intrinsic and contextual scores
+                updated_link.total_score = calculate_total_score(
+                    intrinsic_score=updated_link.intrinsic_score,
+                    contextual_score=updated_link.contextual_score,
+                    score_links_enabled=getattr(config, 'score_links', False),
+                    query_provided=bool(config.link_preview_config.query)
+                )
+                
+                updated_external.append(updated_link)
+            else:
+                # Keep original link unchanged
+                updated_external.append(link)
+        
+        # Sort links by relevance score if available
+        if any(hasattr(link, 'head_data') and link.head_data and 'relevance_score' in link.head_data 
+               for link in updated_internal + updated_external):
+            
+            def get_relevance_score(link):
+                if hasattr(link, 'head_data') and link.head_data and 'relevance_score' in link.head_data:
+                    return link.head_data['relevance_score']
+                return 0.0
+            
+            updated_internal.sort(key=get_relevance_score, reverse=True)
+            updated_external.sort(key=get_relevance_score, reverse=True)
+        
+        return Links(
+            internal=updated_internal,
+            external=updated_external
+        )

crawl4ai/models.py

@@ -1,4 +1,4 @@
-from pydantic import BaseModel, HttpUrl, PrivateAttr
+from pydantic import BaseModel, HttpUrl, PrivateAttr, Field
 from typing import List, Dict, Optional, Callable, Awaitable, Union, Any
 from typing import AsyncGenerator
 from typing import Generic, TypeVar
@@ -129,6 +129,7 @@ class MarkdownGenerationResult(BaseModel):
 class CrawlResult(BaseModel):
     url: str
     html: str
+    fit_html: Optional[str] = None
     success: bool
     cleaned_html: Optional[str] = None
     media: Dict[str, List[Dict]] = {}
@@ -150,6 +151,7 @@ class CrawlResult(BaseModel):
     redirected_url: Optional[str] = None
     network_requests: Optional[List[Dict[str, Any]]] = None
     console_messages: Optional[List[Dict[str, Any]]] = None
+    tables: List[Dict] = Field(default_factory=list)  # NEW – [{headers,rows,caption,summary}]
 
     class Config:
         arbitrary_types_allowed = True
@@ -343,6 +345,12 @@ class Link(BaseModel):
     text: Optional[str] = ""
     title: Optional[str] = ""
     base_domain: Optional[str] = ""
+    head_data: Optional[Dict[str, Any]] = None  # Head metadata extracted from link target
+    head_extraction_status: Optional[str] = None  # "success", "failed", "skipped"
+    head_extraction_error: Optional[str] = None  # Error message if extraction failed
+    intrinsic_score: Optional[float] = None  # Quality score based on URL structure, text, and context
+    contextual_score: Optional[float] = None  # BM25 relevance score based on query and head content
+    total_score: Optional[float] = None  # Combined score from intrinsic and contextual scores
 
 
 class Media(BaseModel):

crawl4ai/processors/pdf/__init__.py

@@ -14,7 +14,7 @@ class PDFCrawlerStrategy(AsyncCrawlerStrategy):
     async def crawl(self, url: str, **kwargs) -> AsyncCrawlResponse:
         # Just pass through with empty HTML - scraper will handle actual processing
         return AsyncCrawlResponse(
-            html="",  # Scraper will handle the real work
+            html="Scraper will handle the real work",  # Scraper will handle the real work
             response_headers={"Content-Type": "application/pdf"},
             status_code=200
         )
@@ -66,6 +66,7 @@ class PDFContentScrapingStrategy(ContentScrapingStrategy):
             image_save_dir=image_save_dir,
             batch_size=batch_size
         )
+        self._temp_files = []  # Track temp files for cleanup
 
     def scrap(self, url: str, html: str, **params) -> ScrapingResult:
         """
@@ -124,7 +125,13 @@ class PDFContentScrapingStrategy(ContentScrapingStrategy):
         finally:
             # Cleanup temp file if downloaded
             if url.startswith(("http://", "https://")):
-                Path(pdf_path).unlink(missing_ok=True)
+                try:
+                    Path(pdf_path).unlink(missing_ok=True)
+                    if pdf_path in self._temp_files:
+                        self._temp_files.remove(pdf_path)
+                except Exception as e:
+                    if self.logger:
+                        self.logger.warning(f"Failed to cleanup temp file {pdf_path}: {e}")
 
     async def ascrap(self, url: str, html: str, **kwargs) -> ScrapingResult:
         # For simple cases, you can use the sync version
@@ -138,22 +145,45 @@ class PDFContentScrapingStrategy(ContentScrapingStrategy):
             
             # Create temp file with .pdf extension
             temp_file = tempfile.NamedTemporaryFile(suffix='.pdf', delete=False)
+            self._temp_files.append(temp_file.name)
             
             try:
-                # Download PDF with streaming
-                response = requests.get(url, stream=True)
+                if self.logger:
+                    self.logger.info(f"Downloading PDF from {url}...")
+                
+                # Download PDF with streaming and timeout
+                # Connection timeout: 10s, Read timeout: 300s (5 minutes for large PDFs)
+                response = requests.get(url, stream=True, timeout=(20, 60 * 10))
                 response.raise_for_status()
                 
+                # Get file size if available
+                total_size = int(response.headers.get('content-length', 0))
+                downloaded = 0
+                
                 # Write to temp file
                 with open(temp_file.name, 'wb') as f:
                     for chunk in response.iter_content(chunk_size=8192):
                         f.write(chunk)
+                        downloaded += len(chunk)
+                        if self.logger and total_size > 0:
+                            progress = (downloaded / total_size) * 100
+                            if progress % 10 < 0.1:  # Log every 10%
+                                self.logger.debug(f"PDF download progress: {progress:.0f}%")
+                
+                if self.logger:
+                    self.logger.info(f"PDF downloaded successfully: {temp_file.name}")
                         
                 return temp_file.name
                 
+            except requests.exceptions.Timeout as e:
+                # Clean up temp file if download fails
+                Path(temp_file.name).unlink(missing_ok=True)
+                self._temp_files.remove(temp_file.name)
+                raise RuntimeError(f"Timeout downloading PDF from {url}: {str(e)}")
             except Exception as e:
                 # Clean up temp file if download fails
                 Path(temp_file.name).unlink(missing_ok=True)
+                self._temp_files.remove(temp_file.name)
                 raise RuntimeError(f"Failed to download PDF from {url}: {str(e)}")
                 
         elif url.startswith("file://"):

crawl4ai/prompts.py

@@ -1054,4 +1054,525 @@ Your output must:
 5. Include all required fields
 6. Use valid XPath selectors
 </output_requirements>
-"""
+"""
+
+GENERATE_SCRIPT_PROMPT = """You are a world-class browser automation specialist. Your sole purpose is to convert a natural language objective and a snippet of HTML into the most **efficient, robust, and simple** script possible to prepare a web page for data extraction.
+
+Your scripts run **before the crawl** to handle dynamic content, user interactions, and other obstacles. You are a master of two tools: raw **JavaScript** and the high-level **Crawl4ai Script (c4a)**.
+
+────────────────────────────────────────────────────────
+## Your Core Philosophy: "Efficiency, Robustness, Simplicity"
+
+This is your mantra. Every line of code you write must adhere to it.
+
+1.  **Efficiency (Shortest Path):** Generate the absolute minimum number of steps to achieve the goal. Do not include redundant actions. If a `CLICK` on one button achieves the goal, don't also scroll and wait unnecessarily.
+2.  **Robustness (Will Not Break):** Prioritize selectors and methods that are resistant to cosmetic site changes. `data-*` attributes are gold. Dynamic, auto-generated class names (`.class-a8B_x3`) are poison. Always prefer waiting for a state change (`WAIT \`#results\``) over a blind delay (`WAIT 5`).
+3.  **Simplicity (Right Tool for the Job):** Use the simplest tool that works. Prefer a direct `c4a` command over `EVAL` with JavaScript. Only use `EVAL` when the task is impossible with standard commands (e.g., accessing Shadow DOM, complex array filtering).
+
+────────────────────────────────────────────────────────
+## Output Mode Selection Logic
+
+Your choice of output mode is a critical strategic decision.
+
+*   **Use `crawl4ai_script` for:**
+    *   Standard, sequential browser actions: login forms, clicking "next page," simple "load more" buttons, accepting cookie banners.
+    *   When the user's goal maps clearly to the available `c4a` commands.
+    *   When you need to define reusable macros with `PROC`.
+
+*   **Use `javascript` for:**
+    *   Complex DOM manipulation that has no `c4a` equivalent (e.g., transforming data, complex filtering).
+    *   Interacting with web components inside **Shadow DOM** or **iFrames**.
+    *   Implementing sophisticated logic like custom scrolling patterns or handling non-standard events.
+    *   When the goal is a fine-grained DOM tweak, not a full user journey.
+
+**If the user specifies a mode, you MUST respect it.** If not, you must choose the mode that best embodies your core philosophy.
+
+────────────────────────────────────────────────────────
+## Available Crawl4ai Commands
+
+| Command                | Arguments / Notes                                            |
+|------------------------|--------------------------------------------------------------|
+| GO `<url>`             | Navigate to absolute URL                                     |
+| RELOAD                 | Hard refresh                                                |
+| BACK / FORWARD         | Browser history nav                                          |
+| WAIT `<seconds>`       | **Avoid!** Passive delay. Use only as a last resort.         |
+| WAIT \`<css>\` `<t>`   | **Preferred wait.** Poll selector until found, timeout in seconds. |
+| WAIT "<text>" `<t>`    | Poll page text until found, timeout in seconds.              |
+| CLICK \`<css>\`        | Single click on element                                     |
+| CLICK `<x>` `<y>`      | Viewport click                                              |
+| DOUBLE_CLICK …         | Two rapid clicks                                            |
+| RIGHT_CLICK …          | Context-menu click                                          |
+| MOVE `<x>` `<y>`       | Mouse move                                                  |
+| DRAG `<x1>` `<y1>` `<x2>` `<y2>` | Click-drag gesture                              |
+| SCROLL UP|DOWN|LEFT|RIGHT `[px]` | Viewport scroll                                 |
+| TYPE "<text>"          | Type into focused element                                   |
+| CLEAR \`<css>\`        | Empty input                                                 |
+| SET \`<css>\` "<val>"  | Set element value and dispatch events                       |
+| PRESS `<Key>`          | Keydown + keyup                                             |
+| KEY_DOWN `<Key>` / KEY_UP `<Key>` | Separate key events                          |
+| EVAL \`<js>\`          | **Your fallback.** Run JS when no direct command exists.     |
+| SETVAR $name = <val>   | Store constant for reuse                                    |
+| PROC name … ENDPROC    | Define macro                                                |
+| IF / ELSE / REPEAT     | Flow control                                                |
+| USE "<file.c4a>"       | Include another script, avoid circular includes             |
+
+────────────────────────────────────────────────────────
+## Strategic Principles & Anti-Patterns
+
+These are your commandments. Do not deviate.
+
+1.  **Selector Quality is Paramount:**
+    *   **GOOD:** `[data-testid="submit-button"]`, `#main-content`, `[aria-label="Close dialog"]`
+    *   **BAD:** `div > span:nth-child(3)`, `.button-gR3xY_s`, `//div[contains(@class, 'button')]`
+
+2.  **Wait for State, Not for Time:**
+    *   **DO:** `CLICK \`#load-more\`` followed by `WAIT \`div.new-item\` 10`. This waits for the *result* of the action.
+    *   **DON'T:** `CLICK \`#load-more\`` followed by `WAIT 5`. This is a guess and it will fail.
+
+3.  **Target the Action, Not the Artifact:** If you need to reveal content, click the button that reveals it. Don't try to manually change CSS `display` properties, as this can break the page's internal state.
+
+4.  **DOM-Awareness is Non-Negotiable:**
+    *   **Shadow DOM:** `c4a` commands CANNOT pierce the Shadow DOM. If you see a `#shadow-root (open)` in the HTML, you MUST use `EVAL` and `element.shadowRoot.querySelector(...)`.
+    *   **iFrames:** Likewise, you MUST use `EVAL` and `iframe.contentDocument.querySelector(...)` to interact with elements inside an iframe.
+
+5.  **Be Idempotent:** Your script must be harmless if run multiple times. Use `IF EXISTS` to check for states before acting (e.g., don't try to log in if already logged in).
+
+6.  **Forbidden Techniques:** Never use `document.write()`. It is destructive. Avoid overly complex JS in `EVAL` that could be simplified into a few `c4a` commands.
+
+────────────────────────────────────────────────────────
+## From Vague Goals to Robust Scripts: Your Duty to Infer and Ensure Reliability
+
+This is your most important responsibility. Users are not automation experts. They will provide incomplete or vague instructions. Your job is to be the expert—to infer their true goal and build a script that is reliable by default. You must add the "invisible scaffolding" of checks and waits to ensure the page is stable and ready for the crawler. **A vague user prompt must still result in a robust, complete script.**
+
+Study these examples. No matter which query is given, your output must be the single, robust solution.
+
+### 1. Scenario: Basic Search Query
+
+*   **High Detail Query:** "Find the search box and search button. Wait for the search box to be visible, click it, clear it, type 'r2d2', click the search button, and then wait for the search results to appear."
+*   **Medium Detail Query:** "Find the search box and search for 'r2d2', click the search button until you get a list of items."
+*   **Low Detail Query:** "Search for r2d2."
+
+**THE CORRECT, ROBUST OUTPUT (for all three queries):**
+```
+WAIT `input[type="search"]` 10
+SET `input[type="search"]` "r2d2"
+CLICK `button[aria-label="Search"]`
+WAIT `div.search-results-container` 15
+```
+**Rationale:** You correctly infer the need to `WAIT` for the input first. You use the more efficient `SET` command. Most importantly, you **infer the crucial final step**: waiting for a results container to appear, confirming the search action was successful.
+
+### 2. Scenario: Clicking a "Load More" Button
+
+*   **High Detail Query:** "Click the button with the text 'Load More'. Afterward, wait for a new item with the class '.product-tile' to show up on the page."
+*   **Medium Detail Query:** "Click the load more button to see more products."
+*   **Low Detail Query:** "Load more items."
+
+**THE CORRECT, ROBUST OUTPUT:**
+```
+IF EXISTS `button.load-more` THEN
+  CLICK `button.load-more`
+  WAIT `div.new-item-indicator` 8
+ENDIF
+```
+**Rationale:** You wrap the action in `IF EXISTS` to prevent errors if the button is not present (e.g., on the last page). You correctly infer the need to wait for the *consequence* of the click—a new item appearing—rather than a blind `WAIT 2`.
+
+### 3. Scenario: Applying a Filter from a Dropdown
+
+*   **High Detail Query:** "First, click the dropdown with id 'color-filter'. Then, from the open menu, click the option that says 'Blue'. Finally, wait for the product grid to update."
+*   **Medium Detail Query:** "Filter the products by the color Blue."
+*   **Low Detail Query:** "Show blue products."
+
+**THE CORRECT, ROBUST OUTPUT:**
+```
+CLICK `#color-filter`
+WAIT `[data-value="blue"]` 3
+CLICK `[data-value="blue"]`
+WAIT `#product-grid[data-status="updated"]` 10
+```
+**Rationale:** You infer the need for two waits: one for the menu options to appear after the first click, and a second for the main content to update after the filter is applied. This prevents race conditions.
+
+### 4. Scenario: User Authentication (Login)
+
+*   **High Detail Query:** "Fill username with 'USER_EMAIL', fill password with 'USER_PASS', click login, and wait for the dashboard to appear."
+*   **Medium Detail Query:** "Log in as USER_EMAIL with password USER_PASS."
+*   **Low Detail Query:** "Log in."
+
+**THE CORRECT, ROBUST OUTPUT:**
+```
+IF EXISTS `[data-testid="logout-button"]` THEN
+  EVAL `console.log("Already logged in.")`
+ELSE
+  WAIT `input[name="username"]` 10
+  SET `input[name="username"]` "USER_EMAIL"
+  SET `input[name="password"]` "USER_PASS"
+  CLICK `button[type="submit"]`
+  WAIT `[data-testid="user-dashboard"]` 15
+ENDIF
+```
+**Rationale:** You build an **idempotent** script. You first check if the user is *already* logged in. If not, you proceed with the login and then, critically, `WAIT` for a post-login element to confirm success. You use placeholders when credentials are not provided in low-detail queries.
+
+### 5. Scenario: Dismissing an Interstitial Modal
+
+*   **High Detail Query:** "Check if a popup with id '#promo-modal' exists. If it does, click the close button inside it with class '.close-x'."
+*   **Medium Detail Query:** "Close the promotional popup."
+*   **Low Detail Query:** "Get rid of the popup."
+
+**THE CORRECT, ROBUST OUTPUT:**
+```
+IF EXISTS `div#promo-modal` THEN
+  CLICK `div#promo-modal button.close-x`
+ENDIF
+```
+**Rationale:** You correctly identify this as a conditional action. The script must not fail if the popup doesn't appear. The `IF EXISTS` block is the perfect, robust way to handle this optional interaction.
+
+────────────────────────────────────────────────────────
+## Advanced Scenarios & Master-Level Examples
+
+Study these solutions. Understand the *why* behind each choice.
+
+### Scenario: Interacting with a Web Component (Shadow DOM)
+**Goal:** Click a button inside a custom element `<user-card>`.
+**HTML Snippet:** `<user-card><#shadow-root (open)><button>Details</button></#shadow-root></user-card>`
+**Correct Mode:** `javascript` (or `c4a` with `EVAL`)
+**Rationale:** Standard selectors can't cross the shadow boundary. JavaScript is mandatory.
+
+```javascript
+// Solution in pure JS mode
+const card = document.querySelector('user-card');
+if (card && card.shadowRoot) {
+  const button = card.shadowRoot.querySelector('button');
+  if (button) button.click();
+}
+```
+```
+# Solution in c4a mode (using EVAL as the weapon of choice)
+EVAL `
+  const card = document.querySelector('user-card');
+  if (card && card.shadowRoot) {
+    const button = card.shadowRoot.querySelector('button');
+    if (button) button.click();
+  }
+`
+```
+
+### Scenario: Handling a Cookie Banner
+**Goal:** Accept the cookies to dismiss the modal.
+**HTML Snippet:** `<div id="cookie-consent-modal"><button id="accept-cookies">Accept All</button></div>`
+**Correct Mode:** `crawl4ai_script`
+**Rationale:** A simple, direct action. `c4a` is cleaner and more declarative.
+
+```
+# The most efficient solution
+IF EXISTS `#cookie-consent-modal` THEN
+  CLICK `#accept-cookies`
+  WAIT `div.content-loaded` 5
+ENDIF
+```
+
+### Scenario: Infinite Scroll Page
+**Goal:** Scroll down 5 times to load more content.
+**HTML Snippet:** `(A page with a long body and no "load more" button)`
+**Correct Mode:** `crawl4ai_script`
+**Rationale:** `REPEAT` is designed for exactly this. It's more readable than a JS loop for this simple task.
+
+```
+REPEAT (
+  SCROLL DOWN 1000,
+  5
+)
+WAIT 2
+```
+
+### Scenario: Hover-to-Reveal Menu
+**Goal:** Hover over "Products" to open the menu, then click "Laptops".
+**HTML Snippet:** `<a href="/products" id="products-menu">Products</a> <div class="menu-dropdown"><a href="/laptops">Laptops</a></div>`
+**Correct Mode:** `crawl4ai_script` (with `EVAL`)
+**Rationale:** `c4a` has no `HOVER` command. `EVAL` is the perfect tool to dispatch the `mouseover` event.
+
+```
+EVAL `document.querySelector('#products-menu').dispatchEvent(new MouseEvent('mouseover', { bubbles: true }))`
+WAIT `div.menu-dropdown a[href="/laptops"]` 3
+CLICK `div.menu-dropdown a[href="/laptops"]`
+```
+
+### Scenario: Login Form
+**Goal:** Fill and submit a login form.
+**HTML Snippet:** `<form><input name="email"><input name="password" type="password"><button type="submit"></button></form>`
+**Correct Mode:** `crawl4ai_script`
+**Rationale:** This is the canonical use case for `c4a`. The commands map 1:1 to the user journey.
+
+```
+WAIT `form` 10
+SET `input[name="email"]` "USER_EMAIL"
+SET `input[name="password"]` "USER_PASS"
+CLICK `button[type="submit"]`
+WAIT `[data-testid="user-dashboard"]` 12
+```
+
+────────────────────────────────────────────────────────
+## Final Output Mandate
+
+1.  **CODE ONLY.** Your entire response must be the script body.
+2.  **NO CHAT.** Do not say "Here is the script" or "This should work."
+3.  **NO MARKDOWN.** Do not wrap your code in ` ``` ` fences.
+4.  **NO COMMENTS.** Do not add comments to the final code output.
+5.  **SYNTACTICALLY PERFECT.** The script must be immediately executable.
+6.  **UTF-8, STANDARD QUOTES.** Use `"` for string literals, not `“` or `”`.
+
+You are an engine of automation. Now, receive the user's request and produce the optimal script."""
+
+
+GENERATE_JS_SCRIPT_PROMPT = """# The World-Class JavaScript Automation Scripter
+
+You are a world-class browser automation specialist. Your sole purpose is to convert a natural language objective and a snippet of HTML into the most **efficient, robust, and simple** pure JavaScript script possible to prepare a web page for data extraction.
+
+Your scripts will be executed directly in the browser (e.g., via Playwright's `page.evaluate()`) to handle dynamic content, user interactions, and other obstacles before the page is crawled. You are a master of browser-native JavaScript APIs.
+
+────────────────────────────────────────────────────────
+## Your Core Philosophy: "Efficiency, Robustness, Simplicity"
+
+This is your mantra. Every line of JavaScript you write must adhere to it.
+
+1.  **Efficiency (Shortest Path):** Generate the absolute minimum number of steps to achieve the goal. Do not include redundant actions. Your code should be concise and direct.
+2.  **Robustness (Will Not Break):** Prioritize selectors that are resistant to cosmetic site changes. `data-*` attributes are gold. Dynamic, auto-generated class names (`.class-a8B_x3`) are poison. Always prefer waiting for a state change over a blind `setTimeout`.
+3.  **Simplicity (Right Tool for the Job):** Use simple, direct DOM methods (`.querySelector`, `.click()`) whenever possible. Avoid overly complex or fragile logic when a simpler approach exists.
+
+────────────────────────────────────────────────────────
+## Essential JavaScript Automation Patterns & Toolkit
+
+All code should be wrapped in an `async` Immediately Invoked Function Expression `(async () => { ... })();` to allow for top-level `await` and to avoid polluting the global scope.
+
+| Task                 | Best-Practice JavaScript Implementation                                                                                                                                                                                                                                                                                                      |
+| -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **Wait for Element** | Create and use a robust `waitForElement` helper function. This is your most important tool. <br> `const waitForElement = (selector, timeout = 10000) => new Promise((resolve, reject) => { const el = document.querySelector(selector); if (el) return resolve(el); const observer = new MutationObserver(() => { const el = document.querySelector(selector); if (el) { observer.disconnect(); resolve(el); } }); observer.observe(document.body, { childList: true, subtree: true }); setTimeout(() => { observer.disconnect(); reject(new Error(`Timeout waiting for ${selector}`)); }, timeout); });` |
+| **Click Element**    | `const el = await waitForElement('selector'); if (el) el.click();`                                                                                                                                                                                                                                                                           |
+| **Set Input Value**  | `const input = await waitForElement('selector'); if (input) { input.value = 'new value'; input.dispatchEvent(new Event('input', { bubbles: true })); input.dispatchEvent(new Event('change', { bubbles: true })); }` <br> *Crucially, always dispatch `input` and `change` events to trigger framework reactivity.* |
+| **Check Existence**  | `const el = document.querySelector('selector'); if (el) { /* ... it exists */ }`                                                                                                                                                                                                                                                            |
+| **Scroll**           | `window.scrollBy(0, window.innerHeight);`                                                                                                                                                                                                                                                                                                    |
+| **Deal with Time**   | Use `await new Promise(r => setTimeout(r, 500));` for short, unavoidable pauses after an action. **Avoid long, blind waits.**                                                                                                                                                                                                                |
+
+REMEMBER: Make sure to generate very deterministic css selector. If you refer to a specific button, then be specific, otherwise you may capture elements you do not need, be very specific about the element you want to interact with.
+
+────────────────────────────────────────────────────────
+## The Art of High-Specificity Selectors: Your Defense Against Ambiguity
+
+This is your most critical skill for ensuring robustness. **You must assume the provided HTML is only a small fragment of the entire page.** A selector that looks unique in the fragment could be disastrously generic on the full page. Your primary defense is to **anchor your selectors to the most specific, stable parent element available in the given HTML context.**
+
+Think of it as creating a "sandbox" for your selectors.
+
+**Your Guiding Principle:** Start from a unique parent, then find the child.
+
+### Scenario: Selecting a Submit Button within a Login Form
+
+**HTML Snippet Provided:**
+```html
+<div class="user-auth-module" id="login-widget">
+  <h2>Member Login</h2>
+  <form action="/login">
+    <input name="email" type="email">
+    <input name="password" type="password">
+    <button type="submit">Sign In</button>
+  </form>
+</div>
+```
+
+*   **TERRIBLE (High Risk):** `button[type="submit"]`
+    *   **Why it's bad:** There could be dozens of other forms on the full page (e.g., a newsletter signup, a search bar in the header). This selector is a shot in the dark.
+
+*   **BETTER (Lower Risk):** `#login-widget button[type="submit"]`
+    *   **Why it's better:** It's anchored to a unique ID (`#login-widget`). This dramatically reduces the chance of ambiguity.
+
+*   **EXCELLENT (Minimal Risk):** `div[id="login-widget"] form button[type="submit"]`
+    *   **Why it's best:** This is a highly specific, descriptive path. It says, "Find the login widget, then the form inside it, and then the submit button inside *that* form." It is virtually guaranteed to be unique and is resilient to minor layout changes within the form.
+
+### Scenario: Selecting a "Add to Cart" Button
+
+**HTML Snippet Provided:**
+```html
+<section data-testid="product-details-main">
+  <h1>Awesome T-Shirt</h1>
+  <div class="product-actions">
+    <button class="add-to-cart-btn">Add to Cart</button>
+  </div>
+</section>
+```
+
+*   **TERRIBLE (High Risk):** `.add-to-cart-btn`
+    *   **Why it's bad:** A "related products" section outside this snippet might also use the same class name.
+
+*   **EXCELLENT (Minimal Risk):** `[data-testid="product-details-main"] .add-to-cart-btn`
+    *   **Why it's best:** It uses the stable `data-testid` attribute of the parent section as an anchor. This is the most robust pattern.
+
+**Your Mandate:** Always examine the provided HTML for a stable, unique parent (like an element with an `id`, a `data-testid`, or a highly specific combination of classes) and use it as the root of your selectors. **NEVER generate a generic, un-anchored selector if a better, more specific parent is available in the context.**
+
+
+────────────────────────────────────────────────────────
+## Strategic Principles & Anti-Patterns
+
+These are your commandments. Do not deviate.
+
+1.  **Selector Quality is Paramount:**
+    *   **GOOD:** `[data-testid="submit-button"]`, `#main-content`, `[aria-label="Close dialog"]`
+    *   **BAD:** `div > span:nth-child(3)`, `.button-gR3xY_s`, `//div[contains(@class, 'button')]`
+
+2.  **Wait for State, Not for Time:**
+    *   **DO:** `(await waitForElement('#load-more')).click(); await waitForElement('div.new-item');` This waits for the *result* of the action.
+    *   **DON'T:** `document.querySelector('#load-more').click(); await new Promise(r => setTimeout(r, 5000));` This is a guess and it will fail.
+
+3.  **Target the Action, Not the Artifact:** If you need to reveal content, click the button that reveals it. Don't try to manually change CSS `display` properties, as this can break the page's internal state.
+
+4.  **DOM-Awareness is Non-Negotiable:**
+    *   **Shadow DOM:** You MUST use `element.shadowRoot.querySelector(...)` to access elements inside a `#shadow-root (open)`.
+    *   **iFrames:** You MUST use `iframe.contentDocument.querySelector(...)` to interact with elements inside an iframe.
+
+5.  **Be Idempotent:** Your script must be harmless if run multiple times. Use `if (document.querySelector(...))` checks to avoid re-doing actions unnecessarily.
+
+6.  **Forbidden Techniques:** Never use `document.write()`. It is destructive.
+
+────────────────────────────────────────────────────────
+## From Vague Goals to Robust Scripts: Your Duty to Infer and Ensure Reliability
+
+This is your most important responsibility. Users are not automation experts. They will provide incomplete or vague instructions. Your job is to be the expert—to infer their true goal and build a script that is reliable by default. **A vague user prompt must still result in a robust, complete script.**
+
+Study these examples. No matter which query is given, your output must be the single, robust solution.
+
+### 1. Scenario: Basic Search Query
+
+*   **High Detail Query:** "Find the search box and search button. Wait for the search box to be visible, click it, clear it, type 'r2d2', click the search button, and then wait for the search results to appear."
+*   **Medium Detail Query:** "Find the search box and search for 'r2d2'."
+*   **Low Detail Query:** "Search for r2d2."
+
+**THE CORRECT, ROBUST JAVASCRIPT OUTPUT (for all three queries):**
+```javascript
+(async () => {
+  const waitForElement = (selector, timeout = 10000) => new Promise((resolve, reject) => { const el = document.querySelector(selector); if (el) return resolve(el); const observer = new MutationObserver(() => { const el = document.querySelector(selector); if (el) { observer.disconnect(); resolve(el); } }); observer.observe(document.body, { childList: true, subtree: true }); setTimeout(() => { observer.disconnect(); reject(new Error(`Timeout waiting for ${selector}`)); }, timeout); });
+  try {
+    const searchInput = await waitForElement('input[type="search"], input[aria-label*="search"]');
+    searchInput.value = 'r2d2';
+    searchInput.dispatchEvent(new Event('input', { bubbles: true }));
+    const searchButton = await waitForElement('button[type="submit"], button[aria-label*="search"]');
+    searchButton.click();
+    await waitForElement('div.search-results-container, #search-results');
+  } catch (e) {
+    console.error('Search script failed:', e.message);
+  }
+})();
+```
+
+### 2. Scenario: Clicking a "Load More" Button
+
+*   **High Detail Query:** "Click the button with the text 'Load More'. Afterward, wait for a new item with the class '.product-tile' to show up."
+*   **Medium Detail Query:** "Click the load more button."
+*   **Low Detail Query:** "Load more items."
+
+**THE CORRECT, ROBUST JAVASCRIPT OUTPUT:**
+```javascript
+(async () => {
+  const loadMoreButton = document.querySelector('button.load-more, [data-testid="load-more"]');
+  if (loadMoreButton) {
+    const initialItemCount = document.querySelectorAll('.product-tile').length;
+    loadMoreButton.click();
+    const waitForNewItem = (timeout = 8000) => new Promise((resolve, reject) => { const t0 = Date.now(); const check = () => { if (document.querySelectorAll('.product-tile').length > initialItemCount) return resolve(); if (Date.now() - t0 > timeout) return reject(new Error('Timeout waiting for new items to load.')); setTimeout(check, 200); }; check(); });
+    await waitForNewItem();
+  }
+})();
+```
+
+### 3. Scenario: User Authentication (Login)
+
+*   **High Detail Query:** "Fill username with 'USER_EMAIL', password with 'USER_PASS', click login, and wait for the dashboard."
+*   **Medium Detail Query:** "Log in as USER_EMAIL."
+*   **Low Detail Query:** "Log in."
+
+**THE CORRECT, ROBUST JAVASCRIPT OUTPUT:**
+```javascript
+(async () => {
+  if (document.querySelector('[data-testid="logout-button"]')) {
+    console.log('Already logged in.');
+    return;
+  }
+  const waitForElement = (selector, timeout = 10000) => new Promise((resolve, reject) => { const el = document.querySelector(selector); if (el) return resolve(el); const observer = new MutationObserver(() => { const el = document.querySelector(selector); if (el) { observer.disconnect(); resolve(el); } }); observer.observe(document.body, { childList: true, subtree: true }); setTimeout(() => { observer.disconnect(); reject(new Error(`Timeout waiting for ${selector}`)); }, timeout); });
+  try {
+    const userInput = await waitForElement('input[name*="user"], input[name*="email"]');
+    userInput.value = 'USER_EMAIL';
+    userInput.dispatchEvent(new Event('input', { bubbles: true }));
+    const passInput = await waitForElement('input[name*="pass"], input[type="password"]');
+    passInput.value = 'USER_PASS';
+    passInput.dispatchEvent(new Event('input', { bubbles: true }));
+    const submitButton = await waitForElement('button[type="submit"]');
+    submitButton.click();
+    await waitForElement('[data-testid="user-dashboard"], #dashboard, .account-page');
+  } catch (e) {
+    console.error('Login script failed:', e.message);
+  }
+})();
+```
+
+────────────────────────────────────────────────────────
+## The Art of High-Specificity Selectors: Your Defense Against Ambiguity
+
+This is your most critical skill for ensuring robustness. **You must assume the provided HTML is only a small fragment of the entire page.** A selector that looks unique in the fragment could be disastrously generic on the full page. Your primary defense is to **anchor your selectors to the most specific, stable parent element available in the given HTML context.**
+
+Think of it as creating a "sandbox" for your selectors.
+
+**Your Guiding Principle:** Start from a unique parent, then find the child.
+
+### Scenario: Selecting a Submit Button within a Login Form
+
+**HTML Snippet Provided:**
+```html
+<div class="user-auth-module" id="login-widget">
+  <h2>Member Login</h2>
+  <form action="/login">
+    <input name="email" type="email">
+    <input name="password" type="password">
+    <button type="submit">Sign In</button>
+  </form>
+</div>
+```
+
+*   **TERRIBLE (High Risk):** `button[type="submit"]`
+    *   **Why it's bad:** There could be dozens of other forms on the full page (e.g., a newsletter signup, a search bar in the header). This selector is a shot in the dark.
+
+*   **BETTER (Lower Risk):** `#login-widget button[type="submit"]`
+    *   **Why it's better:** It's anchored to a unique ID (`#login-widget`). This dramatically reduces the chance of ambiguity.
+
+*   **EXCELLENT (Minimal Risk):** `div[id="login-widget"] form button[type="submit"]`
+    *   **Why it's best:** This is a highly specific, descriptive path. It says, "Find the login widget, then the form inside it, and then the submit button inside *that* form." It is virtually guaranteed to be unique and is resilient to minor layout changes within the form.
+
+### Scenario: Selecting a "Add to Cart" Button
+
+**HTML Snippet Provided:**
+```html
+<section data-testid="product-details-main">
+  <h1>Awesome T-Shirt</h1>
+  <div class="product-actions">
+    <button class="add-to-cart-btn">Add to Cart</button>
+  </div>
+</section>
+```
+
+*   **TERRIBLE (High Risk):** `.add-to-cart-btn`
+    *   **Why it's bad:** A "related products" section outside this snippet might also use the same class name.
+
+*   **EXCELLENT (Minimal Risk):** `[data-testid="product-details-main"] .add-to-cart-btn`
+    *   **Why it's best:** It uses the stable `data-testid` attribute of the parent section as an anchor. This is the most robust pattern.
+
+**Your Mandate:** Always examine the provided HTML for a stable, unique parent (like an element with an `id`, a `data-testid`, or a highly specific combination of classes) and use it as the root of your selectors. **NEVER generate a generic, un-anchored selector if a better, more specific parent is available in the context.**
+
+
+────────────────────────────────────────────────────────
+## Final Output Mandate
+
+1.  **CODE ONLY.** Your entire response must be the script body.
+2.  **NO CHAT.** Do not say "Here is the script" or "This should work."
+3.  **NO MARKDOWN.** Do not wrap your code in ` ``` ` fences.
+4.  **NO COMMENTS.** Do not add comments to the final code output, except within the logic where it's a best practice.
+5.  **SYNTACTICALLY PERFECT.** The script must be a single, self-contained block, immediately executable. Wrap it in `(async () => { ... })();`.
+6.  **UTF-8, STANDARD QUOTES.** Use `'` for string literals, not `“` or `”`.
+
+You are an engine of automation. Now, receive the user's request and produce the optimal JavaScript."""
+
+
+
+

crawl4ai/script/__init__.py

@@ -0,0 +1,35 @@
+"""
+C4A-Script: A domain-specific language for web automation in Crawl4AI
+"""
+
+from .c4a_compile import C4ACompiler, compile, validate, compile_file
+from .c4a_result import (
+    CompilationResult, 
+    ValidationResult, 
+    ErrorDetail, 
+    WarningDetail,
+    ErrorType, 
+    Severity, 
+    Suggestion
+)
+
+__all__ = [
+    # Main compiler
+    "C4ACompiler",
+    
+    # Convenience functions
+    "compile",
+    "validate", 
+    "compile_file",
+    
+    # Result types
+    "CompilationResult",
+    "ValidationResult",
+    "ErrorDetail",
+    "WarningDetail",
+    
+    # Enums
+    "ErrorType",
+    "Severity",
+    "Suggestion"
+]

crawl4ai/script/c4a_compile.py

@@ -0,0 +1,398 @@
+"""
+Clean C4A-Script API with Result pattern
+No exceptions - always returns results
+"""
+
+from __future__ import annotations
+import pathlib
+import re
+from typing import Union, List, Optional
+
+# JSON_SCHEMA_BUILDER is still used elsewhere,
+# but we now also need the new script-builder prompt.
+from ..prompts import GENERATE_JS_SCRIPT_PROMPT, GENERATE_SCRIPT_PROMPT
+import logging
+import re
+
+from .c4a_result import (
+    CompilationResult, ValidationResult, ErrorDetail, WarningDetail,
+    ErrorType, Severity, Suggestion
+)
+from .c4ai_script import Compiler
+from lark.exceptions import UnexpectedToken, UnexpectedCharacters, VisitError
+from ..async_configs import LLMConfig
+from ..utils import perform_completion_with_backoff
+
+
+class C4ACompiler:
+    """Main compiler with result-based API"""
+    
+    # Error code mapping
+    ERROR_CODES = {
+        "missing_then": "E001",
+        "missing_paren": "E002",
+        "missing_comma": "E003",
+        "missing_endproc": "E004",
+        "undefined_proc": "E005",
+        "missing_backticks": "E006",
+        "invalid_command": "E007",
+        "syntax_error": "E999"
+    }
+    
+    @classmethod
+    def compile(cls, script: Union[str, List[str]], root: Optional[pathlib.Path] = None) -> CompilationResult:
+        """
+        Compile C4A-Script to JavaScript
+        
+        Args:
+            script: C4A-Script as string or list of lines
+            root: Root directory for includes
+            
+        Returns:
+            CompilationResult with success status and JS code or errors
+        """
+        # Normalize input
+        if isinstance(script, list):
+            script_text = '\n'.join(script)
+            script_lines = script
+        else:
+            script_text = script
+            script_lines = script.split('\n')
+        
+        try:
+            # Try compilation
+            compiler = Compiler(root)
+            js_code = compiler.compile(script_text)
+            
+            # Success!
+            result = CompilationResult(
+                success=True,
+                js_code=js_code,
+                metadata={
+                    "lineCount": len(script_lines),
+                    "statementCount": len(js_code)
+                }
+            )
+            
+            # Add any warnings (future feature)
+            # result.warnings = cls._check_warnings(script_text)
+            
+            return result
+            
+        except Exception as e:
+            # Convert exception to ErrorDetail
+            error = cls._exception_to_error(e, script_lines)
+            return CompilationResult(
+                success=False,
+                errors=[error],
+                metadata={
+                    "lineCount": len(script_lines)
+                }
+            )
+    
+    @classmethod
+    def validate(cls, script: Union[str, List[str]]) -> ValidationResult:
+        """
+        Validate script syntax without generating code
+        
+        Args:
+            script: C4A-Script to validate
+            
+        Returns:
+            ValidationResult with validity status and any errors
+        """
+        result = cls.compile(script)
+        
+        return ValidationResult(
+            valid=result.success,
+            errors=result.errors,
+            warnings=result.warnings
+        )
+    
+    @classmethod
+    def compile_file(cls, path: Union[str, pathlib.Path]) -> CompilationResult:
+        """
+        Compile a C4A-Script file
+        
+        Args:
+            path: Path to the file
+            
+        Returns:
+            CompilationResult
+        """
+        path = pathlib.Path(path)
+        
+        if not path.exists():
+            error = ErrorDetail(
+                type=ErrorType.RUNTIME,
+                code="E100",
+                severity=Severity.ERROR,
+                message=f"File not found: {path}",
+                line=0,
+                column=0,
+                source_line=""
+            )
+            return CompilationResult(success=False, errors=[error])
+        
+        try:
+            script = path.read_text()
+            return cls.compile(script, root=path.parent)
+        except Exception as e:
+            error = ErrorDetail(
+                type=ErrorType.RUNTIME,
+                code="E101",
+                severity=Severity.ERROR,
+                message=f"Error reading file: {str(e)}",
+                line=0,
+                column=0,
+                source_line=""
+            )
+            return CompilationResult(success=False, errors=[error])
+    
+    @classmethod
+    def _exception_to_error(cls, exc: Exception, script_lines: List[str]) -> ErrorDetail:
+        """Convert an exception to ErrorDetail"""
+        
+        if isinstance(exc, UnexpectedToken):
+            return cls._handle_unexpected_token(exc, script_lines)
+        elif isinstance(exc, UnexpectedCharacters):
+            return cls._handle_unexpected_chars(exc, script_lines)
+        elif isinstance(exc, ValueError):
+            return cls._handle_value_error(exc, script_lines)
+        else:
+            # Generic error
+            return ErrorDetail(
+                type=ErrorType.SYNTAX,
+                code=cls.ERROR_CODES["syntax_error"],
+                severity=Severity.ERROR,
+                message=str(exc),
+                line=1,
+                column=1,
+                source_line=script_lines[0] if script_lines else ""
+            )
+    
+    @classmethod
+    def _handle_unexpected_token(cls, exc: UnexpectedToken, script_lines: List[str]) -> ErrorDetail:
+        """Handle UnexpectedToken errors"""
+        line = exc.line
+        column = exc.column
+        
+        # Get context lines
+        source_line = script_lines[line - 1] if 0 < line <= len(script_lines) else ""
+        line_before = script_lines[line - 2] if line > 1 and line <= len(script_lines) + 1 else None
+        line_after = script_lines[line] if 0 < line < len(script_lines) else None
+        
+        # Determine error type and suggestions
+        if exc.token.type == 'CLICK' and 'THEN' in str(exc.expected):
+            code = cls.ERROR_CODES["missing_then"]
+            message = "Missing 'THEN' keyword after IF condition"
+            suggestions = [
+                Suggestion(
+                    "Add 'THEN' after the condition",
+                    source_line.replace("CLICK", "THEN CLICK") if source_line else None
+                )
+            ]
+        elif exc.token.type == '$END':
+            code = cls.ERROR_CODES["missing_endproc"]
+            message = "Unexpected end of script"
+            suggestions = [
+                Suggestion("Check for missing ENDPROC"),
+                Suggestion("Ensure all procedures are properly closed")
+            ]
+        elif 'RPAR' in str(exc.expected):
+            code = cls.ERROR_CODES["missing_paren"]
+            message = "Missing closing parenthesis ')'"
+            suggestions = [
+                Suggestion("Add closing parenthesis at the end of the condition")
+            ]
+        elif 'COMMA' in str(exc.expected):
+            code = cls.ERROR_CODES["missing_comma"]
+            message = "Missing comma ',' in command"
+            suggestions = [
+                Suggestion("Add comma between arguments")
+            ]
+        else:
+            # Check if this might be missing backticks
+            if exc.token.type == 'NAME' and 'BACKTICK_STRING' in str(exc.expected):
+                code = cls.ERROR_CODES["missing_backticks"]
+                message = "Selector must be wrapped in backticks"
+                suggestions = [
+                    Suggestion(
+                        "Wrap the selector in backticks",
+                        f"`{exc.token.value}`"
+                    )
+                ]
+            else:
+                code = cls.ERROR_CODES["syntax_error"]
+                message = f"Unexpected '{exc.token.value}'"
+                if exc.expected:
+                    expected_list = [str(e) for e in exc.expected if not str(e).startswith('_')][:3]
+                    if expected_list:
+                        message += f". Expected: {', '.join(expected_list)}"
+                suggestions = []
+        
+        return ErrorDetail(
+            type=ErrorType.SYNTAX,
+            code=code,
+            severity=Severity.ERROR,
+            message=message,
+            line=line,
+            column=column,
+            source_line=source_line,
+            line_before=line_before,
+            line_after=line_after,
+            suggestions=suggestions
+        )
+    
+    @classmethod
+    def _handle_unexpected_chars(cls, exc: UnexpectedCharacters, script_lines: List[str]) -> ErrorDetail:
+        """Handle UnexpectedCharacters errors"""
+        line = exc.line
+        column = exc.column
+        
+        source_line = script_lines[line - 1] if 0 < line <= len(script_lines) else ""
+        
+        # Check for missing backticks
+        if "CLICK" in source_line and column > source_line.find("CLICK"):
+            code = cls.ERROR_CODES["missing_backticks"]
+            message = "Selector must be wrapped in backticks"
+            suggestions = [
+                Suggestion(
+                    "Wrap the selector in backticks",
+                    re.sub(r'CLICK\s+([^\s]+)', r'CLICK `\1`', source_line)
+                )
+            ]
+        else:
+            code = cls.ERROR_CODES["syntax_error"]
+            message = f"Invalid character at position {column}"
+            suggestions = []
+        
+        return ErrorDetail(
+            type=ErrorType.SYNTAX,
+            code=code,
+            severity=Severity.ERROR,
+            message=message,
+            line=line,
+            column=column,
+            source_line=source_line,
+            suggestions=suggestions
+        )
+    
+    @classmethod
+    def _handle_value_error(cls, exc: ValueError, script_lines: List[str]) -> ErrorDetail:
+        """Handle ValueError (runtime errors)"""
+        message = str(exc)
+        
+        # Check for undefined procedure
+        if "Unknown procedure" in message:
+            proc_match = re.search(r"'([^']+)'", message)
+            if proc_match:
+                proc_name = proc_match.group(1)
+                
+                # Find the line with the procedure call
+                for i, line in enumerate(script_lines):
+                    if proc_name in line and not line.strip().startswith('PROC'):
+                        return ErrorDetail(
+                            type=ErrorType.RUNTIME,
+                            code=cls.ERROR_CODES["undefined_proc"],
+                            severity=Severity.ERROR,
+                            message=f"Undefined procedure '{proc_name}'",
+                            line=i + 1,
+                            column=line.find(proc_name) + 1,
+                            source_line=line,
+                            suggestions=[
+                                Suggestion(
+                                    f"Define the procedure before using it",
+                                    f"PROC {proc_name}\n  # commands here\nENDPROC"
+                                )
+                            ]
+                        )
+        
+        # Generic runtime error
+        return ErrorDetail(
+            type=ErrorType.RUNTIME,
+            code="E999",
+            severity=Severity.ERROR,
+            message=message,
+            line=1,
+            column=1,
+            source_line=script_lines[0] if script_lines else ""
+        )
+
+    @staticmethod
+    def generate_script(
+        html: str,
+        query: str | None = None,
+        mode: str = "c4a",
+        llm_config: LLMConfig | None = None,
+        **completion_kwargs,
+    ) -> str:
+        """
+        One-shot helper that calls the LLM exactly once to convert a
+        natural-language goal + HTML snippet into either:
+
+        1. raw JavaScript (`mode="js"`)
+        2. Crawl4ai DSL (`mode="c4a"`)
+
+        The returned string is guaranteed to be free of markdown wrappers
+        or explanatory text, ready for direct execution.
+        """
+        if llm_config is None:
+            llm_config = LLMConfig()  # falls back to env vars / defaults
+
+        # Build the user chunk
+        user_prompt = "\n".join(
+            [
+                "## GOAL",
+                "<<goael>>",
+                (query or "Prepare the page for crawling."),
+                "<</goal>>",
+                "",
+                "## HTML",
+                "<<html>>",
+                html[:100000],  # guardrail against token blast
+                "<</html>>",
+                "",
+                "## MODE",
+                mode,
+            ]
+        )
+
+        # Call the LLM with retry/back-off logic
+        full_prompt =  f"{GENERATE_SCRIPT_PROMPT}\n\n{user_prompt}" if mode == "c4a" else f"{GENERATE_JS_SCRIPT_PROMPT}\n\n{user_prompt}"
+        
+        response = perform_completion_with_backoff(
+            provider=llm_config.provider,
+            prompt_with_variables=full_prompt,
+            api_token=llm_config.api_token,
+            json_response=False,
+            base_url=getattr(llm_config, 'base_url', None),
+            **completion_kwargs,
+        )
+        
+        # Extract content from the response
+        raw_response = response.choices[0].message.content.strip()
+
+        # Strip accidental markdown fences (```js … ```)
+        clean = re.sub(r"^```(?:[a-zA-Z0-9_-]+)?\s*|```$", "", raw_response, flags=re.MULTILINE).strip()
+
+        if not clean:
+            raise RuntimeError("LLM returned empty script.")
+
+        return clean
+
+
+# Convenience functions for direct use
+def compile(script: Union[str, List[str]], root: Optional[pathlib.Path] = None) -> CompilationResult:
+    """Compile C4A-Script to JavaScript"""
+    return C4ACompiler.compile(script, root)
+
+
+def validate(script: Union[str, List[str]]) -> ValidationResult:
+    """Validate C4A-Script syntax"""
+    return C4ACompiler.validate(script)
+
+
+def compile_file(path: Union[str, pathlib.Path]) -> CompilationResult:
+    """Compile C4A-Script file"""
+    return C4ACompiler.compile_file(path)

crawl4ai/script/c4a_result.py

@@ -0,0 +1,219 @@
+"""
+Result classes for C4A-Script compilation
+Clean API design with no exceptions
+"""
+
+from __future__ import annotations
+from dataclasses import dataclass, field
+from enum import Enum
+from typing import List, Dict, Any, Optional
+import json
+
+
+class ErrorType(Enum):
+    SYNTAX = "syntax"
+    SEMANTIC = "semantic"
+    RUNTIME = "runtime"
+    
+
+class Severity(Enum):
+    ERROR = "error"
+    WARNING = "warning"
+    INFO = "info"
+
+
+@dataclass
+class Suggestion:
+    """A suggestion for fixing an error"""
+    message: str
+    fix: Optional[str] = None
+    
+    def to_dict(self) -> dict:
+        return {
+            "message": self.message,
+            "fix": self.fix
+        }
+
+
+@dataclass
+class ErrorDetail:
+    """Detailed information about a compilation error"""
+    # Core info
+    type: ErrorType
+    code: str  # E001, E002, etc.
+    severity: Severity
+    message: str
+    
+    # Location
+    line: int
+    column: int
+    
+    # Context
+    source_line: str
+    
+    # Optional fields with defaults
+    end_line: Optional[int] = None
+    end_column: Optional[int] = None
+    line_before: Optional[str] = None
+    line_after: Optional[str] = None
+    
+    # Help
+    suggestions: List[Suggestion] = field(default_factory=list)
+    documentation_url: Optional[str] = None
+    
+    def to_dict(self) -> dict:
+        """Convert to dictionary for JSON serialization"""
+        return {
+            "type": self.type.value,
+            "code": self.code,
+            "severity": self.severity.value,
+            "message": self.message,
+            "location": {
+                "line": self.line,
+                "column": self.column,
+                "endLine": self.end_line,
+                "endColumn": self.end_column
+            },
+            "context": {
+                "sourceLine": self.source_line,
+                "lineBefore": self.line_before,
+                "lineAfter": self.line_after,
+                "marker": {
+                    "start": self.column - 1,
+                    "length": (self.end_column - self.column) if self.end_column else 1
+                }
+            },
+            "suggestions": [s.to_dict() for s in self.suggestions],
+            "documentationUrl": self.documentation_url
+        }
+    
+    def to_json(self) -> str:
+        """Convert to JSON string"""
+        return json.dumps(self.to_dict(), indent=2)
+    
+    @property
+    def formatted_message(self) -> str:
+        """Returns the nice text format for terminals"""
+        lines = []
+        lines.append(f"\n{'='*60}")
+        lines.append(f"{self.type.value.title()} Error [{self.code}]")
+        lines.append(f"{'='*60}")
+        lines.append(f"Location: Line {self.line}, Column {self.column}")
+        lines.append(f"Error: {self.message}")
+        
+        if self.source_line:
+            marker = " " * (self.column - 1) + "^"
+            if self.end_column:
+                marker += "~" * (self.end_column - self.column - 1)
+            lines.append(f"\nCode:")
+            if self.line_before:
+                lines.append(f"  {self.line - 1: >3} | {self.line_before}")
+            lines.append(f"  {self.line: >3} | {self.source_line}")
+            lines.append(f"      | {marker}")
+            if self.line_after:
+                lines.append(f"  {self.line + 1: >3} | {self.line_after}")
+        
+        if self.suggestions:
+            lines.append("\nSuggestions:")
+            for i, suggestion in enumerate(self.suggestions, 1):
+                lines.append(f"  {i}. {suggestion.message}")
+                if suggestion.fix:
+                    lines.append(f"     Fix: {suggestion.fix}")
+        
+        lines.append("="*60)
+        return "\n".join(lines)
+    
+    @property
+    def simple_message(self) -> str:
+        """Returns just the error message without formatting"""
+        return f"Line {self.line}: {self.message}"
+
+
+@dataclass
+class WarningDetail:
+    """Information about a compilation warning"""
+    code: str
+    message: str
+    line: int
+    column: int
+    
+    def to_dict(self) -> dict:
+        return {
+            "code": self.code,
+            "message": self.message,
+            "line": self.line,
+            "column": self.column
+        }
+
+
+@dataclass
+class CompilationResult:
+    """Result of C4A-Script compilation"""
+    success: bool
+    js_code: Optional[List[str]] = None
+    errors: List[ErrorDetail] = field(default_factory=list)
+    warnings: List[WarningDetail] = field(default_factory=list)
+    metadata: Dict[str, Any] = field(default_factory=dict)
+    
+    def to_dict(self) -> dict:
+        """Convert to dictionary for JSON serialization"""
+        return {
+            "success": self.success,
+            "jsCode": self.js_code,
+            "errors": [e.to_dict() for e in self.errors],
+            "warnings": [w.to_dict() for w in self.warnings],
+            "metadata": self.metadata
+        }
+    
+    def to_json(self) -> str:
+        """Convert to JSON string"""
+        return json.dumps(self.to_dict(), indent=2)
+    
+    @property
+    def has_errors(self) -> bool:
+        """Check if there are any errors"""
+        return len(self.errors) > 0
+    
+    @property
+    def has_warnings(self) -> bool:
+        """Check if there are any warnings"""
+        return len(self.warnings) > 0
+    
+    @property
+    def first_error(self) -> Optional[ErrorDetail]:
+        """Get the first error if any"""
+        return self.errors[0] if self.errors else None
+    
+    def __str__(self) -> str:
+        """String representation for debugging"""
+        if self.success:
+            msg = f"✓ Compilation successful"
+            if self.js_code:
+                msg += f" - {len(self.js_code)} statements generated"
+            if self.warnings:
+                msg += f" ({len(self.warnings)} warnings)"
+            return msg
+        else:
+            return f"✗ Compilation failed - {len(self.errors)} error(s)"
+
+
+@dataclass
+class ValidationResult:
+    """Result of script validation"""
+    valid: bool
+    errors: List[ErrorDetail] = field(default_factory=list)
+    warnings: List[WarningDetail] = field(default_factory=list)
+    
+    def to_dict(self) -> dict:
+        return {
+            "valid": self.valid,
+            "errors": [e.to_dict() for e in self.errors],
+            "warnings": [w.to_dict() for w in self.warnings]
+        }
+    
+    def to_json(self) -> str:
+        return json.dumps(self.to_dict(), indent=2)
+    
+    @property
+    def first_error(self) -> Optional[ErrorDetail]:
+        return self.errors[0] if self.errors else None

crawl4ai/script/c4ai_script.py

@@ -0,0 +1,690 @@
+"""
+2025-06-03
+By Unclcode:
+C4A-Script Language Documentation    
+Feeds Crawl4AI via CrawlerRunConfig(js_code=[ ... ]) – no core modifications.
+"""
+
+from __future__ import annotations
+import pathlib, re, sys, textwrap
+from dataclasses import dataclass
+from typing import Any, Dict, List, Union
+
+from lark import Lark, Transformer, v_args
+from lark.exceptions import UnexpectedToken, UnexpectedCharacters, VisitError
+
+
+# --------------------------------------------------------------------------- #
+# Custom Error Classes
+# --------------------------------------------------------------------------- #
+class C4AScriptError(Exception):
+    """Custom error class for C4A-Script compilation errors"""
+    
+    def __init__(self, message: str, line: int = None, column: int = None, 
+                 error_type: str = "Syntax Error", details: str = None):
+        self.message = message
+        self.line = line
+        self.column = column
+        self.error_type = error_type
+        self.details = details
+        super().__init__(self._format_message())
+    
+    def _format_message(self) -> str:
+        """Format a clear error message"""
+        lines = [f"\n{'='*60}"]
+        lines.append(f"C4A-Script {self.error_type}")
+        lines.append(f"{'='*60}")
+        
+        if self.line:
+            lines.append(f"Location: Line {self.line}" + (f", Column {self.column}" if self.column else ""))
+        
+        lines.append(f"Error: {self.message}")
+        
+        if self.details:
+            lines.append(f"\nDetails: {self.details}")
+        
+        lines.append("="*60)
+        return "\n".join(lines)
+    
+    @classmethod
+    def from_exception(cls, exc: Exception, script: Union[str, List[str]]) -> 'C4AScriptError':
+        """Create C4AScriptError from another exception"""
+        script_text = script if isinstance(script, str) else '\n'.join(script)
+        script_lines = script_text.split('\n')
+        
+        if isinstance(exc, UnexpectedToken):
+            # Extract line and column from UnexpectedToken
+            line = exc.line
+            column = exc.column
+            
+            # Get the problematic line
+            if 0 < line <= len(script_lines):
+                problem_line = script_lines[line - 1]
+                marker = " " * (column - 1) + "^"
+                
+                details = f"\nCode:\n  {problem_line}\n  {marker}\n"
+                
+                # Improve error message based on context
+                if exc.token.type == 'CLICK' and 'THEN' in str(exc.expected):
+                    message = "Missing 'THEN' keyword after IF condition"
+                elif exc.token.type == '$END':
+                    message = "Unexpected end of script. Check for missing ENDPROC or incomplete commands"
+                elif 'RPAR' in str(exc.expected):
+                    message = "Missing closing parenthesis ')'"
+                elif 'COMMA' in str(exc.expected):
+                    message = "Missing comma ',' in command"
+                else:
+                    message = f"Unexpected '{exc.token}'"
+                    if exc.expected:
+                        expected_list = [str(e) for e in exc.expected if not e.startswith('_')]
+                        if expected_list:
+                            message += f". Expected: {', '.join(expected_list[:3])}"
+                
+                details += f"Token: {exc.token.type} ('{exc.token.value}')"
+            else:
+                message = str(exc)
+                details = None
+            
+            return cls(message, line, column, "Syntax Error", details)
+        
+        elif isinstance(exc, UnexpectedCharacters):
+            # Extract line and column
+            line = exc.line
+            column = exc.column
+            
+            if 0 < line <= len(script_lines):
+                problem_line = script_lines[line - 1]
+                marker = " " * (column - 1) + "^"
+                
+                details = f"\nCode:\n  {problem_line}\n  {marker}\n"
+                message = f"Invalid character or unexpected text at position {column}"
+            else:
+                message = str(exc)
+                details = None
+            
+            return cls(message, line, column, "Syntax Error", details)
+        
+        elif isinstance(exc, ValueError):
+            # Handle runtime errors like undefined procedures
+            message = str(exc)
+            
+            # Try to find which line caused the error
+            if "Unknown procedure" in message:
+                proc_name = re.search(r"'([^']+)'", message)
+                if proc_name:
+                    proc_name = proc_name.group(1)
+                    for i, line in enumerate(script_lines, 1):
+                        if proc_name in line and not line.strip().startswith('PROC'):
+                            details = f"\nCode:\n  {line.strip()}\n\nMake sure the procedure '{proc_name}' is defined with PROC...ENDPROC"
+                            return cls(f"Undefined procedure '{proc_name}'", i, None, "Runtime Error", details)
+            
+            return cls(message, None, None, "Runtime Error", None)
+        
+        else:
+            # Generic error
+            return cls(str(exc), None, None, "Compilation Error", None)
+
+
+# --------------------------------------------------------------------------- #
+# 1. Grammar
+# --------------------------------------------------------------------------- #
+GRAMMAR = r"""
+start           : line*
+?line           : command | proc_def | include | comment
+
+command         : wait | nav | click_cmd | double_click | right_click | move | drag | scroll
+                | type | clear | set_input | press | key_down | key_up
+                | eval_cmd | setvar | proc_call | if_cmd | repeat_cmd
+
+wait            : "WAIT" (ESCAPED_STRING|BACKTICK_STRING|NUMBER) NUMBER? -> wait_cmd
+nav             : "GO" URL                             -> go
+                | "RELOAD"                             -> reload
+                | "BACK"                               -> back
+                | "FORWARD"                            -> forward
+
+click_cmd       : "CLICK" (BACKTICK_STRING|NUMBER NUMBER) -> click
+double_click    : "DOUBLE_CLICK" (BACKTICK_STRING|NUMBER NUMBER) -> double_click  
+right_click     : "RIGHT_CLICK" (BACKTICK_STRING|NUMBER NUMBER) -> right_click
+
+move            : "MOVE" coords                        -> move
+drag            : "DRAG" coords coords                 -> drag
+scroll          : "SCROLL" DIR NUMBER?                 -> scroll
+
+type            : "TYPE" (ESCAPED_STRING | NAME)       -> type
+clear           : "CLEAR" BACKTICK_STRING              -> clear
+set_input       : "SET" BACKTICK_STRING (ESCAPED_STRING | BACKTICK_STRING | NAME) -> set_input
+press           : "PRESS" WORD                         -> press
+key_down        : "KEY_DOWN" WORD                      -> key_down
+key_up          : "KEY_UP" WORD                        -> key_up
+
+eval_cmd        : "EVAL" BACKTICK_STRING               -> eval_cmd
+setvar          : "SETVAR" NAME "=" value              -> setvar
+proc_call       : NAME                                 -> proc_call
+proc_def        : "PROC" NAME line* "ENDPROC"          -> proc_def
+include         : "USE" ESCAPED_STRING                 -> include
+comment         : /#.*/                                -> comment
+
+if_cmd          : "IF" "(" condition ")" "THEN" command ("ELSE" command)?  -> if_cmd
+repeat_cmd      : "REPEAT" "(" command "," repeat_count ")"  -> repeat_cmd
+
+condition       : not_cond | exists_cond | js_cond
+not_cond        : "NOT" condition                      -> not_cond
+exists_cond     : "EXISTS" BACKTICK_STRING             -> exists_cond
+js_cond         : BACKTICK_STRING                      -> js_cond
+
+repeat_count    : NUMBER | BACKTICK_STRING
+
+coords          : NUMBER NUMBER
+value           : ESCAPED_STRING | BACKTICK_STRING | NUMBER
+DIR             : /(UP|DOWN|LEFT|RIGHT)/i
+REST            : /[^\n]+/
+
+URL             : /(http|https):\/\/[^\s]+/
+NAME            : /\$?[A-Za-z_][A-Za-z0-9_]*/
+WORD            : /[A-Za-z0-9+]+/
+BACKTICK_STRING : /`[^`]*`/
+
+%import common.NUMBER
+%import common.ESCAPED_STRING
+%import common.WS_INLINE
+%import common.NEWLINE
+%ignore WS_INLINE
+%ignore NEWLINE
+"""
+
+# --------------------------------------------------------------------------- #
+# 2. IR dataclasses
+# --------------------------------------------------------------------------- #
+@dataclass
+class Cmd:
+    op: str
+    args: List[Any]
+
+@dataclass
+class Proc:
+    name: str
+    body: List[Cmd]
+
+# --------------------------------------------------------------------------- #
+# 3. AST → IR
+# --------------------------------------------------------------------------- #
+@v_args(inline=True)
+class ASTBuilder(Transformer):
+    # helpers
+    def _strip(self, s): 
+        if s.startswith('"') and s.endswith('"'):
+            return s[1:-1]
+        elif s.startswith('`') and s.endswith('`'):
+            return s[1:-1]
+        return s
+    def start(self,*i):  return list(i)
+    def line(self,i):    return i
+    def command(self,i): return i
+
+    # WAIT
+    def wait_cmd(self, rest, timeout=None):
+        rest_str = str(rest)
+        # Check if it's a number (including floats)
+        try:
+            num_val = float(rest_str)
+            payload = (num_val, "seconds")
+        except ValueError:
+            if rest_str.startswith('"') and rest_str.endswith('"'):
+                payload = (self._strip(rest_str), "text")
+            elif rest_str.startswith('`') and rest_str.endswith('`'):
+                payload = (self._strip(rest_str), "selector")
+            else:
+                payload = (rest_str, "selector")
+        return Cmd("WAIT", [payload, int(timeout) if timeout else None])
+
+    # NAV
+    def go(self,u):    return Cmd("GO",[str(u)])
+    def reload(self):  return Cmd("RELOAD",[])
+    def back(self):    return Cmd("BACK",[])
+    def forward(self): return Cmd("FORWARD",[])
+
+    # CLICK, DOUBLE_CLICK, RIGHT_CLICK
+    def click(self, *args):
+        return self._handle_click("CLICK", args)
+    
+    def double_click(self, *args):
+        return self._handle_click("DBLCLICK", args)
+    
+    def right_click(self, *args):
+        return self._handle_click("RIGHTCLICK", args)
+    
+    def _handle_click(self, op, args):
+        if len(args) == 1:
+            # Single argument - backtick string
+            target = self._strip(str(args[0]))
+            return Cmd(op, [("selector", target)])
+        else:
+            # Two arguments - coordinates
+            x, y = args
+            return Cmd(op, [("coords", int(x), int(y))])
+
+
+    # MOVE / DRAG / SCROLL
+    def coords(self,x,y):       return ("coords",int(x),int(y))
+    def move(self,c):           return Cmd("MOVE",[c])
+    def drag(self,c1,c2):       return Cmd("DRAG",[c1,c2])
+    def scroll(self,dir_tok,amt=None):
+        return Cmd("SCROLL",[dir_tok.upper(), int(amt) if amt else 500])
+
+    # KEYS
+    def type(self,tok):     return Cmd("TYPE",[self._strip(str(tok))])
+    def clear(self,sel):    return Cmd("CLEAR",[self._strip(str(sel))])
+    def set_input(self,sel,val): return Cmd("SET",[self._strip(str(sel)), self._strip(str(val))])
+    def press(self,w):      return Cmd("PRESS",[str(w)])
+    def key_down(self,w):   return Cmd("KEYDOWN",[str(w)])
+    def key_up(self,w):     return Cmd("KEYUP",[str(w)])
+
+    # FLOW
+    def eval_cmd(self,txt):     return Cmd("EVAL",[self._strip(str(txt))])
+    def setvar(self,n,v):      
+        # v might be a Token or a Tree, extract value properly
+        if hasattr(v, 'value'):
+            value = v.value
+        elif hasattr(v, 'children') and len(v.children) > 0:
+            value = v.children[0].value
+        else:
+            value = str(v)
+        return Cmd("SETVAR",[str(n), self._strip(value)])
+    def proc_call(self,n):      return Cmd("CALL",[str(n)])
+    def proc_def(self,n,*body): return Proc(str(n),[b for b in body if isinstance(b,Cmd)])
+    def include(self,p):        return Cmd("INCLUDE",[self._strip(p)])
+    def comment(self,*_):       return Cmd("NOP",[])
+    
+    # IF-THEN-ELSE and EXISTS
+    def if_cmd(self, condition, then_cmd, else_cmd=None):
+        return Cmd("IF", [condition, then_cmd, else_cmd])
+    
+    def condition(self, cond):
+        return cond
+    
+    def not_cond(self, cond):
+        return ("NOT", cond)
+    
+    def exists_cond(self, selector):
+        return ("EXISTS", self._strip(str(selector)))
+    
+    def js_cond(self, expr):
+        return ("JS", self._strip(str(expr)))
+    
+    # REPEAT
+    def repeat_cmd(self, cmd, count):
+        return Cmd("REPEAT", [cmd, count])
+    
+    def repeat_count(self, value):
+        return str(value)
+
+# --------------------------------------------------------------------------- #
+# 4. Compiler
+# --------------------------------------------------------------------------- #
+class Compiler:
+    def __init__(self, root: pathlib.Path|None=None):
+        self.parser = Lark(GRAMMAR,start="start",parser="lalr")
+        self.root   = pathlib.Path(root or ".").resolve()
+        self.vars: Dict[str,Any] = {}
+        self.procs: Dict[str,Proc]= {}
+
+    def compile(self, text: Union[str, List[str]]) -> List[str]:
+        # Handle list input by joining with newlines
+        if isinstance(text, list):
+            text = '\n'.join(text)
+        
+        ir = self._parse_with_includes(text)
+        ir = self._collect_procs(ir)
+        ir = self._inline_calls(ir)
+        ir = self._apply_set_vars(ir)
+        return [self._emit_js(c) for c in ir if isinstance(c,Cmd) and c.op!="NOP"]
+
+    # passes
+    def _parse_with_includes(self,txt,seen=None):
+        seen=seen or set()
+        cmds=ASTBuilder().transform(self.parser.parse(txt))
+        out=[]
+        for c in cmds:
+            if isinstance(c,Cmd) and c.op=="INCLUDE":
+                p=(self.root/c.args[0]).resolve()
+                if p in seen: raise ValueError(f"Circular include {p}")
+                seen.add(p); out+=self._parse_with_includes(p.read_text(),seen)
+            else: out.append(c)
+        return out
+
+    def _collect_procs(self,ir):
+        out=[]
+        for i in ir:
+            if isinstance(i,Proc): self.procs[i.name]=i
+            else: out.append(i)
+        return out
+
+    def _inline_calls(self,ir):
+        out=[]
+        for c in ir:
+            if isinstance(c,Cmd) and c.op=="CALL":
+                if c.args[0] not in self.procs:
+                    raise ValueError(f"Unknown procedure {c.args[0]!r}")
+                out+=self._inline_calls(self.procs[c.args[0]].body)
+            else: out.append(c)
+        return out
+
+    def _apply_set_vars(self,ir):
+        def sub(s): return re.sub(r"\$(\w+)",lambda m:str(self.vars.get(m.group(1),m.group(0))) ,s) if isinstance(s,str) else s
+        out=[]
+        for c in ir:
+            if isinstance(c,Cmd):
+                if c.op=="SETVAR":
+                    # Store variable
+                    self.vars[c.args[0].lstrip('$')]=c.args[1]
+                else:
+                    # Apply variable substitution to commands that use them
+                    if c.op in("TYPE","EVAL","SET"): c.args=[sub(a) for a in c.args]
+                    out.append(c)
+        return out
+
+    # JS emitter
+    def _emit_js(self, cmd: Cmd) -> str:
+        op, a = cmd.op, cmd.args
+        if op == "GO":         return f"window.location.href = '{a[0]}';"
+        if op == "RELOAD":     return "window.location.reload();"
+        if op == "BACK":       return "window.history.back();"
+        if op == "FORWARD":    return "window.history.forward();"
+
+        if op == "WAIT":
+            arg, kind = a[0]
+            timeout   = a[1] or 10
+            if kind == "seconds":
+                return f"await new Promise(r=>setTimeout(r,{arg}*1000));"
+            if kind == "selector":
+                sel = arg.replace("\\","\\\\").replace("'","\\'")
+                return textwrap.dedent(f"""
+                    await new Promise((res,rej)=>{{
+                      const max = {timeout*1000}, t0 = performance.now();
+                      const id = setInterval(()=>{{
+                        if(document.querySelector('{sel}')){{clearInterval(id);res();}}
+                        else if(performance.now()-t0>max){{clearInterval(id);rej('WAIT selector timeout');}}
+                      }},100);
+                    }});
+                """).strip()
+            if kind == "text":
+                txt = arg.replace('`', '\\`')
+                return textwrap.dedent(f"""
+                    await new Promise((res,rej)=>{{
+                      const max={timeout*1000},t0=performance.now();
+                      const id=setInterval(()=>{{
+                        if(document.body.innerText.includes(`{txt}`)){{clearInterval(id);res();}}
+                        else if(performance.now()-t0>max){{clearInterval(id);rej('WAIT text timeout');}}
+                      }},100);
+                    }});
+                """).strip()
+
+        # click-style helpers
+        def _js_click(sel, evt="click", button=0, detail=1):
+            sel = sel.replace("'", "\\'")
+            return textwrap.dedent(f"""
+                (()=>{{
+                  const el=document.querySelector('{sel}');
+                  if(el){{
+                    el.focus&&el.focus();
+                    el.dispatchEvent(new MouseEvent('{evt}',{{bubbles:true,button:{button},detail:{detail}}}));
+                  }}
+                }})();
+            """).strip()
+
+        def _js_click_xy(x, y, evt="click", button=0, detail=1):
+            return textwrap.dedent(f"""
+                (()=>{{
+                  const el=document.elementFromPoint({x},{y});
+                  if(el){{
+                    el.focus&&el.focus();
+                    el.dispatchEvent(new MouseEvent('{evt}',{{bubbles:true,button:{button},detail:{detail}}}));
+                  }}
+                }})();
+            """).strip()
+
+        if op in ("CLICK", "DBLCLICK", "RIGHTCLICK"):
+            evt   = {"CLICK":"click","DBLCLICK":"dblclick","RIGHTCLICK":"contextmenu"}[op]
+            btn   = 2 if op=="RIGHTCLICK" else 0
+            det   = 2 if op=="DBLCLICK"   else 1
+            kind,*rest = a[0]
+            return _js_click_xy(*rest) if kind=="coords" else _js_click(rest[0],evt,btn,det)
+
+        if op == "MOVE":
+            _, x, y = a[0]
+            return textwrap.dedent(f"""
+                document.dispatchEvent(new MouseEvent('mousemove',{{clientX:{x},clientY:{y},bubbles:true}}));
+            """).strip()
+
+        if op == "DRAG":
+            (_, x1, y1), (_, x2, y2) = a
+            return textwrap.dedent(f"""
+                (()=>{{
+                  const s=document.elementFromPoint({x1},{y1});
+                  if(!s) return;
+                  s.dispatchEvent(new MouseEvent('mousedown',{{bubbles:true,clientX:{x1},clientY:{y1}}}));
+                  document.dispatchEvent(new MouseEvent('mousemove',{{bubbles:true,clientX:{x2},clientY:{y2}}}));
+                  document.dispatchEvent(new MouseEvent('mouseup',  {{bubbles:true,clientX:{x2},clientY:{y2}}}));
+                }})();
+            """).strip()
+
+        if op == "SCROLL":
+            dir_, amt = a
+            dx, dy = {"UP":(0,-amt),"DOWN":(0,amt),"LEFT":(-amt,0),"RIGHT":(amt,0)}[dir_]
+            return f"window.scrollBy({dx},{dy});"
+
+        if op == "TYPE":
+            txt = a[0].replace("'", "\\'")
+            return textwrap.dedent(f"""
+                (()=>{{
+                  const el=document.activeElement;
+                  if(el){{
+                    el.value += '{txt}';
+                    el.dispatchEvent(new Event('input',{{bubbles:true}}));
+                  }}
+                }})();
+            """).strip()
+
+        if op == "CLEAR":
+            sel = a[0].replace("'", "\\'")
+            return textwrap.dedent(f"""
+                (()=>{{
+                  const el=document.querySelector('{sel}');
+                  if(el && 'value' in el){{
+                    el.value = '';
+                    el.dispatchEvent(new Event('input',{{bubbles:true}}));
+                    el.dispatchEvent(new Event('change',{{bubbles:true}}));
+                  }}
+                }})();
+            """).strip()
+
+        if op == "SET" and len(a) == 2:
+            # This is SET for input fields (SET `#field` "value")
+            sel = a[0].replace("'", "\\'")
+            val = a[1].replace("'", "\\'")
+            return textwrap.dedent(f"""
+                (()=>{{
+                  const el=document.querySelector('{sel}');
+                  if(el && 'value' in el){{
+                    el.value = '';
+                    el.focus&&el.focus();
+                    el.value = '{val}';
+                    el.dispatchEvent(new Event('input',{{bubbles:true}}));
+                    el.dispatchEvent(new Event('change',{{bubbles:true}}));
+                  }}
+                }})();
+            """).strip()
+
+        if op in ("PRESS","KEYDOWN","KEYUP"):
+            key = a[0]
+            evs = {"PRESS":("keydown","keyup"),"KEYDOWN":("keydown",),"KEYUP":("keyup",)}[op]
+            return ";".join([f"document.dispatchEvent(new KeyboardEvent('{e}',{{key:'{key}',bubbles:true}}))" for e in evs]) + ";"
+
+        if op == "EVAL":
+            return textwrap.dedent(f"""
+                (()=>{{
+                  try {{
+                    {a[0]};
+                  }} catch (e) {{
+                    console.error('C4A-Script EVAL error:', e);
+                  }}
+                }})();
+            """).strip()
+        
+        if op == "IF":
+            condition, then_cmd, else_cmd = a
+            
+            # Generate condition JavaScript
+            js_condition = self._emit_condition(condition)
+            
+            # Generate commands - handle both regular commands and procedure calls
+            then_js = self._handle_cmd_or_proc(then_cmd)
+            else_js = self._handle_cmd_or_proc(else_cmd) if else_cmd else ""
+            
+            if else_cmd:
+                return textwrap.dedent(f"""
+                    if ({js_condition}) {{
+                      {then_js}
+                    }} else {{
+                      {else_js}
+                    }}
+                """).strip()
+            else:
+                return textwrap.dedent(f"""
+                    if ({js_condition}) {{
+                      {then_js}
+                    }}
+                """).strip()
+        
+        if op == "REPEAT":
+            cmd, count = a
+            
+            # Handle the count - could be number or JS expression
+            if count.isdigit():
+                # Simple number
+                repeat_js = self._handle_cmd_or_proc(cmd)
+                return textwrap.dedent(f"""
+                    for (let _i = 0; _i < {count}; _i++) {{
+                      {repeat_js}
+                    }}
+                """).strip()
+            else:
+                # JS expression (from backticks)
+                count_expr = count[1:-1] if count.startswith('`') and count.endswith('`') else count
+                repeat_js = self._handle_cmd_or_proc(cmd)
+                return textwrap.dedent(f"""
+                    (()=>{{
+                      const _count = {count_expr};
+                      if (typeof _count === 'number') {{
+                        for (let _i = 0; _i < _count; _i++) {{
+                          {repeat_js}
+                        }}
+                      }} else if (_count) {{
+                        {repeat_js}
+                      }}
+                    }})();
+                """).strip()
+
+        raise ValueError(f"Unhandled op {op}")
+    
+    def _emit_condition(self, condition):
+        """Convert a condition tuple to JavaScript"""
+        cond_type = condition[0]
+        
+        if cond_type == "EXISTS":
+            return f"!!document.querySelector('{condition[1]}')"
+        elif cond_type == "NOT":
+            # Recursively handle the negated condition
+            inner_condition = self._emit_condition(condition[1])
+            return f"!({inner_condition})"
+        else:  # JS condition
+            return condition[1]
+    
+    def _handle_cmd_or_proc(self, cmd):
+        """Handle a command that might be a regular command or a procedure call"""
+        if not cmd:
+            return ""
+        
+        if isinstance(cmd, Cmd):
+            if cmd.op == "CALL":
+                # Inline the procedure
+                if cmd.args[0] not in self.procs:
+                    raise ValueError(f"Unknown procedure {cmd.args[0]!r}")
+                proc_body = self.procs[cmd.args[0]].body
+                return "\n".join([self._emit_js(c) for c in proc_body if c.op != "NOP"])
+            else:
+                return self._emit_js(cmd)
+        return ""
+
+# --------------------------------------------------------------------------- #
+# 5. Helpers + demo
+# --------------------------------------------------------------------------- #
+
+def compile_string(script: Union[str, List[str]], *, root: Union[pathlib.Path, None] = None) -> List[str]:
+    """Compile C4A-Script from string or list of strings to JavaScript.
+    
+    Args:
+        script: C4A-Script as a string or list of command strings
+        root: Root directory for resolving includes (optional)
+    
+    Returns:
+        List of JavaScript command strings
+    
+    Raises:
+        C4AScriptError: When compilation fails with detailed error information
+    """
+    try:
+        return Compiler(root).compile(script)
+    except Exception as e:
+        # Wrap the error with better formatting
+        raise C4AScriptError.from_exception(e, script)
+
+def compile_file(path: pathlib.Path) -> List[str]:
+    """Compile C4A-Script from file to JavaScript.
+    
+    Args:
+        path: Path to C4A-Script file
+    
+    Returns:
+        List of JavaScript command strings
+    """
+    return compile_string(path.read_text(), root=path.parent)
+
+def compile_lines(lines: List[str], *, root: Union[pathlib.Path, None] = None) -> List[str]:
+    """Compile C4A-Script from list of lines to JavaScript.
+    
+    Args:
+        lines: List of C4A-Script command lines
+        root: Root directory for resolving includes (optional)
+    
+    Returns:
+        List of JavaScript command strings
+    """
+    return compile_string(lines, root=root)
+
+DEMO = """
+# quick sanity demo
+PROC login
+  SET `input[name="username"]` $user
+  SET `input[name="password"]` $pass
+  CLICK `button.submit`
+ENDPROC
+
+SETVAR user = "tom@crawl4ai.com"
+SETVAR pass = "hunter2"
+
+GO https://example.com/login
+WAIT `input[name="username"]` 10
+login
+WAIT 3
+EVAL `console.log('logged in')`
+"""
+
+if __name__ == "__main__":
+    if len(sys.argv) == 2:
+        for js in compile_file(pathlib.Path(sys.argv[1])):
+            print(js)
+    else:
+        print("=== DEMO ===")
+        for js in compile_string(DEMO):
+            print(js)

crawl4ai/types.py

@@ -10,12 +10,16 @@ CacheMode = Union['CacheModeType']
 CrawlResult = Union['CrawlResultType']
 CrawlerHub = Union['CrawlerHubType']
 BrowserProfiler = Union['BrowserProfilerType']
+# NEW: Add AsyncUrlSeederType
+AsyncUrlSeeder = Union['AsyncUrlSeederType']
 
 # Configuration types
 BrowserConfig = Union['BrowserConfigType']
 CrawlerRunConfig = Union['CrawlerRunConfigType']
 HTTPCrawlerConfig = Union['HTTPCrawlerConfigType']
 LLMConfig = Union['LLMConfigType']
+# NEW: Add SeedingConfigType
+SeedingConfig = Union['SeedingConfigType']
 
 # Content scraping types
 ContentScrapingStrategy = Union['ContentScrapingStrategyType']
@@ -94,6 +98,8 @@ if TYPE_CHECKING:
     from .models import CrawlResult as CrawlResultType
     from .hub import CrawlerHub as CrawlerHubType
     from .browser_profiler import BrowserProfiler as BrowserProfilerType
+    # NEW: Import AsyncUrlSeeder for type checking
+    from .async_url_seeder import AsyncUrlSeeder as AsyncUrlSeederType
     
     # Configuration imports
     from .async_configs import (
@@ -101,6 +107,8 @@ if TYPE_CHECKING:
         CrawlerRunConfig as CrawlerRunConfigType,
         HTTPCrawlerConfig as HTTPCrawlerConfigType,
         LLMConfig as LLMConfigType,
+        # NEW: Import SeedingConfig for type checking
+        SeedingConfig as SeedingConfigType,
     )
     
     # Content scraping imports
@@ -184,4 +192,4 @@ if TYPE_CHECKING:
 
 def create_llm_config(*args, **kwargs) -> 'LLMConfigType':
     from .async_configs import LLMConfig
-    return LLMConfig(*args, **kwargs)
+    return LLMConfig(*args, **kwargs)

crawl4ai/utils.py

@@ -6,6 +6,7 @@ import html
 import lxml
 import re
 import os
+import subprocess
 import platform
 from .prompts import PROMPT_EXTRACT_BLOCKS
 from array import array
@@ -20,7 +21,6 @@ from urllib.parse import urljoin
 import requests
 from requests.exceptions import InvalidSchema
 import xxhash
-from colorama import Fore, Style, init
 import textwrap
 import cProfile
 import pstats
@@ -136,13 +136,20 @@ def merge_chunks(
     word_token_ratio: float = 1.0,
     splitter: Callable = None
 ) -> List[str]:
-    """Merges documents into chunks of specified token size.
+    """
+    Merges a sequence of documents into chunks based on a target token count, with optional overlap.
+    
+    Each document is split into tokens using the provided splitter function (defaults to str.split). Tokens are distributed into chunks aiming for the specified target size, with optional overlapping tokens between consecutive chunks. Returns a list of non-empty merged chunks as strings.
     
     Args:
-        docs: Input documents
-        target_size: Desired token count per chunk
-        overlap: Number of tokens to overlap between chunks
-        word_token_ratio: Multiplier for word->token conversion
+        docs: Sequence of input document strings to be merged.
+        target_size: Target number of tokens per chunk.
+        overlap: Number of tokens to overlap between consecutive chunks.
+        word_token_ratio: Multiplier to estimate token count from word count.
+        splitter: Callable used to split each document into tokens.
+    
+    Returns:
+        List of merged document chunks as strings, each not exceeding the target token size.
     """
     # Pre-tokenize all docs and store token counts
     splitter = splitter or str.split
@@ -151,7 +158,7 @@ def merge_chunks(
     total_tokens = 0
     
     for doc in docs:
-        tokens = doc.split()
+        tokens = splitter(doc)
         count = int(len(tokens) * word_token_ratio)
         if count:  # Skip empty docs
             token_counts.append(count)
@@ -441,14 +448,13 @@ def create_box_message(
         str: A formatted string containing the styled message box.
     """
 
-    init()
-
     # Define border and text colors for different types
     styles = {
-        "warning": (Fore.YELLOW, Fore.LIGHTYELLOW_EX, "⚠"),
-        "info": (Fore.BLUE, Fore.LIGHTBLUE_EX, "ℹ"),
-        "success": (Fore.GREEN, Fore.LIGHTGREEN_EX, "✓"),
-        "error": (Fore.RED, Fore.LIGHTRED_EX, "×"),
+        "warning": ("yellow", "bright_yellow", "⚠"),
+        "info": ("blue", "bright_blue", "ℹ"),
+        "debug": ("lightblack", "bright_black", "⋯"),
+        "success": ("green", "bright_green", "✓"),
+        "error": ("red", "bright_red", "×"),
     }
 
     border_color, text_color, prefix = styles.get(type.lower(), styles["info"])
@@ -480,12 +486,12 @@ def create_box_message(
     # Create the box with colored borders and lighter text
     horizontal_line = h_line * (width - 1)
     box = [
-        f"{border_color}{tl}{horizontal_line}{tr}",
+        f"[{border_color}]{tl}{horizontal_line}{tr}[/{border_color}]",
         *[
-            f"{border_color}{v_line}{text_color} {line:<{width-2}}{border_color}{v_line}"
+            f"[{border_color}]{v_line}[{text_color}] {line:<{width-2}}[/{text_color}][{border_color}]{v_line}[/{border_color}]"
             for line in formatted_lines
         ],
-        f"{border_color}{bl}{horizontal_line}{br}{Style.RESET_ALL}",
+        f"[{border_color}]{bl}{horizontal_line}{br}[/{border_color}]",
     ]
 
     result = "\n".join(box)
@@ -1111,6 +1117,23 @@ def get_content_of_website_optimized(
     css_selector: str = None,
     **kwargs,
 ) -> Dict[str, Any]:
+    """
+    Extracts and cleans content from website HTML, optimizing for useful media and contextual information.
+    
+    Parses the provided HTML to extract internal and external links, filters and scores images for usefulness, gathers contextual descriptions for media, removes unwanted or low-value elements, and converts the cleaned HTML to Markdown. Also extracts metadata and returns all structured content in a dictionary.
+    
+    Args:
+        url: The URL of the website being processed.
+        html: The raw HTML content to extract from.
+        word_count_threshold: Minimum word count for elements to be retained.
+        css_selector: Optional CSS selector to restrict extraction to specific elements.
+    
+    Returns:
+        A dictionary containing Markdown content, cleaned HTML, extraction success status, media and link lists, and metadata.
+    
+    Raises:
+        InvalidCSSSelectorError: If a provided CSS selector does not match any elements.
+    """
     if not html:
         return None
 
@@ -1153,6 +1176,20 @@ def get_content_of_website_optimized(
 
     def process_image(img, url, index, total_images):
         # Check if an image has valid display and inside undesired html elements
+        """
+        Processes an HTML image element to determine its relevance and extract metadata.
+        
+        Evaluates an image's visibility, context, and usefulness based on its attributes and parent elements. If the image passes validation and exceeds a usefulness score threshold, returns a dictionary with its source, alt text, contextual description, score, and type. Otherwise, returns None.
+        
+        Args:
+            img: The BeautifulSoup image tag to process.
+            url: The base URL of the page containing the image.
+            index: The index of the image in the list of images on the page.
+            total_images: The total number of images on the page.
+        
+        Returns:
+            A dictionary with image metadata if the image is considered useful, or None otherwise.
+        """
         def is_valid_image(img, parent, parent_classes):
             style = img.get("style", "")
             src = img.get("src", "")
@@ -1174,6 +1211,20 @@ def get_content_of_website_optimized(
         # Score an image for it's usefulness
         def score_image_for_usefulness(img, base_url, index, images_count):
             # Function to parse image height/width value and units
+            """
+            Scores an HTML image element for usefulness based on size, format, attributes, and position.
+            
+            The function evaluates an image's dimensions, file format, alt text, and its position among all images on the page to assign a usefulness score. Higher scores indicate images that are likely more relevant or informative for content extraction or summarization.
+            
+            Args:
+                img: The HTML image element to score.
+                base_url: The base URL used to resolve relative image sources.
+                index: The position of the image in the list of images on the page (zero-based).
+                images_count: The total number of images on the page.
+            
+            Returns:
+                An integer usefulness score for the image.
+            """
             def parse_dimension(dimension):
                 if dimension:
                     match = re.match(r"(\d+)(\D*)", dimension)
@@ -1188,6 +1239,16 @@ def get_content_of_website_optimized(
             # Fetch image file metadata to extract size and extension
             def fetch_image_file_size(img, base_url):
                 # If src is relative path construct full URL, if not it may be CDN URL
+                """
+                Fetches the file size of an image by sending a HEAD request to its URL.
+                
+                Args:
+                    img: A BeautifulSoup tag representing the image element.
+                    base_url: The base URL to resolve relative image sources.
+                
+                Returns:
+                    The value of the "Content-Length" header as a string if available, otherwise None.
+                """
                 img_url = urljoin(base_url, img.get("src"))
                 try:
                     response = requests.head(img_url)
@@ -1198,8 +1259,6 @@ def get_content_of_website_optimized(
                         return None
                 except InvalidSchema:
                     return None
-                finally:
-                    return
 
             image_height = img.get("height")
             height_value, height_unit = parse_dimension(image_height)
@@ -2737,33 +2796,67 @@ def preprocess_html_for_schema(html_content, text_threshold=100, attr_value_thre
             # 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()
+
+        # 4. Detect duplicates and drop them in a single pass
+        seen: dict[tuple, None] = {}
+        for el in list(tree.xpath('//*[@class]')):          # snapshot once, XPath is fast
+            parent = el.getparent()
             if parent is None:
                 continue
-                
-            # Create a signature based on tag and classes
-            classes = element.get('class', '')
-            if not classes:
+
+            cls = el.get('class')
+            if not cls:
                 continue
-            signature = f"{element.tag}.{classes}"
-            
-            if signature in pattern_elements:
-                pattern_elements[signature].append(element)
+
+            # ── build signature ───────────────────────────────────────────
+            h = xxhash.xxh64()                              # stream, no big join()
+            for txt in el.itertext():
+                h.update(txt)
+            sig = (el.tag, cls, h.intdigest())             # tuple cheaper & hashable
+
+            # ── first seen? keep – else drop ─────────────
+            if sig in seen and parent is not None:
+                parent.remove(el)                           # duplicate
             else:
-                pattern_elements[signature] = [element]
+                seen[sig] = None
         
-        # 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)
+        # # 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
+        #     innert_text = ''.join(element.xpath('.//text()'))
+        #     innert_text_hash = xxhash.xxh64(innert_text.encode()).hexdigest()
+        #     signature = f"{element.tag}.{classes}.{innert_text_hash}"
+            
+        #     if signature in pattern_elements:
+        #         pattern_elements[signature].append(element)
+        #     else:
+        #         pattern_elements[signature] = [element]
+        
+        # # Keep only first examples of each repeating pattern
+        # for signature, elements in pattern_elements.items():
+        #     if len(elements) > 1:
+        #         # Keep the first element and remove the rest
+        #         for element in elements[1:]:
+        #             if element.getparent() is not None:
+        #                 element.getparent().remove(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')
@@ -2776,6 +2869,282 @@ def preprocess_html_for_schema(html_content, text_threshold=100, attr_value_thre
     
     except Exception as e:
         # Fallback for parsing errors
-        return html_content[:max_size] if len(html_content) > max_size else html_content
-    
+        return html_content[:max_size] if len(html_content) > max_size else html_content    
+
+def start_colab_display_server():
+    """
+    Start virtual display server in Google Colab.
+    Raises error if not running in Colab environment.
+    """
+    # Check if running in Google Colab
+    try:
+        import google.colab
+        from google.colab import output
+        from IPython.display import IFrame, display
+    except ImportError:
+        raise RuntimeError("This function must be run in Google Colab environment.")
+    
+    import os, time, subprocess
+    
+    os.environ["DISPLAY"] = ":99"
+    
+    # Xvfb
+    xvfb = subprocess.Popen(["Xvfb", ":99", "-screen", "0", "1280x720x24"])
+    time.sleep(2)
+    
+    # minimal window manager
+    fluxbox = subprocess.Popen(["fluxbox"])
+    
+    # VNC → X
+    x11vnc = subprocess.Popen(["x11vnc",
+                              "-display", ":99",
+                              "-nopw", "-forever", "-shared",
+                              "-rfbport", "5900", "-quiet"])
+    
+    # websockify → VNC
+    novnc = subprocess.Popen(["/opt/novnc/utils/websockify/run",
+                              "6080", "localhost:5900",
+                              "--web", "/opt/novnc"])
+    
+    time.sleep(2)  # give ports a moment
+    
+    # Colab proxy url
+    url = output.eval_js("google.colab.kernel.proxyPort(6080)")
+    display(IFrame(f"{url}/vnc.html?autoconnect=true&resize=scale", width=1024, height=768))
+
+
+
+def setup_colab_environment():
+    """
+    Alternative setup using IPython magic commands
+    """
+    from IPython import get_ipython
+    ipython = get_ipython()
+    
+    print("🚀 Setting up Crawl4AI environment in Google Colab...")
+    
+    # Run the bash commands
+    ipython.run_cell_magic('bash', '', '''
+set -e
+
+echo "📦 Installing system dependencies..."
+apt-get update -y
+apt-get install -y xvfb x11vnc fluxbox websockify git
+
+echo "📥 Setting up virtual display..."
+git clone https://github.com/novnc/noVNC         /opt/novnc
+git clone https://github.com/novnc/websockify    /opt/novnc/utils/websockify
+
+pip install -q nest_asyncio google-colab
+echo "✅ Setup complete!"
+''')
+
+
+# Link Quality Scoring Functions
+def extract_page_context(page_title: str, headlines_text: str, meta_description: str, base_url: str) -> dict:
+    """
+    Extract page context for link scoring - called ONCE per page for performance.
+    Parser-agnostic function that takes pre-extracted data.
+    
+    Args:
+        page_title: Title of the page
+        headlines_text: Combined text from h1, h2, h3 elements
+        meta_description: Meta description content
+        base_url: Base URL of the page
+        
+    Returns:
+        Dictionary containing page context data for fast link scoring
+    """
+    context = {
+        'terms': set(),
+        'headlines': headlines_text or '',
+        'meta_description': meta_description or '',
+        'domain': '',
+        'is_docs_site': False
+    }
+    
+    try:
+        from urllib.parse import urlparse
+        parsed = urlparse(base_url)
+        context['domain'] = parsed.netloc.lower()
+        
+        # Check if this is a documentation/reference site
+        context['is_docs_site'] = any(indicator in context['domain'] 
+                                    for indicator in ['docs.', 'api.', 'developer.', 'reference.'])
+        
+        # Create term set for fast intersection (performance optimization)
+        all_text = ((page_title or '') + ' ' + context['headlines'] + ' ' + context['meta_description']).lower()
+        # Simple tokenization - fast and sufficient for scoring
+        context['terms'] = set(word.strip('.,!?;:"()[]{}') 
+                             for word in all_text.split() 
+                             if len(word.strip('.,!?;:"()[]{}')) > 2)
+                             
+    except Exception:
+        # Fail gracefully - return empty context
+        pass
+    
+    return context
+
+
+def calculate_link_intrinsic_score(
+    link_text: str, 
+    url: str, 
+    title_attr: str, 
+    class_attr: str, 
+    rel_attr: str, 
+    page_context: dict
+) -> float:
+    """
+    Ultra-fast link quality scoring using only provided data (no DOM access needed).
+    Parser-agnostic function.
+    
+    Args:
+        link_text: Text content of the link
+        url: Link URL
+        title_attr: Title attribute of the link
+        class_attr: Class attribute of the link
+        rel_attr: Rel attribute of the link
+        page_context: Pre-computed page context from extract_page_context()
+        
+    Returns:
+        Quality score (0.0 - 10.0), higher is better
+    """
+    score = 0.0
+    
+    try:
+        # 1. ATTRIBUTE QUALITY (string analysis - very fast)
+        if title_attr and len(title_attr.strip()) > 3:
+            score += 1.0
+            
+        class_str = (class_attr or '').lower()
+        # Navigation/important classes boost score
+        if any(nav_class in class_str for nav_class in ['nav', 'menu', 'primary', 'main', 'important']):
+            score += 1.5
+        # Marketing/ad classes reduce score  
+        if any(bad_class in class_str for bad_class in ['ad', 'sponsor', 'track', 'promo', 'banner']):
+            score -= 1.0
+            
+        rel_str = (rel_attr or '').lower()
+        # Semantic rel values
+        if any(good_rel in rel_str for good_rel in ['canonical', 'next', 'prev', 'chapter']):
+            score += 1.0
+        if any(bad_rel in rel_str for bad_rel in ['nofollow', 'sponsored', 'ugc']):
+            score -= 0.5
+            
+        # 2. URL STRUCTURE QUALITY (string operations - very fast)
+        url_lower = url.lower()
+        
+        # High-value path patterns
+        if any(good_path in url_lower for good_path in ['/docs/', '/api/', '/guide/', '/tutorial/', '/reference/', '/manual/']):
+            score += 2.0
+        elif any(medium_path in url_lower for medium_path in ['/blog/', '/article/', '/post/', '/news/']):
+            score += 1.0
+            
+        # Penalize certain patterns
+        if any(bad_path in url_lower for bad_path in ['/admin/', '/login/', '/cart/', '/checkout/', '/track/', '/click/']):
+            score -= 1.5
+            
+        # URL depth (shallow URLs often more important)
+        url_depth = url.count('/') - 2  # Subtract protocol and domain
+        if url_depth <= 2:
+            score += 1.0
+        elif url_depth > 5:
+            score -= 0.5
+            
+        # HTTPS bonus
+        if url.startswith('https://'):
+            score += 0.5
+            
+        # 3. TEXT QUALITY (string analysis - very fast)
+        if link_text:
+            text_clean = link_text.strip()
+            if len(text_clean) > 3:
+                score += 1.0
+                
+            # Multi-word links are usually more descriptive
+            word_count = len(text_clean.split())
+            if word_count >= 2:
+                score += 0.5
+            if word_count >= 4:
+                score += 0.5
+                
+            # Avoid generic link text
+            generic_texts = ['click here', 'read more', 'more info', 'link', 'here']
+            if text_clean.lower() in generic_texts:
+                score -= 1.0
+                
+        # 4. CONTEXTUAL RELEVANCE (pre-computed page terms - very fast)
+        if page_context.get('terms') and link_text:
+            link_words = set(word.strip('.,!?;:"()[]{}').lower() 
+                           for word in link_text.split() 
+                           if len(word.strip('.,!?;:"()[]{}')) > 2)
+            
+            if link_words:
+                # Calculate word overlap ratio
+                overlap = len(link_words & page_context['terms'])
+                if overlap > 0:
+                    relevance_ratio = overlap / min(len(link_words), 10)  # Cap to avoid over-weighting
+                    score += relevance_ratio * 2.0  # Up to 2 points for relevance
+                    
+        # 5. DOMAIN CONTEXT BONUSES (very fast string checks)
+        if page_context.get('is_docs_site', False):
+            # Documentation sites: prioritize internal navigation
+            if link_text and any(doc_keyword in link_text.lower() 
+                               for doc_keyword in ['api', 'reference', 'guide', 'tutorial', 'example']):
+                score += 1.0
+                
+    except Exception:
+        # Fail gracefully - return minimal score
+        score = 0.5
+        
+    # Ensure score is within reasonable bounds
+    return max(0.0, min(score, 10.0))
+
+
+def calculate_total_score(
+    intrinsic_score: Optional[float] = None,
+    contextual_score: Optional[float] = None,
+    score_links_enabled: bool = False,
+    query_provided: bool = False
+) -> float:
+    """
+    Calculate combined total score from intrinsic and contextual scores with smart fallbacks.
+    
+    Args:
+        intrinsic_score: Quality score based on URL structure, text, and context (0-10)
+        contextual_score: BM25 relevance score based on query and head content (0-1 typically)
+        score_links_enabled: Whether link scoring is enabled
+        query_provided: Whether a query was provided for contextual scoring
+        
+    Returns:
+        Combined total score (0-10 scale)
+        
+    Scoring Logic:
+        - No scoring: return 5.0 (neutral score)
+        - Only intrinsic: return normalized intrinsic score
+        - Only contextual: return contextual score scaled to 10
+        - Both: weighted combination (70% intrinsic, 30% contextual scaled)
+    """
+    # Case 1: No scoring enabled at all
+    if not score_links_enabled:
+        return 5.0  # Neutral score - all links treated equally
+    
+    # Normalize scores to handle None values
+    intrinsic = intrinsic_score if intrinsic_score is not None else 0.0
+    contextual = contextual_score if contextual_score is not None else 0.0
+    
+    # Case 2: Only intrinsic scoring (no query provided or no head extraction)
+    if not query_provided or contextual_score is None:
+        # Use intrinsic score directly (already 0-10 scale)
+        return max(0.0, min(intrinsic, 10.0))
+    
+    # Case 3: Both intrinsic and contextual scores available
+    # Scale contextual score (typically 0-1) to 0-10 range
+    contextual_scaled = min(contextual * 10.0, 10.0)
+    
+    # Weighted combination: 70% intrinsic (structure/content quality) + 30% contextual (query relevance)
+    # This gives more weight to link quality while still considering relevance
+    total = (intrinsic * 0.7) + (contextual_scaled * 0.3)
+    
+    return max(0.0, min(total, 10.0))
 

deploy/docker/README.md

@@ -58,7 +58,7 @@ Pull and run images directly from Docker Hub without building locally.
 
 #### 1. Pull the Image
 
-Our latest release candidate is `0.6.0rc1-r1`. Images are built with multi-arch manifests, so Docker automatically pulls the correct version for your system.
+Our latest release candidate is `0.6.0-r1`. Images are built with multi-arch manifests, so Docker automatically pulls the correct version for your system.
 
 ```bash
 # Pull the release candidate (recommended for latest features)
@@ -124,9 +124,9 @@ docker stop crawl4ai && docker rm crawl4ai
 #### Docker Hub Versioning Explained
 
 *   **Image Name:** `unclecode/crawl4ai`
-*   **Tag Format:** `LIBRARY_VERSION[-SUFFIX]` (e.g., `0.6.0rc1-r1`)
+*   **Tag Format:** `LIBRARY_VERSION[-SUFFIX]` (e.g., `0.6.0-r1`)
     *   `LIBRARY_VERSION`: The semantic version of the core `crawl4ai` Python library
-    *   `SUFFIX`: Optional tag for release candidates (`rc1`) and revisions (`r1`)
+    *   `SUFFIX`: Optional tag for release candidates (``) and revisions (`r1`)
 *   **`latest` Tag:** Points to the most recent stable version
 *   **Multi-Architecture Support:** All images support both `linux/amd64` and `linux/arm64` architectures through a single tag
 

deploy/docker/api.py

@@ -1,8 +1,10 @@
 import os
 import json
 import asyncio
-from typing import List, Tuple
+from typing import List, Tuple, Dict
 from functools import partial
+from uuid import uuid4
+from datetime import datetime
 
 import logging
 from typing import Optional, AsyncGenerator
@@ -272,7 +274,9 @@ async def handle_llm_request(
 async def handle_task_status(
     redis: aioredis.Redis,
     task_id: str,
-    base_url: str
+    base_url: str,
+    *,
+    keep: bool = False
 ) -> JSONResponse:
     """Handle task status check requests."""
     task = await redis.hgetall(f"task:{task_id}")
@@ -286,7 +290,7 @@ async def handle_task_status(
     response = create_task_response(task, task_id, base_url)
 
     if task["status"] in [TaskStatus.COMPLETED, TaskStatus.FAILED]:
-        if should_cleanup_task(task["created_at"]):
+        if not keep and should_cleanup_task(task["created_at"]):
             await redis.delete(f"task:{task_id}")
 
     return JSONResponse(response)
@@ -520,4 +524,48 @@ async def handle_stream_crawl_request(
         raise HTTPException(
             status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
             detail=str(e)
-        )
+        )
+        
+async def handle_crawl_job(
+    redis,
+    background_tasks: BackgroundTasks,
+    urls: List[str],
+    browser_config: Dict,
+    crawler_config: Dict,
+    config: Dict,
+) -> Dict:
+    """
+    Fire-and-forget version of handle_crawl_request.
+    Creates a task in Redis, runs the heavy work in a background task,
+    lets /crawl/job/{task_id} polling fetch the result.
+    """
+    task_id = f"crawl_{uuid4().hex[:8]}"
+    await redis.hset(f"task:{task_id}", mapping={
+        "status": TaskStatus.PROCESSING,         # <-- keep enum values consistent
+        "created_at": datetime.utcnow().isoformat(),
+        "url": json.dumps(urls),                 # store list as JSON string
+        "result": "",
+        "error": "",
+    })
+
+    async def _runner():
+        try:
+            result = await handle_crawl_request(
+                urls=urls,
+                browser_config=browser_config,
+                crawler_config=crawler_config,
+                config=config,
+            )
+            await redis.hset(f"task:{task_id}", mapping={
+                "status": TaskStatus.COMPLETED,
+                "result": json.dumps(result),
+            })
+            await asyncio.sleep(5)  # Give Redis time to process the update
+        except Exception as exc:
+            await redis.hset(f"task:{task_id}", mapping={
+                "status": TaskStatus.FAILED,
+                "error": str(exc),
+            })
+
+    background_tasks.add_task(_runner)
+    return {"task_id": task_id}

deploy/docker/c4ai-code-context.md

@@ -1263,7 +1263,7 @@ class LLMConfig:
         provider: str = DEFAULT_PROVIDER,
         api_token: Optional[str] = None,
         base_url: Optional[str] = None,
-        temprature: Optional[float] = None,
+        temperature: Optional[float] = None,
         max_tokens: Optional[int] = None,
         top_p: Optional[float] = None,
         frequency_penalty: Optional[float] = None,
@@ -1291,7 +1291,7 @@ class LLMConfig:
                 self.provider = DEFAULT_PROVIDER
                 self.api_token = os.getenv(DEFAULT_PROVIDER_API_KEY)
         self.base_url = base_url
-        self.temprature = temprature
+        self.temperature = temperature
         self.max_tokens = max_tokens
         self.top_p = top_p
         self.frequency_penalty = frequency_penalty
@@ -1305,7 +1305,7 @@ class LLMConfig:
             provider=kwargs.get("provider", DEFAULT_PROVIDER),
             api_token=kwargs.get("api_token"),
             base_url=kwargs.get("base_url"),
-            temprature=kwargs.get("temprature"),
+            temperature=kwargs.get("temperature"),
             max_tokens=kwargs.get("max_tokens"),
             top_p=kwargs.get("top_p"),
             frequency_penalty=kwargs.get("frequency_penalty"),
@@ -1319,7 +1319,7 @@ class LLMConfig:
             "provider": self.provider,
             "api_token": self.api_token,
             "base_url": self.base_url,
-            "temprature": self.temprature,
+            "temperature": self.temperature,
             "max_tokens": self.max_tokens,
             "top_p": self.top_p,
             "frequency_penalty": self.frequency_penalty,
@@ -4075,7 +4075,7 @@ class LLMExtractionStrategy(ExtractionStrategy):
             api_token: The API token for the provider.
             base_url: The base URL for the API request.
             api_base: The base URL for the API request.
-            extra_args: Additional arguments for the API request, such as temprature, max_tokens, etc.
+            extra_args: Additional arguments for the API request, such as temperature, max_tokens, etc.
         """
         super().__init__( input_format=input_format, **kwargs)
         self.llm_config = llm_config
@@ -7901,7 +7901,7 @@ 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 (
+from crawl4ai import (
     JsonCssExtractionStrategy,
     LLMExtractionStrategy,
 )
@@ -8301,7 +8301,7 @@ async def crawl_dynamic_content_pages_method_2():
 
 
 async def cosine_similarity_extraction():
-    from crawl4ai.extraction_strategy import CosineStrategy
+    from crawl4ai import CosineStrategy
     crawl_config = CrawlerRunConfig(
         cache_mode=CacheMode.BYPASS,
         extraction_strategy=CosineStrategy(

deploy/docker/c4ai-doc-context.md

@@ -354,7 +354,7 @@ In a typical scenario, you define **one** `BrowserConfig` for your crawler sessi
 ```python
 import asyncio
 from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode, LLMConfig
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 
 async def main():
     # 1) Browser config: headless, bigger viewport, no proxy
@@ -1042,7 +1042,7 @@ You can combine content selection with a more advanced extraction strategy. For
 import asyncio
 import json
 from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, CacheMode
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 
 async def main():
     # Minimal schema for repeated items
@@ -1094,7 +1094,7 @@ import asyncio
 import json
 from pydantic import BaseModel, Field
 from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, LLMConfig
-from crawl4ai.extraction_strategy import LLMExtractionStrategy
+from crawl4ai import LLMExtractionStrategy
 
 class ArticleData(BaseModel):
     headline: str
@@ -1139,7 +1139,7 @@ Below is a short function that unifies **CSS selection**, **exclusion** logic, a
 import asyncio
 import json
 from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, CacheMode
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 
 async def extract_main_articles(url: str):
     schema = {
@@ -1488,7 +1488,7 @@ If you run a JSON-based extraction strategy (CSS, XPath, LLM, etc.), the structu
 import asyncio
 import json
 from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, CacheMode
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 
 async def main():
     schema = {
@@ -4722,7 +4722,7 @@ if __name__ == "__main__":
 Once dynamic content is loaded, you can attach an **`extraction_strategy`** (like `JsonCssExtractionStrategy` or `LLMExtractionStrategy`). For example:
 
 ```python
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 
 schema = {
     "name": "Commits",
@@ -4902,7 +4902,7 @@ Crawl4AI can also extract structured data (JSON) using CSS or XPath selectors. B
 > **New!** Crawl4AI now provides a powerful utility to automatically generate extraction schemas using LLM. This is a one-time cost that gives you a reusable schema for fast, LLM-free extractions:
 
 ```python
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 from crawl4ai import LLMConfig
 
 # Generate a schema (one-time cost)
@@ -4932,7 +4932,7 @@ Here's a basic extraction example:
 import asyncio
 import json
 from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, CacheMode
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 
 async def main():
     schema = {
@@ -4987,7 +4987,7 @@ import json
 import asyncio
 from pydantic import BaseModel, Field
 from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, LLMConfig
-from crawl4ai.extraction_strategy import LLMExtractionStrategy
+from crawl4ai import LLMExtractionStrategy
 
 class OpenAIModelFee(BaseModel):
     model_name: str = Field(..., description="Name of the OpenAI model.")
@@ -5103,7 +5103,7 @@ Some sites require multiple “page clicks” or dynamic JavaScript updates. Bel
 ```python
 import asyncio
 from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 
 async def extract_structured_data_using_css_extractor():
     print("\n--- Using JsonCssExtractionStrategy for Fast Structured Output ---")
@@ -6705,7 +6705,7 @@ dispatcher = MemoryAdaptiveDispatcher(
 3. **`max_session_permit`** (`int`, default: `10`)  
   The maximum number of concurrent crawling tasks allowed. This ensures resource limits are respected while maintaining concurrency.
 
-4. **`memory_wait_timeout`** (`float`, default: `300.0`)  
+4. **`memory_wait_timeout`** (`float`, default: `600.0`)
   Optional timeout (in seconds). If memory usage exceeds `memory_threshold_percent` for longer than this duration, a `MemoryError` is raised.
 
 5. **`rate_limiter`** (`RateLimiter`, default: `None`)  
@@ -7300,7 +7300,7 @@ Here's an example of crawling GitHub commits across multiple pages while preserv
 
 ```python
 from crawl4ai.async_configs import CrawlerRunConfig
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 from crawl4ai.cache_context import CacheMode
 
 async def crawl_dynamic_content():
@@ -7850,7 +7850,7 @@ The Cosine Strategy:
 ## Basic Usage
 
 ```python
-from crawl4ai.extraction_strategy import CosineStrategy
+from crawl4ai import CosineStrategy
 
 strategy = CosineStrategy(
     semantic_filter="product reviews",    # Target content type
@@ -8161,7 +8161,7 @@ import json
 from pydantic import BaseModel, Field
 from typing import List
 from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode, LLMConfig
-from crawl4ai.extraction_strategy import LLMExtractionStrategy
+from crawl4ai import LLMExtractionStrategy
 
 class Product(BaseModel):
     name: str
@@ -8278,7 +8278,7 @@ import asyncio
 from typing import List
 from pydantic import BaseModel, Field
 from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
-from crawl4ai.extraction_strategy import LLMExtractionStrategy
+from crawl4ai import LLMExtractionStrategy
 
 class Entity(BaseModel):
     name: str
@@ -8423,7 +8423,7 @@ Let’s begin with a **simple** schema-based extraction using the `JsonCssExtrac
 import json
 import asyncio
 from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, CacheMode
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 
 async def extract_crypto_prices():
     # 1. Define a simple extraction schema
@@ -8493,7 +8493,7 @@ Below is a short example demonstrating **XPath** extraction plus the **`raw://`*
 import json
 import asyncio
 from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
-from crawl4ai.extraction_strategy import JsonXPathExtractionStrategy
+from crawl4ai import JsonXPathExtractionStrategy
 
 async def extract_crypto_prices_xpath():
     # 1. Minimal dummy HTML with some repeating rows
@@ -8694,7 +8694,7 @@ Key Takeaways:
 import json
 import asyncio
 from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 
 ecommerce_schema = {
     # ... the advanced schema from above ...
@@ -8804,7 +8804,7 @@ While manually crafting schemas is powerful and precise, Crawl4AI now offers a c
 The schema generator is available as a static method on both `JsonCssExtractionStrategy` and `JsonXPathExtractionStrategy`. You can choose between OpenAI's GPT-4 or the open-source Ollama for schema generation:
 
 ```python
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy, JsonXPathExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy, JsonXPathExtractionStrategy
 from crawl4ai import LLMConfig
 
 # Sample HTML with product information

deploy/docker/config.yml

@@ -3,7 +3,7 @@ app:
   title: "Crawl4AI API"
   version: "1.0.0"
   host: "0.0.0.0"
-  port: 11235
+  port: 11234
   reload: False
   workers: 1
   timeout_keep_alive: 300

deploy/docker/job.py

@@ -0,0 +1,99 @@
+"""
+Job endpoints (enqueue + poll) for long-running LL​M extraction and raw crawl.
+Relies on the existing Redis task helpers in api.py
+"""
+
+from typing import Dict, Optional, Callable
+from fastapi import APIRouter, BackgroundTasks, Depends, Request
+from pydantic import BaseModel, HttpUrl
+
+from api import (
+    handle_llm_request,
+    handle_crawl_job,
+    handle_task_status,
+)
+
+# ------------- dependency placeholders -------------
+_redis = None        # will be injected from server.py
+_config = None
+_token_dep: Callable = lambda: None  # dummy until injected
+
+# public router
+router = APIRouter()
+
+
+# === init hook called by server.py =========================================
+def init_job_router(redis, config, token_dep) -> APIRouter:
+    """Inject shared singletons and return the router for mounting."""
+    global _redis, _config, _token_dep
+    _redis, _config, _token_dep = redis, config, token_dep
+    return router
+
+
+# ---------- payload models --------------------------------------------------
+class LlmJobPayload(BaseModel):
+    url:    HttpUrl
+    q:      str
+    schema: Optional[str] = None
+    cache:  bool = False
+
+
+class CrawlJobPayload(BaseModel):
+    urls:           list[HttpUrl]
+    browser_config: Dict = {}
+    crawler_config: Dict = {}
+
+
+# ---------- LL​M job ---------------------------------------------------------
+@router.post("/llm/job", status_code=202)
+async def llm_job_enqueue(
+        payload: LlmJobPayload,
+        background_tasks: BackgroundTasks,
+        request: Request,
+        _td: Dict = Depends(lambda: _token_dep()),   # late-bound dep
+):
+    return await handle_llm_request(
+        _redis,
+        background_tasks,
+        request,
+        str(payload.url),
+        query=payload.q,
+        schema=payload.schema,
+        cache=payload.cache,
+        config=_config,
+    )
+
+
+@router.get("/llm/job/{task_id}")
+async def llm_job_status(
+    request: Request,
+    task_id: str,
+    _td: Dict = Depends(lambda: _token_dep())
+):
+    return await handle_task_status(_redis, task_id)
+
+
+# ---------- CRAWL job -------------------------------------------------------
+@router.post("/crawl/job", status_code=202)
+async def crawl_job_enqueue(
+        payload: CrawlJobPayload,
+        background_tasks: BackgroundTasks,
+        _td: Dict = Depends(lambda: _token_dep()),
+):
+    return await handle_crawl_job(
+        _redis,
+        background_tasks,
+        [str(u) for u in payload.urls],
+        payload.browser_config,
+        payload.crawler_config,
+        config=_config,
+    )
+
+
+@router.get("/crawl/job/{task_id}")
+async def crawl_job_status(
+    request: Request,
+    task_id: str,
+    _td: Dict = Depends(lambda: _token_dep())
+):
+    return await handle_task_status(_redis, task_id, base_url=str(request.base_url))

deploy/docker/requirements.txt

@@ -14,3 +14,4 @@ anyio==4.9.0
 PyJWT==2.10.1
 mcp>=1.6.0
 websockets>=15.0.1
+httpx[http2]>=0.27.2

deploy/docker/schemas.py

@@ -0,0 +1,42 @@
+from typing import List, Optional, Dict
+from enum import Enum
+from pydantic import BaseModel, Field
+from utils import FilterType
+
+
+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)
+
+class MarkdownRequest(BaseModel):
+    """Request body for the /md endpoint."""
+    url: str                    = Field(...,  description="Absolute http/https URL to fetch")
+    f:   FilterType             = Field(FilterType.FIT,
+                                        description="Content‑filter strategy: FIT, RAW, BM25, or LLM")
+    q:   Optional[str] = Field(None,  description="Query string used by BM25/LLM filters")
+    c:   Optional[str] = Field("0",   description="Cache‑bust / revision counter")
+
+
+class RawCode(BaseModel):
+    code: str
+
+class HTMLRequest(BaseModel):
+    url: str
+    
+class ScreenshotRequest(BaseModel):
+    url: str
+    screenshot_wait_for: Optional[float] = 2
+    output_path: Optional[str] = None
+
+class PDFRequest(BaseModel):
+    url: str
+    output_path: Optional[str] = None
+
+
+class JSEndpointRequest(BaseModel):
+    url: str
+    scripts: List[str] = Field(
+        ...,
+        description="List of separated JavaScript snippets to execute"
+    )

deploy/docker/server.py

@@ -12,7 +12,7 @@ from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig
 from auth import create_access_token, get_token_dependency, TokenRequest
 from pydantic import BaseModel
 from typing import Optional, List, Dict
-from fastapi import Request, Depends 
+from fastapi import Request, Depends
 from fastapi.responses import FileResponse
 import base64
 import re
@@ -22,6 +22,16 @@ from api import (
     handle_stream_crawl_request, handle_crawl_request,
     stream_results
 )
+from schemas import (
+    CrawlRequest,
+    MarkdownRequest,
+    RawCode,
+    HTMLRequest,
+    ScreenshotRequest,
+    PDFRequest,
+    JSEndpointRequest,
+)
+
 from utils import (
     FilterType, load_config, setup_logging, verify_email_domain
 )
@@ -37,23 +47,13 @@ from fastapi import (
     FastAPI, HTTPException, Request, Path, Query, Depends
 )
 from rank_bm25 import BM25Okapi
-
-def chunk_code_functions(code: str) -> List[str]:
-    tree = ast.parse(code)
-    lines = code.splitlines()
-    chunks = []
-    for node in tree.body:
-        if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef, ast.ClassDef)):
-            start = node.lineno - 1
-            end = getattr(node, 'end_lineno', start + 1)
-            chunks.append("\n".join(lines[start:end]))
-    return chunks
 from fastapi.responses import (
     StreamingResponse, RedirectResponse, PlainTextResponse, JSONResponse
 )
 from fastapi.middleware.httpsredirect import HTTPSRedirectMiddleware
 from fastapi.middleware.trustedhost import TrustedHostMiddleware
 from fastapi.staticfiles import StaticFiles
+from job import init_job_router
 
 from mcp_bridge import attach_mcp, mcp_resource, mcp_template, mcp_tool
 
@@ -129,8 +129,6 @@ app.mount(
     name="play",
 )
 
-# Optional nice‑to‑have: opening the root shows the playground
-
 
 @app.get("/")
 async def root():
@@ -211,48 +209,10 @@ def _safe_eval_config(expr: str) -> dict:
     return obj.dump()
 
 
-# ───────────────────────── Schemas ───────────────────────────
-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)
-
-# ────────────── Schemas ──────────────
-class MarkdownRequest(BaseModel):
-    """Request body for the /md endpoint."""
-    url: str                    = Field(...,  description="Absolute http/https URL to fetch")
-    f:   FilterType             = Field(FilterType.FIT,
-                                        description="Content‑filter strategy: FIT, RAW, BM25, or LLM")
-    q:   Optional[str] = Field(None,  description="Query string used by BM25/LLM filters")
-    c:   Optional[str] = Field("0",   description="Cache‑bust / revision counter")
-
-
-class RawCode(BaseModel):
-    code: str
-
-class HTMLRequest(BaseModel):
-    url: str
-    
-class ScreenshotRequest(BaseModel):
-    url: str
-    screenshot_wait_for: Optional[float] = 2
-    output_path: Optional[str] = None
-
-class PDFRequest(BaseModel):
-    url: str
-    output_path: Optional[str] = None
-
-
-class JSEndpointRequest(BaseModel):
-    url: str
-    scripts: List[str] = Field(
-        ...,
-        description="List of separated JavaScript snippets to execute"
-    )
+# ── job router ──────────────────────────────────────────────
+app.include_router(init_job_router(redis, config, token_dep))
 
 # ──────────────────────── Endpoints ──────────────────────────
-
-
 @app.post("/token")
 async def get_token(req: TokenRequest):
     if not verify_email_domain(req.email):
@@ -278,7 +238,8 @@ async def get_markdown(
     _td: Dict = Depends(token_dep),
 ):
     if not body.url.startswith(("http://", "https://")):
-        raise HTTPException(400, "URL must be absolute and start with http/https")
+        raise HTTPException(
+            400, "URL must be absolute and start with http/https")
     markdown = await handle_markdown_request(
         body.url, body.f, body.q, body.c, config
     )
@@ -314,12 +275,13 @@ async def generate_html(
 
 # Screenshot endpoint
 
+
 @app.post("/screenshot")
 @limiter.limit(config["rate_limiting"]["default_limit"])
 @mcp_tool("screenshot")
 async def generate_screenshot(
     request: Request,
-    body: ScreenshotRequest, 
+    body: ScreenshotRequest,
     _td: Dict = Depends(token_dep),
 ):
     """
@@ -327,7 +289,8 @@ async def generate_screenshot(
     Use when you need an image snapshot of the rendered page. Its recommened to provide an output path to save the screenshot.
     Then in result instead of the screenshot you will get a path to the saved file.
     """
-    cfg = CrawlerRunConfig(screenshot=True, screenshot_wait_for=body.screenshot_wait_for)
+    cfg = CrawlerRunConfig(
+        screenshot=True, screenshot_wait_for=body.screenshot_wait_for)
     async with AsyncWebCrawler(config=BrowserConfig()) as crawler:
         results = await crawler.arun(url=body.url, config=cfg)
     screenshot_data = results[0].screenshot
@@ -341,12 +304,13 @@ async def generate_screenshot(
 
 # PDF endpoint
 
+
 @app.post("/pdf")
 @limiter.limit(config["rate_limiting"]["default_limit"])
 @mcp_tool("pdf")
 async def generate_pdf(
     request: Request,
-    body: PDFRequest, 
+    body: PDFRequest,
     _td: Dict = Depends(token_dep),
 ):
     """
@@ -384,7 +348,7 @@ async def execute_js(
         Your script will replace '{script}' and execute in the browser context. So provide either an IIFE or a sync/async function that returns a value.
     Return Format:
         - The return result is an instance of CrawlResult, so you have access to markdown, links, and other stuff. If this is enough, you don't need to call again for other endpoints.
-        
+
         ```python
         class CrawlResult(BaseModel):
             url: str
@@ -418,7 +382,7 @@ async def execute_js(
             fit_markdown: Optional[str] = None
             fit_html: Optional[str] = None
         ```
-        
+
     """
     cfg = CrawlerRunConfig(js_code=body.scripts)
     async with AsyncWebCrawler(config=BrowserConfig()) as crawler:
@@ -507,6 +471,7 @@ async def crawl_stream(
         },
     )
 
+
 def chunk_code_functions(code_md: str) -> List[str]:
     """Extract each function/class from markdown code blocks per file."""
     pattern = re.compile(
@@ -530,6 +495,7 @@ def chunk_code_functions(code_md: str) -> List[str]:
                 chunks.append(f"# File: {file_path}\n{snippet}")
     return chunks
 
+
 def chunk_doc_sections(doc: str) -> List[str]:
     lines = doc.splitlines(keepends=True)
     sections = []
@@ -545,6 +511,7 @@ def chunk_doc_sections(doc: str) -> List[str]:
         sections.append("".join(current))
     return sections
 
+
 @app.get("/ask")
 @limiter.limit(config["rate_limiting"]["default_limit"])
 @mcp_tool("ask")
@@ -552,21 +519,24 @@ async def get_context(
     request: Request,
     _td: Dict = Depends(token_dep),
     context_type: str = Query("all", regex="^(code|doc|all)$"),
-    query: Optional[str] = Query(None, description="search query to filter chunks"),
-    score_ratio: float = Query(0.5, ge=0.0, le=1.0, description="min score as fraction of max_score"),
-    max_results: int = Query(20, ge=1, description="absolute cap on returned chunks"),
+    query: Optional[str] = Query(
+        None, description="search query to filter chunks"),
+    score_ratio: float = Query(
+        0.5, ge=0.0, le=1.0, description="min score as fraction of max_score"),
+    max_results: int = Query(
+        20, ge=1, description="absolute cap on returned chunks"),
 ):
     """
     This end point is design for any questions about Crawl4ai library. It returns a plain text markdown with extensive information about Crawl4ai. 
     You can use this as a context for any AI assistant. Use this endpoint for AI assistants to retrieve library context for decision making or code generation tasks.
     Alway is BEST practice you provide a query to filter the context. Otherwise the lenght of the response will be very long.
-    
+
     Parameters:
     - context_type: Specify "code" for code context, "doc" for documentation context, or "all" for both.
     - query: RECOMMENDED search query to filter paragraphs using BM25. You can leave this empty to get all the context.
     - score_ratio: Minimum score as a fraction of the maximum score for filtering results.
     - max_results: Maximum number of results to return. Default is 20.
-    
+
     Returns:
     - JSON response with the requested context.
     - If "code" is specified, returns the code context.
@@ -576,7 +546,7 @@ async def get_context(
     # load contexts
     base = os.path.dirname(__file__)
     code_path = os.path.join(base, "c4ai-code-context.md")
-    doc_path  = os.path.join(base, "c4ai-doc-context.md")
+    doc_path = os.path.join(base, "c4ai-doc-context.md")
     if not os.path.exists(code_path) or not os.path.exists(doc_path):
         raise HTTPException(404, "Context files not found")
 
@@ -626,7 +596,7 @@ async def get_context(
         ]
 
     return JSONResponse(results)
-    
+
 
 # attach MCP layer (adds /mcp/ws, /mcp/sse, /mcp/schema)
 print(f"MCP server running on {config['app']['host']}:{config['app']['port']}")

deploy/docker/static/playground/index.html

@@ -193,7 +193,48 @@
                 <textarea id="urls" class="w-full bg-dark border border-border rounded p-2 h-32 text-sm mb-4"
                     spellcheck="false">https://example.com</textarea>
 
-                <details class="mb-4">
+                <!-- Specific options for /md endpoint -->
+                <details id="md-options" class="mb-4 hidden">
+                    <summary class="text-sm text-secondary cursor-pointer">/md Options</summary>
+                    <div class="mt-2 space-y-3 p-2 border border-border rounded">
+                        <div>
+                            <label for="md-filter" class="block text-xs text-secondary mb-1">Filter Type</label>
+                            <select id="md-filter" class="bg-dark border border-border rounded px-2 py-1 text-sm w-full">
+                                <option value="fit">fit - Adaptive content filtering</option>
+                                <option value="raw">raw - No filtering</option>
+                                <option value="bm25">bm25 - BM25 keyword relevance</option>
+                                <option value="llm">llm - LLM-based filtering</option>
+                            </select>
+                        </div>
+                        <div>
+                            <label for="md-query" class="block text-xs text-secondary mb-1">Query (for BM25/LLM filters)</label>
+                            <input id="md-query" type="text" placeholder="Enter search terms or instructions" 
+                                class="bg-dark border border-border rounded px-2 py-1 text-sm w-full">
+                        </div>
+                        <div>
+                            <label for="md-cache" class="block text-xs text-secondary mb-1">Cache Mode</label>
+                            <select id="md-cache" class="bg-dark border border-border rounded px-2 py-1 text-sm w-full">
+                                <option value="0">Write-Only (0)</option>
+                                <option value="1">Enabled (1)</option>
+                            </select>
+                        </div>
+                    </div>
+                </details>
+
+                <!-- Specific options for /llm endpoint -->
+                <details id="llm-options" class="mb-4 hidden">
+                    <summary class="text-sm text-secondary cursor-pointer">/llm Options</summary>
+                    <div class="mt-2 space-y-3 p-2 border border-border rounded">
+                        <div>
+                            <label for="llm-question" class="block text-xs text-secondary mb-1">Question</label>
+                            <input id="llm-question" type="text" value="What is this page about?" 
+                                class="bg-dark border border-border rounded px-2 py-1 text-sm w-full">
+                        </div>
+                    </div>
+                </details>
+
+                <!-- Advanced config for /crawl endpoints -->
+                <details id="adv-config" class="mb-4">
                     <summary class="text-sm text-secondary cursor-pointer">Advanced Config <span
                         class="text-xs text-primary">(Python → auto‑JSON)</span></summary>
 
@@ -437,6 +478,33 @@
             cm.setValue(TEMPLATES[e.target.value]);
             document.getElementById('cfg-status').textContent = '';
         });
+        
+        // Handle endpoint selection change to show appropriate options
+        document.getElementById('endpoint').addEventListener('change', function(e) {
+            const endpoint = e.target.value;
+            const mdOptions = document.getElementById('md-options');
+            const llmOptions = document.getElementById('llm-options');
+            const advConfig = document.getElementById('adv-config');
+            
+            // Hide all option sections first
+            mdOptions.classList.add('hidden');
+            llmOptions.classList.add('hidden');
+            advConfig.classList.add('hidden');
+            
+            // Show the appropriate section based on endpoint
+            if (endpoint === 'md') {
+                mdOptions.classList.remove('hidden');
+                // Auto-open the /md options
+                mdOptions.setAttribute('open', '');
+            } else if (endpoint === 'llm') {
+                llmOptions.classList.remove('hidden');
+                // Auto-open the /llm options
+                llmOptions.setAttribute('open', '');
+            } else {
+                // For /crawl endpoints, show the advanced config
+                advConfig.classList.remove('hidden');
+            }
+        });
 
         async function pyConfigToJson() {
             const code = cm.getValue().trim();
@@ -494,10 +562,18 @@
         }
 
         // Generate code snippets
-        function generateSnippets(api, payload) {
+        function generateSnippets(api, payload, method = 'POST') {
             // Python snippet
             const pyCodeEl = document.querySelector('#python-content code');
-            const pySnippet = `import httpx\n\nasync def crawl():\n    async with httpx.AsyncClient() as client:\n        response = await client.post(\n            "${window.location.origin}${api}",\n            json=${JSON.stringify(payload, null, 4).replace(/\n/g, '\n            ')}\n        )\n        return response.json()`;
+            let pySnippet;
+            
+            if (method === 'GET') {
+                // GET request (for /llm endpoint)
+                pySnippet = `import httpx\n\nasync def crawl():\n    async with httpx.AsyncClient() as client:\n        response = await client.get(\n            "${window.location.origin}${api}"\n        )\n        return response.json()`;
+            } else {
+                // POST request (for /crawl and /md endpoints)
+                pySnippet = `import httpx\n\nasync def crawl():\n    async with httpx.AsyncClient() as client:\n        response = await client.post(\n            "${window.location.origin}${api}",\n            json=${JSON.stringify(payload, null, 4).replace(/\n/g, '\n            ')}\n        )\n        return response.json()`;
+            }
 
             pyCodeEl.textContent = pySnippet;
             pyCodeEl.className = 'python hljs'; // Reset classes
@@ -505,7 +581,15 @@
 
             // cURL snippet
             const curlCodeEl = document.querySelector('#curl-content code');
-            const curlSnippet = `curl -X POST ${window.location.origin}${api} \\\n  -H "Content-Type: application/json" \\\n  -d '${JSON.stringify(payload)}'`;
+            let curlSnippet;
+            
+            if (method === 'GET') {
+                // GET request (for /llm endpoint)
+                curlSnippet = `curl -X GET "${window.location.origin}${api}"`;
+            } else {
+                // POST request (for /crawl and /md endpoints)
+                curlSnippet = `curl -X POST ${window.location.origin}${api} \\\n  -H "Content-Type: application/json" \\\n  -d '${JSON.stringify(payload)}'`;
+            }
 
             curlCodeEl.textContent = curlSnippet;
             curlCodeEl.className = 'bash hljs'; // Reset classes
@@ -536,20 +620,39 @@
 
             const endpointMap = {
                 crawl: '/crawl',
-            };
-
-            /*const endpointMap = {
-                crawl: '/crawl',
-                crawl_stream: '/crawl/stream',
+                // crawl_stream: '/crawl/stream',
                 md: '/md',
                 llm: '/llm'
-            };*/
+            };
 
             const api = endpointMap[endpoint];
-            const payload = {
-                urls,
-                ...advConfig
-            };
+            let payload;
+            
+            // Create appropriate payload based on endpoint type
+            if (endpoint === 'md') {
+                // Get values from the /md specific inputs
+                const filterType = document.getElementById('md-filter').value;
+                const query = document.getElementById('md-query').value.trim();
+                const cache = document.getElementById('md-cache').value;
+                
+                // MD endpoint expects: { url, f, q, c }
+                payload = {
+                    url: urls[0], // Take first URL
+                    f: filterType, // Lowercase filter type as required by server
+                    q: query || null, // Use the query if provided, otherwise null
+                    c: cache
+                };
+            } else if (endpoint === 'llm') {
+                // LLM endpoint has a different URL pattern and uses query params
+                // This will be handled directly in the fetch below
+                payload = null;
+            } else {
+                // Default payload for /crawl and /crawl/stream
+                payload = {
+                    urls,
+                    ...advConfig
+                };
+            }
 
             updateStatus('processing');
 
@@ -557,7 +660,18 @@
                 const startTime = performance.now();
                 let response, responseData;
 
-                if (endpoint === 'crawl_stream') {
+                if (endpoint === 'llm') {
+                    // Special handling for LLM endpoint which uses URL pattern: /llm/{encoded_url}?q={query}
+                    const url = urls[0];
+                    const encodedUrl = encodeURIComponent(url);
+                    // Get the question from the LLM-specific input
+                    const question = document.getElementById('llm-question').value.trim() || "What is this page about?";
+                    
+                    response = await fetch(`${api}/${encodedUrl}?q=${encodeURIComponent(question)}`, {
+                        method: 'GET',
+                        headers: { 'Accept': 'application/json' }
+                    });
+                } else if (endpoint === 'crawl_stream') {
                     // Stream processing
                     response = await fetch(api, {
                         method: 'POST',
@@ -597,7 +711,7 @@
                     document.querySelector('#response-content code').className = 'json hljs'; // Reset classes
                     forceHighlightElement(document.querySelector('#response-content code'));
                 } else {
-                    // Regular request
+                    // Regular request (handles /crawl and /md)
                     response = await fetch(api, {
                         method: 'POST',
                         headers: { 'Content-Type': 'application/json' },
@@ -625,7 +739,16 @@
                 }
 
                 forceHighlightElement(document.querySelector('#response-content code'));
-                generateSnippets(api, payload);
+                
+                // For generateSnippets, handle the LLM case specially
+                if (endpoint === 'llm') {
+                    const url = urls[0];
+                    const encodedUrl = encodeURIComponent(url);
+                    const question = document.getElementById('llm-question').value.trim() || "What is this page about?";
+                    generateSnippets(`${api}/${encodedUrl}?q=${encodeURIComponent(question)}`, null, 'GET');
+                } else {
+                    generateSnippets(api, payload);
+                }
             } catch (error) {
                 console.error('Error:', error);
                 updateStatus('error');
@@ -807,9 +930,24 @@
                 });
             });
         }
+        
+        // Function to initialize UI based on selected endpoint
+        function initUI() {
+            // Trigger the endpoint change handler to set initial UI state
+            const endpointSelect = document.getElementById('endpoint');
+            const event = new Event('change');
+            endpointSelect.dispatchEvent(event);
+            
+            // Initialize copy buttons
+            initCopyButtons();
+        }
 
-        // Call this in your DOMContentLoaded or initialization
-        initCopyButtons();
+        // Initialize on page load
+        document.addEventListener('DOMContentLoaded', initUI);
+        // Also call it immediately in case the script runs after DOM is already loaded
+        if (document.readyState !== 'loading') {
+            initUI();
+        }
 
     </script>
 </body>

deploy/docker/utils.py

@@ -45,10 +45,10 @@ def datetime_handler(obj: any) -> Optional[str]:
         return obj.isoformat()
     raise TypeError(f"Object of type {type(obj)} is not JSON serializable")
 
-def should_cleanup_task(created_at: str) -> bool:
+def should_cleanup_task(created_at: str, ttl_seconds: int = 3600) -> bool:
     """Check if task should be cleaned up based on creation time."""
     created = datetime.fromisoformat(created_at)
-    return (datetime.now() - created).total_seconds() > 3600
+    return (datetime.now() - created).total_seconds() > ttl_seconds
 
 def decode_redis_hash(hash_data: Dict[bytes, bytes]) -> Dict[str, str]:
     """Decode Redis hash data from bytes to strings."""

docs/apps/linkdin/README.md

@@ -0,0 +1,131 @@
+# Crawl4AI Prospect‑Wizard – step‑by‑step guide
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/10nRCwmfxPjVrRUHyJsYlX7BH5bvPoGpx?usp=sharing)
+
+A three‑stage demo that goes from **LinkedIn scraping** ➜ **LLM reasoning** ➜ **graph visualisation**.
+
+**Try it in Google Colab!** Click the badge above to run this demo in a cloud environment with zero setup required.
+
+```
+prospect‑wizard/
+├─ c4ai_discover.py         # Stage 1 – scrape companies + people
+├─ c4ai_insights.py         # Stage 2 – embeddings, org‑charts, scores
+├─ graph_view_template.html # Stage 3 – graph viewer (static HTML)
+└─ data/                    # output lands here (*.jsonl / *.json)
+```
+
+---
+
+## 1  Install & boot a LinkedIn profile (one‑time)
+
+### 1.1  Install dependencies
+```bash
+pip install crawl4ai litellm sentence-transformers pandas rich
+```
+
+### 1.2  Create / warm a LinkedIn browser profile
+```bash
+crwl profiles
+```
+1. The interactive shell shows **New profile** – hit **enter**.
+2. Choose a name, e.g. `profile_linkedin_uc`.
+3. A Chromium window opens – log in to LinkedIn, solve whatever CAPTCHA, then close.
+
+> Remember the **profile name**. All future runs take `--profile-name <your_name>`.
+
+---
+
+## 2  Discovery – scrape companies & people
+
+```bash
+python c4ai_discover.py full \
+  --query "health insurance management" \
+  --geo 102713980 \               # Malaysia geoUrn
+  --title-filters "" \            # or "Product,Engineering"
+  --max-companies 10 \            # default set small for workshops
+  --max-people 20 \               # \^ same
+  --profile-name profile_linkedin_uc \
+  --outdir ./data \
+  --concurrency 2 \
+  --log-level debug
+```
+**Outputs** in `./data/`:
+* `companies.jsonl` – one JSON per company
+* `people.jsonl` – one JSON per employee
+
+🛠️  **Dry‑run:** `C4AI_DEMO_DEBUG=1 python c4ai_discover.py full --query coffee` uses bundled HTML snippets, no network.
+
+### Handy geoUrn cheatsheet
+| Location | geoUrn |
+|----------|--------|
+| Singapore | **103644278** |
+| Malaysia | **102713980** |
+| United States | **103644922** |
+| United Kingdom | **102221843** |
+| Australia | **101452733** |
+_See more: <https://www.linkedin.com/search/results/companies/?geoUrn=XXX> – the number after `geoUrn=` is what you need._
+
+---
+
+## 3  Insights – embeddings, org‑charts, decision makers
+
+```bash
+python c4ai_insights.py \
+  --in ./data \
+  --out ./data \
+  --embed-model all-MiniLM-L6-v2 \
+  --llm-provider gemini/gemini-2.0-flash \
+  --llm-api-key "" \
+  --top-k 10 \
+  --max-llm-tokens 8024 \
+  --llm-temperature 1.0 \
+  --workers 4
+```
+Emits next to the Stage‑1 files:
+* `company_graph.json` – inter‑company similarity graph
+* `org_chart_<handle>.json` – one per company
+* `decision_makers.csv` – hand‑picked ‘who to pitch’ list
+
+Flags reference (straight from `build_arg_parser()`):
+| Flag | Default | Purpose |
+|------|---------|---------|
+| `--in` | `.` | Stage‑1 output dir |
+| `--out` | `.` | Destination dir |
+| `--embed_model` | `all-MiniLM-L6-v2` | Sentence‑Transformer model |
+| `--top_k` | `10` | Neighbours per company in graph |
+| `--openai_model` | `gpt-4.1` | LLM for scoring decision makers |
+| `--max_llm_tokens` | `8024` | Token budget per LLM call |
+| `--llm_temperature` | `1.0` | Creativity knob |
+| `--stub` | off | Skip OpenAI and fabricate tiny charts |
+| `--workers` | `4` | Parallel LLM workers |
+
+---
+
+## 4  Visualise – interactive graph
+
+After Stage 2 completes, simply open the HTML viewer from the project root:
+```bash
+open graph_view_template.html   # or Live Server / Python -http
+```
+The page fetches `data/company_graph.json` and the `org_chart_*.json` files automatically; keep the `data/` folder beside the HTML file.
+
+* Left pane → list of companies (clans).
+* Click a node to load its org‑chart on the right.
+* Chat drawer lets you ask follow‑up questions; context is pulled from `people.jsonl`.
+
+---
+
+## 5  Common snags
+
+| Symptom | Fix |
+|---------|-----|
+| Infinite CAPTCHA | Use a residential proxy: `--proxy http://user:pass@ip:port` |
+| 429 Too Many Requests | Lower `--concurrency`, rotate profile, add delay |
+| Blank graph | Check JSON paths, clear `localStorage` in browser |
+
+---
+
+### TL;DR
+`crwl profiles` → `c4ai_discover.py` → `c4ai_insights.py` → open `graph_view_template.html`.  
+Live long and `import crawl4ai`.
+

docs/apps/linkdin/c4ai_discover.py

@@ -0,0 +1,446 @@
+#!/usr/bin/env python3
+"""
+c4ai-discover — Stage‑1 Discovery CLI
+
+Scrapes LinkedIn company search + their people pages and dumps two newline‑delimited
+JSON files: companies.jsonl and people.jsonl.
+
+Key design rules
+----------------
+* No BeautifulSoup — Crawl4AI only for network + HTML fetch.
+* JsonCssExtractionStrategy for structured scraping; schema auto‑generated once
+  from sample HTML provided by user and then cached under ./schemas/.
+* Defaults are embedded so the file runs inside VS Code debugger without CLI args.
+* If executed as a console script (argv > 1), CLI flags win.
+* Lightweight deps: argparse + Crawl4AI stack.
+
+Author: Tom @ Kidocode 2025‑04‑26
+"""
+from __future__ import annotations
+
+import warnings, re
+warnings.filterwarnings(
+    "ignore",
+    message=r"The pseudo class ':contains' is deprecated, ':-soup-contains' should be used.*",
+    category=FutureWarning,
+    module=r"soupsieve"
+)
+
+
+# ───────────────────────────────────────────────────────────────────────────────
+# Imports
+# ───────────────────────────────────────────────────────────────────────────────
+import argparse
+import random
+import asyncio
+import json
+import logging
+import os
+import pathlib
+import sys
+# 3rd-party rich for pretty logging
+from rich.console import Console
+from rich.logging import RichHandler
+
+from datetime import datetime, UTC
+from textwrap import dedent
+from types import SimpleNamespace
+from typing import Dict, List, Optional
+from urllib.parse import quote
+from pathlib import Path
+from glob import glob
+
+from crawl4ai import (
+    AsyncWebCrawler,
+    BrowserConfig,
+    CacheMode,
+    CrawlerRunConfig,
+    JsonCssExtractionStrategy,
+    BrowserProfiler,
+    LLMConfig,
+)
+
+# ───────────────────────────────────────────────────────────────────────────────
+# Constants / paths
+# ───────────────────────────────────────────────────────────────────────────────
+BASE_DIR = pathlib.Path(__file__).resolve().parent
+SCHEMA_DIR = BASE_DIR / "schemas"
+SCHEMA_DIR.mkdir(parents=True, exist_ok=True)
+COMPANY_SCHEMA_PATH = SCHEMA_DIR / "company_card.json"
+PEOPLE_SCHEMA_PATH = SCHEMA_DIR / "people_card.json"
+
+# ---------- deterministic target JSON examples ----------
+_COMPANY_SCHEMA_EXAMPLE = {
+    "handle": "/company/posify/",
+    "profile_image": "https://media.licdn.com/dms/image/v2/.../logo.jpg",
+    "name": "Management Research Services, Inc. (MRS, Inc)",
+    "descriptor": "Insurance • Milwaukee, Wisconsin",
+    "about": "Insurance • Milwaukee, Wisconsin",
+    "followers": 1000
+}
+
+_PEOPLE_SCHEMA_EXAMPLE = {
+    "profile_url": "https://www.linkedin.com/in/lily-ng/",
+    "name": "Lily Ng",
+    "headline": "VP Product @ Posify",
+    "followers": 890,
+    "connection_degree": "2nd",
+    "avatar_url": "https://media.licdn.com/dms/image/v2/.../lily.jpg"
+}
+
+# Provided sample HTML snippets (trimmed) — used exactly once to cold‑generate schema.
+_SAMPLE_COMPANY_HTML = (Path(__file__).resolve().parent / "snippets/company.html").read_text()
+_SAMPLE_PEOPLE_HTML = (Path(__file__).resolve().parent / "snippets/people.html").read_text()
+
+# --------- tighter schema prompts ----------
+_COMPANY_SCHEMA_QUERY = dedent(
+    """
+    Using the supplied <li> company-card HTML, build a JsonCssExtractionStrategy schema that,
+    for every card, outputs *exactly* the keys shown in the example JSON below.
+    JSON spec:
+      • handle        – href of the outermost <a> that wraps the logo/title, e.g. "/company/posify/"
+      • profile_image – absolute URL of the <img> inside that link
+      • name          – text of the <a> inside the <span class*='t-16'>
+      • descriptor    – text line with industry • location
+      • about         – text of the <div class*='t-normal'> below the name (industry + geo)
+      • followers     – integer parsed from the <div> containing 'followers'
+      
+    IMPORTANT: Do not use the base64 kind of classes to target element. It's not reliable.
+    The main div parent contains these li element is "div.search-results-container" you can use this.
+    The <ul> parent has "role" equal to "list". Using these two should be enough to target the <li> elements.    
+
+    IMPORTANT: Remember there might be multiple <a> tags that start with https://www.linkedin.com/company/[NAME], 
+    so in case you refer to them for different fields, make sure to be more specific. One has the image, and one 
+    has the person's name.
+    
+    IMPORTANT: Be very smart in selecting the correct and unique way to address the element. You should ensure 
+    your selector points to a single element and is unique to the place that contains the information.
+    """
+)
+
+_PEOPLE_SCHEMA_QUERY = dedent(
+    """
+    Using the supplied <li> people-card HTML, build a JsonCssExtractionStrategy schema that
+    outputs exactly the keys in the example JSON below.
+    Fields:
+      • profile_url        – href of the outermost profile link
+      • name               – text inside artdeco-entity-lockup__title
+      • headline           – inner text of artdeco-entity-lockup__subtitle
+      • followers          – integer parsed from the span inside lt-line-clamp--multi-line
+      • connection_degree  – '1st', '2nd', etc. from artdeco-entity-lockup__badge
+      • avatar_url         – src of the <img> within artdeco-entity-lockup__image
+      
+    IMPORTANT: Do not use the base64 kind of classes to target element. It's not reliable.
+    The main div parent contains these li element is a "div" has these classes "artdeco-card org-people-profile-card__card-spacing org-people__card-margin-bottom".
+    """
+)
+
+# ---------------------------------------------------------------------------
+# Utility helpers
+# ---------------------------------------------------------------------------
+
+def _load_or_build_schema(
+    path: pathlib.Path, 
+    sample_html: str, 
+    query: str, 
+    example_json: Dict,
+    force = False
+) -> Dict:
+    """Load schema from path, else call generate_schema once and persist."""
+    if path.exists() and not force:
+        return json.loads(path.read_text())
+
+    logging.info("[SCHEMA] Generating schema %s", path.name)
+    schema = JsonCssExtractionStrategy.generate_schema(
+        html=sample_html,
+        llm_config=LLMConfig(
+            provider=os.getenv("C4AI_SCHEMA_PROVIDER", "openai/gpt-4o"),
+            api_token=os.getenv("OPENAI_API_KEY", "env:OPENAI_API_KEY"),
+        ),
+        query=query,
+        target_json_example=json.dumps(example_json, indent=2),
+    )
+    path.write_text(json.dumps(schema, indent=2))
+    return schema
+
+
+def _openai_friendly_number(text: str) -> Optional[int]:
+    """Extract first int from text like '1K followers' (returns 1000)."""
+    import re
+
+    m = re.search(r"(\d[\d,]*)", text.replace(",", ""))
+    if not m:
+        return None
+    val = int(m.group(1))
+    if "k" in text.lower():
+        val *= 1000
+    if "m" in text.lower():
+        val *= 1_000_000
+    return val
+
+# ---------------------------------------------------------------------------
+# Core async workers
+# ---------------------------------------------------------------------------
+async def crawl_company_search(crawler: AsyncWebCrawler, url: str, schema: Dict, limit: int) -> List[Dict]:
+    """Paginate 10-item company search pages until `limit` reached."""
+    extraction = JsonCssExtractionStrategy(schema)
+    cfg = CrawlerRunConfig(
+        extraction_strategy=extraction,
+        cache_mode=CacheMode.BYPASS,
+        wait_for = ".search-marvel-srp",
+        session_id="company_search",
+        delay_before_return_html=1,
+        magic = True,
+        verbose= False,
+    )
+    companies, page = [], 1
+    while len(companies) < max(limit, 10):
+        paged_url = f"{url}&page={page}"
+        res = await crawler.arun(paged_url, config=cfg)
+        batch = json.loads(res[0].extracted_content)
+        if not batch:
+            break
+        for item in batch:
+            name = item.get("name", "").strip()
+            handle = item.get("handle", "").strip()
+            if not handle or not name:
+                continue
+            descriptor = item.get("descriptor")
+            about = item.get("about")
+            followers = _openai_friendly_number(str(item.get("followers", "")))
+            companies.append(
+                {
+                    "handle": handle,
+                    "name": name,
+                    "descriptor": descriptor,
+                    "about": about,
+                    "followers": followers,
+                    "people_url": f"{handle}people/",
+                    "captured_at": datetime.now(UTC).isoformat(timespec="seconds") + "Z",
+                }
+            )
+        page += 1
+        logging.info(
+            f"[dim]Page {page}[/] — running total: {len(companies)}/{limit} companies"
+        )
+
+    return companies[:max(limit, 10)]
+
+
+async def crawl_people_page(
+    crawler: AsyncWebCrawler,
+    people_url: str,
+    schema: Dict,
+    limit: int,
+    title_kw: str,
+) -> List[Dict]:
+    people_u = f"{people_url}?keywords={quote(title_kw)}"
+    extraction = JsonCssExtractionStrategy(schema)
+    cfg = CrawlerRunConfig(
+        extraction_strategy=extraction,
+        # scan_full_page=True,
+        cache_mode=CacheMode.BYPASS,
+        magic=True,
+        wait_for=".org-people-profile-card__card-spacing",
+        wait_for_images=5000,
+        delay_before_return_html=1,
+        session_id="people_search",
+    )
+    res = await crawler.arun(people_u, config=cfg)
+    if not res[0].success:
+        return []
+    raw = json.loads(res[0].extracted_content)
+    people = []
+    for p in raw[:limit]:
+        followers = _openai_friendly_number(str(p.get("followers", "")))
+        people.append(
+            {
+                "profile_url": p.get("profile_url"),
+                "name": p.get("name"),
+                "headline": p.get("headline"),
+                "followers": followers,
+                "connection_degree": p.get("connection_degree"),
+                "avatar_url": p.get("avatar_url"),
+            }
+        )
+    return people
+
+# ---------------------------------------------------------------------------
+# CLI + main
+# ---------------------------------------------------------------------------
+
+def build_arg_parser() -> argparse.ArgumentParser:
+    ap = argparse.ArgumentParser("c4ai-discover — Crawl4AI LinkedIn discovery")
+    sub = ap.add_subparsers(dest="cmd", required=False, help="run scope")
+
+    def add_flags(parser: argparse.ArgumentParser):
+        parser.add_argument("--query", required=False, help="query keyword(s)")
+        parser.add_argument("--geo", required=False, type=int, help="LinkedIn geoUrn")
+        parser.add_argument("--title-filters", default="Product,Engineering", help="comma list of job keywords")
+        parser.add_argument("--max-companies", type=int, default=1000)
+        parser.add_argument("--max-people", type=int, default=500)
+        parser.add_argument("--profile-name", default=str(pathlib.Path.home() / ".crawl4ai/profiles/profile_linkedin_uc"))
+        parser.add_argument("--outdir", default="./output")
+        parser.add_argument("--concurrency", type=int, default=4)
+        parser.add_argument("--log-level", default="info", choices=["debug", "info", "warn", "error"])
+
+    add_flags(sub.add_parser("full"))
+    add_flags(sub.add_parser("companies"))
+    add_flags(sub.add_parser("people"))
+
+    # global flags
+    ap.add_argument(
+        "--debug",
+        action="store_true",
+        help="Use built-in demo defaults (same as C4AI_DEMO_DEBUG=1)",
+    )
+    return ap
+
+
+def detect_debug_defaults(force = False) -> SimpleNamespace:
+    if not force and sys.gettrace() is None and not os.getenv("C4AI_DEMO_DEBUG"):
+        return SimpleNamespace()
+    # ----- debug‑friendly defaults -----
+    return SimpleNamespace(
+        cmd="full",
+        query="health insurance management",
+        geo=102713980,
+        # title_filters="Product,Engineering",
+        title_filters="",
+        max_companies=10,
+        max_people=5,
+        profile_name="profile_linkedin_uc",
+        outdir="./debug_out",
+        concurrency=2,
+        log_level="debug",
+    )
+
+
+async def async_main(opts):
+    # ─────────── logging setup ───────────
+    console = Console()
+    logging.basicConfig(
+        level=opts.log_level.upper(),
+        format="%(message)s",
+        handlers=[RichHandler(console=console, markup=True, rich_tracebacks=True)],
+    )
+
+    # -------------------------------------------------------------------
+    # Load or build schemas (one‑time LLM call each)
+    # -------------------------------------------------------------------
+    company_schema = _load_or_build_schema(
+        COMPANY_SCHEMA_PATH,
+        _SAMPLE_COMPANY_HTML,
+        _COMPANY_SCHEMA_QUERY,
+        _COMPANY_SCHEMA_EXAMPLE,
+        # True
+    )
+    people_schema = _load_or_build_schema(
+        PEOPLE_SCHEMA_PATH,
+        _SAMPLE_PEOPLE_HTML,
+        _PEOPLE_SCHEMA_QUERY,
+        _PEOPLE_SCHEMA_EXAMPLE,
+        # True
+    )
+
+    outdir = BASE_DIR / pathlib.Path(opts.outdir)
+    outdir.mkdir(parents=True, exist_ok=True)
+    f_companies = (BASE_DIR / outdir / "companies.jsonl").open("a", encoding="utf-8")
+    f_people = (BASE_DIR / outdir / "people.jsonl").open("a", encoding="utf-8")
+
+    # -------------------------------------------------------------------
+    # Prepare crawler with cookie pool rotation
+    # -------------------------------------------------------------------
+    profiler = BrowserProfiler()
+    path = profiler.get_profile_path(opts.profile_name)
+    bc = BrowserConfig(
+        headless=False,        
+        verbose=False,
+        user_data_dir=path,
+        use_managed_browser=True,
+        user_agent_mode = "random",
+        user_agent_generator_config= {
+            "platforms": "mobile",
+            "os": "Android"
+        }
+    )
+    crawler = AsyncWebCrawler(config=bc)
+    
+    await crawler.start()
+
+    # Single worker for simplicity; concurrency can be scaled by arun_many if needed.
+    # crawler = await next_crawler().start()
+    try:
+        # Build LinkedIn search URL
+        search_url = f'https://www.linkedin.com/search/results/companies/?keywords={quote(opts.query)}&companyHqGeo="{opts.geo}"'
+        logging.info("Seed URL => %s", search_url)
+
+        companies: List[Dict] = []
+        if opts.cmd in ("companies", "full"):
+            companies = await crawl_company_search(
+                crawler, search_url, company_schema, opts.max_companies
+            )
+            for c in companies:
+                f_companies.write(json.dumps(c, ensure_ascii=False) + "\n")
+            logging.info(f"[bold green]✓[/] Companies scraped so far: {len(companies)}")
+
+        if opts.cmd in ("people", "full"):
+            if not companies:
+                # load from previous run
+                src = outdir / "companies.jsonl"
+                if not src.exists():
+                    logging.error("companies.jsonl missing — run companies/full first")
+                    return 10
+                companies = [json.loads(l) for l in src.read_text().splitlines()]
+            total_people = 0
+            title_kw = " ".join([t.strip() for t in opts.title_filters.split(",") if t.strip()]) if opts.title_filters else ""
+            for comp in companies:
+                people = await crawl_people_page(
+                    crawler,
+                    comp["people_url"],
+                    people_schema,
+                    opts.max_people,
+                    title_kw,
+                )
+                for p in people:
+                    rec = p | {
+                        "company_handle": comp["handle"],
+                        # "captured_at": datetime.now(UTC).isoformat(timespec="seconds") + "Z",
+                        "captured_at": datetime.now(UTC).isoformat(timespec="seconds") + "Z",
+                    }
+                    f_people.write(json.dumps(rec, ensure_ascii=False) + "\n")
+                total_people += len(people)
+                logging.info(
+                    f"{comp['name']} — [cyan]{len(people)}[/] people extracted"
+                )
+                await asyncio.sleep(random.uniform(0.5, 1))
+            logging.info("Total people scraped: %d", total_people)
+    finally:
+        await crawler.close()
+        f_companies.close()
+        f_people.close()
+
+    return 0
+
+
+def main():
+    parser = build_arg_parser()
+    cli_opts = parser.parse_args()
+
+    # decide on debug defaults
+    if cli_opts.debug:
+        opts = detect_debug_defaults(force=True)
+        cli_opts = opts
+    else:
+        env_defaults = detect_debug_defaults()
+        opts = env_defaults if env_defaults else cli_opts
+
+    if not getattr(opts, "cmd", None):
+        opts.cmd = "full"
+
+    exit_code = asyncio.run(async_main(cli_opts))
+    sys.exit(exit_code)
+
+
+if __name__ == "__main__":
+    main()

docs/apps/linkdin/c4ai_insights.py

@@ -0,0 +1,381 @@
+#!/usr/bin/env python3
+"""
+Stage-2 Insights builder
+------------------------
+Reads companies.jsonl & people.jsonl (Stage-1 output) and produces:
+ • company_graph.json
+ • org_chart_<handle>.json  (one per company)
+ • decision_makers.csv
+ • graph_view.html          (interactive visualisation)
+
+Run:
+    python c4ai_insights.py --in ./stage1_out --out ./stage2_out
+
+Author : Tom @ Kidocode, 2025-04-28
+"""
+
+from __future__ import annotations
+
+# ───────────────────────────────────────────────────────────────────────────────
+# Imports & Third-party
+# ───────────────────────────────────────────────────────────────────────────────
+
+import argparse, asyncio, json, pathlib, random
+from datetime import datetime, UTC
+from types import SimpleNamespace
+from pathlib import Path
+from typing import List, Dict, Any
+# Pretty CLI UX
+from rich.console import Console
+from rich.logging import RichHandler
+from rich.progress import Progress, SpinnerColumn, BarColumn, TextColumn, TimeElapsedColumn
+
+
+# ───────────────────────────────────────────────────────────────────────────────
+
+BASE_DIR = pathlib.Path(__file__).resolve().parent
+
+# ───────────────────────────────────────────────────────────────────────────────
+# 3rd-party deps
+# ───────────────────────────────────────────────────────────────────────────────
+import numpy as np
+# from sentence_transformers import SentenceTransformer
+# from sklearn.metrics.pairwise import cosine_similarity
+import pandas as pd
+import hashlib
+
+from litellm import completion   #Support any LLM Provider
+
+
+
+# ───────────────────────────────────────────────────────────────────────────────
+# Utils
+# ───────────────────────────────────────────────────────────────────────────────
+def load_jsonl(path: Path) -> List[Dict[str, Any]]:
+    with open(path, "r", encoding="utf-8") as f:
+        return [json.loads(l) for l in f]
+
+def dump_json(obj, path: Path):
+    with open(path, "w", encoding="utf-8") as f:
+        json.dump(obj, f, ensure_ascii=False, indent=2)
+
+# ───────────────────────────────────────────────────────────────────────────────
+# Constants
+# ───────────────────────────────────────────────────────────────────────────────
+BASE_DIR = pathlib.Path(__file__).resolve().parent
+
+# ───────────────────────────────────────────────────────────────────────────────
+# Debug defaults   (mirrors Stage-1 trick)
+# ───────────────────────────────────────────────────────────────────────────────
+def dev_defaults() -> SimpleNamespace:
+    return SimpleNamespace(
+        in_dir="./samples",          
+        out_dir="./samples/insights",
+        embed_model="all-MiniLM-L6-v2",
+        top_k=10,
+        llm_provider="openai/gpt-4.1", 
+        llm_api_key=None,
+        max_llm_tokens=8000,
+        llm_temperature=1.0,
+        stub=False,  # Set to True to use a stub for org-chart inference
+        llm_base_url=None,  # e.g., "https://api.openai.com/v1" for OpenAI
+        workers=4
+    )
+
+# ───────────────────────────────────────────────────────────────────────────────
+# Graph builders
+# ───────────────────────────────────────────────────────────────────────────────
+def embed_descriptions(companies, model_name:str, opts) -> np.ndarray:
+    from sentence_transformers import SentenceTransformer
+
+    console = Console()
+    console.print(f"Using embedding model: [bold cyan]{model_name}[/]")
+    cache_path = BASE_DIR / Path(opts.out_dir) / "embeds_cache.json"
+    cache = {}
+    if cache_path.exists():
+        with open(cache_path) as f:
+            cache = json.load(f)
+        # flush cache if model differs
+        if cache.get("_model") != model_name:
+            cache = {}
+
+    model = SentenceTransformer(model_name)
+    new_texts, new_indices = [], []
+    vectors = np.zeros((len(companies), 384), dtype=np.float32)
+
+    for idx, comp in enumerate(companies):
+        text = comp.get("about") or comp.get("descriptor","")
+        h = hashlib.sha1(text.encode("utf-8")).hexdigest()
+        cached = cache.get(comp["handle"])
+        if cached and cached["hash"] == h:
+            vectors[idx] = np.array(cached["vector"], dtype=np.float32)
+        else:
+            new_texts.append(text)
+            new_indices.append((idx, comp["handle"], h))
+
+    if new_texts:
+        embeds = model.encode(new_texts, show_progress_bar=False, convert_to_numpy=True)
+        for vec, (idx, handle, h) in zip(embeds, new_indices):
+            vectors[idx] = vec
+            cache[handle] = {"hash": h, "vector": vec.tolist()}
+        cache["_model"] = model_name
+        with open(cache_path, "w") as f:
+            json.dump(cache, f)
+
+    return vectors
+
+def build_company_graph(companies, embeds:np.ndarray, top_k:int) -> Dict[str,Any]:
+    from sklearn.metrics.pairwise import cosine_similarity
+    sims = cosine_similarity(embeds)
+    nodes, edges = [], []
+    for i,c in enumerate(companies):
+        node = dict(
+            id=c["handle"].strip("/"),
+            name=c["name"],
+            handle=c["handle"],
+            about=c.get("about",""),
+            people_url=c.get("people_url",""),
+            industry=c.get("descriptor","").split("•")[0].strip(),
+            geoUrn=c.get("geoUrn"),
+            followers=c.get("followers",0),
+            # desc_embed=embeds[i].tolist(),
+            desc_embed=[],
+        )
+        nodes.append(node)
+        # pick top-k most similar except itself
+        top_idx = np.argsort(sims[i])[::-1][1:top_k+1]
+        for j in top_idx:
+            tgt = companies[j]
+            weight = float(sims[i,j])
+            if node["industry"] == tgt.get("descriptor","").split("•")[0].strip():
+                weight += 0.10
+            if node["geoUrn"] == tgt.get("geoUrn"):
+                weight += 0.05
+            tgt['followers'] = tgt.get("followers", None) or 1
+            node["followers"] = node.get("followers", None) or 1
+            follower_ratio = min(node["followers"], tgt.get("followers",1)) / max(node["followers"] or 1, tgt.get("followers",1))
+            weight += 0.05 * follower_ratio
+            edges.append(dict(
+                source=node["id"],
+                target=tgt["handle"].strip("/"),
+                weight=round(weight,4),
+                drivers=dict(
+                    embed_sim=round(float(sims[i,j]),4),
+                    industry_match=0.10 if node["industry"] == tgt.get("descriptor","").split("•")[0].strip() else 0,
+                    geo_overlap=0.05 if node["geoUrn"] == tgt.get("geoUrn") else 0,
+                )
+            ))
+    # return {"nodes":nodes,"edges":edges,"meta":{"generated_at":datetime.now(UTC).isoformat()}}
+    return {"nodes":nodes,"edges":edges,"meta":{"generated_at":datetime.now(UTC).isoformat()}}
+
+# ───────────────────────────────────────────────────────────────────────────────
+# Org-chart via LLM
+# ───────────────────────────────────────────────────────────────────────────────
+async def infer_org_chart_llm(company, people, llm_provider:str, api_key:str, max_tokens:int, temperature:float, stub:bool=False, base_url:str=None):
+    if stub:
+        # Tiny fake org-chart when debugging offline
+        chief = random.choice(people)
+        nodes = [{
+            "id": chief["profile_url"],
+            "name": chief["name"],
+            "title": chief["headline"],
+            "dept": chief["headline"].split()[:1][0],
+            "yoe_total": 8,
+            "yoe_current": 2,
+            "seniority_score": 0.8,
+            "decision_score": 0.9,
+            "avatar_url": chief.get("avatar_url")
+        }]
+        return {"nodes":nodes,"edges":[],"meta":{"debug_stub":True,"generated_at":datetime.now(UTC).isoformat()}}
+    
+    prompt = [
+        {"role":"system","content":"You are an expert B2B org-chart reasoner."},
+        {"role":"user","content":f"""Here is the company description:
+         
+<company>
+{json.dumps(company, ensure_ascii=False)}
+</company>
+                
+Here is a JSON list of employees:
+<employees>
+{json.dumps(people, ensure_ascii=False)}
+</employees>
+
+1) Build a reporting tree (manager -> direct reports)
+2) For each person output a decision_score 0-1 for buying new software
+
+Return JSON: {{ "nodes":[{{id,name,title,dept,yoe_total,yoe_current,seniority_score,decision_score,avatar_url,profile_url}}], "edges":[{{source,target,type,confidence}}] }}
+"""}
+    ]
+    resp = completion(
+        model=llm_provider,
+        messages=prompt,
+        max_tokens=max_tokens,
+        temperature=temperature,
+        response_format={"type":"json_object"},
+        api_key=api_key,
+        base_url=base_url
+    )
+    chart = json.loads(resp.choices[0].message.content)
+    chart["meta"] = dict(
+        model=llm_provider,
+        generated_at=datetime.now(UTC).isoformat()
+    )
+    return chart
+
+# ───────────────────────────────────────────────────────────────────────────────
+# CSV flatten
+# ───────────────────────────────────────────────────────────────────────────────
+def export_decision_makers(charts_dir:Path, csv_path:Path, threshold:float=0.5):
+    rows=[]
+    for p in charts_dir.glob("org_chart_*.json"):
+        data=json.loads(p.read_text())
+        comp = p.stem.split("org_chart_")[1]
+        for n in data.get("nodes",[]):
+            if n.get("decision_score",0)>=threshold:
+                rows.append(dict(
+                    company=comp,
+                    person=n["name"],
+                    title=n["title"],
+                    decision_score=n["decision_score"],
+                    profile_url=n["id"]
+                ))
+    pd.DataFrame(rows).to_csv(csv_path,index=False)
+
+# ───────────────────────────────────────────────────────────────────────────────
+# HTML rendering
+# ───────────────────────────────────────────────────────────────────────────────
+def render_html(out:Path, template_dir:Path):
+    # From template folder cp graph_view.html and ai.js in out folder
+    import shutil
+    shutil.copy(template_dir/"graph_view_template.html", out / "graph_view.html")
+    shutil.copy(template_dir/"ai.js", out)
+
+
+# ───────────────────────────────────────────────────────────────────────────────
+# Main async pipeline
+# ───────────────────────────────────────────────────────────────────────────────
+async def run(opts):
+    # ── silence SDK noise ──────────────────────────────────────────────────────
+    # for noisy in ("openai", "httpx", "httpcore"):
+    #     lg = logging.getLogger(noisy)
+    #     lg.setLevel(logging.WARNING)     # or ERROR if you want total silence
+    #     lg.propagate = False             # optional: stop them reaching root
+
+    # ────────────── logging bootstrap ──────────────
+    console = Console()
+    # logging.basicConfig(
+    #     level="INFO",
+    #     format="%(message)s",
+    #     handlers=[RichHandler(console=console, markup=True, rich_tracebacks=True)],
+    # )
+
+    in_dir  = BASE_DIR / Path(opts.in_dir)
+    out_dir = BASE_DIR / Path(opts.out_dir)
+    out_dir.mkdir(parents=True, exist_ok=True)
+
+    companies = load_jsonl(in_dir/"companies.jsonl")
+    people    = load_jsonl(in_dir/"people.jsonl")
+
+    console.print(f"[bold cyan]Loaded[/] {len(companies)} companies, {len(people)} people")
+
+    console.print("[bold]⇢[/] Embedding company descriptions…")
+    embeds = embed_descriptions(companies, opts.embed_model, opts)
+    
+    console.print("[bold]⇢[/] Building similarity graph")
+    company_graph = build_company_graph(companies, embeds, opts.top_k)
+    dump_json(company_graph, out_dir/"company_graph.json")
+
+    # Filter companies that need processing
+    to_process = []
+    for comp in companies:
+        handle = comp["handle"].strip("/").replace("/","_")
+        out_file = out_dir/f"org_chart_{handle}.json"
+        if out_file.exists():
+            console.print(f"[green]✓[/] Skipping existing {comp['name']}")
+            continue
+        to_process.append(comp)
+    
+    
+    if not to_process:
+        console.print("[yellow]All companies already processed[/]")
+    else:
+        workers = getattr(opts, 'workers', 1)
+        parallel = workers > 1
+        
+        console.print(f"[bold]⇢[/] Inferring org-charts via LLM {f'(parallel={workers} workers)' if parallel else ''}")
+        
+        with Progress(
+            SpinnerColumn(),
+            BarColumn(),
+            TextColumn("[progress.description]{task.description}"),
+            TimeElapsedColumn(),
+            console=console,
+        ) as progress:
+            task = progress.add_task("Org charts", total=len(to_process))
+            
+            async def process_one(comp):
+                handle = comp["handle"].strip("/").replace("/","_")
+                persons = [p for p in people if p["company_handle"].strip("/") == comp["handle"].strip("/")]
+                chart = await infer_org_chart_llm(
+                    comp, persons,
+                    llm_provider=opts.llm_provider,
+                    api_key=opts.llm_api_key or None,
+                    max_tokens=opts.max_llm_tokens,
+                    temperature=opts.llm_temperature,
+                    stub=opts.stub or False,
+                    base_url=opts.llm_base_url or None
+                )
+                chart["meta"]["company"] = comp["name"]
+                
+                # Save the result immediately
+                dump_json(chart, out_dir/f"org_chart_{handle}.json")
+                
+                progress.update(task, advance=1, description=f"{comp['name']} ({len(persons)} ppl)")
+            
+            # Create tasks for all companies
+            tasks = [process_one(comp) for comp in to_process]
+            
+            # Process in batches based on worker count
+            semaphore = asyncio.Semaphore(workers)
+            
+            async def bounded_process(coro):
+                async with semaphore:
+                    return await coro
+            
+            # Run with concurrency control
+            await asyncio.gather(*(bounded_process(task) for task in tasks))
+
+    console.print("[bold]⇢[/] Flattening decision-makers CSV")
+    export_decision_makers(out_dir, out_dir/"decision_makers.csv")
+        
+    render_html(out_dir, template_dir=BASE_DIR/"templates")
+    console.print(f"[bold green]✓[/] Stage-2 artefacts written to {out_dir}")
+
+# ───────────────────────────────────────────────────────────────────────────────
+# CLI
+# ───────────────────────────────────────────────────────────────────────────────
+def build_arg_parser():
+    p = argparse.ArgumentParser(description="Build graphs & visualisation from Stage-1 output")
+    p.add_argument("--in",       dest="in_dir",  required=False, help="Stage-1 output dir", default=".")
+    p.add_argument("--out",      dest="out_dir", required=False, help="Destination dir",   default=".")
+    p.add_argument("--embed-model", default="all-MiniLM-L6-v2")
+    p.add_argument("--top-k", type=int, default=10, help="Top-k neighbours per company")
+    p.add_argument("--llm-provider", default="openai/gpt-4.1", 
+                  help="LLM model to use in format 'provider/model_name' (e.g., 'anthropic/claude-3')")
+    p.add_argument("--llm-api-key", help="API key for LLM provider (defaults to env vars)")
+    p.add_argument("--llm-base-url", help="Base URL for LLM API endpoint")
+    p.add_argument("--max-llm-tokens", type=int, default=8024)
+    p.add_argument("--llm-temperature", type=float, default=1.0)
+    p.add_argument("--stub", action="store_true", help="Skip OpenAI call and generate tiny fake org charts")
+    p.add_argument("--workers", type=int, default=4, help="Number of parallel workers for LLM inference")
+    return p
+
+def main():
+    dbg = dev_defaults()
+    opts = dbg if True else build_arg_parser().parse_args()
+    # opts = build_arg_parser().parse_args()
+    asyncio.run(run(opts))
+
+if __name__ == "__main__":
+    main()

docs/apps/linkdin/samples/companies.jsonl

@@ -0,0 +1,9 @@
+{"handle": "https://www.linkedin.com/company/healthpartnersng/", "name": "Health Partners HMO", "descriptor": "Hospitals and Health Care • Ikoyi, LAGOS", "about": "Healthpartners Ltd is a leading HMO in Nigeria providing affordablehealthinsuranceandhealthmanagementservices for companies and individuals in Nigeria.     We have several individual and group plans that meets yourhealthmanagementneeds.     Call us now at 0807-460-9165, 0807-714-0759 or email...", "followers": null, "people_url": "https://www.linkedin.com/company/healthpartnersng/people/", "captured_at": "2025-04-29T10:46:08Z"}
+{"handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "name": "Health & Insurance Management Services Organization", "descriptor": "Non-profit Organizations • Mbeya", "about": "Health&InsuranceManagementServices Organization (HIMSO) was established and registered in 2012 as a Non- Government Organization (NGO) with the aim...", "followers": 35, "people_url": "https://www.linkedin.com/company/health-insurance-management-services-organization/people/", "captured_at": "2025-04-29T13:15:04Z"}
+{"handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "name": "National Health Insurance Management Authority", "descriptor": "Insurance • Lusaka, Lusaka", "about": "The NationalHealthInsuranceManagementAuthority (NHIMA) is established pursuant to section 4 of the NationalHealthInsurance(NHI) Act No. 2 of 2018.  The compulsory NationalHealthInsurancescheme seeks to provide for a sound and reliable healthcare financing for Zambian households and the entirehealthsector...", "followers": null, "people_url": "https://www.linkedin.com/company/national-health-insurance-management-authority/people/", "captured_at": "2025-04-29T13:15:04Z"}
+{"handle": "https://www.linkedin.com/company/health-alliance-plan/", "name": "Health Alliance Plan", "descriptor": "Hospitals and Health Care • Detroit, MI", "about": "...organizations to enhance the lives of those we touch. We offer six distincthealthinsurancelines:     • Group Insured Commercial  • Individual  • Medicare  • Medicaid  • Self-Funded  • Network Leasing    HAP also provides:    • Award-winning wellness programs  • Community outreach  • Digitalhealthtools  • Diseasemanagement...", "followers": null, "people_url": "https://www.linkedin.com/company/health-alliance-plan/people/", "captured_at": "2025-04-29T13:15:04Z"}
+{"handle": "https://www.linkedin.com/company/insurance-recruiting-solutions/", "name": "Insurance Recruiting Solutions", "descriptor": "Insurance • Waukee, Iowa", "about": "InsuranceRecruiting Solutions provides staffing and recruiting services exclusively to theinsuranceindustry. We are committed to providing highly personalized recruiting services, tailored to each candidate and employer. With years ofinsuranceindustry experience, we speak your language. As a leading national...", "followers": null, "people_url": "https://www.linkedin.com/company/insurance-recruiting-solutions/people/", "captured_at": "2025-04-29T13:15:04Z"}
+{"handle": "https://www.linkedin.com/company/healthplanofsanmateo/", "name": "Health Plan of San Mateo (HPSM)", "descriptor": "Hospitals and Health Care • South San Francisco, California", "about": "TheHealthPlan of San Mateo (HPSM) is a local non-profithealthcare plan that offershealthcoverage and a provider network to San Mateo County's under-insured population. We currently serve more than 145,000 County residents.", "followers": null, "people_url": "https://www.linkedin.com/company/healthplanofsanmateo/people/", "captured_at": "2025-04-29T13:15:04Z"}
+{"handle": "https://www.linkedin.com/company/insurance-management-group_2/", "name": "Insurance Management Group", "descriptor": "Insurance • Marion, Indiana", "about": "InsuranceManagementGroup is an all-riskinsuranceagency with over 140 years of experience, specializing in Home, Auto, BusinessInsurance, Individual Life &Health, and Employee Benefits. We represent highly rated and financially soundinsurancecarriers, to ensure that our clients are getting the best coverage...", "followers": null, "people_url": "https://www.linkedin.com/company/insurance-management-group_2/people/", "captured_at": "2025-04-29T13:15:04Z"}
+{"handle": "https://www.linkedin.com/company/carecard-health-insurance-management-co/", "name": "CareCard Health Insurance Management Co", "descriptor": "Insurance • Damascus", "about": "CareCard offers Business Process Outsourcing (BPO) services toInsurance, Self Funded and Retireehealthplan market. CareCard provides operational outsourcing...", "followers": 187, "people_url": "https://www.linkedin.com/company/carecard-health-insurance-management-co/people/", "captured_at": "2025-04-29T13:15:04Z"}
+{"handle": "https://www.linkedin.com/company/healthcluster/", "name": "Health Cluster", "descriptor": "Technology, Information and Internet • Dubai", "about": "..., knowledge and interaction. The company has solutions and products inHealthTech, eHealth, DigitalHealth, Revenue CycleManagement– RCM Solutions, AI & ML, Internet...", "followers": null, "people_url": "https://www.linkedin.com/company/healthcluster/people/", "captured_at": "2025-04-29T13:15:04Z"}

docs/apps/linkdin/samples/people.jsonl

@@ -0,0 +1,108 @@
+{"profile_url": null, "name": "Yahya Ipuge", "headline": "Senior Health Specialist, Independent Consultant, Certified Board Director, Board Chair in NGO and Private Entities", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C4E03AQFuqPObSyLPMQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1517757008397?e=1751500800&v=beta&t=zaHc2CY7AJ-eX1MCSvazp8ny37iBAu3YsyaZjwq6gB0", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-29T13:15:33Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Field officer at Health and Insurance Management Services Organization", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C5103AQEVmdDwTIhsjQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1540989154156?e=1751500800&v=beta&t=7N0baJNfZ26dbrNNbv2055sbGlacQUwQu07wUTN0whs", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-29T13:15:33Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Medical Practitioner @ Health & Insurance | Master's Degree in Infection Control", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQHjMXy7dSmmLg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1725975429410?e=1751500800&v=beta&t=lDIL2KhDw471XYvtCrRfkHAnG3Q-npDJnwDdK0sYvpA", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-29T13:15:34Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "--", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-29T13:15:38Z"}
+{"profile_url": null, "name": "Fadhy Mtanga", "headline": "Executive Director at Health & Insurance Management Services Organization (HIMSO) Author | Creative Writer | Social Scientist", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4E03AQEloEreyg3qVQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1704391866585?e=1751500800&v=beta&t=86am-v3cjBPBldLTwgt8-AY-YbxFY6QZQzObwLTtMEA", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-29T13:15:38Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Business Administrator at Consultancy Business investments", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQEuKXJmknr2YA/profile-displayphoto-shrink_800_800/profile-displayphoto-shrink_800_800/0/1714545221728?e=1751500800&v=beta&t=zJG-rDZgYJJ0eROibf-Wag-v_JecCghwU3ul4TaH2Eg", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-29T13:15:48Z"}
+{"profile_url": null, "name": "Tamani Phiri", "headline": "Corporate Business Strategy | Thought Leadership | Corporate Governance", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQF4mFx8jY2n-w/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1730302954035?e=1751500800&v=beta&t=i4QIrHA6A9eLtKolwTRNhuoiaTad28sf5KHxAFuXG-w", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-29T13:15:48Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Member Service Assistant @ National Health Insurance Management Authority (NHIMA) | Clinical Officer | Health Insurance & Public Health | Claims Processing & Customer Support | Data & Policy Analyst", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQGob13KyxrB0g/profile-displayphoto-shrink_100_100/B4DZYCgreeHIAU-/0/1743798848889?e=1751500800&v=beta&t=uXxTsMLi5s7hr8FBEzVTDw7V3eJ85kpTaIC7i_5fM-Y", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-29T13:15:48Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Economist/ Development Analyst/ Planner/ Customer Care", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4E03AQFEc3EgfdpZeg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1727782989867?e=1751500800&v=beta&t=dWjKzSu5FDRgmxAVret9jQPhWF2VjcrnmEpR2LDMC1Q", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-29T13:15:48Z"}
+{"profile_url": null, "name": "Samantha Ngandwe", "headline": "Quality Assurance and Accreditation Officer at National Health Insurance Management Authority", "followers": 382, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQHyOjyoz7d95g/profile-displayphoto-shrink_100_100/B4DZYvvhP5GwAY-/0/1744557712084?e=1751500800&v=beta&t=DLYRpz20zmwUWx1UY1Dn-ykvgWBnwn8XHWLaDMf199M", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-29T13:15:48Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Dental Surgery Assistant at Health Promotion Board", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-29T13:16:11Z"}
+{"profile_url": null, "name": "Liz England Tucker", "headline": "Medical Performance Optimization", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQFY6yx360QunQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1713831102587?e=1751500800&v=beta&t=u-C8Ozpl_ITkTpdgt5QD-C5_Qt7MA0DagLRmiuGKngQ", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-29T13:16:11Z"}
+{"profile_url": null, "name": "Merrill Hausenfluck", "headline": "Chief Financial Officer", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4E03AQGKxDKRJM_BCg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1696292650180?e=1751500800&v=beta&t=NbUVC-QP-XL3frBpQcn3GtGrZ04Fl0xdko4V-mHxPag", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-29T13:16:11Z"}
+{"profile_url": null, "name": "Mike Treash", "headline": "Senior Vice President and Chief Operating Officer at Health Alliance Plan", "followers": 2000, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQH_c6tIq929gw/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1720478900599?e=1751500800&v=beta&t=l9RLnLDKBBJjJQTsFMJMa_1MpWCKcV4AUa3dcjGnSXQ", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-29T13:16:11Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Manager at Health Alliance Plan", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-29T13:16:11Z"}
+{"profile_url": null, "name": "Scot Dickerson", "headline": "Insurance Industry Specialist, Insurance Recruiter, Talent Acquisition, Talent Sourcing, Hiring Consultant, Career Consultant, Staffing, Executive Recruiter at Insurance Recruiting Solutions #insurancejobs #insurance", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQGLFvtPPU3HEw/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1724950672124?e=1751500800&v=beta&t=uT4SFSMF32O1d50Z0dbnd6zRRKdABHxSGlOZdxWdXBM", "company_handle": "https://www.linkedin.com/company/insurance-recruiting-solutions/", "captured_at": "2025-04-29T13:16:24Z"}
+{"profile_url": null, "name": "Steele Dickerson", "headline": "Insurance Recruiting Solutions", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQEyICWaE_PvXA/profile-displayphoto-shrink_100_100/B56ZQuDHyZH0Ac-/0/1735939358232?e=1751500800&v=beta&t=9FdnWHrjnPQ7LQ5FdwC7sY8sS6hm-R4zfWO5Vmwm46w", "company_handle": "https://www.linkedin.com/company/insurance-recruiting-solutions/", "captured_at": "2025-04-29T13:16:24Z"}
+{"profile_url": null, "name": "Madeline Judas", "headline": "Recruiting Operations & Business Development Specialist", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQG6xiTaJ71UiA/profile-displayphoto-shrink_100_100/B56ZU_N_jPHoAY-/0/1740522388021?e=1751500800&v=beta&t=CxvAsYgU0zelghZsRhUJOC26ILVovP3ZPn4nMnWkEJE", "company_handle": "https://www.linkedin.com/company/insurance-recruiting-solutions/", "captured_at": "2025-04-29T13:16:24Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "All Lines Claims Adjuster / General Lines Agent (Property & Casualty : Life, Accident, Health & HMO)", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQFTjkb7SxTWWg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1725920318474?e=1751500800&v=beta&t=BGEzQg1c2l8qxuy2iKJ896nElsiYcaWnhkf-mqc-KhY", "company_handle": "https://www.linkedin.com/company/insurance-recruiting-solutions/", "captured_at": "2025-04-29T13:16:24Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Clinical Pharmacy Manager at Health Plan of San Mateo (HPSM)", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C5603AQEPO0pZOxznoA/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1551565536585?e=1751500800&v=beta&t=qwMGzWX_Zefkciq8h2m9daLMflT0WoDr5F1R5pXvyM4", "company_handle": "https://www.linkedin.com/company/healthplanofsanmateo/", "captured_at": "2025-04-29T13:16:40Z"}
+{"profile_url": null, "name": "Tamana M.", "headline": "MPH Candidate at Brown University | Data Coordinator", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQEY3iDtFmpzlg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1714197678074?e=1751500800&v=beta&t=IsVT0uC7A-T-Tp22gZFDG9wiT7LMB5GmhccuI8f9c-I", "company_handle": "https://www.linkedin.com/company/healthplanofsanmateo/", "captured_at": "2025-04-29T13:16:40Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Program Manager", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/healthplanofsanmateo/", "captured_at": "2025-04-29T13:16:40Z"}
+{"profile_url": null, "name": "Mackenzie Baysinger Moniz, MSW", "headline": "Program Manager at Health Plan of San Mateo", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQHAd3A4zLyuWA/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1675716742150?e=1751500800&v=beta&t=ot3fMyJFnHwwNfKJiA_YxZp6MOK_iVGtSCUgVNq867g", "company_handle": "https://www.linkedin.com/company/healthplanofsanmateo/", "captured_at": "2025-04-29T13:16:40Z"}
+{"profile_url": null, "name": "John O.", "headline": "Healthcare Delivery Strategy Execution", "followers": null, "connection_degree": "· 3rd", "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/healthplanofsanmateo/", "captured_at": "2025-04-29T13:16:40Z"}
+{"profile_url": null, "name": "Daniel McQuilkin", "headline": "Senior Vice President", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C4E03AQFkScOqwhxvfQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1521406683682?e=1751500800&v=beta&t=iohhak3lrV1gpmA6dnoCxTRJidskfgmZUXKbNQbkxjs", "company_handle": "https://www.linkedin.com/company/insurance-management-group_2/", "captured_at": "2025-04-29T13:17:05Z"}
+{"profile_url": null, "name": "Tony Bonacuse", "headline": "Senior Vice President at Insurance Management Group", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C5603AQF_JJOFLjkZoQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1516269003018?e=1751500800&v=beta&t=0APZt5RNhvUj4IxsSdi7JO9KxezZzOH_WQCibn5Szgs", "company_handle": "https://www.linkedin.com/company/insurance-management-group_2/", "captured_at": "2025-04-29T13:17:05Z"}
+{"profile_url": null, "name": "Mark Bilger", "headline": "Director - Sr. Vice President at Insurance Management Group", "followers": 1000, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C4D03AQEzX5qUfqhd2g/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1663842785708?e=1751500800&v=beta&t=YyKXRQol0cDntoq8vbdxyaRvEFf0vWKNHPxk0cyWiG8", "company_handle": "https://www.linkedin.com/company/insurance-management-group_2/", "captured_at": "2025-04-29T13:17:05Z"}
+{"profile_url": null, "name": "Adam Young, MBA", "headline": "Husband | Father | Traveler | Sports Fanatic | Food Enthusiast | Independent Insurance Professional", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C5603AQErWIq1AVyxKg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1601480475688?e=1751500800&v=beta&t=jK_mhX0PkDdG8WBZaipIIYRDm1PnWIuFR7sCKDhDi6s", "company_handle": "https://www.linkedin.com/company/insurance-management-group_2/", "captured_at": "2025-04-29T13:17:05Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Senior Vice President at Insurance Management Group / Partner", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C5603AQH3dm30dXH82w/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1572228299104?e=1751500800&v=beta&t=iuBQYs4iLHJgRgjFbSA2YiNiAI8zDILqg-nVsLR9Qjk", "company_handle": "https://www.linkedin.com/company/insurance-management-group_2/", "captured_at": "2025-04-29T13:17:05Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Doctor at CareCard Health Insurance Management Co", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/carecard-health-insurance-management-co/", "captured_at": "2025-04-29T13:17:09Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Pharmacist", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C4D03AQHyPi4Amu_Dkw/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1640460490377?e=1751500800&v=beta&t=q7R_b7bD9CR-1-Dvu81WoEHN_ljHK16l6ioTIA0LN7Q", "company_handle": "https://www.linkedin.com/company/carecard-health-insurance-management-co/", "captured_at": "2025-04-29T13:17:09Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "IT Manager at CareCard Health Insurance Management Co", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/carecard-health-insurance-management-co/", "captured_at": "2025-04-29T13:17:09Z"}
+{"profile_url": null, "name": "Amal Shabani", "headline": "at carecard", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C5603AQFLzeP3yPkjgg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1519625412373?e=1751500800&v=beta&t=GULSoesSn83F_fYkkH_nPxWIjjs1d9Pucc3dUDNei6I", "company_handle": "https://www.linkedin.com/company/carecard-health-insurance-management-co/", "captured_at": "2025-04-29T13:17:09Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "--", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/carecard-health-insurance-management-co/", "captured_at": "2025-04-29T13:17:09Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Biologiste | Pharmaco-épidemiologie & Pharmaco-économie | Software Helath Care Management", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C4D03AQHOPXrX5-oeug/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1663013895834?e=1751500800&v=beta&t=yE2RGp0rfhcJkjh_vdM0VwpaPUtoPewM80lTlr20OHU", "company_handle": "https://www.linkedin.com/company/healthcluster/", "captured_at": "2025-04-29T13:17:14Z"}
+{"profile_url": null, "name": "Ruqaia Ali Alkhalifa", "headline": "‎‏ RN,BSN, MSN,NE Database Officer for Scholarship Programs and Central Committee rapporteur at Al-Ahsa Health Cluster.", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4E03AQGfNujqDnuZDA/profile-displayphoto-shrink_100_100/B4EZOvsQThH0AU-/0/1733819436577?e=1751500800&v=beta&t=jleAVvhbg0H85tSi9TG96x0fqdkS1oytfaU02LHsFEI", "company_handle": "https://www.linkedin.com/company/healthcluster/", "captured_at": "2025-04-29T13:17:14Z"}
+{"profile_url": null, "name": "Fahad Mohyuddin", "headline": "Healthcare AI Strategist | Digital Health | SaaS | Telehealth | HIS | EHR | IoT", "followers": 7000, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C4E03AQFLnPh8fu-HHg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1647320077586?e=1751500800&v=beta&t=S__knVzEVrGZuyqwszCe_5V_kawbG5tejmmEe3fkMJE", "company_handle": "https://www.linkedin.com/company/healthcluster/", "captured_at": "2025-04-29T13:17:14Z"}
+{"profile_url": null, "name": "Muhammad Moid Shams", "headline": "Azure DevOps | AWS Cloud Infrastructure| Freight Tech | Health Tech | HL7- NABIDH | HL7+ FHIR | KSA -NPHIES | FHIR - MOPH | HL7- Riayati | Freight Tech | Insure Tech | with Azure, Azure AI , PowerApps, D365 , M365", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQEzousRurY2Zg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1711283874675?e=1751500800&v=beta&t=ZheuoRIAkS_9M8WXafdwB1nJEuy-a5HEsrXlfOANx80", "company_handle": "https://www.linkedin.com/company/healthcluster/", "captured_at": "2025-04-29T13:17:14Z"}
+{"profile_url": null, "name": "Muhammad Shahzaib (PMP® - SCRUM®)", "headline": "PMP-Certified Project Manager | Health Care & Web Solutions Expert | Customer Success & Operations Management Expert | Business Transformation Expert", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4D35AQFyp7WcBZinYA/profile-framedphoto-shrink_100_100/profile-framedphoto-shrink_100_100/0/1730638721808?e=1746540000&v=beta&t=QoGze1AlotUfm3K9kMWG6ZGVHS3ADu38THVPlxlYUys", "company_handle": "https://www.linkedin.com/company/healthcluster/", "captured_at": "2025-04-29T13:17:14Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Music Professional at Health Options Worldwide", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C5103AQGF-Dp6v6nkGw/profile-displayphoto-shrink_800_800/profile-displayphoto-shrink_800_800/0/1585401654822?e=1751500800&v=beta&t=7yeO-dGz1p_B66cJVSlTSdAYJLMFFwxPIhwwcR8uWWo", "company_handle": "https://www.linkedin.com/company/health-options-worldwide/", "captured_at": "2025-04-29T13:17:17Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Trainer/instructor at Health Options Worldwide", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/health-options-worldwide/", "captured_at": "2025-04-29T13:17:17Z"}
+{"profile_url": null, "name": "Michael Akpoarebe-Isaac", "headline": "Chief Operating officer, Health Partners HMO", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C4E03AQE7KNFaLMyqYg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1602714385413?e=1751500800&v=beta&t=In5GaREqoXtO3sPCx9ZJJBwIPY4008ii13RPRl0w0Fw", "company_handle": "https://www.linkedin.com/company/healthpartnersng/", "captured_at": "2025-04-29T13:17:22Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "REGISTERED NURSE/CLAIMS SUPERVISOR/HEALTH EDUCATOR/ CASE MANAGER/ Lekki.", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4E35AQEEqf5i5pD76g/profile-framedphoto-shrink_100_100/profile-framedphoto-shrink_100_100/0/1724219552412?e=1746540000&v=beta&t=1PAfKEpQFL196LZHfY0wHAZ35TH0fRjku9ihSfDdOk4", "company_handle": "https://www.linkedin.com/company/healthpartnersng/", "captured_at": "2025-04-29T13:17:22Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Data Analyst|Dedicated Retention Officer Boosting Customer Loyalty| Business Developer/ Event planner", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4D35AQHIgeS1H7w65w/profile-framedphoto-shrink_100_100/B4DZV1QfcCGcAk-/0/1741429012517?e=1746540000&v=beta&t=NCIbW7MWY7Cy4YEC2xzLoX54-Lm5CNhorbuSQe0lZSk", "company_handle": "https://www.linkedin.com/company/healthpartnersng/", "captured_at": "2025-04-29T13:17:22Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Former Group managing director at Health Partners Ltd", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C4E03AQHPQPvIQbPQPg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1583328612508?e=1751500800&v=beta&t=LpynArccJCWrdWMSBvYLH4SI5G-xae7ECoWUUAl_CeU", "company_handle": "https://www.linkedin.com/company/healthpartnersng/", "captured_at": "2025-04-29T13:17:22Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "HEAD, FINCON, @ HEALTH PARTNERS (HMO) LTD", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C4D03AQG8XOvnazEibQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1518882054975?e=1751500800&v=beta&t=5gT6GAWGTqYfpvkjOk0ArvV73I_KspkWXgoG-VhoStg", "company_handle": "https://www.linkedin.com/company/healthpartnersng/", "captured_at": "2025-04-29T13:17:22Z"}
+{"profile_url": null, "name": "Yahya Ipuge", "headline": "Senior Health Specialist, Independent Consultant, Certified Board Director, Board Chair in NGO and Private Entities", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C4E03AQFuqPObSyLPMQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1517757008397?e=1751500800&v=beta&t=zaHc2CY7AJ-eX1MCSvazp8ny37iBAu3YsyaZjwq6gB0", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-30T07:36:39Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Field officer at Health and Insurance Management Services Organization", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C5103AQEVmdDwTIhsjQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1540989154156?e=1751500800&v=beta&t=7N0baJNfZ26dbrNNbv2055sbGlacQUwQu07wUTN0whs", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-30T07:36:39Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Medical Practitioner @ Health & Insurance | Master's Degree in Infection Control", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQHjMXy7dSmmLg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1725975429410?e=1751500800&v=beta&t=lDIL2KhDw471XYvtCrRfkHAnG3Q-npDJnwDdK0sYvpA", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-30T07:36:39Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "--", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-30T07:36:39Z"}
+{"profile_url": null, "name": "Fadhy Mtanga", "headline": "Executive Director at Health & Insurance Management Services Organization (HIMSO) Author | Creative Writer | Social Scientist", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4E03AQEloEreyg3qVQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1704391866585?e=1751500800&v=beta&t=86am-v3cjBPBldLTwgt8-AY-YbxFY6QZQzObwLTtMEA", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-30T07:36:39Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Member Service Assistant @ National Health Insurance Management Authority (NHIMA) | Clinical Officer | Health Insurance & Public Health | Claims Processing & Customer Support | Data & Policy Analyst", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQGob13KyxrB0g/profile-displayphoto-shrink_100_100/B4DZYCgreeHIAU-/0/1743798848889?e=1751500800&v=beta&t=uXxTsMLi5s7hr8FBEzVTDw7V3eJ85kpTaIC7i_5fM-Y", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-30T07:36:45Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Business Administrator at Consultancy Business investments", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQEuKXJmknr2YA/profile-displayphoto-shrink_800_800/profile-displayphoto-shrink_800_800/0/1714545221728?e=1751500800&v=beta&t=zJG-rDZgYJJ0eROibf-Wag-v_JecCghwU3ul4TaH2Eg", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-30T07:36:45Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Economist/ Development Analyst/ Planner/ Customer Care", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4E03AQFEc3EgfdpZeg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1727782989867?e=1751500800&v=beta&t=dWjKzSu5FDRgmxAVret9jQPhWF2VjcrnmEpR2LDMC1Q", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-30T07:36:45Z"}
+{"profile_url": null, "name": "Tamani Phiri", "headline": "Corporate Business Strategy | Thought Leadership | Corporate Governance", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQF4mFx8jY2n-w/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1730302954035?e=1751500800&v=beta&t=i4QIrHA6A9eLtKolwTRNhuoiaTad28sf5KHxAFuXG-w", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-30T07:36:45Z"}
+{"profile_url": null, "name": "Samantha Ngandwe", "headline": "Quality Assurance and Accreditation Officer at National Health Insurance Management Authority", "followers": 382, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQHyOjyoz7d95g/profile-displayphoto-shrink_100_100/B4DZYvvhP5GwAY-/0/1744557712084?e=1751500800&v=beta&t=DLYRpz20zmwUWx1UY1Dn-ykvgWBnwn8XHWLaDMf199M", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-30T07:36:45Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Dental Surgery Assistant at Health Promotion Board", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-30T07:36:51Z"}
+{"profile_url": null, "name": "Merrill Hausenfluck", "headline": "Chief Financial Officer", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4E03AQGKxDKRJM_BCg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1696292650180?e=1751500800&v=beta&t=NbUVC-QP-XL3frBpQcn3GtGrZ04Fl0xdko4V-mHxPag", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-30T07:36:51Z"}
+{"profile_url": null, "name": "Mike Treash", "headline": "Senior Vice President and Chief Operating Officer at Health Alliance Plan", "followers": 2000, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQH_c6tIq929gw/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1720478900599?e=1751500800&v=beta&t=l9RLnLDKBBJjJQTsFMJMa_1MpWCKcV4AUa3dcjGnSXQ", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-30T07:36:51Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Manager at Health Alliance Plan", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-30T07:36:51Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Manager, Government Programs at Health Alliance Plan", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C5603AQF473eFGZeIpQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1654455840818?e=1751500800&v=beta&t=FllKCznSi0Ndm75QYy2i5UDtflCojNGkVzRpoChPC8c", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-30T07:36:51Z"}
+{"profile_url": null, "name": "Steele Dickerson", "headline": "Insurance Recruiting Solutions", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQEyICWaE_PvXA/profile-displayphoto-shrink_100_100/B56ZQuDHyZH0Ac-/0/1735939358232?e=1751500800&v=beta&t=9FdnWHrjnPQ7LQ5FdwC7sY8sS6hm-R4zfWO5Vmwm46w", "company_handle": "https://www.linkedin.com/company/insurance-recruiting-solutions/", "captured_at": "2025-04-30T07:36:56Z"}
+{"profile_url": null, "name": "Yahya Ipuge", "headline": "Senior Health Specialist, Independent Consultant, Certified Board Director, Board Chair in NGO and Private Entities", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C4E03AQFuqPObSyLPMQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1517757008397?e=1751500800&v=beta&t=zaHc2CY7AJ-eX1MCSvazp8ny37iBAu3YsyaZjwq6gB0", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-30T07:44:32+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Field officer at Health and Insurance Management Services Organization", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C5103AQEVmdDwTIhsjQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1540989154156?e=1751500800&v=beta&t=7N0baJNfZ26dbrNNbv2055sbGlacQUwQu07wUTN0whs", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-30T07:44:32+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Medical Practitioner @ Health & Insurance | Master's Degree in Infection Control", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQHjMXy7dSmmLg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1725975429410?e=1751500800&v=beta&t=lDIL2KhDw471XYvtCrRfkHAnG3Q-npDJnwDdK0sYvpA", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-30T07:44:32+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "--", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-30T07:44:32+00:00Z"}
+{"profile_url": null, "name": "Fadhy Mtanga", "headline": "Executive Director at Health & Insurance Management Services Organization (HIMSO) Author | Creative Writer | Social Scientist", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4E03AQEloEreyg3qVQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1704391866585?e=1751500800&v=beta&t=86am-v3cjBPBldLTwgt8-AY-YbxFY6QZQzObwLTtMEA", "company_handle": "https://www.linkedin.com/company/health-insurance-management-services-organization/", "captured_at": "2025-04-30T07:44:32+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Member Service Assistant @ National Health Insurance Management Authority (NHIMA) | Clinical Officer | Health Insurance & Public Health | Claims Processing & Customer Support | Data & Policy Analyst", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQGob13KyxrB0g/profile-displayphoto-shrink_100_100/B4DZYCgreeHIAU-/0/1743798848889?e=1751500800&v=beta&t=uXxTsMLi5s7hr8FBEzVTDw7V3eJ85kpTaIC7i_5fM-Y", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-30T07:44:38+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Business Administrator at Consultancy Business investments", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQEuKXJmknr2YA/profile-displayphoto-shrink_800_800/profile-displayphoto-shrink_800_800/0/1714545221728?e=1751500800&v=beta&t=zJG-rDZgYJJ0eROibf-Wag-v_JecCghwU3ul4TaH2Eg", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-30T07:44:38+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Economist/ Development Analyst/ Planner/ Customer Care", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4E03AQFEc3EgfdpZeg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1727782989867?e=1751500800&v=beta&t=dWjKzSu5FDRgmxAVret9jQPhWF2VjcrnmEpR2LDMC1Q", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-30T07:44:38+00:00Z"}
+{"profile_url": null, "name": "Tamani Phiri", "headline": "Corporate Business Strategy | Thought Leadership | Corporate Governance", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQF4mFx8jY2n-w/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1730302954035?e=1751500800&v=beta&t=i4QIrHA6A9eLtKolwTRNhuoiaTad28sf5KHxAFuXG-w", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-30T07:44:38+00:00Z"}
+{"profile_url": null, "name": "Samantha Ngandwe", "headline": "Quality Assurance and Accreditation Officer at National Health Insurance Management Authority", "followers": 382, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQHyOjyoz7d95g/profile-displayphoto-shrink_100_100/B4DZYvvhP5GwAY-/0/1744557712084?e=1751500800&v=beta&t=DLYRpz20zmwUWx1UY1Dn-ykvgWBnwn8XHWLaDMf199M", "company_handle": "https://www.linkedin.com/company/national-health-insurance-management-authority/", "captured_at": "2025-04-30T07:44:38+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Dental Surgery Assistant at Health Promotion Board", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-30T07:44:43+00:00Z"}
+{"profile_url": null, "name": "Merrill Hausenfluck", "headline": "Chief Financial Officer", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4E03AQGKxDKRJM_BCg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1696292650180?e=1751500800&v=beta&t=NbUVC-QP-XL3frBpQcn3GtGrZ04Fl0xdko4V-mHxPag", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-30T07:44:43+00:00Z"}
+{"profile_url": null, "name": "Mike Treash", "headline": "Senior Vice President and Chief Operating Officer at Health Alliance Plan", "followers": 2000, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQH_c6tIq929gw/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1720478900599?e=1751500800&v=beta&t=l9RLnLDKBBJjJQTsFMJMa_1MpWCKcV4AUa3dcjGnSXQ", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-30T07:44:43+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Manager at Health Alliance Plan", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-30T07:44:43+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Manager, Government Programs at Health Alliance Plan", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C5603AQF473eFGZeIpQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1654455840818?e=1751500800&v=beta&t=FllKCznSi0Ndm75QYy2i5UDtflCojNGkVzRpoChPC8c", "company_handle": "https://www.linkedin.com/company/health-alliance-plan/", "captured_at": "2025-04-30T07:44:43+00:00Z"}
+{"profile_url": null, "name": "Steele Dickerson", "headline": "Insurance Recruiting Solutions", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQEyICWaE_PvXA/profile-displayphoto-shrink_100_100/B56ZQuDHyZH0Ac-/0/1735939358232?e=1751500800&v=beta&t=9FdnWHrjnPQ7LQ5FdwC7sY8sS6hm-R4zfWO5Vmwm46w", "company_handle": "https://www.linkedin.com/company/insurance-recruiting-solutions/", "captured_at": "2025-04-30T07:44:48+00:00Z"}
+{"profile_url": null, "name": "Scot Dickerson", "headline": "Insurance Industry Specialist, Insurance Recruiter, Talent Acquisition, Talent Sourcing, Hiring Consultant, Career Consultant, Staffing, Executive Recruiter at Insurance Recruiting Solutions #insurancejobs #insurance", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQGLFvtPPU3HEw/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1724950672124?e=1751500800&v=beta&t=uT4SFSMF32O1d50Z0dbnd6zRRKdABHxSGlOZdxWdXBM", "company_handle": "https://www.linkedin.com/company/insurance-recruiting-solutions/", "captured_at": "2025-04-30T07:44:48+00:00Z"}
+{"profile_url": null, "name": "Madeline Judas", "headline": "Recruiting Operations & Business Development Specialist", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQG6xiTaJ71UiA/profile-displayphoto-shrink_100_100/B56ZU_N_jPHoAY-/0/1740522388021?e=1751500800&v=beta&t=CxvAsYgU0zelghZsRhUJOC26ILVovP3ZPn4nMnWkEJE", "company_handle": "https://www.linkedin.com/company/insurance-recruiting-solutions/", "captured_at": "2025-04-30T07:44:48+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "All Lines Claims Adjuster / General Lines Agent (Property & Casualty : Life, Accident, Health & HMO)", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQFTjkb7SxTWWg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1725920318474?e=1751500800&v=beta&t=BGEzQg1c2l8qxuy2iKJ896nElsiYcaWnhkf-mqc-KhY", "company_handle": "https://www.linkedin.com/company/insurance-recruiting-solutions/", "captured_at": "2025-04-30T07:44:48+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Clinical Pharmacy Manager at Health Plan of San Mateo (HPSM)", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C5603AQEPO0pZOxznoA/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1551565536585?e=1751500800&v=beta&t=qwMGzWX_Zefkciq8h2m9daLMflT0WoDr5F1R5pXvyM4", "company_handle": "https://www.linkedin.com/company/healthplanofsanmateo/", "captured_at": "2025-04-30T07:44:54+00:00Z"}
+{"profile_url": null, "name": "Tamana M.", "headline": "MPH Candidate at Brown University | Data Coordinator", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQEY3iDtFmpzlg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1714197678074?e=1751500800&v=beta&t=IsVT0uC7A-T-Tp22gZFDG9wiT7LMB5GmhccuI8f9c-I", "company_handle": "https://www.linkedin.com/company/healthplanofsanmateo/", "captured_at": "2025-04-30T07:44:54+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Program Manager", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/healthplanofsanmateo/", "captured_at": "2025-04-30T07:44:54+00:00Z"}
+{"profile_url": null, "name": "Mackenzie Baysinger Moniz, MSW", "headline": "Program Manager at Health Plan of San Mateo", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D5603AQHAd3A4zLyuWA/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1675716742150?e=1751500800&v=beta&t=ot3fMyJFnHwwNfKJiA_YxZp6MOK_iVGtSCUgVNq867g", "company_handle": "https://www.linkedin.com/company/healthplanofsanmateo/", "captured_at": "2025-04-30T07:44:54+00:00Z"}
+{"profile_url": null, "name": "John O.", "headline": "Healthcare Delivery Strategy Execution", "followers": null, "connection_degree": "· 3rd", "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/healthplanofsanmateo/", "captured_at": "2025-04-30T07:44:54+00:00Z"}
+{"profile_url": null, "name": "Daniel McQuilkin", "headline": "Senior Vice President", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C4E03AQFkScOqwhxvfQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1521406683682?e=1751500800&v=beta&t=iohhak3lrV1gpmA6dnoCxTRJidskfgmZUXKbNQbkxjs", "company_handle": "https://www.linkedin.com/company/insurance-management-group_2/", "captured_at": "2025-04-30T07:44:59+00:00Z"}
+{"profile_url": null, "name": "Tony Bonacuse", "headline": "Senior Vice President at Insurance Management Group", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C5603AQF_JJOFLjkZoQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1516269003018?e=1751500800&v=beta&t=0APZt5RNhvUj4IxsSdi7JO9KxezZzOH_WQCibn5Szgs", "company_handle": "https://www.linkedin.com/company/insurance-management-group_2/", "captured_at": "2025-04-30T07:44:59+00:00Z"}
+{"profile_url": null, "name": "Mark Bilger", "headline": "Director - Sr. Vice President at Insurance Management Group", "followers": 1000, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C4D03AQEzX5qUfqhd2g/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1663842785708?e=1751500800&v=beta&t=YyKXRQol0cDntoq8vbdxyaRvEFf0vWKNHPxk0cyWiG8", "company_handle": "https://www.linkedin.com/company/insurance-management-group_2/", "captured_at": "2025-04-30T07:44:59+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Senior Vice President at Insurance Management Group / Partner", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C5603AQH3dm30dXH82w/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1572228299104?e=1751500800&v=beta&t=iuBQYs4iLHJgRgjFbSA2YiNiAI8zDILqg-nVsLR9Qjk", "company_handle": "https://www.linkedin.com/company/insurance-management-group_2/", "captured_at": "2025-04-30T07:44:59+00:00Z"}
+{"profile_url": null, "name": "Adam Young, MBA", "headline": "Husband | Father | Traveler | Sports Fanatic | Food Enthusiast | Independent Insurance Professional", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C5603AQErWIq1AVyxKg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1601480475688?e=1751500800&v=beta&t=jK_mhX0PkDdG8WBZaipIIYRDm1PnWIuFR7sCKDhDi6s", "company_handle": "https://www.linkedin.com/company/insurance-management-group_2/", "captured_at": "2025-04-30T07:44:59+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Doctor at CareCard Health Insurance Management Co", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/carecard-health-insurance-management-co/", "captured_at": "2025-04-30T07:45:04+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Pharmacist", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C4D03AQHyPi4Amu_Dkw/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1640460490377?e=1751500800&v=beta&t=q7R_b7bD9CR-1-Dvu81WoEHN_ljHK16l6ioTIA0LN7Q", "company_handle": "https://www.linkedin.com/company/carecard-health-insurance-management-co/", "captured_at": "2025-04-30T07:45:04+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "IT Manager at CareCard Health Insurance Management Co", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/carecard-health-insurance-management-co/", "captured_at": "2025-04-30T07:45:04+00:00Z"}
+{"profile_url": null, "name": "Amal Shabani", "headline": "at carecard", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C5603AQFLzeP3yPkjgg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1519625412373?e=1751500800&v=beta&t=GULSoesSn83F_fYkkH_nPxWIjjs1d9Pucc3dUDNei6I", "company_handle": "https://www.linkedin.com/company/carecard-health-insurance-management-co/", "captured_at": "2025-04-30T07:45:04+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "--", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/carecard-health-insurance-management-co/", "captured_at": "2025-04-30T07:45:04+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Biologiste | Pharmaco-épidemiologie & Pharmaco-économie | Software Helath Care Management", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C4D03AQHOPXrX5-oeug/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1663013895834?e=1751500800&v=beta&t=yE2RGp0rfhcJkjh_vdM0VwpaPUtoPewM80lTlr20OHU", "company_handle": "https://www.linkedin.com/company/healthcluster/", "captured_at": "2025-04-30T07:45:09+00:00Z"}
+{"profile_url": null, "name": "Ruqaia Ali Alkhalifa", "headline": "‎‏ RN,BSN, MSN,NE Database Officer for Scholarship Programs and Central Committee rapporteur at Al-Ahsa Health Cluster.", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4E03AQGfNujqDnuZDA/profile-displayphoto-shrink_100_100/B4EZOvsQThH0AU-/0/1733819436577?e=1751500800&v=beta&t=jleAVvhbg0H85tSi9TG96x0fqdkS1oytfaU02LHsFEI", "company_handle": "https://www.linkedin.com/company/healthcluster/", "captured_at": "2025-04-30T07:45:09+00:00Z"}
+{"profile_url": null, "name": "Fahad Mohyuddin", "headline": "Healthcare AI Strategist | Digital Health | SaaS | Telehealth | HIS | EHR | IoT", "followers": 7000, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C4E03AQFLnPh8fu-HHg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1647320077586?e=1751500800&v=beta&t=S__knVzEVrGZuyqwszCe_5V_kawbG5tejmmEe3fkMJE", "company_handle": "https://www.linkedin.com/company/healthcluster/", "captured_at": "2025-04-30T07:45:09+00:00Z"}
+{"profile_url": null, "name": "Muhammad Moid Shams", "headline": "Azure DevOps | AWS Cloud Infrastructure| Freight Tech | Health Tech | HL7- NABIDH | HL7+ FHIR | KSA -NPHIES | FHIR - MOPH | HL7- Riayati | Freight Tech | Insure Tech | with Azure, Azure AI , PowerApps, D365 , M365", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4D03AQEzousRurY2Zg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1711283874675?e=1751500800&v=beta&t=ZheuoRIAkS_9M8WXafdwB1nJEuy-a5HEsrXlfOANx80", "company_handle": "https://www.linkedin.com/company/healthcluster/", "captured_at": "2025-04-30T07:45:09+00:00Z"}
+{"profile_url": null, "name": "Muhammad Shahzaib (PMP® - SCRUM®)", "headline": "PMP-Certified Project Manager | Health Care & Web Solutions Expert | Customer Success & Operations Management Expert | Business Transformation Expert", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/D4D35AQFyp7WcBZinYA/profile-framedphoto-shrink_100_100/profile-framedphoto-shrink_100_100/0/1730638721808?e=1746604800&v=beta&t=oewST3uZcxrt48z76eiJgTxl1EPoo63Cq-JcTwrFTbs", "company_handle": "https://www.linkedin.com/company/healthcluster/", "captured_at": "2025-04-30T07:45:09+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Music Professional at Health Options Worldwide", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C5103AQGF-Dp6v6nkGw/profile-displayphoto-shrink_800_800/profile-displayphoto-shrink_800_800/0/1585401654822?e=1751500800&v=beta&t=7yeO-dGz1p_B66cJVSlTSdAYJLMFFwxPIhwwcR8uWWo", "company_handle": "https://www.linkedin.com/company/health-options-worldwide/", "captured_at": "2025-04-30T07:45:13+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Trainer/instructor at Health Options Worldwide", "followers": null, "connection_degree": null, "avatar_url": "data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7", "company_handle": "https://www.linkedin.com/company/health-options-worldwide/", "captured_at": "2025-04-30T07:45:13+00:00Z"}
+{"profile_url": null, "name": "Michael Akpoarebe-Isaac", "headline": "Chief Operating officer, Health Partners HMO", "followers": null, "connection_degree": "· 3rd", "avatar_url": "https://media.licdn.com/dms/image/v2/C4E03AQE7KNFaLMyqYg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1602714385413?e=1751500800&v=beta&t=In5GaREqoXtO3sPCx9ZJJBwIPY4008ii13RPRl0w0Fw", "company_handle": "https://www.linkedin.com/company/healthpartnersng/", "captured_at": "2025-04-30T07:45:19+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "REGISTERED NURSE/CLAIMS SUPERVISOR/HEALTH EDUCATOR/ CASE MANAGER/ Lekki.", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4E35AQEEqf5i5pD76g/profile-framedphoto-shrink_100_100/profile-framedphoto-shrink_100_100/0/1724219552412?e=1746604800&v=beta&t=h0kqmp2KnpqQxsCCwyy7NpA8CAkSQ6qgbsZ0p0H7mXM", "company_handle": "https://www.linkedin.com/company/healthpartnersng/", "captured_at": "2025-04-30T07:45:19+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Data Analyst|Dedicated Retention Officer Boosting Customer Loyalty| Business Developer/ Event planner", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/D4D35AQHIgeS1H7w65w/profile-framedphoto-shrink_100_100/B4DZV1QfcCGcAk-/0/1741429012517?e=1746604800&v=beta&t=zZi8WjnLpDrQD271jAId2mnfld_hO538QrN1-q2G4Zw", "company_handle": "https://www.linkedin.com/company/healthpartnersng/", "captured_at": "2025-04-30T07:45:19+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "Former Group managing director at Health Partners Ltd", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C4E03AQHPQPvIQbPQPg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1583328612508?e=1751500800&v=beta&t=LpynArccJCWrdWMSBvYLH4SI5G-xae7ECoWUUAl_CeU", "company_handle": "https://www.linkedin.com/company/healthpartnersng/", "captured_at": "2025-04-30T07:45:19+00:00Z"}
+{"profile_url": null, "name": "LinkedIn Member", "headline": "HEAD, FINCON, @ HEALTH PARTNERS (HMO) LTD", "followers": null, "connection_degree": null, "avatar_url": "https://media.licdn.com/dms/image/v2/C4D03AQG8XOvnazEibQ/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1518882054975?e=1751500800&v=beta&t=5gT6GAWGTqYfpvkjOk0ArvV73I_KspkWXgoG-VhoStg", "company_handle": "https://www.linkedin.com/company/healthpartnersng/", "captured_at": "2025-04-30T07:45:19+00:00Z"}

docs/apps/linkdin/schemas/company_card.json

@@ -0,0 +1,51 @@
+{
+  "name": "LinkedIn Company Search Result Card",
+  "baseSelector": "div[data-chameleon-result-urn][data-view-name=\"search-entity-result-universal-template\"]",
+  "baseFields": [
+    {
+      "name": "chameleon_result_urn",
+      "type": "attribute",
+      "attribute": "data-chameleon-result-urn"
+    },
+    {
+      "name": "view_name",
+      "type": "attribute",
+      "attribute": "data-view-name"
+    }
+  ],
+  "fields": [
+    {
+      "name": "handle",
+      "selector": "div.mb1 div.display-flex span a[data-test-app-aware-link]",
+      "type": "attribute",
+      "attribute": "href"
+    },
+    {
+      "name": "profile_image",
+      "selector": "div.ivm-image-view-model img",
+      "type": "attribute",
+      "attribute": "src"
+    },
+    {
+      "name": "name",
+      "selector": "div.mb1 div.display-flex span a[data-test-app-aware-link]",
+      "type": "text"
+    },
+    {
+      "name": "descriptor",
+      "selector": "div.mb1 > div[class*=\"t-14 t-black\"]",
+      "type": "text"
+    },
+    {
+      "name": "about",
+      "selector": "p.entity-result__summary--2-lines",
+      "type": "text"
+    },
+    {
+      "name": "followers",
+      "selector": "div.mb1 > div:nth-of-type(3)",
+      "type": "regex",
+      "pattern": "(\\d+[KM]?) followers"
+    }
+  ]
+}

docs/apps/linkdin/schemas/people_card.json

@@ -0,0 +1,41 @@
+{
+  "name": "LinkedIn People Profile Card",
+  "baseSelector": "li.org-people-profile-card__profile-card-spacing",
+  "baseFields": [],
+  "fields": [
+    {
+      "name": "profile_url",
+      "selector": "div.artdeco-entity-lockup__title a[data-test-app-aware-link]",
+      "type": "attribute",
+      "attribute": "href"
+    },
+    {
+      "name": "avatar_url",
+      "selector": "div.artdeco-entity-lockup__image img",
+      "type": "attribute",
+      "attribute": "src"
+    },
+    {
+      "name": "name",
+      "selector": "div.artdeco-entity-lockup__title a div.lt-line-clamp--single-line",
+      "type": "text"
+    },
+    {
+      "name": "headline",
+      "selector": "div.artdeco-entity-lockup__subtitle div.lt-line-clamp--multi-line",
+      "type": "text"
+    },
+    {
+      "name": "followers",
+      "selector": "span.text-align-center span.lt-line-clamp--multi-line",
+      "type": "regex",
+      "pattern": "(\\d+)"
+    },
+    {
+      "name": "connection_degree",
+      "selector": "span.artdeco-entity-lockup__degree",
+      "type": "regex",
+      "pattern": "(\\d+\\w+)"
+    }
+  ]
+}

docs/apps/linkdin/snippets/company.html

@@ -0,0 +1,138 @@
+<li class="kZRArQqqhjjrHYceWaFbyEGWHRZbtqjTMawKA">
+    <!----><!---->
+
+
+
+    <div class="xAuWirHJDUTuhkfOpmJApZWziplUyPIc" data-chameleon-result-urn="urn:li:company:2095237"
+        data-view-name="search-entity-result-universal-template">
+
+
+
+
+        <div class="linked-area flex-1
+          cursor-pointer">
+
+            <div class="qMGLeKnJyQnibGOueKodvnfLgWpsuA">
+                <div class="cBPGFfFovHsbNhBFmECDIsPgMWmtMozOUfIAbs">
+                    <div class="display-flex align-items-center">
+                        <!---->
+
+                        <a class="sDWEFrcVubKuUVGggeBOYqLlgYgPbojOc  scale-down " aria-hidden="true" tabindex="-1"
+                            href="https://www.linkedin.com/company/health-insurance/" data-test-app-aware-link="">
+
+                            <div class="ivm-image-view-model   ">
+
+                                <div class="ivm-view-attr__img-wrapper
+        
+        ">
+                                    <!---->
+                                    <!----> <img width="48"
+                                        src="https://media.licdn.com/dms/image/v2/C560BAQEXIoLSJbShlw/company-logo_100_100/company-logo_100_100/0/1662748332921/health_insurance_logo?e=1753920000&amp;v=beta&amp;t=p2ZNMYNsC9KSlp-sIqMYuc88avBTjKF4CqDobq1Xr2M"
+                                        loading="lazy" height="48" alt="Health Insurance" id="ember28"
+                                        class="ivm-view-attr__img--centered EntityPhoto-square-3   evi-image lazy-image ember-view">
+                                </div>
+
+                            </div>
+
+                        </a>
+
+
+                    </div>
+                </div>
+                <div
+                    class="BNxZPngZfeRnDrIUbICgBZvQjRvMAUnwCHuDrmRg yNRlrJOHDflDBnYPLbVmiAkUsCUZKUznmAc pt3 pb3 t-12 t-black--light">
+                    <div class="mb1">
+
+                        <div class="t-roman t-sans">
+
+
+
+                            <div class="display-flex">
+                                <span
+                                    class="kmApjJVnFerynwITxTBSCqzqgoHwVfkiA HHGiVqODTCkszDUDWwPGPJGUPfAeRpygAKwwLePrQ ">
+                                    <span class="OjTMoZLoiuspGuWWptwqxZRcMcHZBoSDxfig
+            t-16">
+                                        <a class="sDWEFrcVubKuUVGggeBOYqLlgYgPbojOc "
+                                            href="https://www.linkedin.com/company/health-insurance/"
+                                            data-test-app-aware-link="">
+                                            <!---->Health Insurance<!---->
+                                            <!----> </a>
+                                        <!----> </span>
+                                </span>
+                                <!---->
+                            </div>
+
+
+
+                        </div>
+
+
+
+                        <div class="kFTZPhxHBbvnnRxiRPmTxafKGLUNSiaeInag
+          t-14 t-black t-normal">
+                            <!---->Insurance • Cardiff, CA<!---->
+                        </div>
+
+                        <div class="FlWUwyrEUZpkVCgzGTDwUHTLntfZNseavlY
+          t-14 t-normal">
+                            <!---->3K followers<!---->
+                        </div>
+
+
+
+
+
+                    </div>
+
+                    <!---->
+                    <p class="JBUEKeXhPyClEtYwdsASPYsZsCkTvUBqsDUs
+                entity-result__summary--2-lines
+                t-12 t-black--light
+                ">
+                        <!---->Your<span class="white-space-pre"> </span><strong><!---->health<!----></strong><span
+                            class="white-space-pre"> </span><!----><!----><strong><!---->insurance<!----></strong><span
+                            class="white-space-pre"> </span>expert for all stages of your life; Medicare, Individuals,
+                        Families, Small Groups, CoveredCA.<!---->
+                    </p>
+
+                    <!---->
+                </div>
+                <div class="JZcKRppsWfaxfMaqtvfVwEeAtzNwryBOMdo yNRlrJOHDflDBnYPLbVmiAkUsCUZKUznmAc">
+                    <!---->
+
+
+                    <div>
+
+
+
+
+                        <button aria-label="Follow Health Insurance" id="ember49"
+                            class="artdeco-button artdeco-button--2 artdeco-button--secondary ember-view"
+                            type="button"><!---->
+                            <span class="artdeco-button__text">
+                                Follow
+                            </span></button>
+
+
+
+                        <!---->
+                        <!---->
+
+
+                    </div>
+
+
+
+                </div>
+            </div>
+
+        </div>
+
+
+
+
+    </div>
+
+
+
+</li>

docs/apps/linkdin/snippets/people.html

@@ -0,0 +1,93 @@
+<li class="grid grid__col--lg-8 block org-people-profile-card__profile-card-spacing">
+    <div>
+
+
+        <section class="artdeco-card full-width IxXiAcHfbZpayHVZUYdQwfYOkMbOirmr">
+            <!---->
+
+            <img width="210" src="data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7"
+                ariarole="presentation" loading="lazy" height="210" alt="" id="ember102"
+                class="evi-image lazy-image ghost-default ember-view org-people-profile-card__cover-photo org-people-profile-card__cover-photo--people">
+
+            <div class="org-people-profile-card__profile-info">
+                <div id="ember103"
+                    class="artdeco-entity-lockup artdeco-entity-lockup--stacked-center artdeco-entity-lockup--size-7 ember-view">
+                    <div id="ember104"
+                        class="artdeco-entity-lockup__image artdeco-entity-lockup__image--type-circle ember-view"
+                        type="circle">
+
+                        <a class="sDWEFrcVubKuUVGggeBOYqLlgYgPbojOc " id="org-people-profile-card__profile-image-0"
+                            href="https://www.linkedin.com/in/ericweberhcbd?miniProfileUrn=urn%3Ali%3Afs_miniProfile%3AACoAAABVh2MBFoyTaAxDqYQQcW8oGxVsqsKioHw"
+                            data-test-app-aware-link="">
+                            <img width="104"
+                                src="https://media.licdn.com/dms/image/v2/C4D03AQHNP9KoXtSrkg/profile-displayphoto-shrink_100_100/profile-displayphoto-shrink_100_100/0/1573501774845?e=1753920000&amp;v=beta&amp;t=JYsY56biGUmDzbYj2ORZMcd1dSm2IRWCA-IM3KNFLw8"
+                                loading="lazy" height="104" alt="Eric Weber" id="ember105"
+                                class="evi-image lazy-image ember-view">
+                        </a>
+
+
+                    </div>
+                    <div id="ember106" class="artdeco-entity-lockup__content ember-view">
+                        <div id="ember107" class="artdeco-entity-lockup__title ember-view">
+                            <a class="sDWEFrcVubKuUVGggeBOYqLlgYgPbojOc  link-without-visited-state"
+                                aria-label="View Eric Weber’s profile"
+                                href="https://www.linkedin.com/in/ericweberhcbd?miniProfileUrn=urn%3Ali%3Afs_miniProfile%3AACoAAABVh2MBFoyTaAxDqYQQcW8oGxVsqsKioHw"
+                                data-test-app-aware-link="">
+                                <div id="ember109" class="ember-view lt-line-clamp lt-line-clamp--single-line rMKrzkehlCEvJWoQjDQJFaHmBFAYQLMGrNY
+                      t-black" style="">
+                                    Eric Weber
+
+                                    <!---->
+                                </div>
+
+                            </a>
+
+                        </div>
+                        <div id="ember110" class="artdeco-entity-lockup__badge ember-view"> <span class="a11y-text">3rd+
+                                degree connection</span>
+                            <span class="artdeco-entity-lockup__degree" aria-hidden="true">
+                                ·&nbsp;3rd
+                            </span>
+                            <!----><!---->
+                        </div>
+                        <div id="ember111" class="artdeco-entity-lockup__subtitle ember-view">
+                            <div class="t-14 t-black--light t-normal">
+                                <div id="ember113" class="ember-view lt-line-clamp lt-line-clamp--multi-line"
+                                    style="-webkit-line-clamp: 2">
+                                    HIPN Executive Editor | Healthcare BizDev CEO — Health Insurance Plan News.
+
+                                    <!---->
+                                </div>
+
+                            </div>
+                        </div>
+                        <div id="ember114" class="artdeco-entity-lockup__caption ember-view"></div>
+                    </div>
+
+                </div>
+                <span class="text-align-center">
+                    <span id="ember116"
+                        class="ember-view lt-line-clamp lt-line-clamp--multi-line t-12 t-black--light mt2"
+                        style="-webkit-line-clamp: 3">
+                        10K followers
+
+                        <!----> </span>
+
+                </span>
+            </div>
+
+            <footer class="ph3 pb3">
+                <button aria-label="Follow Eric Weber" id="ember117"
+                    class="artdeco-button artdeco-button--2 artdeco-button--secondary ember-view full-width"
+                    type="button"><!---->
+                    <span class="artdeco-button__text">
+                        Follow
+                    </span></button>
+            </footer>
+
+        </section>
+
+
+    </div>
+
+</li>

docs/apps/linkdin/templates/ai.js

@@ -0,0 +1,50 @@
+// ==== File: ai.js ====
+
+class ApiHandler {
+    constructor(apiKey = null) {
+      this.apiKey = apiKey || localStorage.getItem("openai_api_key") || "";
+      console.log("ApiHandler ready");
+    }
+  
+    setApiKey(k) {
+      this.apiKey = k.trim();
+      if (this.apiKey) localStorage.setItem("openai_api_key", this.apiKey);
+    }
+  
+    async *chatStream(messages, {model = "gpt-4o", temperature = 0.7} = {}) {
+      if (!this.apiKey) throw new Error("OpenAI API key missing");
+      const payload = {model, messages, stream: true, max_tokens: 1024};
+      const controller = new AbortController();
+  
+      const res = await fetch("https://api.openai.com/v1/chat/completions", {
+        method: "POST",
+        headers: {
+          "Content-Type": "application/json",
+          Authorization: `Bearer ${this.apiKey}`,
+        },
+        body: JSON.stringify(payload),
+        signal: controller.signal,
+      });
+      if (!res.ok) throw new Error(`OpenAI: ${res.statusText}`);
+      const reader = res.body.getReader();
+      const dec = new TextDecoder();
+  
+      let buf = "";
+      while (true) {
+        const {done, value} = await reader.read();
+        if (done) break;
+        buf += dec.decode(value, {stream: true});
+        for (const line of buf.split("\n")) {
+          if (!line.startsWith("data: ")) continue;
+          if (line.includes("[DONE]")) return;
+          const json = JSON.parse(line.slice(6));
+          const delta = json.choices?.[0]?.delta?.content;
+          if (delta) yield delta;
+        }
+        buf = buf.endsWith("\n") ? "" : buf; // keep partial line
+      }
+    }
+  }
+  
+  window.API = new ApiHandler();
+  

docs/codebase/browser.md

@@ -0,0 +1,51 @@
+### browser_manager.py
+
+| Function | What it does |
+|---|---|
+| `ManagedBrowser.build_browser_flags` | Returns baseline Chromium CLI flags, disables GPU and sandbox, plugs locale, timezone, stealth tweaks, and any extras from `BrowserConfig`. |
+| `ManagedBrowser.__init__` | Stores config and logger, creates temp dir, preps internal state. |
+| `ManagedBrowser.start` | Spawns or connects to the Chromium process, returns its CDP endpoint plus the `subprocess.Popen` handle. |
+| `ManagedBrowser._initial_startup_check` | Pings the CDP endpoint once to be sure the browser is alive, raises if not. |
+| `ManagedBrowser._monitor_browser_process` | Async-loops on the subprocess, logs exits or crashes, restarts if policy allows. |
+| `ManagedBrowser._get_browser_path_WIP` | Old helper that maps OS + browser type to an executable path. |
+| `ManagedBrowser._get_browser_path` | Current helper, checks env vars, Playwright cache, and OS defaults for the real executable. |
+| `ManagedBrowser._get_browser_args` | Builds the final CLI arg list by merging user flags, stealth flags, and defaults. |
+| `ManagedBrowser.cleanup` | Terminates the browser, stops monitors, deletes the temp dir. |
+| `ManagedBrowser.create_profile` | Opens a visible browser so a human can log in, then zips the resulting user-data-dir to `~/.crawl4ai/profiles/<name>`. |
+| `ManagedBrowser.list_profiles` | Thin wrapper, now forwarded to `BrowserProfiler.list_profiles()`. |
+| `ManagedBrowser.delete_profile` | Thin wrapper, now forwarded to `BrowserProfiler.delete_profile()`. |
+| `BrowserManager.__init__` | Holds the global Playwright instance, browser handle, config signature cache, session map, and logger. |
+| `BrowserManager.start` | Boots the underlying `ManagedBrowser`, then spins up the default Playwright browser context with stealth patches. |
+| `BrowserManager._build_browser_args` | Translates `CrawlerRunConfig` (proxy, UA, timezone, headless flag, etc.) into Playwright `launch_args`. |
+| `BrowserManager.setup_context` | Applies locale, geolocation, permissions, cookies, and UA overrides on a fresh context. |
+| `BrowserManager.create_browser_context` | Internal helper that actually calls `browser.new_context(**options)` after running `setup_context`. |
+| `BrowserManager._make_config_signature` | Hashes the non-ephemeral parts of `CrawlerRunConfig` so contexts can be reused safely. |
+| `BrowserManager.get_page` | Returns a ready `Page` for a given session id, reusing an existing one or creating a new context/page, injects helper scripts, updates `last_used`. |
+| `BrowserManager.kill_session` | Force-closes a context/page for a session and removes it from the session map. |
+| `BrowserManager._cleanup_expired_sessions` | Periodic sweep that drops sessions idle longer than `ttl_seconds`. |
+| `BrowserManager.close` | Gracefully shuts down all contexts, the browser, Playwright, and background tasks. |
+
+---
+
+### browser_profiler.py
+
+| Function | What it does |
+|---|---|
+| `BrowserProfiler.__init__` | Sets up profile folder paths, async logger, and signal handlers. |
+| `BrowserProfiler.create_profile` | Launches a visible browser with a new user-data-dir for manual login, on exit compresses and stores it as a named profile. |
+| `BrowserProfiler.cleanup_handler` | General SIGTERM/SIGINT cleanup wrapper that kills child processes. |
+| `BrowserProfiler.sigint_handler` | Handles Ctrl-C during an interactive session, makes sure the browser shuts down cleanly. |
+| `BrowserProfiler.listen_for_quit_command` | Async REPL that exits when the user types `q`. |
+| `BrowserProfiler.list_profiles` | Enumerates `~/.crawl4ai/profiles`, prints profile name, browser type, size, and last modified. |
+| `BrowserProfiler.get_profile_path` | Returns the absolute path of a profile given its name, or `None` if missing. |
+| `BrowserProfiler.delete_profile` | Removes a profile folder or a direct path from disk, with optional confirmation prompt. |
+| `BrowserProfiler.interactive_manager` | Text UI loop for listing, creating, deleting, or launching profiles. |
+| `BrowserProfiler.launch_standalone_browser` | Starts a non-headless Chromium with remote debugging enabled and keeps it alive for manual tests. |
+| `BrowserProfiler.get_cdp_json` | Pulls `/json/version` from a CDP endpoint and returns the parsed JSON. |
+| `BrowserProfiler.launch_builtin_browser` | Spawns a headless Chromium in the background, saves `{wsEndpoint, pid, started_at}` to `~/.crawl4ai/builtin_browser.json`. |
+| `BrowserProfiler.get_builtin_browser_info` | Reads that JSON file, verifies the PID, and returns browser status info. |
+| `BrowserProfiler._is_browser_running` | Cross-platform helper that checks if a PID is still alive. |
+| `BrowserProfiler.kill_builtin_browser` | Terminates the background builtin browser and removes its status file. |
+| `BrowserProfiler.get_builtin_browser_status` | Returns `{running: bool, wsEndpoint, pid, started_at}` for quick health checks. |
+
+Let me know what you want to tweak or dive into next.

docs/codebase/cli.md

@@ -0,0 +1,40 @@
+### `cli.py` command surface
+
+| Command | Inputs / flags | What it does |
+|---|---|---|
+| **profiles** | *(none)* | Opens the interactive profile manager, lets you list, create, delete saved browser profiles that live in `~/.crawl4ai/profiles`. |
+| **browser status** | – | Prints whether the always-on *builtin* browser is running, shows its CDP URL, PID, start time. |
+| **browser stop** | – | Kills the builtin browser and deletes its status file. |
+| **browser view** | `--url, -u` URL *(optional)* | Pops a visible window of the builtin browser, navigates to `URL` or `about:blank`. |
+| **config list** | – | Dumps every global setting, showing current value, default, and description. |
+| **config get** | `key` | Prints the value of a single setting, falls back to default if unset. |
+| **config set** | `key value` | Persists a new value in the global config (stored under `~/.crawl4ai/config.yml`). |
+| **examples** | – | Just spits out real-world CLI usage samples. |
+| **crawl** | `url` *(positional)*<br>`--browser-config,-B` path<br>`--crawler-config,-C` path<br>`--filter-config,-f` path<br>`--extraction-config,-e` path<br>`--json-extract,-j` [desc]\*<br>`--schema,-s` path<br>`--browser,-b` k=v list<br>`--crawler,-c` k=v list<br>`--output,-o` all,json,markdown,md,markdown-fit,md-fit *(default all)*<br>`--output-file,-O` path<br>`--bypass-cache,-b` *(flag, default true — note flag reuse)*<br>`--question,-q` str<br>`--verbose,-v` *(flag)*<br>`--profile,-p` profile-name | One-shot crawl + extraction. Builds `BrowserConfig` and `CrawlerRunConfig` from inline flags or separate YAML/JSON files, runs `AsyncWebCrawler.run()`, can route through a named saved profile and pipe the result to stdout or a file. |
+| **(default)** | Same flags as **crawl**, plus `--example` | Shortcut so you can type just `crwl https://site.com`. When first arg is not a known sub-command, it falls through to *crawl*. |
+
+\* `--json-extract/-j` with no value turns on LLM-based JSON extraction using an auto schema, supplying a string lets you prompt-engineer the field descriptions.
+
+> Quick mental model  
+> `profiles` = manage identities,  
+> `browser ...` = control long-running headless Chrome that all crawls can piggy-back on,  
+> `crawl` = do the actual work,  
+> `config` = tweak global defaults,  
+> everything else is sugar.
+
+### Quick-fire “profile” usage cheatsheet
+
+| Scenario | Command (copy-paste ready) | Notes |
+|---|---|---|
+| **Launch interactive Profile Manager UI** | `crwl profiles` | Opens TUI with options: 1 List, 2 Create, 3 Delete, 4 Use-to-crawl, 5 Exit. |
+| **Create a fresh profile** | `crwl profiles` → choose **2** → name it → browser opens → log in → press **q** in terminal | Saves to `~/.crawl4ai/profiles/<name>`. |
+| **List saved profiles** | `crwl profiles` → choose **1** | Shows name, browser type, size, last-modified. |
+| **Delete a profile** | `crwl profiles` → choose **3** → pick the profile index → confirm | Removes the folder. |
+| **Crawl with a profile (default alias)** | `crwl https://site.com/dashboard -p my-profile` | Keeps login cookies, sets `use_managed_browser=true` under the hood. |
+| **Crawl + verbose JSON output** | `crwl https://site.com -p my-profile -o json -v` | Any other `crawl` flags work the same. |
+| **Crawl with extra browser tweaks** | `crwl https://site.com -p my-profile -b "headless=true,viewport_width=1680"` | CLI overrides go on top of the profile. |
+| **Same but via explicit sub-command** | `crwl crawl https://site.com -p my-profile` | Identical to default alias. |
+| **Use profile from inside Profile Manager** | `crwl profiles` → choose **4** → pick profile → enter URL → follow prompts | Handy when demo-ing to non-CLI folks. |
+| **One-off crawl with a profile folder path (no name lookup)** | `crwl https://site.com -b "user_data_dir=$HOME/.crawl4ai/profiles/my-profile,use_managed_browser=true"` | Bypasses registry, useful for CI scripts. |
+| **Launch a dev browser on CDP port with the same identity** | `crwl cdp -d $HOME/.crawl4ai/profiles/my-profile -P 9223` | Lets Puppeteer/Playwright attach for debugging. |
+

docs/examples/amazon_product_extraction_direct_url.py

@@ -5,7 +5,7 @@ prices, ratings, and other details using CSS selectors.
 """
 
 from crawl4ai import AsyncWebCrawler
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 from crawl4ai.async_configs import BrowserConfig, CrawlerRunConfig
 import json
 

docs/examples/amazon_product_extraction_using_hooks.py

@@ -5,7 +5,7 @@ prices, ratings, and other details using CSS selectors.
 """
 
 from crawl4ai import AsyncWebCrawler, CacheMode
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 from crawl4ai.async_configs import BrowserConfig, CrawlerRunConfig
 import json
 from playwright.async_api import Page, BrowserContext

docs/examples/amazon_product_extraction_using_use_javascript.py

@@ -5,7 +5,7 @@ prices, ratings, and other details using CSS selectors.
 """
 
 from crawl4ai import AsyncWebCrawler, CacheMode
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+from crawl4ai import JsonCssExtractionStrategy
 from crawl4ai.async_configs import BrowserConfig, CrawlerRunConfig
 import json
 

docs/examples/assets/virtual_scroll_append_only.html

@@ -0,0 +1,132 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>Append-Only Scroll (Traditional Infinite Scroll)</title>
+    <style>
+        body {
+            font-family: Arial, sans-serif;
+            margin: 0;
+            padding: 20px;
+            background-color: #f5f5f5;
+        }
+        
+        h1 {
+            color: #333;
+            text-align: center;
+        }
+        
+        .posts-container {
+            max-width: 800px;
+            margin: 0 auto;
+            background: white;
+            border: 1px solid #ddd;
+            border-radius: 5px;
+            padding: 20px;
+        }
+        
+        .post {
+            background: #f9f9f9;
+            padding: 15px;
+            margin-bottom: 15px;
+            border-radius: 5px;
+            border: 1px solid #eee;
+        }
+        
+        .post-title {
+            font-size: 18px;
+            font-weight: bold;
+            color: #2c3e50;
+            margin-bottom: 10px;
+        }
+        
+        .post-content {
+            color: #555;
+            line-height: 1.6;
+        }
+        
+        .loading {
+            text-align: center;
+            padding: 20px;
+            color: #888;
+        }
+    </style>
+</head>
+<body>
+    <h1>Traditional Infinite Scroll Demo</h1>
+    <p style="text-align: center; color: #666;">This appends new content without removing old content</p>
+    <div class="posts-container"></div>
+    
+    <script>
+        // Traditional infinite scroll - APPENDS content
+        const container = document.querySelector('.posts-container');
+        const totalPosts = 200;
+        const postsPerPage = 20;
+        let loadedPosts = 0;
+        let isLoading = false;
+        
+        // Generate fake post data
+        function generatePost(index) {
+            return {
+                id: index,
+                title: `Post Title #${index + 1}`,
+                content: `This is the content of post ${index + 1}. In traditional infinite scroll, new content is appended to existing content. The DOM keeps growing. Post ID: ${index}`
+            };
+        }
+        
+        // Load more posts - APPENDS to existing content
+        function loadMorePosts() {
+            if (isLoading || loadedPosts >= totalPosts) return;
+            
+            isLoading = true;
+            
+            // Show loading indicator
+            const loadingDiv = document.createElement('div');
+            loadingDiv.className = 'loading';
+            loadingDiv.textContent = 'Loading more posts...';
+            container.appendChild(loadingDiv);
+            
+            // Simulate network delay
+            setTimeout(() => {
+                // Remove loading indicator
+                container.removeChild(loadingDiv);
+                
+                // Add new posts
+                const fragment = document.createDocumentFragment();
+                const endIndex = Math.min(loadedPosts + postsPerPage, totalPosts);
+                
+                for (let i = loadedPosts; i < endIndex; i++) {
+                    const post = generatePost(i);
+                    const postElement = document.createElement('div');
+                    postElement.className = 'post';
+                    postElement.setAttribute('data-post-id', post.id);
+                    postElement.innerHTML = `
+                        <div class="post-title">${post.title}</div>
+                        <div class="post-content">${post.content}</div>
+                    `;
+                    fragment.appendChild(postElement);
+                }
+                
+                // APPEND new posts to existing ones
+                container.appendChild(fragment);
+                loadedPosts = endIndex;
+                isLoading = false;
+                
+                console.log(`Loaded ${loadedPosts} of ${totalPosts} posts`);
+            }, 300);
+        }
+        
+        // Initial load
+        loadMorePosts();
+        
+        // Load more on scroll
+        window.addEventListener('scroll', () => {
+            const scrollBottom = window.innerHeight + window.scrollY;
+            const threshold = document.body.offsetHeight - 500;
+            
+            if (scrollBottom >= threshold) {
+                loadMorePosts();
+            }
+        });
+    </script>
+</body>
+</html>

docs/examples/assets/virtual_scroll_instagram_grid.html

@@ -0,0 +1,158 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>Instagram-like Grid Virtual Scroll</title>
+    <style>
+        body {
+            font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Helvetica, Arial, sans-serif;
+            margin: 0;
+            padding: 20px;
+            background-color: #fafafa;
+        }
+        
+        h1 {
+            text-align: center;
+            color: #262626;
+            font-weight: 300;
+        }
+        
+        .feed-container {
+            max-width: 935px;
+            margin: 0 auto;
+            height: 800px;
+            overflow-y: auto;
+            background: white;
+            border: 1px solid #dbdbdb;
+            border-radius: 3px;
+        }
+        
+        .grid {
+            display: grid;
+            grid-template-columns: repeat(3, 1fr);
+            gap: 28px;
+            padding: 28px;
+        }
+        
+        .post {
+            aspect-ratio: 1;
+            background: #f0f0f0;
+            border-radius: 3px;
+            position: relative;
+            overflow: hidden;
+            cursor: pointer;
+        }
+        
+        .post:hover .overlay {
+            opacity: 1;
+        }
+        
+        .post img {
+            width: 100%;
+            height: 100%;
+            object-fit: cover;
+        }
+        
+        .overlay {
+            position: absolute;
+            top: 0;
+            left: 0;
+            right: 0;
+            bottom: 0;
+            background: rgba(0, 0, 0, 0.3);
+            display: flex;
+            align-items: center;
+            justify-content: center;
+            color: white;
+            font-size: 14px;
+            opacity: 0;
+            transition: opacity 0.2s;
+        }
+        
+        .stats {
+            display: flex;
+            gap: 20px;
+        }
+    </style>
+</head>
+<body>
+    <h1>Instagram Grid Virtual Scroll</h1>
+    <p style="text-align: center; color: #8e8e8e;">Grid layout with virtual scrolling - only visible rows are rendered</p>
+    <div class="feed-container">
+        <div class="grid" id="grid"></div>
+    </div>
+    
+    <script>
+        // Instagram-like grid virtual scroll
+        const grid = document.getElementById('grid');
+        const container = document.querySelector('.feed-container');
+        const totalPosts = 999; // Instagram style count
+        const postsPerRow = 3;
+        const rowsPerPage = 4; // 12 posts per page
+        const postsPerPage = postsPerRow * rowsPerPage;
+        let currentStartIndex = 0;
+        
+        // Generate fake Instagram post data
+        const allPosts = [];
+        for (let i = 0; i < totalPosts; i++) {
+            allPosts.push({
+                id: i,
+                likes: Math.floor(Math.random() * 10000),
+                comments: Math.floor(Math.random() * 500),
+                imageNumber: (i % 10) + 1 // Cycle through 10 placeholder images
+            });
+        }
+        
+        // Render grid - REPLACES content for performance
+        function renderGrid(startIndex) {
+            const posts = [];
+            const endIndex = Math.min(startIndex + postsPerPage, totalPosts);
+            
+            for (let i = startIndex; i < endIndex; i++) {
+                const post = allPosts[i];
+                posts.push(`
+                    <div class="post" data-post-id="${post.id}">
+                        <img src="data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' width='400' height='400'%3E%3Crect width='400' height='400' fill='%23${Math.floor(Math.random()*16777215).toString(16)}'/%3E%3Ctext x='50%25' y='50%25' text-anchor='middle' dy='.3em' font-family='Arial' font-size='48' fill='white'%3E${post.id + 1}%3C/text%3E%3C/svg%3E" alt="Post ${post.id + 1}">
+                        <div class="overlay">
+                            <div class="stats">
+                                <span>❤️ ${post.likes.toLocaleString()}</span>
+                                <span>💬 ${post.comments}</span>
+                            </div>
+                        </div>
+                    </div>
+                `);
+            }
+            
+            // REPLACE grid content (virtual scroll)
+            grid.innerHTML = posts.join('');
+            currentStartIndex = startIndex;
+        }
+        
+        // Initial render
+        renderGrid(0);
+        
+        // Handle scroll
+        let scrollTimeout;
+        container.addEventListener('scroll', () => {
+            clearTimeout(scrollTimeout);
+            scrollTimeout = setTimeout(() => {
+                const scrollTop = container.scrollTop;
+                const scrollHeight = container.scrollHeight;
+                const clientHeight = container.clientHeight;
+                
+                // Calculate which "page" we should show
+                const scrollPercentage = scrollTop / (scrollHeight - clientHeight);
+                const targetIndex = Math.floor(scrollPercentage * (totalPosts - postsPerPage) / postsPerPage) * postsPerPage;
+                
+                // When scrolled to bottom, show next page
+                if (scrollTop + clientHeight >= scrollHeight - 100) {
+                    const nextIndex = currentStartIndex + postsPerPage;
+                    if (nextIndex < totalPosts) {
+                        renderGrid(nextIndex);
+                        container.scrollTop = 100; // Reset scroll for continuous experience
+                    }
+                }
+            }, 50);
+        });
+    </script>
+</body>
+</html>

docs/examples/assets/virtual_scroll_news_feed.html

@@ -0,0 +1,210 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>News Feed with Mixed Scroll Behavior</title>
+    <style>
+        body {
+            font-family: Georgia, serif;
+            margin: 0;
+            padding: 20px;
+            background-color: #f8f8f8;
+        }
+        
+        h1 {
+            text-align: center;
+            color: #1a1a1a;
+            font-size: 32px;
+            margin-bottom: 10px;
+        }
+        
+        .description {
+            text-align: center;
+            color: #666;
+            margin-bottom: 20px;
+        }
+        
+        #newsContainer {
+            max-width: 900px;
+            margin: 0 auto;
+            height: 700px;
+            overflow-y: auto;
+            background: white;
+            box-shadow: 0 2px 10px rgba(0,0,0,0.1);
+            padding: 20px;
+        }
+        
+        .article {
+            margin-bottom: 30px;
+            padding-bottom: 30px;
+            border-bottom: 1px solid #e0e0e0;
+        }
+        
+        .article:last-child {
+            border-bottom: none;
+        }
+        
+        .article-header {
+            margin-bottom: 15px;
+        }
+        
+        .category {
+            display: inline-block;
+            background: #ff6b6b;
+            color: white;
+            padding: 4px 12px;
+            font-size: 12px;
+            text-transform: uppercase;
+            border-radius: 3px;
+            margin-bottom: 10px;
+        }
+        
+        .headline {
+            font-size: 24px;
+            font-weight: bold;
+            color: #1a1a1a;
+            margin: 10px 0;
+            line-height: 1.3;
+        }
+        
+        .meta {
+            color: #888;
+            font-size: 14px;
+            margin-bottom: 15px;
+        }
+        
+        .content {
+            font-size: 16px;
+            line-height: 1.8;
+            color: #333;
+        }
+        
+        .featured {
+            background: #fff9e6;
+            padding: 20px;
+            border-radius: 5px;
+            margin-bottom: 30px;
+        }
+        
+        .featured .category {
+            background: #ffa500;
+        }
+    </style>
+</head>
+<body>
+    <h1>📰 Dynamic News Feed</h1>
+    <p class="description">Mixed behavior: Featured articles stay, regular articles use virtual scroll</p>
+    <div id="newsContainer"></div>
+    
+    <script>
+        const container = document.getElementById('newsContainer');
+        const totalArticles = 100;
+        const articlesPerPage = 5;
+        let currentRegularIndex = 0;
+        
+        // Categories for variety
+        const categories = ['Politics', 'Technology', 'Business', 'Science', 'Sports', 'Entertainment'];
+        
+        // Generate article data
+        const featuredArticles = [];
+        const regularArticles = [];
+        
+        // 3 featured articles that always stay
+        for (let i = 0; i < 3; i++) {
+            featuredArticles.push({
+                id: `featured-${i}`,
+                category: 'Featured',
+                headline: `Breaking: Major Story ${i + 1} That Stays Visible`,
+                date: new Date().toLocaleDateString(),
+                content: `This is featured article ${i + 1}. Featured articles remain in the DOM and are not replaced during scrolling. They provide important persistent content.`
+            });
+        }
+        
+        // Regular articles that get virtualized
+        for (let i = 0; i < totalArticles; i++) {
+            regularArticles.push({
+                id: `article-${i}`,
+                category: categories[i % categories.length],
+                headline: `${categories[i % categories.length]} News: Article ${i + 1} of ${totalArticles}`,
+                date: new Date(Date.now() - i * 86400000).toLocaleDateString(),
+                content: `This is regular article ${i + 1}. These articles are replaced as you scroll to maintain performance. Only a subset is shown at any time. Article ID: ${i}`
+            });
+        }
+        
+        // Render articles - Featured stay, regular ones are replaced
+        function renderArticles(regularStartIndex) {
+            const html = [];
+            
+            // Always show featured articles
+            featuredArticles.forEach(article => {
+                html.push(`
+                    <div class="article featured" data-article-id="${article.id}">
+                        <div class="article-header">
+                            <span class="category">${article.category}</span>
+                            <h2 class="headline">${article.headline}</h2>
+                            <div class="meta">📅 ${article.date}</div>
+                        </div>
+                        <div class="content">${article.content}</div>
+                    </div>
+                `);
+            });
+            
+            // Add divider
+            html.push('<div style="text-align: center; color: #999; margin: 20px 0;">— Latest News —</div>');
+            
+            // Show current page of regular articles (virtual scroll)
+            const endIndex = Math.min(regularStartIndex + articlesPerPage, totalArticles);
+            for (let i = regularStartIndex; i < endIndex; i++) {
+                const article = regularArticles[i];
+                html.push(`
+                    <div class="article" data-article-id="${article.id}">
+                        <div class="article-header">
+                            <span class="category" style="background: ${getCategoryColor(article.category)}">${article.category}</span>
+                            <h2 class="headline">${article.headline}</h2>
+                            <div class="meta">📅 ${article.date}</div>
+                        </div>
+                        <div class="content">${article.content}</div>
+                    </div>
+                `);
+            }
+            
+            container.innerHTML = html.join('');
+            currentRegularIndex = regularStartIndex;
+        }
+        
+        function getCategoryColor(category) {
+            const colors = {
+                'Politics': '#e74c3c',
+                'Technology': '#3498db',
+                'Business': '#2ecc71',
+                'Science': '#9b59b6',
+                'Sports': '#f39c12',
+                'Entertainment': '#e91e63'
+            };
+            return colors[category] || '#95a5a6';
+        }
+        
+        // Initial render
+        renderArticles(0);
+        
+        // Handle scroll
+        container.addEventListener('scroll', () => {
+            const scrollTop = container.scrollTop;
+            const scrollHeight = container.scrollHeight;
+            const clientHeight = container.clientHeight;
+            
+            // When near bottom, load next page of regular articles
+            if (scrollTop + clientHeight >= scrollHeight - 200) {
+                const nextIndex = currentRegularIndex + articlesPerPage;
+                if (nextIndex < totalArticles) {
+                    renderArticles(nextIndex);
+                    // Scroll to where regular articles start
+                    const regularStart = document.querySelector('.article:not(.featured)');
+                    if (regularStart) {
+                        container.scrollTop = regularStart.offsetTop - 100;
+                    }
+                }
+            }
+        });
+    </script>
+</body>
+</html>

docs/examples/assets/virtual_scroll_twitter_like.html

@@ -0,0 +1,122 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>Twitter-like Virtual Scroll</title>
+    <style>
+        body {
+            font-family: Arial, sans-serif;
+            margin: 0;
+            padding: 20px;
+            background-color: #f0f2f5;
+        }
+        
+        h1 {
+            color: #1da1f2;
+            text-align: center;
+        }
+        
+        #timeline {
+            max-width: 600px;
+            margin: 0 auto;
+            height: 600px;
+            overflow-y: auto;
+            background: white;
+            border: 1px solid #e1e8ed;
+            border-radius: 10px;
+        }
+        
+        .tweet {
+            padding: 15px;
+            border-bottom: 1px solid #e1e8ed;
+            min-height: 80px;
+        }
+        
+        .tweet:hover {
+            background-color: #f7f9fa;
+        }
+        
+        .author {
+            font-weight: bold;
+            color: #14171a;
+            margin-bottom: 5px;
+        }
+        
+        .content {
+            color: #14171a;
+            line-height: 1.5;
+        }
+        
+        .stats {
+            color: #657786;
+            font-size: 14px;
+            margin-top: 10px;
+        }
+    </style>
+</head>
+<body>
+    <h1>Virtual Scroll Demo - Twitter Style</h1>
+    <p style="text-align: center; color: #666;">This simulates Twitter's timeline where content is replaced as you scroll</p>
+    <div id="timeline"></div>
+    
+    <script>
+        // Simulate Twitter-like virtual scrolling where DOM elements are replaced
+        const timeline = document.getElementById('timeline');
+        const totalTweets = 500;
+        const tweetsPerPage = 10;
+        let currentIndex = 0;
+        
+        // Generate fake tweet data
+        const allTweets = [];
+        for (let i = 0; i < totalTweets; i++) {
+            allTweets.push({
+                id: i,
+                author: `User_${i + 1}`,
+                content: `This is tweet #${i + 1} of ${totalTweets}. Virtual scrolling replaces DOM elements to maintain performance. Unique content ID: ${i}`,
+                likes: Math.floor(Math.random() * 1000),
+                retweets: Math.floor(Math.random() * 500)
+            });
+        }
+        
+        // Render tweets - REPLACES content
+        function renderTweets(startIndex) {
+            const tweets = [];
+            const endIndex = Math.min(startIndex + tweetsPerPage, totalTweets);
+            
+            for (let i = startIndex; i < endIndex; i++) {
+                const tweet = allTweets[i];
+                tweets.push(`
+                    <div class="tweet" data-tweet-id="${tweet.id}">
+                        <div class="author">@${tweet.author}</div>
+                        <div class="content">${tweet.content}</div>
+                        <div class="stats">❤️ ${tweet.likes} | 🔁 ${tweet.retweets}</div>
+                    </div>
+                `);
+            }
+            
+            // REPLACE entire content (virtual scroll behavior)
+            timeline.innerHTML = tweets.join('');
+            currentIndex = startIndex;
+        }
+        
+        // Initial render
+        renderTweets(0);
+        
+        // Handle scroll
+        timeline.addEventListener('scroll', () => {
+            const scrollTop = timeline.scrollTop;
+            const scrollHeight = timeline.scrollHeight;
+            const clientHeight = timeline.clientHeight;
+            
+            // When near bottom, load next page
+            if (scrollTop + clientHeight >= scrollHeight - 100) {
+                const nextIndex = currentIndex + tweetsPerPage;
+                if (nextIndex < totalTweets) {
+                    renderTweets(nextIndex);
+                    // Small scroll adjustment for continuous scrolling
+                    timeline.scrollTop = 50;
+                }
+            }
+        });
+    </script>
+</body>
+</html>

docs/examples/c4a_script/amazon_example/README.md

@@ -0,0 +1,171 @@
+# Amazon R2D2 Product Search Example
+
+A real-world demonstration of Crawl4AI's multi-step crawling with LLM-generated automation scripts.
+
+## 🎯 What This Example Shows
+
+This example demonstrates advanced Crawl4AI features:
+- **LLM-Generated Scripts**: Automatically create C4A-Script from HTML snippets
+- **Multi-Step Crawling**: Navigate through multiple pages using session persistence
+- **Structured Data Extraction**: Extract product data using JSON CSS schemas
+- **Visual Automation**: Watch the browser perform the search (headless=False)
+
+## 🚀 How It Works
+
+### 1. **Script Generation Phase**
+The example uses `C4ACompiler.generate_script()` to analyze Amazon's HTML and create:
+- **Search Script**: Automates filling the search box and clicking search
+- **Extraction Schema**: Defines how to extract product information
+
+### 2. **Crawling Workflow**
+```
+Homepage → Execute Search Script → Extract Products → Save Results
+```
+
+All steps use the same `session_id` to maintain browser state.
+
+### 3. **Data Extraction**
+Products are extracted with:
+- Title, price, rating, reviews
+- Delivery information
+- Sponsored/Small Business badges
+- Direct product URLs
+
+## 📁 Files
+
+- `amazon_r2d2_search.py` - Main example script
+- `header.html` - Amazon search bar HTML (provided)
+- `product.html` - Product card HTML (provided)
+- **Generated files:**
+  - `generated_search_script.c4a` - Auto-generated search automation
+  - `generated_product_schema.json` - Auto-generated extraction rules
+  - `extracted_products.json` - Final scraped data
+  - `search_results_screenshot.png` - Visual proof of results
+
+## 🏃 Running the Example
+
+1. **Prerequisites**
+   ```bash
+   # Ensure Crawl4AI is installed
+   pip install crawl4ai
+   
+   # Set up LLM API key (for script generation)
+   export OPENAI_API_KEY="your-key-here"
+   ```
+
+2. **Run the scraper**
+   ```bash
+   python amazon_r2d2_search.py
+   ```
+
+3. **Watch the magic!**
+   - Browser window opens (not headless)
+   - Navigates to Amazon.com
+   - Searches for "r2d2"
+   - Extracts all products
+   - Saves results to JSON
+
+## 📊 Sample Output
+
+```json
+[
+  {
+    "title": "Death Star BB8 R2D2 Golf Balls with 20 Printed tees",
+    "price": "29.95",
+    "rating": "4.7",
+    "reviews_count": "184",
+    "delivery": "FREE delivery Thu, Jun 19",
+    "url": "https://www.amazon.com/Death-Star-R2D2-Balls-Printed/dp/B081XSYZMS",
+    "is_sponsored": true,
+    "small_business": true
+  },
+  ...
+]
+```
+
+## 🔍 Key Features Demonstrated
+
+### Session Persistence
+```python
+# Same session_id across multiple arun() calls
+config = CrawlerRunConfig(
+    session_id="amazon_r2d2_session",
+    # ... other settings
+)
+```
+
+### LLM Script Generation
+```python
+# Generate automation from natural language + HTML
+script = C4ACompiler.generate_script(
+    html=header_html,
+    query="Find search box, type 'r2d2', click search",
+    mode="c4a"
+)
+```
+
+### JSON CSS Extraction
+```python
+# Structured data extraction with CSS selectors
+schema = {
+    "baseSelector": "[data-component-type='s-search-result']",
+    "fields": [
+        {"name": "title", "selector": "h2 a span", "type": "text"},
+        {"name": "price", "selector": ".a-price-whole", "type": "text"}
+    ]
+}
+```
+
+## 🛠️ Customization
+
+### Search Different Products
+Change the search term in the script generation:
+```python
+search_goal = """
+...
+3. Type "star wars lego" into the search box
+...
+"""
+```
+
+### Extract More Data
+Add fields to the extraction schema:
+```python
+"fields": [
+    # ... existing fields
+    {"name": "prime", "selector": ".s-prime", "type": "exists"},
+    {"name": "image_url", "selector": "img.s-image", "type": "attribute", "attribute": "src"}
+]
+```
+
+### Use Different Sites
+Adapt the approach for other e-commerce sites by:
+1. Providing their HTML snippets
+2. Adjusting the search goals
+3. Updating the extraction schema
+
+## 🎓 Learning Points
+
+1. **No Manual Scripting**: LLM generates all automation code
+2. **Session Management**: Maintain state across page navigations
+3. **Robust Extraction**: Handle dynamic content and multiple products
+4. **Error Handling**: Graceful fallbacks if generation fails
+
+## 🐛 Troubleshooting
+
+- **"No products found"**: Check if Amazon's HTML structure changed
+- **"Script generation failed"**: Ensure LLM API key is configured
+- **"Page timeout"**: Increase wait times in the config
+- **"Session lost"**: Ensure same session_id is used consistently
+
+## 📚 Next Steps
+
+- Try searching for different products
+- Add pagination to get more results
+- Extract product details pages
+- Compare prices across different sellers
+- Build a price monitoring system
+
+---
+
+This example shows the power of combining LLM intelligence with web automation. The scripts adapt to HTML changes and natural language instructions make automation accessible to everyone!

docs/examples/c4a_script/amazon_example/amazon_r2d2_search.py

@@ -0,0 +1,202 @@
+#!/usr/bin/env python3
+"""
+Amazon R2D2 Product Search Example using Crawl4AI
+
+This example demonstrates:
+1. Using LLM to generate C4A-Script from HTML snippets
+2. Multi-step crawling with session persistence
+3. JSON CSS extraction for structured product data
+4. Complete workflow: homepage → search → extract products
+
+Requirements:
+- Crawl4AI with generate_script support
+- LLM API key (configured in environment)
+"""
+
+import asyncio
+import json
+import os
+from pathlib import Path
+from typing import List, Dict, Any
+
+from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
+from crawl4ai import JsonCssExtractionStrategy
+from crawl4ai.script.c4a_compile import C4ACompiler
+
+
+class AmazonR2D2Scraper:
+    def __init__(self):
+        self.base_dir = Path(__file__).parent
+        self.search_script_path = self.base_dir / "generated_search_script.js"
+        self.schema_path = self.base_dir / "generated_product_schema.json"
+        self.results_path = self.base_dir / "extracted_products.json"
+        self.session_id = "amazon_r2d2_session"
+        
+    async def generate_search_script(self) -> str:
+        """Generate JavaScript for Amazon search interaction"""
+        print("🔧 Generating search script from header.html...")
+        
+        # Check if already generated
+        if self.search_script_path.exists():
+            print("✅ Using cached search script")
+            return self.search_script_path.read_text()
+        
+        # Read the header HTML
+        header_html = (self.base_dir / "header.html").read_text()
+        
+        # Generate script using LLM
+        search_goal = """
+        Find the search box and search button, then:
+        1. Wait for the search box to be visible
+        2. Click on the search box to focus it
+        3. Clear any existing text
+        4. Type "r2d2" into the search box
+        5. Click the search submit button
+        6. Wait for navigation to complete and search results to appear
+        """
+        
+        try:
+            script = C4ACompiler.generate_script(
+                html=header_html,
+                query=search_goal,
+                mode="js"
+            )
+            
+            # Save for future use
+            self.search_script_path.write_text(script)
+            print("✅ Search script generated and saved!")
+            print(f"📄 Script:\n{script}")
+            return script
+            
+        except Exception as e:
+            print(f"❌ Error generating search script: {e}")
+
+    
+    async def generate_product_schema(self) -> Dict[str, Any]:
+        """Generate JSON CSS extraction schema from product HTML"""
+        print("\n🔧 Generating product extraction schema...")
+        
+        # Check if already generated
+        if self.schema_path.exists():
+            print("✅ Using cached extraction schema")
+            return json.loads(self.schema_path.read_text())
+        
+        # Read the product HTML
+        product_html = (self.base_dir / "product.html").read_text()
+        
+        # Generate extraction schema using LLM
+        schema_goal = """
+        Create a JSON CSS extraction schema to extract:
+        - Product title (from the h2 element)
+        - Price (the dollar amount)
+        - Rating (star rating value)
+        - Number of reviews
+        - Delivery information
+        - Product URL (from the main product link)
+        - Whether it's sponsored
+        - Small business badge if present
+        
+        The schema should handle multiple products on a search results page.
+        """
+        
+        try:
+            # Generate JavaScript that returns the schema
+            schema = JsonCssExtractionStrategy.generate_schema(
+                html=product_html,
+                query=schema_goal,
+            )
+            
+            # Save for future use
+            self.schema_path.write_text(json.dumps(schema, indent=2))
+            print("✅ Extraction schema generated and saved!")
+            print(f"📄 Schema fields: {[f['name'] for f in schema['fields']]}")
+            return schema
+            
+        except Exception as e:
+            print(f"❌ Error generating schema: {e}")
+    
+    async def crawl_amazon(self):
+        """Main crawling logic with 2 calls using same session"""
+        print("\n🚀 Starting Amazon R2D2 product search...")
+        
+        # Generate scripts and schemas
+        search_script = await self.generate_search_script()
+        product_schema = await self.generate_product_schema()
+        
+        # Configure browser (headless=False to see the action)
+        browser_config = BrowserConfig(
+            headless=False,
+            verbose=True,
+            viewport_width=1920,
+            viewport_height=1080
+        )
+        
+        async with AsyncWebCrawler(config=browser_config) as crawler:
+            print("\n📍 Step 1: Navigate to Amazon and search for R2D2")
+            
+            # FIRST CALL: Navigate to Amazon and execute search
+            search_config = CrawlerRunConfig(
+                session_id=self.session_id,
+                js_code= f"(() => {{ {search_script} }})()",  # Execute generated JS
+                wait_for=".s-search-results",  # Wait for search results
+                extraction_strategy=JsonCssExtractionStrategy(schema=product_schema),
+                delay_before_return_html=3.0  # Give time for results to load
+            )
+            
+            results = await crawler.arun(
+                url="https://www.amazon.com",
+                config=search_config
+            )
+            
+            if not results.success:
+                print("❌ Failed to search Amazon")
+                print(f"Error: {results.error_message}")
+                return
+            
+            print("✅ Search completed successfully!")            
+            print("✅ Product extraction completed!")
+            
+            # Extract and save results
+            print("\n📍 Extracting product data")
+            
+            if results[0].extracted_content:
+                products = json.loads(results[0].extracted_content)
+                print(f"🔍 Found {len(products)} products in search results")
+
+                print(f"✅ Extracted {len(products)} R2D2 products")
+
+                # Save results
+                self.results_path.write_text(
+                    json.dumps(products, indent=2)
+                )
+                print(f"💾 Results saved to: {self.results_path}")
+                
+                # Print sample results
+                print("\n📊 Sample Results:")
+                for i, product in enumerate(products[:3], 1):
+                    print(f"\n{i}. {product['title'][:60]}...")
+                    print(f"   Price: ${product['price']}")
+                    print(f"   Rating: {product['rating']} ({product['number_of_reviews']} reviews)")
+                    print(f"   {'🏪 Small Business' if product['small_business_badge'] else ''}")
+                    print(f"   {'📢 Sponsored' if product['sponsored'] else ''}")
+                
+            else:
+                print("❌ No products extracted")
+
+
+
+async def main():
+    """Run the Amazon scraper"""
+    scraper = AmazonR2D2Scraper()
+    await scraper.crawl_amazon()
+    
+    print("\n🎉 Amazon R2D2 search example completed!")
+    print("Check the generated files:")
+    print("  - generated_search_script.js")
+    print("  - generated_product_schema.json") 
+    print("  - extracted_products.json")
+    print("  - search_results_screenshot.png")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/c4a_script/amazon_example/extracted_products.json

@@ -0,0 +1,114 @@
+[
+  {
+    "title": "Death Star BB8 R2D2 Golf Balls with 20 Printed tees \u2022 Great Gift IDEA from Moms, DADS and Kids -",
+    "price": "$29.95",
+    "rating": "4.7 out of 5 stars",
+    "number_of_reviews": "184",
+    "delivery_info": "FREE delivery",
+    "product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfYXRmOjIwMDA2NzY0ODgwMjc5ODo6MDo6&url=%2FDeath-Star-R2D2-Balls-Printed%2Fdp%2FB081XSYZMS%2Fref%3Dsr_1_1_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-1-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9hdGY%26psc%3D1",
+    "sponsored": "Sponsored",
+    "small_business_badge": "Small Business"
+  },
+  {
+    "title": "TEENKON French Press Insulated 304 Stainless Steel Coffee Maker, 32 Oz Robot R2D2 Hand Home Coffee Presser, with Filter Screen for Brew Coffee and Tea (White)",
+    "price": "$49.99",
+    "rating": "4.3 out of 5 stars",
+    "number_of_reviews": "82",
+    "delivery_info": "Delivery",
+    "product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjMwMDAzNzc4Njg4MDAwMjo6MDo6&url=%2FTEENKON-French-Insulated-Stainless-Presser%2Fdp%2FB0CD3HH5PN%2Fref%3Dsr_1_17_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-17-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
+    "sponsored": "Sponsored"
+  },
+  {
+    "title": "3D Illusion LED Night Light,7 Colors Gradual Changing Touch Switch USB Table Lamp for Holiday Gifts or Home Decorations (R2-D2)",
+    "price": "$9.97",
+    "rating": "4.3 out of 5 stars",
+    "number_of_reviews": "235",
+    "delivery_info": "Delivery",
+    "product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjIwMDA0NjMwMTQwODA4MTo6MDo6&url=%2FIllusion-Gradual-Changing-Holiday-Decorations%2Fdp%2FB089NMBKF2%2Fref%3Dsr_1_18_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-18-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
+    "sponsored": "Sponsored"
+  },
+  {
+    "title": "Paladone Star Wars R2-D2 Headlamp with Droid Sounds, Officially Licensed Disney Star Wars Head Lamp and Reading Light",
+    "price": "$21.99",
+    "rating": "4.1 out of 5 stars",
+    "number_of_reviews": "66",
+    "delivery_info": "FREE delivery",
+    "product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjMwMDI1NjA0MDQwMTUwMjo6MDo6&url=%2FSounds-Officially-Licensed-Headlamp-Flashlight%2Fdp%2FB09RTDZF8J%2Fref%3Dsr_1_19_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-19-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
+    "sponsored": "Sponsored"
+  },
+  {
+    "title": "4 Pcs Set Star Wars Kylo Ren BB8 Stormtrooper R2D2 Silicone Travel Luggage Baggage Identification Labels ID Tag for Bag Suitcase Plane Cruise Ships with Belt Strap",
+    "price": "$16.99",
+    "rating": "4.7 out of 5 stars",
+    "number_of_reviews": "3,414",
+    "delivery_info": "FREE delivery",
+    "product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjIwMDAyMzk3ODkwMzIxMTo6MDo6&url=%2FFinex-Set-Suitcase-Adjustable-Stormtrooper%2Fdp%2FB01D1CBFJS%2Fref%3Dsr_1_24_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-24-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
+    "sponsored": "Sponsored",
+    "small_business_badge": "Small Business"
+  },
+  {
+    "title": "Papyrus Star Wars Birthday Card Assortment, Darth Vader, Storm Trooper, and R2-D2 (3-Count)",
+    "price": "$23.16",
+    "rating": "4.8 out of 5 stars",
+    "number_of_reviews": "328",
+    "delivery_info": "FREE delivery",
+    "product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjMwMDcwNzI4MjA1MzcwMjo6MDo6&url=%2FPapyrus-Birthday-Assortment-Characters-3-Count%2Fdp%2FB07YT2ZPKX%2Fref%3Dsr_1_25_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-25-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
+    "sponsored": "Sponsored"
+  },
+  {
+    "title": "STAR WARS R2-D2 Artoo 3D Top Motion Lamp, Mood Light | 18 Inches",
+    "price": "$69.99",
+    "rating": "4.5 out of 5 stars",
+    "number_of_reviews": "520",
+    "delivery_info": "FREE delivery",
+    "product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjIwMDA5NDc3MzczMTQ0MTo6MDo6&url=%2FR2-D2-Artoo-Motion-Light-Inches%2Fdp%2FB08MCWPHQR%2Fref%3Dsr_1_26_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-26-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
+    "sponsored": "Sponsored"
+  },
+  {
+    "title": "Saturday Park Star Wars Droids Full Sheet Set - 4 Piece 100% Organic Cotton Sheets Features R2-D2 & BB-8 - GOTS & Oeko-TEX Certified (Star Wars Official)",
+    "price": "$70.00",
+    "rating": "4.5 out of 5 stars",
+    "number_of_reviews": "388",
+    "delivery_info": "FREE delivery",
+    "product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjMwMDAyMzI0NDI5MDQwMjo6MDo6&url=%2FSaturday-Park-Star-Droids-Sheet%2Fdp%2FB0BBSFX4J2%2Fref%3Dsr_1_27_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-27-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
+    "sponsored": "Sponsored",
+    "small_business_badge": "1 sustainability feature"
+  },
+  {
+    "title": "AQUARIUS Star Wars R2D2 Action Figure Funky Chunky Novelty Magnet for Refrigerator, Locker, Whiteboard & Game Room Officially Licensed Merchandise & Collectibles",
+    "price": "$11.94",
+    "rating": "4.3 out of 5 stars",
+    "number_of_reviews": "10",
+    "delivery_info": "FREE delivery",
+    "product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjMwMDA5MDMwMzY5NjEwMjo6MDo6&url=%2FAQUARIUS-Refrigerator-Whiteboard-Merchandise-Collectibles%2Fdp%2FB09W8VKXGC%2Fref%3Dsr_1_32_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-32-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
+    "sponsored": "Sponsored"
+  },
+  {
+    "title": "STAR WARS C-3PO and R2-D2 Men's Crew Socks 2 Pair Pack",
+    "price": "$11.95",
+    "rating": "4.7 out of 5 stars",
+    "number_of_reviews": "1,272",
+    "delivery_info": "Delivery",
+    "product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjIwMDAxMDk5NDkyMTg2MTo6MDo6&url=%2FStar-Wars-R2-D2-C-3PO-Socks%2Fdp%2FB0178IU1GY%2Fref%3Dsr_1_33_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-33-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
+    "sponsored": "Sponsored"
+  },
+  {
+    "title": "Buckle-Down Belt Women's Cinch Star Wars R2D2 Bounding Parts3 White Black Blue Gray Available In Adjustable Sizes",
+    "price": "$24.95",
+    "rating": "4.3 out of 5 stars",
+    "number_of_reviews": "32",
+    "delivery_info": "FREE delivery",
+    "product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjMwMDY1OTQ5NTQ4MzkwMjo6MDo6&url=%2FWomens-Cinch-Bounding-Parts3-Inches%2Fdp%2FB07WK7RG4D%2Fref%3Dsr_1_34_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-34-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
+    "sponsored": "Sponsored",
+    "small_business_badge": "Small Business"
+  },
+  {
+    "title": "Star Wars R2D2 Metal Head Vintage Disney+ T-Shirt",
+    "price": "$22.99",
+    "rating": "4.8 out of 5 stars",
+    "number_of_reviews": "869",
+    "product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjIwMDA1OTUyMzgzNDMyMTo6MDo6&url=%2FStar-Wars-Vintage-Graphic-T-Shirt%2Fdp%2FB07H9PSNXS%2Fref%3Dsr_1_35_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-35-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
+    "sponsored": "Sponsored",
+    "small_business_badge": "1 sustainability feature"
+  }
+]

docs/examples/c4a_script/amazon_example/generated_product_schema.json

@@ -0,0 +1,47 @@
+{
+  "name": "Amazon Product Search Results",
+  "baseSelector": "div[data-component-type='s-impression-counter']",
+  "fields": [
+    {
+      "name": "title",
+      "selector": "h2.a-size-base-plus.a-spacing-none.a-color-base.a-text-normal span",
+      "type": "text"
+    },
+    {
+      "name": "price",
+      "selector": "span.a-price > span.a-offscreen",
+      "type": "text"
+    },
+    {
+      "name": "rating",
+      "selector": "i.a-icon-star-small span.a-icon-alt",
+      "type": "text"
+    },
+    {
+      "name": "number_of_reviews",
+      "selector": "a.a-link-normal.s-underline-text span.a-size-base",
+      "type": "text"
+    },
+    {
+      "name": "delivery_info",
+      "selector": "div[data-cy='delivery-recipe'] span.a-color-base",
+      "type": "text"
+    },
+    {
+      "name": "product_url",
+      "selector": "a.a-link-normal.s-no-outline",
+      "type": "attribute",
+      "attribute": "href"
+    },
+    {
+      "name": "sponsored",
+      "selector": "span.puis-label-popover-default span.a-color-secondary",
+      "type": "text"
+    },
+    {
+      "name": "small_business_badge",
+      "selector": "span.a-size-base.a-color-base",
+      "type": "text"
+    }
+  ]
+}

docs/examples/c4a_script/amazon_example/generated_search_script.js

@@ -0,0 +1,9 @@
+const searchBox = document.querySelector('#twotabsearchtextbox');
+const searchButton = document.querySelector('#nav-search-submit-button');
+
+if (searchBox && searchButton) {
+  searchBox.focus();
+  searchBox.value = '';
+  searchBox.value = 'r2d2';
+  searchButton.click();
+}

docs/examples/c4a_script/amazon_example/header.html

@@ -0,0 +1,214 @@
+<div id="nav-belt" style="width: 100%;">
+    <div class="nav-left">
+        <script type="text/javascript">window.navmet.tmp = +new Date();</script>
+        <div id="nav-logo">
+            <a href="/ref=nav_logo" id="nav-logo-sprites" class="nav-logo-link nav-progressive-attribute"
+                aria-label="Amazon" lang="en">
+                <span class="nav-sprite nav-logo-base"></span>
+                <span id="logo-ext" class="nav-sprite nav-logo-ext nav-progressive-content"></span>
+                <span class="nav-logo-locale">.us</span>
+            </a>
+        </div>
+        <script
+            type="text/javascript">window.navmet.push({ key: 'Logo', end: +new Date(), begin: window.navmet.tmp });</script>
+
+        <div id="nav-global-location-slot">
+            <span id="nav-global-location-data-modal-action" class="a-declarative nav-progressive-attribute"
+                data-a-modal="{&quot;width&quot;:375, &quot;closeButton&quot;:&quot;true&quot;,&quot;popoverLabel&quot;:&quot;Choose your location&quot;, &quot;ajaxHeaders&quot;:{&quot;anti-csrftoken-a2z&quot;:&quot;hHBwllskaYQrylaW9ifYQIdmqBZOtGdKro0TWb5kDoPKAAAAAGhEMhsAAAAB&quot;}, &quot;name&quot;:&quot;glow-modal&quot;, &quot;url&quot;:&quot;/portal-migration/hz/glow/get-rendered-address-selections?deviceType=desktop&amp;pageType=Gateway&amp;storeContext=NoStoreName&amp;actionSource=desktop-modal&quot;, &quot;footer&quot;:&quot;<span class=\&quot;a-declarative\&quot; data-action=\&quot;a-popover-close\&quot; data-a-popover-close=\&quot;{}\&quot;><span class=\&quot;a-button a-button-primary\&quot;><span class=\&quot;a-button-inner\&quot;><button name=\&quot;glowDoneButton\&quot; class=\&quot;a-button-text\&quot; type=\&quot;button\&quot;>Done</button></span></span></span>&quot;,&quot;header&quot;:&quot;Choose your location&quot;}"
+                data-action="a-modal">
+                <a id="nav-global-location-popover-link" role="button" tabindex="0"
+                    class="nav-a nav-a-2 a-popover-trigger a-declarative nav-progressive-attribute" href="">
+                    <div class="nav-sprite nav-progressive-attribute" id="nav-packard-glow-loc-icon"></div>
+                    <div id="glow-ingress-block">
+                        <span class="nav-line-1 nav-progressive-content" id="glow-ingress-line1">
+                            Deliver to
+                        </span>
+                        <span class="nav-line-2 nav-progressive-content" id="glow-ingress-line2">
+                            Malaysia
+                        </span>
+                    </div>
+                </a>
+            </span>
+            <input data-addnewaddress="add-new" id="unifiedLocation1ClickAddress" name="dropdown-selection"
+                type="hidden" value="add-new" class="nav-progressive-attribute">
+            <input data-addnewaddress="add-new" id="ubbShipTo" name="dropdown-selection-ubb" type="hidden"
+                value="add-new" class="nav-progressive-attribute">
+            <input id="glowValidationToken" name="glow-validation-token" type="hidden"
+                value="hHBwllskaYQrylaW9ifYQIdmqBZOtGdKro0TWb5kDoPKAAAAAGhEMhsAAAAB" class="nav-progressive-attribute">
+            <input id="glowDestinationType" name="glow-destination-type" type="hidden" value="COUNTRY"
+                class="nav-progressive-attribute">
+        </div>
+
+        <div id="nav-global-location-toaster-script-container" class="nav-progressive-content">
+            <!-- NAVYAAN-GLOW-NAV-TOASTER -->
+            <script>
+                P.when('glow-toaster-strings').execute(function (S) {
+                    S.load({ "glow-toaster-address-change-error": "An error has occurred and the address has not been updated. Please try again.", "glow-toaster-unknown-error": "An error has occurred. Please try again." });
+                });
+            </script>
+            <script>
+                P.when('glow-toaster-manager').execute(function (M) {
+                    M.create({ "pageType": "Gateway", "aisTransitionState": null, "rancorLocationSource": "REALM_DEFAULT" })
+                });
+            </script>
+        </div>
+
+    </div>
+    <div class="nav-fill" id="nav-fill-search">
+        <script type="text/javascript">window.navmet.tmp = +new Date();</script>
+        <div id="nav-search">
+            <div id="nav-bar-left"></div>
+            <form id="nav-search-bar-form" accept-charset="utf-8" action="/s/ref=nb_sb_noss_1"
+                class="nav-searchbar nav-progressive-attribute" method="GET" name="site-search" role="search">
+
+                <div class="nav-left">
+                    <div id="nav-search-dropdown-card">
+
+                        <div class="nav-search-scope nav-sprite">
+                            <div class="nav-search-facade" data-value="search-alias=aps">
+                                <span id="nav-search-label-id" class="nav-search-label nav-progressive-content"
+                                    style="width: auto;">All</span>
+                                <i class="nav-icon"></i>
+                            </div>
+                            <label id="searchDropdownDescription" for="searchDropdownBox"
+                                class="nav-progressive-attribute" style="display:none">Select the department you want to
+                                search in</label>
+                            <select aria-describedby="searchDropdownDescription"
+                                class="nav-search-dropdown searchSelect nav-progressive-attrubute nav-progressive-search-dropdown"
+                                data-nav-digest="k+fyIAyB82R9jVEmroQ0OWwSW3A=" data-nav-selected="0"
+                                id="searchDropdownBox" name="url" style="display: block; top: 2.5px;" tabindex="0"
+                                title="Search in">
+                                <option selected="selected" value="search-alias=aps">All Departments</option>
+                                <option value="search-alias=arts-crafts-intl-ship">Arts &amp; Crafts</option>
+                                <option value="search-alias=automotive-intl-ship">Automotive</option>
+                                <option value="search-alias=baby-products-intl-ship">Baby</option>
+                                <option value="search-alias=beauty-intl-ship">Beauty &amp; Personal Care</option>
+                                <option value="search-alias=stripbooks-intl-ship">Books</option>
+                                <option value="search-alias=fashion-boys-intl-ship">Boys' Fashion</option>
+                                <option value="search-alias=computers-intl-ship">Computers</option>
+                                <option value="search-alias=deals-intl-ship">Deals</option>
+                                <option value="search-alias=digital-music">Digital Music</option>
+                                <option value="search-alias=electronics-intl-ship">Electronics</option>
+                                <option value="search-alias=fashion-girls-intl-ship">Girls' Fashion</option>
+                                <option value="search-alias=hpc-intl-ship">Health &amp; Household</option>
+                                <option value="search-alias=kitchen-intl-ship">Home &amp; Kitchen</option>
+                                <option value="search-alias=industrial-intl-ship">Industrial &amp; Scientific</option>
+                                <option value="search-alias=digital-text">Kindle Store</option>
+                                <option value="search-alias=luggage-intl-ship">Luggage</option>
+                                <option value="search-alias=fashion-mens-intl-ship">Men's Fashion</option>
+                                <option value="search-alias=movies-tv-intl-ship">Movies &amp; TV</option>
+                                <option value="search-alias=music-intl-ship">Music, CDs &amp; Vinyl</option>
+                                <option value="search-alias=pets-intl-ship">Pet Supplies</option>
+                                <option value="search-alias=instant-video">Prime Video</option>
+                                <option value="search-alias=software-intl-ship">Software</option>
+                                <option value="search-alias=sporting-intl-ship">Sports &amp; Outdoors</option>
+                                <option value="search-alias=tools-intl-ship">Tools &amp; Home Improvement</option>
+                                <option value="search-alias=toys-and-games-intl-ship">Toys &amp; Games</option>
+                                <option value="search-alias=videogames-intl-ship">Video Games</option>
+                                <option value="search-alias=fashion-womens-intl-ship">Women's Fashion</option>
+                            </select>
+                        </div>
+
+                    </div>
+                </div>
+                <div class="nav-fill">
+                    <div class="nav-search-field ">
+                        <label for="twotabsearchtextbox" style="display: none;">Search Amazon</label>
+                        <input type="text" id="twotabsearchtextbox" value="" name="field-keywords" autocomplete="off"
+                            placeholder="Search Amazon" class="nav-input nav-progressive-attribute" dir="auto"
+                            tabindex="0" aria-label="Search Amazon" role="searchbox" aria-autocomplete="list"
+                            aria-controls="sac-autocomplete-results-container" aria-expanded="false"
+                            aria-haspopup="grid" spellcheck="false">
+                    </div>
+                    <div id="nav-iss-attach"></div>
+                </div>
+                <div class="nav-right">
+                    <div class="nav-search-submit nav-sprite">
+                        <span id="nav-search-submit-text"
+                            class="nav-search-submit-text nav-sprite nav-progressive-attribute" aria-label="Go">
+                            <input id="nav-search-submit-button" type="submit"
+                                class="nav-input nav-progressive-attribute" value="Go" tabindex="0">
+                        </span>
+                    </div>
+                </div>
+                <input type="hidden" id="isscrid" name="crid" value="15O5T5OCG5OZE"><input type="hidden" id="issprefix"
+                    name="sprefix" value="r2d2,aps,588">
+            </form>
+        </div>
+        <script
+            type="text/javascript">window.navmet.push({ key: 'Search', end: +new Date(), begin: window.navmet.tmp });</script>
+    </div>
+    <div class="nav-right">
+        <script type="text/javascript">window.navmet.tmp = +new Date();</script>
+        <div id="nav-tools" class="layoutToolbarPadding">
+
+
+
+
+            <div class="nav-div" id="icp-nav-flyout">
+                <a href="/customer-preferences/edit?ie=UTF8&amp;preferencesReturnUrl=%2F&amp;ref_=topnav_lang_ais"
+                    class="nav-a nav-a-2 icp-link-style-2" aria-label="Choose a language for shopping in Amazon United States. The current selection is English (EN).
+">
+                    <span class="icp-nav-link-inner">
+                        <span class="nav-line-1">
+                        </span>
+                        <span class="nav-line-2">
+                            <span class="icp-nav-flag icp-nav-flag-us icp-nav-flag-lop" role="img"
+                                aria-label="United States"></span>
+                            <div>EN</div>
+                        </span>
+                    </span>
+                </a>
+                <button class="nav-flyout-button nav-icon nav-arrow" aria-label="Expand to Change Language or Country"
+                    tabindex="0" style="visibility: visible;"></button>
+            </div>
+
+
+            <div class="nav-div" id="nav-link-accountList">
+                <a href="https://www.amazon.com/ap/signin?openid.pape.max_auth_age=0&amp;openid.return_to=https%3A%2F%2Fwww.amazon.com%2F%3Fref_%3Dnav_ya_signin&amp;openid.identity=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0%2Fidentifier_select&amp;openid.assoc_handle=usflex&amp;openid.mode=checkid_setup&amp;openid.claimed_id=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0%2Fidentifier_select&amp;openid.ns=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0"
+                    class="nav-a nav-a-2   nav-progressive-attribute" data-nav-ref="nav_ya_signin"
+                    data-nav-role="signin" data-ux-jq-mouseenter="true" tabindex="0" data-csa-c-type="link"
+                    data-csa-c-slot-id="nav-link-accountList" data-csa-c-content-id="nav_ya_signin"
+                    aria-controls="nav-flyout-accountList" data-csa-c-id="37vs0l-z575id-52hnw3-x34ncp">
+                    <div class="nav-line-1-container"><span id="nav-link-accountList-nav-line-1"
+                            class="nav-line-1 nav-progressive-content">Hello, sign in</span></div>
+                    <span class="nav-line-2 ">Account &amp; Lists
+                    </span>
+                </a>
+                <button class="nav-flyout-button nav-icon nav-arrow" aria-label="Expand Account and Lists" tabindex="0"
+                    style="visibility: visible;"></button>
+            </div>
+
+
+            <a href="/gp/css/order-history?ref_=nav_orders_first" class="nav-a nav-a-2   nav-progressive-attribute"
+                id="nav-orders" tabindex="0">
+                <span class="nav-line-1">Returns</span>
+                <span class="nav-line-2">&amp; Orders<span class="nav-icon nav-arrow"></span></span>
+            </a>
+
+
+
+            <a href="/gp/cart/view.html?ref_=nav_cart" aria-label="0 items in cart"
+                class="nav-a nav-a-2 nav-progressive-attribute" id="nav-cart">
+                <div id="nav-cart-count-container">
+                    <span id="nav-cart-count" aria-hidden="true"
+                        class="nav-cart-count nav-cart-0 nav-progressive-attribute nav-progressive-content">0</span>
+                    <span class="nav-cart-icon nav-sprite"></span>
+                </div>
+                <div id="nav-cart-text-container" class=" nav-progressive-attribute">
+                    <span aria-hidden="true" class="nav-line-1">
+
+                    </span>
+                    <span aria-hidden="true" class="nav-line-2">
+                        Cart
+                        <span class="nav-icon nav-arrow"></span>
+                    </span>
+                </div>
+            </a>
+
+        </div>
+        <script
+            type="text/javascript">window.navmet.push({ key: 'Tools', end: +new Date(), begin: window.navmet.tmp });</script>
+
+    </div>
+</div>

docs/examples/c4a_script/amazon_example/product.html

@@ -0,0 +1,206 @@
+<div class="sg-col-inner">
+    <div cel_widget_id="MAIN-SEARCH_RESULTS-2"
+        class="s-widget-container s-spacing-small s-widget-container-height-small celwidget slot=MAIN template=SEARCH_RESULTS widgetId=search-results_1"
+        data-csa-c-pos="1" data-csa-c-item-id="amzn1.asin.1.B081XSYZMS" data-csa-op-log-render="" data-csa-c-type="item"
+        data-csa-c-id="dp9zuy-vyww1v-brlmmq-fmgitb" data-cel-widget="MAIN-SEARCH_RESULTS-2">
+
+
+        <div data-component-type="s-impression-logger"
+            data-component-props="{&quot;percentageShownToFire&quot;:&quot;50&quot;,&quot;batchable&quot;:true,&quot;requiredElementSelector&quot;:&quot;.s-image:visible&quot;,&quot;url&quot;:&quot;https://unagi-na.amazon.com/1/events/com.amazon.eel.SponsoredProductsEventTracking.prod?qualifier=1749299833&amp;id=1740514893473797&amp;widgetName=sp_atf&amp;adId=200067648802798&amp;eventType=1&amp;adIndex=0&quot;}"
+            class="rush-component s-expand-height" data-component-id="6">
+
+
+
+            <div data-component-type="s-impression-counter"
+                data-component-props="{&quot;presenceCounterName&quot;:&quot;sp_delivered&quot;,&quot;testElementSelector&quot;:&quot;.s-image&quot;,&quot;hiddenCounterName&quot;:&quot;sp_hidden&quot;}"
+                class="rush-component s-featured-result-item s-expand-height" data-component-id="7">
+                <span class="a-declarative" data-version-id="v2dwi5hq8xzthf26x0gg1mcl2oj"
+                    data-render-id="r3o8bgr5zt3kmy2jv4su6fn4kyw" data-action="puis-card-container-declarative"
+                    data-csa-c-func-deps="aui-da-puis-card-container-declarative"
+                    data-csa-c-item-id="amzn1.asin.B081XSYZMS" data-csa-c-posx="1" data-csa-c-type="item"
+                    data-csa-c-owner="puis" data-csa-c-id="88w0j1-kcbf5g-80v4i9-96cv88">
+                    <div class="puis-card-container s-card-container s-overflow-hidden aok-relative puis-expand-height puis-include-content-margin puis puis-v2dwi5hq8xzthf26x0gg1mcl2oj s-latency-cf-section puis-card-border"
+                        data-cy="asin-faceout-container">
+                        <div class="a-section a-spacing-base">
+                            <div class="s-product-image-container aok-relative s-text-center s-image-overlay-grey puis-image-overlay-grey s-padding-left-small s-padding-right-small puis-spacing-small s-height-equalized puis puis-v2dwi5hq8xzthf26x0gg1mcl2oj"
+                                data-cy="image-container" style="padding-top: 0px !important;"><span
+                                    data-component-type="s-product-image" class="rush-component"
+                                    data-version-id="v2dwi5hq8xzthf26x0gg1mcl2oj"
+                                    data-render-id="r3o8bgr5zt3kmy2jv4su6fn4kyw"><a aria-hidden="true"
+                                        class="a-link-normal s-no-outline" tabindex="-1"
+                                        href="/sspa/click?ie=UTF8&amp;spc=MToxNzQwNTE0ODkzNDczNzk3OjE3NDkyOTk4MzM6c3BfYXRmOjIwMDA2NzY0ODgwMjc5ODo6MDo6&amp;url=%2FDeath-Star-R2D2-Balls-Printed%2Fdp%2FB081XSYZMS%2Fref%3Dsr_1_1_sspa%3Fcrid%3D3C1EXMXN59Q9G%26dib%3DeyJ2IjoiMSJ9.7tBl5bhZh59L9qIPZUe9SLa2fy_HvzboxuQxvrRcAc0VUXayi9fxQFsMLyFplDE9vMkIJbP76AVpa-5-fxhNza3DqhX4tss4NlB49WPi_dA00Hw6O8qK5pDzdetYlhGgOyXOLBe7mTG9oJ5W0wcvQhEVoX9mpJk_SGeqRLWGA0dBSjYCZtiyrY8_B-DP53S7fbYwiSYtq-g7sQDXKVadRpGvUyKq7yxA0SLsU42uvoqSGb0qcd6udL1wbnTEkKmwNjNSb7xIUb-8PyE7DTPMt1ScJksn70sFQMJNkM2aK5M.x9_jYvKPnSibV1d0umUStZBxlSTSXrzVIFKqFzS8c-U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749299833%26sprefix%3Dr2d2%252Caps%252C548%26sr%3D8-1-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9hdGY%26psc%3D1">
+                                        <div class="a-section aok-relative s-image-square-aspect"><img class="s-image"
+                                                src="https://m.media-amazon.com/images/I/61kAC69zQUL._AC_UL320_.jpg"
+                                                srcset="https://m.media-amazon.com/images/I/61kAC69zQUL._AC_UL320_.jpg 1x, https://m.media-amazon.com/images/I/61kAC69zQUL._AC_UL480_FMwebp_QL65_.jpg 1.5x, https://m.media-amazon.com/images/I/61kAC69zQUL._AC_UL640_FMwebp_QL65_.jpg 2x, https://m.media-amazon.com/images/I/61kAC69zQUL._AC_UL800_FMwebp_QL65_.jpg 2.5x, https://m.media-amazon.com/images/I/61kAC69zQUL._AC_UL960_FMwebp_QL65_.jpg 3x"
+                                                alt="Sponsored Ad - Death Star BB8 R2D2 Golf Balls with 20 Printed tees • Great Gift IDEA from Moms, DADS and Kids -"
+                                                aria-hidden="true" data-image-index="1" data-image-load=""
+                                                data-image-latency="s-product-image" data-image-source-density="1">
+                                        </div>
+                                    </a></span></div>
+                            <div class="a-section a-spacing-small puis-padding-left-small puis-padding-right-small">
+                                <div data-cy="title-recipe"
+                                    class="a-section a-spacing-none a-spacing-top-small s-title-instructions-style">
+                                    <div class="a-row a-spacing-micro"><span class="a-declarative"
+                                            data-version-id="v2dwi5hq8xzthf26x0gg1mcl2oj"
+                                            data-render-id="r3o8bgr5zt3kmy2jv4su6fn4kyw" data-action="a-popover"
+                                            data-csa-c-func-deps="aui-da-a-popover"
+                                            data-a-popover="{&quot;name&quot;:&quot;sp-info-popover-B081XSYZMS&quot;,&quot;position&quot;:&quot;triggerVertical&quot;,&quot;popoverLabel&quot;:&quot;View Sponsored information or leave ad feedback&quot;,&quot;closeButtonLabel&quot;:&quot;Close popup&quot;,&quot;closeButton&quot;:&quot;true&quot;,&quot;dataStrategy&quot;:&quot;preload&quot;}"
+                                            data-csa-c-type="widget" data-csa-c-id="wqddan-z1l67e-lissct-rciw65"><a
+                                                href="javascript:void(0)" role="button" style="text-decoration: none;"
+                                                class="puis-label-popover puis-sponsored-label-text"><span
+                                                    class="puis-label-popover-default"><span
+                                                        aria-label="View Sponsored information or leave ad feedback"
+                                                        class="a-color-secondary">Sponsored</span></span><span
+                                                    class="puis-label-popover-hover"><span aria-hidden="true"
+                                                        class="a-color-base">Sponsored</span></span> <span
+                                                    class="aok-inline-block puis-sponsored-label-info-icon"></span></a></span>
+                                        <div class="a-popover-preload" id="a-popover-sp-info-popover-B081XSYZMS">
+                                            <div class="puis puis-v2dwi5hq8xzthf26x0gg1mcl2oj"><span>You’re seeing this
+                                                    ad based on the product’s relevance to your search query.</span>
+                                                <div class="a-row"><span class="a-declarative"
+                                                        data-version-id="v2dwi5hq8xzthf26x0gg1mcl2oj"
+                                                        data-render-id="r3o8bgr5zt3kmy2jv4su6fn4kyw"
+                                                        data-action="s-safe-ajax-modal-trigger"
+                                                        data-csa-c-func-deps="aui-da-s-safe-ajax-modal-trigger"
+                                                        data-s-safe-ajax-modal-trigger="{&quot;header&quot;:&quot;Leave feedback&quot;,&quot;dataStrategy&quot;:&quot;ajax&quot;,&quot;ajaxUrl&quot;:&quot;/af/sp-loom/feedback-form?pl=%7B%22adPlacementMetaData%22%3A%7B%22searchTerms%22%3A%22cjJkMg%3D%3D%22%2C%22pageType%22%3A%22Search%22%2C%22feedbackType%22%3A%22sponsoredProductsLoom%22%2C%22slotName%22%3A%22TOP%22%7D%2C%22adCreativeMetaData%22%3A%7B%22adProgramId%22%3A1024%2C%22adCreativeDetails%22%3A%5B%7B%22asin%22%3A%22B081XSYZMS%22%2C%22title%22%3A%22Death+Star+BB8+R2D2+Golf+Balls+with+20+Printed+tees+%E2%80%A2+Great+Gift+IDEA+from+Moms%2C+DADS+and+Kids+-%22%2C%22priceInfo%22%3A%7B%22amount%22%3A29.95%2C%22currencyCode%22%3A%22USD%22%7D%2C%22sku%22%3A%22starwars3pk20tees%22%2C%22adId%22%3A%22A03790291PREH7M3Q3SVS%22%2C%22campaignId%22%3A%22A01050612Q0SQZ2PTMGO9%22%2C%22advertiserIdNS%22%3Anull%2C%22selectionSignals%22%3Anull%7D%5D%7D%7D&quot;}"
+                                                        data-csa-c-type="widget"
+                                                        data-csa-c-id="ygslsp-ir23ei-7k9x6z-73l1tp"><a
+                                                            class="a-link-normal s-underline-text s-underline-link-text s-link-style"
+                                                            href="#"><span>Leave ad feedback</span> </a> </span></div>
+                                            </div>
+                                        </div>
+                                    </div><a class="a-link-normal s-line-clamp-4 s-link-style a-text-normal"
+                                        href="/sspa/click?ie=UTF8&amp;spc=MToxNzQwNTE0ODkzNDczNzk3OjE3NDkyOTk4MzM6c3BfYXRmOjIwMDA2NzY0ODgwMjc5ODo6MDo6&amp;url=%2FDeath-Star-R2D2-Balls-Printed%2Fdp%2FB081XSYZMS%2Fref%3Dsr_1_1_sspa%3Fcrid%3D3C1EXMXN59Q9G%26dib%3DeyJ2IjoiMSJ9.7tBl5bhZh59L9qIPZUe9SLa2fy_HvzboxuQxvrRcAc0VUXayi9fxQFsMLyFplDE9vMkIJbP76AVpa-5-fxhNza3DqhX4tss4NlB49WPi_dA00Hw6O8qK5pDzdetYlhGgOyXOLBe7mTG9oJ5W0wcvQhEVoX9mpJk_SGeqRLWGA0dBSjYCZtiyrY8_B-DP53S7fbYwiSYtq-g7sQDXKVadRpGvUyKq7yxA0SLsU42uvoqSGb0qcd6udL1wbnTEkKmwNjNSb7xIUb-8PyE7DTPMt1ScJksn70sFQMJNkM2aK5M.x9_jYvKPnSibV1d0umUStZBxlSTSXrzVIFKqFzS8c-U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749299833%26sprefix%3Dr2d2%252Caps%252C548%26sr%3D8-1-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9hdGY%26psc%3D1">
+                                        <h2 aria-label="Sponsored Ad - Death Star BB8 R2D2 Golf Balls with 20 Printed tees • Great Gift IDEA from Moms, DADS and Kids -"
+                                            class="a-size-base-plus a-spacing-none a-color-base a-text-normal">
+                                            <span>Death Star BB8 R2D2 Golf Balls with 20 Printed tees • Great Gift IDEA
+                                                from Moms, DADS and Kids -</span></h2>
+                                    </a>
+                                </div>
+                                <div data-cy="reviews-block" class="a-section a-spacing-none a-spacing-top-micro">
+                                    <div class="a-row a-size-small"><span class="a-declarative"
+                                            data-version-id="v2dwi5hq8xzthf26x0gg1mcl2oj"
+                                            data-render-id="r3o8bgr5zt3kmy2jv4su6fn4kyw" data-action="a-popover"
+                                            data-csa-c-func-deps="aui-da-a-popover"
+                                            data-a-popover="{&quot;position&quot;:&quot;triggerBottom&quot;,&quot;popoverLabel&quot;:&quot;4.7 out of 5 stars, rating details&quot;,&quot;url&quot;:&quot;/review/widgets/average-customer-review/popover/ref=acr_search__popover?ie=UTF8&amp;asin=B081XSYZMS&amp;ref_=acr_search__popover&amp;contextId=search&quot;,&quot;closeButton&quot;:true,&quot;closeButtonLabel&quot;:&quot;&quot;}"
+                                            data-csa-c-type="widget" data-csa-c-id="oykdvt-8s1ebj-2kegf2-7ii7tp"><a
+                                                aria-label="4.7 out of 5 stars, rating details"
+                                                href="javascript:void(0)" role="button"
+                                                class="a-popover-trigger a-declarative"><i
+                                                    data-cy="reviews-ratings-slot" aria-hidden="true"
+                                                    class="a-icon a-icon-star-small a-star-small-4-5"><span
+                                                        class="a-icon-alt">4.7 out of 5 stars</span></i><i
+                                                    class="a-icon a-icon-popover"></i></a></span> <span
+                                            data-component-type="s-client-side-analytics" class="rush-component"
+                                            data-version-id="v2dwi5hq8xzthf26x0gg1mcl2oj"
+                                            data-render-id="r3o8bgr5zt3kmy2jv4su6fn4kyw" data-component-id="8">
+                                            <div style="display: inline-block"
+                                                class="s-csa-instrumentation-wrapper alf-search-csa-instrumentation-wrapper"
+                                                data-csa-c-type="alf-af-component"
+                                                data-csa-c-content-id="alf-customer-ratings-count-component"
+                                                data-csa-c-slot-id="alf-reviews" data-csa-op-log-render=""
+                                                data-csa-c-layout="GRID" data-csa-c-asin="B081XSYZMS"
+                                                data-csa-c-id="6l5wc4-ngelan-hd9x4t-d4a2k7"><a aria-label="184 ratings"
+                                                    class="a-link-normal s-underline-text s-underline-link-text s-link-style"
+                                                    href="/sspa/click?ie=UTF8&amp;spc=MToxNzQwNTE0ODkzNDczNzk3OjE3NDkyOTk4MzM6c3BfYXRmOjIwMDA2NzY0ODgwMjc5ODo6MDo6&amp;url=%2FDeath-Star-R2D2-Balls-Printed%2Fdp%2FB081XSYZMS%2Fref%3Dsr_1_1_sspa%3Fcrid%3D3C1EXMXN59Q9G%26dib%3DeyJ2IjoiMSJ9.7tBl5bhZh59L9qIPZUe9SLa2fy_HvzboxuQxvrRcAc0VUXayi9fxQFsMLyFplDE9vMkIJbP76AVpa-5-fxhNza3DqhX4tss4NlB49WPi_dA00Hw6O8qK5pDzdetYlhGgOyXOLBe7mTG9oJ5W0wcvQhEVoX9mpJk_SGeqRLWGA0dBSjYCZtiyrY8_B-DP53S7fbYwiSYtq-g7sQDXKVadRpGvUyKq7yxA0SLsU42uvoqSGb0qcd6udL1wbnTEkKmwNjNSb7xIUb-8PyE7DTPMt1ScJksn70sFQMJNkM2aK5M.x9_jYvKPnSibV1d0umUStZBxlSTSXrzVIFKqFzS8c-U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749299833%26sprefix%3Dr2d2%252Caps%252C548%26sr%3D8-1-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9hdGY%26psc%3D1#customerReviews"><span
+                                                        aria-hidden="true"
+                                                        class="a-size-base s-underline-text">184</span> </a> </div>
+                                        </span></div>
+                                    <div class="a-row a-size-base"><span class="a-size-base a-color-secondary">50+
+                                            bought in past month</span></div>
+                                </div>
+                                <div data-cy="price-recipe"
+                                    class="a-section a-spacing-none a-spacing-top-small s-price-instructions-style">
+                                    <div class="a-row a-size-base a-color-base">
+                                        <div class="a-row"><span id="price-link" class="aok-offscreen">Price, product
+                                                page</span><a aria-describedby="price-link"
+                                                class="a-link-normal s-no-hover s-underline-text s-underline-link-text s-link-style a-text-normal"
+                                                href="/sspa/click?ie=UTF8&amp;spc=MToxNzQwNTE0ODkzNDczNzk3OjE3NDkyOTk4MzM6c3BfYXRmOjIwMDA2NzY0ODgwMjc5ODo6MDo6&amp;url=%2FDeath-Star-R2D2-Balls-Printed%2Fdp%2FB081XSYZMS%2Fref%3Dsr_1_1_sspa%3Fcrid%3D3C1EXMXN59Q9G%26dib%3DeyJ2IjoiMSJ9.7tBl5bhZh59L9qIPZUe9SLa2fy_HvzboxuQxvrRcAc0VUXayi9fxQFsMLyFplDE9vMkIJbP76AVpa-5-fxhNza3DqhX4tss4NlB49WPi_dA00Hw6O8qK5pDzdetYlhGgOyXOLBe7mTG9oJ5W0wcvQhEVoX9mpJk_SGeqRLWGA0dBSjYCZtiyrY8_B-DP53S7fbYwiSYtq-g7sQDXKVadRpGvUyKq7yxA0SLsU42uvoqSGb0qcd6udL1wbnTEkKmwNjNSb7xIUb-8PyE7DTPMt1ScJksn70sFQMJNkM2aK5M.x9_jYvKPnSibV1d0umUStZBxlSTSXrzVIFKqFzS8c-U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749299833%26sprefix%3Dr2d2%252Caps%252C548%26sr%3D8-1-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9hdGY%26psc%3D1"><span
+                                                    class="a-price" data-a-size="xl" data-a-color="base"><span
+                                                        class="a-offscreen">$29.95</span><span aria-hidden="true"><span
+                                                            class="a-price-symbol">$</span><span
+                                                            class="a-price-whole">29<span
+                                                                class="a-price-decimal">.</span></span><span
+                                                            class="a-price-fraction">95</span></span></span></a></div>
+                                        <div class="a-row"></div>
+                                    </div>
+                                </div>
+                                <div data-cy="delivery-recipe" class="a-section a-spacing-none a-spacing-top-micro">
+                                    <div class="a-row a-size-base a-color-secondary s-align-children-center"><span
+                                            aria-label="FREE delivery Thu, Jun 19 to Malaysia on $49 of eligible items"><span
+                                                class="a-color-base">FREE delivery </span><span
+                                                class="a-color-base a-text-bold">Thu, Jun 19 </span><span
+                                                class="a-color-base">to Malaysia on $49 of eligible items</span></span>
+                                    </div>
+                                </div>
+                                <div data-cy="certification-recipe"
+                                    class="a-section a-spacing-none a-spacing-top-micro">
+                                    <div class="a-row">
+                                        <div class="a-section a-spacing-none s-align-children-center">
+                                            <div class="a-section a-spacing-none s-pc-faceout-container">
+                                                <div>
+                                                    <div class="s-align-children-center"><span class="a-declarative"
+                                                            data-version-id="v2dwi5hq8xzthf26x0gg1mcl2oj"
+                                                            data-render-id="r3o8bgr5zt3kmy2jv4su6fn4kyw"
+                                                            data-action="s-pc-sidesheet-open"
+                                                            data-csa-c-func-deps="aui-da-s-pc-sidesheet-open"
+                                                            data-s-pc-sidesheet-open="{&quot;preloadDomId&quot;:&quot;pc-side-sheet-B081XSYZMS&quot;,&quot;popoverLabel&quot;:&quot;Product certifications&quot;,&quot;interactLoggingMetricsList&quot;:[&quot;provenanceCertifications_desktop_sbe_badge&quot;],&quot;closeButtonLabel&quot;:&quot;Close popup&quot;,&quot;dwellMetric&quot;:&quot;provenanceCertifications_desktop_sbe_badge_t&quot;}"
+                                                            data-csa-c-type="widget"
+                                                            data-csa-c-id="hdfxi6-bjlgup-5dql15-88t9ao"><a
+                                                                data-cy="s-pc-faceout-badge"
+                                                                class="a-link-normal s-no-underline s-pc-badge s-align-children-center aok-block"
+                                                                href="javascript:void(0)" role="button">
+                                                                <div
+                                                                    class="a-section s-pc-attribute-pill-text s-margin-bottom-none s-margin-bottom-none aok-block s-pc-certification-faceout">
+                                                                    <span class="faceout-image-view"></span><img alt=""
+                                                                        src="https://m.media-amazon.com/images/I/111mHoVK0kL._SS200_.png"
+                                                                        class="s-image" height="18px" width="18px">
+                                                                    <span class="a-size-base a-color-base">Small
+                                                                        Business</span>
+                                                                    <div
+                                                                        class="s-margin-bottom-none s-pc-sidesheet-chevron aok-nowrap">
+                                                                        <i class="a-icon a-icon-popover aok-align-center"
+                                                                            role="presentation"></i></div>
+                                                                </div>
+                                                            </a></span></div>
+                                                </div>
+                                            </div>
+                                        </div>
+                                        <div id="pc-side-sheet-B081XSYZMS"
+                                            class="a-section puis puis-v2dwi5hq8xzthf26x0gg1mcl2oj aok-hidden">
+                                            <div class="a-section s-pc-container-side-sheet">
+                                                <div class="s-align-children-center a-spacing-small">
+                                                    <div class="s-align-children-center s-pc-certification"
+                                                        role="heading" aria-level="2"><span
+                                                            class="faceout-image-view"></span>
+                                                        <div alt="" style="height: 24px; width: 24px;"
+                                                            class="a-image-wrapper a-lazy-loaded a-manually-loaded s-image"
+                                                            data-a-image-source="https://m.media-amazon.com/images/I/111mHoVK0kL._SS200_.png">
+                                                            <noscript><img alt=""
+                                                                    src="https://m.media-amazon.com/images/I/111mHoVK0kL._SS200_.png"
+                                                                    height="24px" width="24px" /></noscript></div> <span
+                                                            class="a-size-medium-plus a-color-base a-text-bold">Small
+                                                            Business</span>
+                                                    </div>
+                                                </div>
+                                                <div class="a-spacing-medium s-pc-link-container"><span
+                                                        class="a-size-base a-color-secondary">Shop products from small
+                                                        business brands sold in Amazon’s store. Discover more about the
+                                                        small businesses partnering with Amazon and Amazon’s commitment
+                                                        to empowering them.</span> <a
+                                                        class="a-size-base a-link-normal s-link-style"
+                                                        href="https://www.amazon.com/b/ref=s9_acss_bw_cg_sbp22c_1e1_w/ref=SBE_navbar_5?pf_rd_r=6W5X52VNZRB7GK1E1VX2&amp;pf_rd_p=56621c3d-cff4-45e1-9bf4-79bbeb8006fc&amp;pf_rd_m=ATVPDKIKX0DER&amp;pf_rd_s=merchandised-search-top-3&amp;pf_rd_t=30901&amp;pf_rd_i=17879387011&amp;node=18018208011">Learn
+                                                        more</a> </div>
+                                            </div>
+                                        </div>
+                                    </div>
+                                </div>
+                            </div>
+                        </div>
+                    </div>
+                </span>
+            </div>
+
+        </div>
+    </div>
+</div>

docs/examples/c4a_script/api_usage_examples.py

@@ -0,0 +1,217 @@
+"""
+C4A-Script API Usage Examples
+Shows how to use the new Result-based API in various scenarios
+"""
+
+from c4a_compile import compile, validate, compile_file
+from c4a_result import CompilationResult, ValidationResult
+import json
+
+
+print("C4A-Script API Usage Examples")
+print("=" * 80)
+
+# Example 1: Basic compilation
+print("\n1. Basic Compilation")
+print("-" * 40)
+
+script = """
+GO https://example.com
+WAIT 2
+IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
+REPEAT (SCROLL DOWN 300, 3)
+"""
+
+result = compile(script)
+print(f"Success: {result.success}")
+print(f"Statements generated: {len(result.js_code) if result.js_code else 0}")
+
+# Example 2: Error handling
+print("\n\n2. Error Handling")
+print("-" * 40)
+
+error_script = """
+GO https://example.com
+IF (EXISTS `.modal`) CLICK `.close`
+undefined_procedure
+"""
+
+result = compile(error_script)
+if not result.success:
+    # Access error details
+    error = result.first_error
+    print(f"Error on line {error.line}: {error.message}")
+    print(f"Error code: {error.code}")
+    
+    # Show suggestions if available
+    if error.suggestions:
+        print("Suggestions:")
+        for suggestion in error.suggestions:
+            print(f"  - {suggestion.message}")
+
+# Example 3: Validation only
+print("\n\n3. Validation (no code generation)")
+print("-" * 40)
+
+validation_script = """
+PROC validate_form
+  IF (EXISTS `#email`) THEN TYPE "test@example.com"
+  PRESS Tab
+ENDPROC
+
+validate_form
+"""
+
+validation = validate(validation_script)
+print(f"Valid: {validation.valid}")
+if validation.errors:
+    print(f"Errors found: {len(validation.errors)}")
+
+# Example 4: JSON output for UI
+print("\n\n4. JSON Output for UI Integration")
+print("-" * 40)
+
+ui_script = """
+CLICK button.submit
+"""
+
+result = compile(ui_script)
+if not result.success:
+    # Get JSON for UI
+    error_json = result.to_dict()
+    print("Error data for UI:")
+    print(json.dumps(error_json["errors"][0], indent=2))
+
+# Example 5: File compilation
+print("\n\n5. File Compilation")
+print("-" * 40)
+
+# Create a test file
+test_file = "test_script.c4a"
+with open(test_file, "w") as f:
+    f.write("""
+GO https://example.com
+WAIT `.content` 5
+CLICK `.main-button`
+""")
+
+result = compile_file(test_file)
+print(f"File compilation: {'Success' if result.success else 'Failed'}")
+if result.success:
+    print(f"Generated {len(result.js_code)} JavaScript statements")
+
+# Clean up
+import os
+os.remove(test_file)
+
+# Example 6: Batch processing
+print("\n\n6. Batch Processing Multiple Scripts")
+print("-" * 40)
+
+scripts = [
+    "GO https://example1.com\nCLICK `.button`",
+    "GO https://example2.com\nWAIT 2",
+    "GO https://example3.com\nINVALID_CMD"
+]
+
+results = []
+for i, script in enumerate(scripts, 1):
+    result = compile(script)
+    results.append(result)
+    status = "✓" if result.success else "✗"
+    print(f"Script {i}: {status}")
+
+# Summary
+successful = sum(1 for r in results if r.success)
+print(f"\nBatch result: {successful}/{len(scripts)} successful")
+
+# Example 7: Custom error formatting
+print("\n\n7. Custom Error Formatting")
+print("-" * 40)
+
+def format_error_for_ide(error):
+    """Format error for IDE integration"""
+    return f"{error.source_line}:{error.line}:{error.column}: {error.type.value}: {error.message} [{error.code}]"
+
+error_script = "IF EXISTS `.button` THEN CLICK `.button`"
+result = compile(error_script)
+
+if not result.success:
+    error = result.first_error
+    print("IDE format:", format_error_for_ide(error))
+    print("Simple format:", error.simple_message)
+    print("Full format:", error.formatted_message)
+
+# Example 8: Working with warnings (future feature)
+print("\n\n8. Handling Warnings")
+print("-" * 40)
+
+# In the future, we might have warnings
+result = compile("GO https://example.com\nWAIT 100")  # Very long wait
+print(f"Success: {result.success}")
+print(f"Warnings: {len(result.warnings)}")
+
+# Example 9: Metadata usage
+print("\n\n9. Using Metadata")
+print("-" * 40)
+
+complex_script = """
+PROC helper1
+  CLICK `.btn1`
+ENDPROC
+
+PROC helper2
+  CLICK `.btn2`
+ENDPROC
+
+GO https://example.com
+helper1
+helper2
+"""
+
+result = compile(complex_script)
+if result.success:
+    print(f"Script metadata:")
+    for key, value in result.metadata.items():
+        print(f"  {key}: {value}")
+
+# Example 10: Integration patterns
+print("\n\n10. Integration Patterns")
+print("-" * 40)
+
+# Web API endpoint simulation
+def api_compile(request_body):
+    """Simulate API endpoint"""
+    script = request_body.get("script", "")
+    result = compile(script)
+    
+    response = {
+        "status": "success" if result.success else "error",
+        "data": result.to_dict()
+    }
+    return response
+
+# CLI tool simulation
+def cli_compile(script, output_format="text"):
+    """Simulate CLI tool"""
+    result = compile(script)
+    
+    if output_format == "json":
+        return result.to_json()
+    elif output_format == "simple":
+        if result.success:
+            return f"OK: {len(result.js_code)} statements"
+        else:
+            return f"ERROR: {result.first_error.simple_message}"
+    else:
+        return str(result)
+
+# Test the patterns
+api_response = api_compile({"script": "GO https://example.com"})
+print(f"API response status: {api_response['status']}")
+
+cli_output = cli_compile("WAIT 2", "simple")
+print(f"CLI output: {cli_output}")
+
+print("\n" + "=" * 80)
+print("All examples completed successfully!")

docs/examples/c4a_script/c4a_script_hello_world.py

@@ -0,0 +1,53 @@
+"""
+C4A-Script Hello World
+A concise example showing how to use the C4A-Script compiler
+"""
+
+from c4a_compile import compile
+
+# Define your C4A-Script
+script = """
+GO https://example.com
+WAIT `#content` 5
+IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
+CLICK `button.submit`
+"""
+
+# Compile the script
+result = compile(script)
+
+# Check if compilation was successful
+if result.success:
+    # Success! Use the generated JavaScript
+    print("✅ Compilation successful!")
+    print(f"Generated {len(result.js_code)} JavaScript statements:\n")
+    
+    for i, js in enumerate(result.js_code, 1):
+        print(f"{i}. {js}\n")
+    
+    # In real usage, you'd pass result.js_code to Crawl4AI:
+    # config = CrawlerRunConfig(js_code=result.js_code)
+    
+else:
+    # Error! Handle the compilation error
+    print("❌ Compilation failed!")
+    
+    # Get the first error (there might be multiple)
+    error = result.first_error
+    
+    # Show error details
+    print(f"Error at line {error.line}, column {error.column}")
+    print(f"Message: {error.message}")
+    
+    # Show the problematic code
+    print(f"\nCode: {error.source_line}")
+    print(" " * (6 + error.column) + "^")
+    
+    # Show suggestions if available
+    if error.suggestions:
+        print("\n💡 How to fix:")
+        for suggestion in error.suggestions:
+            print(f"   {suggestion.message}")
+    
+    # For debugging or logging, you can also get JSON
+    # error_json = result.to_json()

docs/examples/c4a_script/c4a_script_hello_world_error.py

@@ -0,0 +1,53 @@
+"""
+C4A-Script Hello World - Error Example
+Shows how error handling works
+"""
+
+from c4a_compile import compile
+
+# Define a script with an error (missing THEN)
+script = """
+GO https://example.com
+WAIT `#content` 5
+IF (EXISTS `.cookie-banner`) CLICK `.accept`
+CLICK `button.submit`
+"""
+
+# Compile the script
+result = compile(script)
+
+# Check if compilation was successful
+if result.success:
+    # Success! Use the generated JavaScript
+    print("✅ Compilation successful!")
+    print(f"Generated {len(result.js_code)} JavaScript statements:\n")
+    
+    for i, js in enumerate(result.js_code, 1):
+        print(f"{i}. {js}\n")
+    
+    # In real usage, you'd pass result.js_code to Crawl4AI:
+    # config = CrawlerRunConfig(js_code=result.js_code)
+    
+else:
+    # Error! Handle the compilation error
+    print("❌ Compilation failed!")
+    
+    # Get the first error (there might be multiple)
+    error = result.first_error
+    
+    # Show error details
+    print(f"Error at line {error.line}, column {error.column}")
+    print(f"Message: {error.message}")
+    
+    # Show the problematic code
+    print(f"\nCode: {error.source_line}")
+    print(" " * (6 + error.column) + "^")
+    
+    # Show suggestions if available
+    if error.suggestions:
+        print("\n💡 How to fix:")
+        for suggestion in error.suggestions:
+            print(f"   {suggestion.message}")
+    
+    # For debugging or logging, you can also get JSON
+    # error_json = result.to_json()

docs/examples/c4a_script/demo_c4a_crawl4ai.py

@@ -0,0 +1,285 @@
+"""
+Demonstration of C4A-Script integration with Crawl4AI
+Shows various use cases and features
+"""
+
+import asyncio
+from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
+from crawl4ai import c4a_compile, CompilationResult
+
+async def example_basic_usage():
+    """Basic C4A-Script usage with Crawl4AI"""
+    print("\n" + "="*60)
+    print("Example 1: Basic C4A-Script Usage")
+    print("="*60)
+    
+    # Define your automation script
+    c4a_script = """
+    # Wait for page to load
+    WAIT `body` 2
+    
+    # Handle cookie banner if present
+    IF (EXISTS `.cookie-banner`) THEN CLICK `.accept-btn`
+    
+    # Scroll down to load more content
+    SCROLL DOWN 500
+    WAIT 1
+    
+    # Click load more button if exists
+    IF (EXISTS `.load-more`) THEN CLICK `.load-more`
+    """
+    
+    # Create crawler config with C4A script
+    config = CrawlerRunConfig(
+        url="https://example.com",
+        c4a_script=c4a_script,
+        wait_for="css:.content",
+        verbose=False
+    )
+    
+    print("✅ C4A Script compiled successfully!")
+    print(f"Generated {len(config.js_code)} JavaScript commands")
+    
+    # In production, you would run:
+    # async with AsyncWebCrawler() as crawler:
+    #     result = await crawler.arun(config=config)
+
+
+async def example_form_filling():
+    """Form filling with C4A-Script"""
+    print("\n" + "="*60)
+    print("Example 2: Form Filling with C4A-Script")
+    print("="*60)
+    
+    # Form automation script
+    form_script = """
+    # Set form values
+    SET email = "test@example.com"
+    SET message = "This is a test message"
+    
+    # Fill the form
+    CLICK `#email-input`
+    TYPE $email
+    
+    CLICK `#message-textarea`
+    TYPE $message
+    
+    # Submit the form
+    CLICK `button[type="submit"]`
+    
+    # Wait for success message
+    WAIT `.success-message` 10
+    """
+    
+    config = CrawlerRunConfig(
+        url="https://example.com/contact",
+        c4a_script=form_script
+    )
+    
+    print("✅ Form filling script ready")
+    print("Script will:")
+    print("  - Fill email field")
+    print("  - Fill message textarea")
+    print("  - Submit form")
+    print("  - Wait for confirmation")
+
+
+async def example_dynamic_loading():
+    """Handle dynamic content loading"""
+    print("\n" + "="*60)
+    print("Example 3: Dynamic Content Loading")
+    print("="*60)
+    
+    # Script for infinite scroll or pagination
+    pagination_script = """
+    # Initial wait
+    WAIT `.product-list` 5
+    
+    # Load all products by clicking "Load More" repeatedly
+    REPEAT (CLICK `.load-more`, `document.querySelector('.load-more') !== null`)
+    
+    # Alternative: Scroll to load (infinite scroll)
+    # REPEAT (SCROLL DOWN 1000, `document.querySelectorAll('.product').length < 100`)
+    
+    # Extract count
+    EVAL `console.log('Products loaded: ' + document.querySelectorAll('.product').length)`
+    """
+    
+    config = CrawlerRunConfig(
+        url="https://example.com/products",
+        c4a_script=pagination_script,
+        screenshot=True  # Capture final state
+    )
+    
+    print("✅ Dynamic loading script ready")
+    print("Script will load all products by repeatedly clicking 'Load More'")
+
+
+async def example_multi_step_workflow():
+    """Complex multi-step workflow with procedures"""
+    print("\n" + "="*60)
+    print("Example 4: Multi-Step Workflow with Procedures")
+    print("="*60)
+    
+    # Complex workflow with reusable procedures
+    workflow_script = """
+    # Define login procedure
+    PROC login
+      CLICK `#username`
+      TYPE "demo_user"
+      CLICK `#password`
+      TYPE "demo_pass"
+      CLICK `#login-btn`
+      WAIT `.dashboard` 10
+    ENDPROC
+    
+    # Define search procedure
+    PROC search_product
+      CLICK `.search-box`
+      TYPE "laptop"
+      PRESS Enter
+      WAIT `.search-results` 5
+    ENDPROC
+    
+    # Main workflow
+    GO https://example.com
+    login
+    search_product
+    
+    # Process results
+    IF (EXISTS `.no-results`) THEN EVAL `console.log('No products found')`
+    ELSE REPEAT (CLICK `.add-to-cart`, 3)
+    """
+    
+    # Compile to check for errors
+    result = c4a_compile(workflow_script)
+    
+    if result.success:
+        print("✅ Complex workflow compiled successfully!")
+        print("Workflow includes:")
+        print("  - Login procedure")
+        print("  - Product search")
+        print("  - Conditional cart additions")
+        
+        config = CrawlerRunConfig(
+            url="https://example.com",
+            c4a_script=workflow_script
+        )
+    else:
+        print("❌ Compilation error:")
+        error = result.first_error
+        print(f"  Line {error.line}: {error.message}")
+
+
+async def example_error_handling():
+    """Demonstrate error handling"""
+    print("\n" + "="*60)
+    print("Example 5: Error Handling")
+    print("="*60)
+    
+    # Script with intentional error
+    bad_script = """
+    WAIT body 2
+    CLICK button
+    IF (EXISTS .modal) CLICK .close
+    """
+    
+    try:
+        config = CrawlerRunConfig(
+            url="https://example.com",
+            c4a_script=bad_script
+        )
+    except ValueError as e:
+        print("✅ Error caught as expected:")
+        print(f"  {e}")
+        
+    # Fixed version
+    good_script = """
+    WAIT `body` 2
+    CLICK `button`
+    IF (EXISTS `.modal`) THEN CLICK `.close`
+    """
+    
+    config = CrawlerRunConfig(
+        url="https://example.com",
+        c4a_script=good_script
+    )
+    
+    print("\n✅ Fixed script compiled successfully!")
+
+
+async def example_combining_with_extraction():
+    """Combine C4A-Script with extraction strategies"""
+    print("\n" + "="*60)
+    print("Example 6: C4A-Script + Extraction Strategies")
+    print("="*60)
+    
+    from crawl4ai import JsonCssExtractionStrategy
+    
+    # Script to prepare page for extraction
+    prep_script = """
+    # Expand all collapsed sections
+    REPEAT (CLICK `.expand-btn`, `document.querySelectorAll('.expand-btn:not(.expanded)').length > 0`)
+    
+    # Load all comments
+    IF (EXISTS `.load-comments`) THEN CLICK `.load-comments`
+    WAIT `.comments-section` 5
+    
+    # Close any popups
+    IF (EXISTS `.popup-close`) THEN CLICK `.popup-close`
+    """
+    
+    # Define extraction schema
+    schema = {
+        "name": "article",
+        "selector": "article.main",
+        "fields": {
+            "title": {"selector": "h1", "type": "text"},
+            "content": {"selector": ".content", "type": "text"},
+            "comments": {
+                "selector": ".comment",
+                "type": "list",
+                "fields": {
+                    "author": {"selector": ".author", "type": "text"},
+                    "text": {"selector": ".text", "type": "text"}
+                }
+            }
+        }
+    }
+    
+    config = CrawlerRunConfig(
+        url="https://example.com/article",
+        c4a_script=prep_script,
+        extraction_strategy=JsonCssExtractionStrategy(schema),
+        wait_for="css:.comments-section"
+    )
+    
+    print("✅ Combined C4A + Extraction ready")
+    print("Workflow:")
+    print("  1. Expand collapsed sections")
+    print("  2. Load comments")
+    print("  3. Extract structured data")
+
+
+async def main():
+    """Run all examples"""
+    print("\n🚀 C4A-Script + Crawl4AI Integration Demo\n")
+    
+    # Run all examples
+    await example_basic_usage()
+    await example_form_filling()
+    await example_dynamic_loading()
+    await example_multi_step_workflow()
+    await example_error_handling()
+    await example_combining_with_extraction()
+    
+    print("\n" + "="*60)
+    print("✅ All examples completed successfully!")
+    print("="*60)
+    
+    print("\nTo run actual crawls, uncomment the AsyncWebCrawler sections")
+    print("or create your own scripts using these examples as templates.")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/c4a_script/generate_script_hello_world.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python3
+"""
+Hello World Example: LLM-Generated C4A-Script
+
+This example shows how to use the new generate_script() function to automatically
+create C4A-Script automation from natural language descriptions and HTML.
+"""
+
+from crawl4ai.script.c4a_compile import C4ACompiler
+
+def main():
+    print("🤖 C4A-Script Generation Hello World")
+    print("=" * 50)
+    
+    # Example 1: Simple login form
+    html = """
+    <html>
+    <body>
+        <form id="login">
+            <input id="email" type="email" placeholder="Email">
+            <input id="password" type="password" placeholder="Password">
+            <button id="submit">Login</button>
+        </form>
+    </body>
+    </html>
+    """
+    
+    goal = "Fill in email 'user@example.com', password 'secret123', and submit the form"
+    
+    print("📝 Goal:", goal)
+    print("🌐 HTML: Simple login form")
+    print()
+    
+    # Generate C4A-Script
+    print("🔧 Generated C4A-Script:")
+    print("-" * 30)
+    c4a_script = C4ACompiler.generate_script(
+        html=html,
+        query=goal,
+        mode="c4a"
+    )
+    print(c4a_script)
+    print()
+    
+    # Generate JavaScript
+    print("🔧 Generated JavaScript:")
+    print("-" * 30)
+    js_script = C4ACompiler.generate_script(
+        html=html,
+        query=goal,
+        mode="js"
+    )
+    print(js_script)
+    print()
+    
+    # Example 2: Simple button click
+    html2 = """
+    <html>
+    <body>
+        <div class="content">
+            <h1>Welcome!</h1>
+            <button id="start-btn" class="primary">Get Started</button>
+        </div>
+    </body>
+    </html>
+    """
+    
+    goal2 = "Click the 'Get Started' button"
+    
+    print("=" * 50)
+    print("📝 Goal:", goal2)
+    print("🌐 HTML: Simple button")
+    print()
+    
+    print("🔧 Generated C4A-Script:")
+    print("-" * 30)
+    c4a_script2 = C4ACompiler.generate_script(
+        html=html2,
+        query=goal2,
+        mode="c4a"
+    )
+    print(c4a_script2)
+    print()
+    
+    print("✅ Done! The LLM automatically converted natural language goals")
+    print("   into executable automation scripts.")
+
+if __name__ == "__main__":
+    main()

docs/examples/c4a_script/github_search/extracted_repositories.json

@@ -0,0 +1,111 @@
+[
+  {
+    "repository_name": "unclecode/crawl4ai",
+    "repository_owner": "unclecode/crawl4ai",
+    "repository_url": "/unclecode/crawl4ai",
+    "description": "\ud83d\ude80\ud83e\udd16Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here:https://discord.gg/jP8KfhDhyN",
+    "primary_language": "Python",
+    "star_count": "45.1k",
+    "topics": [],
+    "last_updated": "23 hours ago"
+  },
+  {
+    "repository_name": "coleam00/mcp-crawl4ai-rag",
+    "repository_owner": "coleam00/mcp-crawl4ai-rag",
+    "repository_url": "/coleam00/mcp-crawl4ai-rag",
+    "description": "Web Crawling and RAG Capabilities for AI Agents and AI Coding Assistants",
+    "primary_language": "Python",
+    "star_count": "748",
+    "topics": [],
+    "last_updated": "yesterday"
+  },
+  {
+    "repository_name": "pdichone/crawl4ai-rag-system",
+    "repository_owner": "pdichone/crawl4ai-rag-system",
+    "repository_url": "/pdichone/crawl4ai-rag-system",
+    "primary_language": "Python",
+    "star_count": "44",
+    "topics": [],
+    "last_updated": "on 21 Jan"
+  },
+  {
+    "repository_name": "weidwonder/crawl4ai-mcp-server",
+    "repository_owner": "weidwonder/crawl4ai-mcp-server",
+    "repository_url": "/weidwonder/crawl4ai-mcp-server",
+    "description": "\u7528\u4e8e\u63d0\u4f9b\u7ed9\u672c\u5730\u5f00\u53d1\u8005\u7684 LLM\u7684\u9ad8\u6548\u4e92\u8054\u7f51\u641c\u7d22&\u5185\u5bb9\u83b7\u53d6\u7684MCP Server\uff0c \u8282\u7701\u4f60\u7684token",
+    "primary_language": "Python",
+    "star_count": "87",
+    "topics": [],
+    "last_updated": "24 days ago"
+  },
+  {
+    "repository_name": "leonardogrig/crawl4ai-deepseek-example",
+    "repository_owner": "leonardogrig/crawl4ai-deepseek-example",
+    "repository_url": "/leonardogrig/crawl4ai-deepseek-example",
+    "primary_language": "Python",
+    "star_count": "29",
+    "topics": [],
+    "last_updated": "on 18 Jan"
+  },
+  {
+    "repository_name": "laurentvv/crawl4ai-mcp",
+    "repository_owner": "laurentvv/crawl4ai-mcp",
+    "repository_url": "/laurentvv/crawl4ai-mcp",
+    "description": "Web crawling tool that integrates with AI assistants via the MCP",
+    "primary_language": "Python",
+    "star_count": "10",
+    "topics": [
+      {},
+      {},
+      {},
+      {},
+      {}
+    ],
+    "last_updated": "on 16 Mar"
+  },
+  {
+    "repository_name": "kaymen99/ai-web-scraper",
+    "repository_owner": "kaymen99/ai-web-scraper",
+    "repository_url": "/kaymen99/ai-web-scraper",
+    "description": "AI web scraper built withCrawl4AIfor extracting structured leads data from websites.",
+    "primary_language": "Python",
+    "star_count": "30",
+    "topics": [
+      {},
+      {},
+      {},
+      {},
+      {}
+    ],
+    "last_updated": "on 13 Feb"
+  },
+  {
+    "repository_name": "atakkant/ai_web_crawler",
+    "repository_owner": "atakkant/ai_web_crawler",
+    "repository_url": "/atakkant/ai_web_crawler",
+    "description": "crawl4ai, DeepSeek, Groq",
+    "primary_language": "Python",
+    "star_count": "9",
+    "topics": [],
+    "last_updated": "on 19 Feb"
+  },
+  {
+    "repository_name": "Croups/auto-scraper-with-llms",
+    "repository_owner": "Croups/auto-scraper-with-llms",
+    "repository_url": "/Croups/auto-scraper-with-llms",
+    "description": "Web scraping AI that leverages thecrawl4ailibrary to extract structured data from web pages using various large language models (LLMs).",
+    "primary_language": "Python",
+    "star_count": "49",
+    "topics": [],
+    "last_updated": "on 8 Apr"
+  },
+  {
+    "repository_name": "leonardogrig/crawl4ai_llm_examples",
+    "repository_owner": "leonardogrig/crawl4ai_llm_examples",
+    "repository_url": "/leonardogrig/crawl4ai_llm_examples",
+    "primary_language": "Python",
+    "star_count": "8",
+    "topics": [],
+    "last_updated": "on 29 Jan"
+  }
+]

docs/examples/c4a_script/github_search/generated_result_schema.json

@@ -0,0 +1,66 @@
+{
+  "name": "GitHub Repository Cards",
+  "baseSelector": "div.Box-sc-g0xbh4-0.iwUbcA",
+  "fields": [
+    {
+      "name": "repository_name",
+      "selector": "div.search-title a span",
+      "type": "text",
+      "transform": "strip"
+    },
+    {
+      "name": "repository_owner",
+      "selector": "div.search-title a span",
+      "type": "text",
+      "transform": "split",
+      "pattern": "/"
+    },
+    {
+      "name": "repository_url",
+      "selector": "div.search-title a",
+      "type": "attribute",
+      "attribute": "href",
+      "transform": "prepend",
+      "pattern": "https://github.com"
+    },
+    {
+      "name": "description",
+      "selector": "div.dcdlju span",
+      "type": "text"
+    },
+    {
+      "name": "primary_language",
+      "selector": "ul.bZkODq li span[aria-label]",
+      "type": "text"
+    },
+    {
+      "name": "star_count",
+      "selector": "ul.bZkODq li a[href*='stargazers'] span",
+      "type": "text",
+      "transform": "strip"
+    },
+    {
+      "name": "topics",
+      "type": "list",
+      "selector": "div.jgRnBg div a",
+      "fields": [
+        {
+          "name": "topic_name",
+          "selector": "a",
+          "type": "text"
+        }
+      ]
+    },
+    {
+      "name": "last_updated",
+      "selector": "ul.bZkODq li span[title]",
+      "type": "text"
+    },
+    {
+      "name": "has_sponsor_button",
+      "selector": "button[aria-label*='Sponsor']",
+      "type": "text",
+      "transform": "exists"
+    }
+  ]
+}

docs/examples/c4a_script/github_search/generated_search_script.js

@@ -0,0 +1,39 @@
+(async () => {
+  const waitForElement = (selector, timeout = 10000) => new Promise((resolve, reject) => {
+    const el = document.querySelector(selector);
+    if (el) return resolve(el);
+    const observer = new MutationObserver(() => {
+      const el = document.querySelector(selector);
+      if (el) {
+        observer.disconnect();
+        resolve(el);
+      }
+    });
+    observer.observe(document.body, { childList: true, subtree: true });
+    setTimeout(() => {
+      observer.disconnect();
+      reject(new Error(`Timeout waiting for ${selector}`));
+    }, timeout);
+  });
+
+  try {
+    const searchInput = await waitForElement('#adv_code_search input[type="text"]');
+    searchInput.value = 'crawl4AI';
+    searchInput.dispatchEvent(new Event('input', { bubbles: true }));
+
+    const languageSelect = await waitForElement('#search_language');
+    languageSelect.value = 'Python';
+    languageSelect.dispatchEvent(new Event('change', { bubbles: true }));
+
+    const starsInput = await waitForElement('#search_stars');
+    starsInput.value = '>10000';
+    starsInput.dispatchEvent(new Event('input', { bubbles: true }));
+
+    const searchButton = await waitForElement('#adv_code_search button[type="submit"]');
+    searchButton.click();
+
+    await waitForElement('.codesearch-results, #search-results');
+  } catch (e) {
+    console.error('Search script failed:', e.message);
+  }
+})();

docs/examples/c4a_script/github_search/github_search_crawler.py

@@ -0,0 +1,211 @@
+#!/usr/bin/env python3
+"""
+GitHub Advanced Search Example using Crawl4AI
+
+This example demonstrates:
+1. Using LLM to generate C4A-Script from HTML snippets
+2. Single arun() call with navigation, search form filling, and extraction
+3. JSON CSS extraction for structured repository data
+4. Complete workflow: navigate → fill form → submit → extract results
+
+Requirements:
+- Crawl4AI with generate_script support
+- LLM API key (configured in environment)
+"""
+
+import asyncio
+import json
+import os
+from pathlib import Path
+from typing import List, Dict, Any
+
+from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
+from crawl4ai import JsonCssExtractionStrategy
+from crawl4ai.script.c4a_compile import C4ACompiler
+
+
+class GitHubSearchScraper:
+    def __init__(self):
+        self.base_dir = Path(__file__).parent
+        self.search_script_path = self.base_dir / "generated_search_script.js"
+        self.schema_path = self.base_dir / "generated_result_schema.json"
+        self.results_path = self.base_dir / "extracted_repositories.json"
+        self.session_id = "github_search_session"
+        
+    async def generate_search_script(self) -> str:
+        """Generate JavaScript for GitHub advanced search interaction"""
+        print("🔧 Generating search script from search_form.html...")
+        
+        # Check if already generated
+        if self.search_script_path.exists():
+            print("✅ Using cached search script")
+            return self.search_script_path.read_text()
+        
+        # Read the search form HTML
+        search_form_html = (self.base_dir / "search_form.html").read_text()
+        
+        # Generate script using LLM
+        search_goal = """
+        Search for crawl4AI repositories written in Python with more than 10000 stars:
+        1. Wait for the main search input to be visible
+        2. Type "crawl4AI" into the main search box
+        3. Select "Python" from the language dropdown (#search_language)
+        4. Type ">10000" into the stars input field (#search_stars)
+        5. Click the search button to submit the form
+        6. Wait for the search results to appear
+        """
+        
+        try:
+            script = C4ACompiler.generate_script(
+                html=search_form_html,
+                query=search_goal,
+                mode="js"
+            )
+            
+            # Save for future use
+            self.search_script_path.write_text(script)
+            print("✅ Search script generated and saved!")
+            print(f"📄 Script preview:\n{script[:500]}...")
+            return script
+            
+        except Exception as e:
+            print(f"❌ Error generating search script: {e}")
+            raise
+
+    
+    async def generate_result_schema(self) -> Dict[str, Any]:
+        """Generate JSON CSS extraction schema from result HTML"""
+        print("\n🔧 Generating result extraction schema...")
+        
+        # Check if already generated
+        if self.schema_path.exists():
+            print("✅ Using cached extraction schema")
+            return json.loads(self.schema_path.read_text())
+        
+        # Read the result HTML
+        result_html = (self.base_dir / "result.html").read_text()
+        
+        # Generate extraction schema using LLM
+        schema_goal = """
+        Create a JSON CSS extraction schema to extract from each repository card:
+        - Repository name (the repository name only, not including owner)
+        - Repository owner (organization or username)
+        - Repository URL (full GitHub URL)
+        - Description 
+        - Primary programming language
+        - Star count (numeric value)
+        - Topics/tags (array of topic names)
+        - Last updated (time ago string)
+        - Whether it has a sponsor button
+        
+        The schema should handle multiple repository results on the search results page.
+        """
+        
+        try:
+            # Generate schema
+            schema = JsonCssExtractionStrategy.generate_schema(
+                html=result_html,
+                query=schema_goal,
+            )
+            
+            # Save for future use
+            self.schema_path.write_text(json.dumps(schema, indent=2))
+            print("✅ Extraction schema generated and saved!")
+            print(f"📄 Schema fields: {[f['name'] for f in schema['fields']]}")
+            return schema
+            
+        except Exception as e:
+            print(f"❌ Error generating schema: {e}")
+            raise
+    
+    async def crawl_github(self):
+        """Main crawling logic with single arun() call"""
+        print("\n🚀 Starting GitHub repository search...")
+        
+        # Generate scripts and schemas
+        search_script = await self.generate_search_script()
+        result_schema = await self.generate_result_schema()
+        
+        # Configure browser (headless=False to see the action)
+        browser_config = BrowserConfig(
+            headless=False,
+            verbose=True,
+            viewport_width=1920,
+            viewport_height=1080
+        )
+        
+        async with AsyncWebCrawler(config=browser_config) as crawler:
+            print("\n📍 Navigating to GitHub advanced search and executing search...")
+            
+            # Single call: Navigate, execute search, and extract results
+            search_config = CrawlerRunConfig(
+                session_id=self.session_id,
+                js_code=search_script,  # Execute generated JS
+                # wait_for="[data-testid='results-list']",  # Wait for search results
+                wait_for=".Box-sc-g0xbh4-0.iwUbcA",  # Wait for search results
+                extraction_strategy=JsonCssExtractionStrategy(schema=result_schema),
+                delay_before_return_html=3.0,  # Give time for results to fully load
+                cache_mode=CacheMode.BYPASS  # Don't cache for fresh results
+            )
+            
+            result = await crawler.arun(
+                url="https://github.com/search/advanced",
+                config=search_config
+            )
+            
+            if not result.success:
+                print("❌ Failed to search GitHub")
+                print(f"Error: {result.error_message}")
+                return
+            
+            print("✅ Search and extraction completed successfully!")
+            
+            # Extract and save results
+            if result.extracted_content:
+                repositories = json.loads(result.extracted_content)
+                print(f"\n🔍 Found {len(repositories)} repositories matching criteria")
+                
+                # Save results
+                self.results_path.write_text(
+                    json.dumps(repositories, indent=2)
+                )
+                print(f"💾 Results saved to: {self.results_path}")
+                
+                # Print sample results
+                print("\n📊 Sample Results:")
+                for i, repo in enumerate(repositories[:5], 1):
+                    print(f"\n{i}. {repo.get('owner', 'Unknown')}/{repo.get('name', 'Unknown')}")
+                    print(f"   Description: {repo.get('description', 'No description')[:80]}...")
+                    print(f"   Language: {repo.get('language', 'Unknown')}")
+                    print(f"   Stars: {repo.get('stars', 'Unknown')}")
+                    print(f"   Updated: {repo.get('last_updated', 'Unknown')}")
+                    if repo.get('topics'):
+                        print(f"   Topics: {', '.join(repo['topics'][:5])}")
+                    print(f"   URL: {repo.get('url', 'Unknown')}")
+                
+            else:
+                print("❌ No repositories extracted")
+            
+            # Save screenshot for reference
+            if result.screenshot:
+                screenshot_path = self.base_dir / "search_results_screenshot.png"
+                with open(screenshot_path, "wb") as f:
+                    f.write(result.screenshot)
+                print(f"\n📸 Screenshot saved to: {screenshot_path}")
+
+
+async def main():
+    """Run the GitHub search scraper"""
+    scraper = GitHubSearchScraper()
+    await scraper.crawl_github()
+    
+    print("\n🎉 GitHub search example completed!")
+    print("Check the generated files:")
+    print("  - generated_search_script.js")
+    print("  - generated_result_schema.json") 
+    print("  - extracted_repositories.json")
+    print("  - search_results_screenshot.png")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/c4a_script/github_search/result.html

@@ -0,0 +1,54 @@
+<div class="Box-sc-g0xbh4-0 iwUbcA"><div class="Box-sc-g0xbh4-0 cSURfY"><div class="Box-sc-g0xbh4-0 gPrlij"><h3 class="Box-sc-g0xbh4-0 cvnppv"><div class="Box-sc-g0xbh4-0 kYLlPM"><div class="Box-sc-g0xbh4-0 eurdCD"><img data-component="Avatar" class="prc-Avatar-Avatar-ZRS-m" alt="" data-square="" width="20" height="20" src="https://github.com/TheAlgorithms.png?size=40" data-testid="github-avatar" style="--avatarSize-regular: 20px;"></div><div class="Box-sc-g0xbh4-0 MHoGG search-title"><a class="prc-Link-Link-85e08" href="/TheAlgorithms/Python"><span class="Box-sc-g0xbh4-0 kzfhBO search-match prc-Text-Text-0ima0">TheAlgorithms/<em>Python</em></span></a></div></div></h3><div class="Box-sc-g0xbh4-0 dcdlju"><span class="Box-sc-g0xbh4-0 gKFdvh search-match prc-Text-Text-0ima0">All Algorithms implemented in <em>Python</em></span></div><div class="Box-sc-g0xbh4-0 jgRnBg"><div><a class="Box-sc-g0xbh4-0 hIVEGR prc-Link-Link-85e08" href="/topics/python">python</a></div><div><a class="Box-sc-g0xbh4-0 hIVEGR prc-Link-Link-85e08" href="/topics/education">education</a></div><div><a class="Box-sc-g0xbh4-0 hIVEGR prc-Link-Link-85e08" href="/topics/algorithm">algorithm</a></div><div><a class="Box-sc-g0xbh4-0 hIVEGR prc-Link-Link-85e08" href="/topics/practice">practice</a></div><div><a class="Box-sc-g0xbh4-0 hIVEGR prc-Link-Link-85e08" href="/topics/interview">interview</a></div></div><ul class="Box-sc-g0xbh4-0 bZkODq"><li class="Box-sc-g0xbh4-0 eCfCAC"><div class="Box-sc-g0xbh4-0 hjDqIa"><div class="Box-sc-g0xbh4-0 fwSYsx"></div></div><span aria-label="Python language">Python</span></li><span class="Box-sc-g0xbh4-0 eXQoFa prc-Text-Text-0ima0" aria-hidden="true">·</span><li class="Box-sc-g0xbh4-0 eCfCAC"><a class="Box-sc-g0xbh4-0 iPuHRc prc-Link-Link-85e08" href="/TheAlgorithms/Python/stargazers" aria-label="201161 stars"><svg aria-hidden="true" focusable="false" class="octicon octicon-star Octicon-sc-9kayk9-0 kHVtWu" viewBox="0 0 16 16" width="16" height="16" fill="currentColor" display="inline-block" overflow="visible" style="vertical-align: text-bottom;"><path d="M8 .25a.75.75 0 0 1 .673.418l1.882 3.815 4.21.612a.75.75 0 0 1 .416 1.279l-3.046 2.97.719 4.192a.751.751 0 0 1-1.088.791L8 12.347l-3.766 1.98a.75.75 0 0 1-1.088-.79l.72-4.194L.818 6.374a.75.75 0 0 1 .416-1.28l4.21-.611L7.327.668A.75.75 0 0 1 8 .25Zm0 2.445L6.615 5.5a.75.75 0 0 1-.564.41l-3.097.45 2.24 2.184a.75.75 0 0 1 .216.664l-.528 3.084 2.769-1.456a.75.75 0 0 1 .698 0l2.77 1.456-.53-3.084a.75.75 0 0 1 .216-.664l2.24-2.183-3.096-.45a.75.75 0 0 1-.564-.41L8 2.694Z"></path></svg><span class="prc-Text-Text-0ima0">201k</span></a></li><span class="Box-sc-g0xbh4-0 eXQoFa prc-Text-Text-0ima0" aria-hidden="true">·</span><li class="Box-sc-g0xbh4-0 eCfCAC"><span>Updated <div title="3 Jun 2025, 01:57 GMT+8" class="Truncate__StyledTruncate-sc-23o1d2-0 liVpTx"><span class="prc-Text-Text-0ima0" title="3 Jun 2025, 01:57 GMT+8">4 days ago</span></div></span></li></ul></div><div class="Box-sc-g0xbh4-0 gtlRHe"><div class="Box-sc-g0xbh4-0 fvaNTI"><button type="button" class="prc-Button-ButtonBase-c50BI" data-loading="false" data-size="small" data-variant="default" aria-describedby=":r1c:-loading-announcement"><span data-component="buttonContent" data-align="center" class="prc-Button-ButtonContent-HKbr-"><span data-component="leadingVisual" class="prc-Button-Visual-2epfX prc-Button-VisualWrap-Db-eB"><svg aria-hidden="true" focusable="false" class="octicon octicon-star" viewBox="0 0 16 16" width="16" height="16" fill="currentColor" display="inline-block" overflow="visible" style="vertical-align: text-bottom;"><path d="M8 .25a.75.75 0 0 1 .673.418l1.882 3.815 4.21.612a.75.75 0 0 1 .416 1.279l-3.046 2.97.719 4.192a.751.751 0 0 1-1.088.791L8 12.347l-3.766 1.98a.75.75 0 0 1-1.088-.79l.72-4.194L.818 6.374a.75.75 0 0 1 .416-1.28l4.21-.611L7.327.668A.75.75 0 0 1 8 .25Zm0 2.445L6.615 5.5a.75.75 0 0 1-.564.41l-3.097.45 2.24 2.184a.75.75 0 0 1 .216.664l-.528 3.084 2.769-1.456a.75.75 0 0 1 .698 0l2.77 1.456-.53-3.084a.75.75 0 0 1 .216-.664l2.24-2.183-3.096-.45a.75.75 0 0 1-.564-.41L8 2.694Z"></path></svg></span><span data-component="text" class="prc-Button-Label-pTQ3x">Star</span></span></button></div><div class="Box-sc-g0xbh4-0 llZEgI"><div class="Box-sc-g0xbh4-0">  <button id="dialog-show-funding-links-modal-TheAlgorithms-Python" aria-label="Sponsor TheAlgorithms/Python" data-show-dialog-id="funding-links-modal-TheAlgorithms-Python" type="button" data-view-component="true" class="Button--secondary Button--small Button">  <span class="Button-content">
+    <span class="Button-label"><svg aria-hidden="true" height="16" viewBox="0 0 16 16" version="1.1" width="16" data-view-component="true" class="octicon octicon-heart icon-sponsor mr-1 color-fg-sponsors">
+    <path d="m8 14.25.345.666a.75.75 0 0 1-.69 0l-.008-.004-.018-.01a7.152 7.152 0 0 1-.31-.17 22.055 22.055 0 0 1-3.434-2.414C2.045 10.731 0 8.35 0 5.5 0 2.836 2.086 1 4.25 1 5.797 1 7.153 1.802 8 3.02 8.847 1.802 10.203 1 11.75 1 13.914 1 16 2.836 16 5.5c0 2.85-2.045 5.231-3.885 6.818a22.066 22.066 0 0 1-3.744 2.584l-.018.01-.006.003h-.002ZM4.25 2.5c-1.336 0-2.75 1.164-2.75 3 0 2.15 1.58 4.144 3.365 5.682A20.58 20.58 0 0 0 8 13.393a20.58 20.58 0 0 0 3.135-2.211C12.92 9.644 14.5 7.65 14.5 5.5c0-1.836-1.414-3-2.75-3-1.373 0-2.609.986-3.029 2.456a.749.749 0 0 1-1.442 0C6.859 3.486 5.623 2.5 4.25 2.5Z"></path>
+</svg> <span data-view-component="true">Sponsor</span></span>
+  </span>
+</button>
+
+<dialog-helper>
+  <dialog id="funding-links-modal-TheAlgorithms-Python" aria-modal="true" aria-labelledby="funding-links-modal-TheAlgorithms-Python-title" aria-describedby="funding-links-modal-TheAlgorithms-Python-description" data-view-component="true" class="Overlay Overlay-whenNarrow Overlay--size-medium Overlay--motion-scaleFade Overlay--disableScroll">
+    <div data-view-component="true" class="Overlay-header">
+  <div class="Overlay-headerContentWrap">
+    <div class="Overlay-titleWrap">
+      <h1 class="Overlay-title " id="funding-links-modal-TheAlgorithms-Python-title">
+        Sponsor TheAlgorithms/Python
+      </h1>
+        
+    </div>
+    <div class="Overlay-actionWrap">
+      <button data-close-dialog-id="funding-links-modal-TheAlgorithms-Python" aria-label="Close" type="button" data-view-component="true" class="close-button Overlay-closeButton"><svg aria-hidden="true" height="16" viewBox="0 0 16 16" version="1.1" width="16" data-view-component="true" class="octicon octicon-x">
+    <path d="M3.72 3.72a.75.75 0 0 1 1.06 0L8 6.94l3.22-3.22a.749.749 0 0 1 1.275.326.749.749 0 0 1-.215.734L9.06 8l3.22 3.22a.749.749 0 0 1-.326 1.275.749.749 0 0 1-.734-.215L8 9.06l-3.22 3.22a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042L6.94 8 3.72 4.78a.75.75 0 0 1 0-1.06Z"></path>
+</svg></button>
+    </div>
+  </div>
+  
+</div>
+      <scrollable-region data-labelled-by="funding-links-modal-TheAlgorithms-Python-title" data-catalyst="" style="overflow: auto;">
+        <div data-view-component="true" class="Overlay-body">      <div class="text-left f5">
+  <div class="pt-3 color-bg-overlay">
+      <h5 class="flex-auto mb-3 mt-0">External links</h5>
+      <div class="d-flex mb-3">
+        <div class="circle mr-2 border d-flex flex-justify-center flex-items-center flex-shrink-0" style="width:24px;height:24px;">
+          <img width="16" height="16" class="octicon rounded-2 d-block" alt="liberapay" src="https://github.githubassets.com/assets/liberapay-48108ded7267.svg">
+        </div>
+        <div class="flex-auto min-width-0">
+          <a target="_blank" data-ga-click="Dashboard, click, Nav menu - item:org-profile context:organization" data-hydro-click="{&quot;event_type&quot;:&quot;sponsors.repo_funding_links_link_click&quot;,&quot;payload&quot;:{&quot;platform&quot;:{&quot;platform_type&quot;:&quot;LIBERAPAY&quot;,&quot;platform_url&quot;:&quot;https://liberapay.com/TheAlgorithms&quot;},&quot;platforms&quot;:[{&quot;platform_type&quot;:&quot;LIBERAPAY&quot;,&quot;platform_url&quot;:&quot;https://liberapay.com/TheAlgorithms&quot;}],&quot;repo_id&quot;:63476337,&quot;owner_id&quot;:20487725,&quot;user_id&quot;:12494079,&quot;originating_url&quot;:&quot;https://github.com/TheAlgorithms/Python/funding_links?fragment=1&quot;}}" data-hydro-click-hmac="123b5aa7d5ffff5ef0530f8e7fbaebcb564e8de1af26f1b858a19b0e1d4f9e5f" href="https://liberapay.com/TheAlgorithms"><span>liberapay.com/<strong>TheAlgorithms</strong></span></a>
+        </div>
+      </div>
+
+  </div>
+  <div class="text-small p-3 border-top">
+    <p class="my-0">
+      <a class="Link--inTextBlock" href="https://docs.github.com/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/displaying-a-sponsor-button-in-your-repository">Learn more about funding links in repositories</a>.
+    </p>
+      <p class="my-0">
+        <a class="Link--secondary" href="/contact/report-abuse?report=TheAlgorithms%2FPython+%28Repository+Funding+Links%29">Report abuse</a>
+      </p>
+  </div>
+</div>
+
+</div>
+      </scrollable-region>
+      
+</dialog></dialog-helper>
+</div></div></div></div></div>

docs/examples/c4a_script/github_search/search_form.html

@@ -0,0 +1,336 @@
+<form id="search_form" class="search_repos" data-turbo="false" action="/search" accept-charset="UTF-8" method="get">
+  
+<div class="pagehead codesearch-head color-border-muted">
+  <div class="container-lg p-responsive d-flex flex-column flex-md-row">
+    <h1 class="flex-shrink-0" id="search-title">Advanced search</h1>
+    <div class="search-form-fluid flex-auto d-flex flex-column flex-md-row pt-2 pt-md-0" id="adv_code_search">
+      <div class="flex-auto pr-md-2">
+        <label class="form-control search-page-label js-advanced-search-label">
+          <input aria-labelledby="search-title" class="form-control input-block search-page-input js-advanced-search-input js-advanced-search-prefix" data-search-prefix="" type="text" value="">
+          <p class="completed-query js-advanced-query top-0 right-0 left-0"><span></span> </p>
+        </label>
+        <input class="js-search-query" type="hidden" name="q" value="">
+        <input class="js-type-value" type="hidden" name="type" value="Repositories">
+        <input type="hidden" name="ref" value="advsearch">
+      </div>
+      <div class="d-flex d-md-block flex-shrink-0 pt-2 pt-md-0">
+          <button type="submit" data-view-component="true" class="btn flex-auto">    Search
+</button>
+      </div>
+    </div>
+  </div>
+</div>
+
+<div class="container-lg p-responsive advanced-search-form">
+  <fieldset class="pb-3 mb-4 border-bottom color-border-muted min-width-0">
+    <h3>Advanced options</h3>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_from">From these owners</label></dt>
+      <dd><input id="search_from" type="text" class="form-control js-advanced-search-prefix" placeholder="github, atom, electron, octokit" data-search-prefix="user:"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_repos">In these repositories</label></dt>
+      <dd><input id="search_repos" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="twbs/bootstrap, rails/rails" data-search-prefix="repo:"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_date">Created on the dates</label></dt>
+      <dd><input id="search_date" type="text" class="form-control js-advanced-search-prefix" value="" placeholder=">YYYY-MM-DD, YYYY-MM-DD" data-search-prefix="created:"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_language">Written in this language</label></dt>
+      <dd>
+        <select id="search_language" name="l" class="form-select js-advanced-search-prefix" data-search-prefix="language:">
+          <option value="">Any language</option>
+          <optgroup label="Popular">
+            <option value="C">C</option>
+<option value="C#">C#</option>
+<option value="C++">C++</option>
+<option value="CoffeeScript">CoffeeScript</option>
+<option value="CSS">CSS</option>
+<option value="Dart">Dart</option>
+<option value="DM">DM</option>
+<option value="Elixir">Elixir</option>
+<option value="Go">Go</option>
+<option value="Groovy">Groovy</option>
+<option value="HTML">HTML</option>
+<option value="Java">Java</option>
+<option value="JavaScript">JavaScript</option>
+<option value="Kotlin">Kotlin</option>
+<option value="Objective-C">Objective-C</option>
+<option value="Perl">Perl</option>
+<option value="PHP">PHP</option>
+<option value="PowerShell">PowerShell</option>
+<option value="Python">Python</option>
+<option value="Ruby">Ruby</option>
+<option value="Rust">Rust</option>
+<option value="Scala">Scala</option>
+<option value="Shell">Shell</option>
+<option value="Swift">Swift</option>
+<option value="TypeScript">TypeScript</option>
+          </optgroup>
+          <optgroup label="Everything else">
+            <option value="1C Enterprise">1C Enterprise</option>
+<option value="2-Dimensional Array">2-Dimensional Array</option>
+<option value="4D">4D</option>
+<option value="ABAP">ABAP</option>
+<option value="ABAP CDS">ABAP CDS</option>
+<option value="ABNF">ABNF</option>
+<option value="ActionScript">ActionScript</option>
+<option value="Ada">Ada</option>
+<option value="Adblock Filter List">Adblock Filter List</option>
+<option value="Adobe Font Metrics">Adobe Font Metrics</option>
+<option value="Agda">Agda</option>
+<option value="AGS Script">AGS Script</option>
+<option value="AIDL">AIDL</option>
+<option value="Aiken">Aiken</option>
+          </optgroup>
+        </select>
+      </dd>
+    </dl>
+  </fieldset>
+  <fieldset class="pb-3 mb-4 border-bottom color-border-muted min-width-0">
+    <h3>Repositories options</h3>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_stars">With this many stars</label></dt>
+      <dd><input id="search_stars" type="text" class="form-control js-advanced-search-prefix" placeholder="0..100, 200, >1000" data-search-prefix="stars:" data-search-type="Repositories"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_forks">With this many forks</label></dt>
+      <dd><input id="search_forks" type="text" class="form-control js-advanced-search-prefix" placeholder="50..100, 200, <5" data-search-prefix="forks:" data-search-type="Repositories"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_size">Of this size</label></dt>
+      <dd><input id="search_size" type="text" class="form-control js-advanced-search-prefix" placeholder="Repository size in KB" data-search-prefix="size:" data-search-type="Repositories"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_push">Pushed to</label></dt>
+      <dd><input id="search_push" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="<YYYY-MM-DD" data-search-prefix="pushed:" data-search-type="Repositories"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_license">With this license</label></dt>
+      <dd>
+          <select id="search_license" class="form-select js-advanced-search-prefix" data-search-prefix="license:" data-search-type="Repositories">
+          <option value="">Any license</option>
+          <optgroup label="Licenses">
+            <option value="0bsd">BSD Zero Clause License</option>
+<option value="afl-3.0">Academic Free License v3.0</option>
+<option value="agpl-3.0">GNU Affero General Public License v3.0</option>
+<option value="apache-2.0">Apache License 2.0</option>
+<option value="artistic-2.0">Artistic License 2.0</option>
+<option value="blueoak-1.0.0">Blue Oak Model License 1.0.0</option>
+<option value="bsd-2-clause">BSD 2-Clause "Simplified" License</option>
+<option value="bsd-2-clause-patent">BSD-2-Clause Plus Patent License</option>
+<option value="bsd-3-clause">BSD 3-Clause "New" or "Revised" License</option>
+<option value="bsd-3-clause-clear">BSD 3-Clause Clear License</option>
+<option value="bsd-4-clause">BSD 4-Clause "Original" or "Old" License</option>
+<option value="bsl-1.0">Boost Software License 1.0</option>
+<option value="cc-by-4.0">Creative Commons Attribution 4.0 International</option>
+<option value="cc-by-sa-4.0">Creative Commons Attribution Share Alike 4.0 International</option>
+<option value="cc0-1.0">Creative Commons Zero v1.0 Universal</option>
+<option value="cecill-2.1">CeCILL Free Software License Agreement v2.1</option>
+<option value="cern-ohl-p-2.0">CERN Open Hardware Licence Version 2 - Permissive</option>
+<option value="cern-ohl-s-2.0">CERN Open Hardware Licence Version 2 - Strongly Reciprocal</option>
+<option value="cern-ohl-w-2.0">CERN Open Hardware Licence Version 2 - Weakly Reciprocal</option>
+<option value="ecl-2.0">Educational Community License v2.0</option>
+<option value="epl-1.0">Eclipse Public License 1.0</option>
+<option value="epl-2.0">Eclipse Public License 2.0</option>
+<option value="eupl-1.1">European Union Public License 1.1</option>
+<option value="eupl-1.2">European Union Public License 1.2</option>
+<option value="gfdl-1.3">GNU Free Documentation License v1.3</option>
+<option value="gpl-2.0">GNU General Public License v2.0</option>
+<option value="gpl-3.0">GNU General Public License v3.0</option>
+<option value="isc">ISC License</option>
+<option value="lgpl-2.1">GNU Lesser General Public License v2.1</option>
+<option value="lgpl-3.0">GNU Lesser General Public License v3.0</option>
+<option value="lppl-1.3c">LaTeX Project Public License v1.3c</option>
+<option value="mit">MIT License</option>
+<option value="mit-0">MIT No Attribution</option>
+<option value="mpl-2.0">Mozilla Public License 2.0</option>
+<option value="ms-pl">Microsoft Public License</option>
+<option value="ms-rl">Microsoft Reciprocal License</option>
+<option value="mulanpsl-2.0">Mulan Permissive Software License, Version 2</option>
+<option value="ncsa">University of Illinois/NCSA Open Source License</option>
+<option value="odbl-1.0">Open Data Commons Open Database License v1.0</option>
+<option value="ofl-1.1">SIL Open Font License 1.1</option>
+<option value="osl-3.0">Open Software License 3.0</option>
+<option value="postgresql">PostgreSQL License</option>
+<option value="unlicense">The Unlicense</option>
+<option value="upl-1.0">Universal Permissive License v1.0</option>
+<option value="vim">Vim License</option>
+<option value="wtfpl">Do What The F*ck You Want To Public License</option>
+<option value="zlib">zlib License</option>
+          </optgroup>
+          <optgroup label="License families">
+            <option value="cc">Creative Commons</option>
+<option value="gpl">GNU General Public License</option>
+<option value="lgpl">GNU Lesser General Public License</option>
+          </optgroup>
+        </select>
+      </dd>
+    </dl>
+    <label>
+      Return repositories <select class="form-select js-advanced-search-prefix" data-search-prefix="fork:" data-search-type="Repositories">
+      <option value="">not</option>
+      <option value="true">and</option>
+      <option value="only">only</option>
+      </select> including forks.
+    </label>
+  </fieldset>
+  <fieldset class="pb-3 mb-4 border-bottom color-border-muted min-width-0">
+    <h3>Code options</h3>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_extension">With this extension</label></dt>
+      <dd>
+        <input id="search_extension" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="rb, py, jpg" data-search-type="Code" data-search-prefix="path:" data-glob-pattern="*.$0" data-regex-pattern="/.$0$/" data-use-or="true">
+      </dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_path">In this path</label></dt>
+      <dd><input id="search_path" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="/foo/bar/baz/qux" data-search-prefix="path:" data-search-type="Code" data-use-or=""></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_filename">With this file name</label></dt>
+      <dd>
+        <input id="search_filename" type="text" class="form-control js-advanced-search-prefix" placeholder="app.rb, footer.erb" data-search-type="code:" data-search-prefix="path:" data-glob-pattern="**/$0" data-regex-pattern="/(^|/)$0$/" data-use-or="true">
+      </dd>
+    </dl>
+    <label>
+      Return code <select class="form-select js-advanced-search-prefix" data-search-prefix="fork:" data-search-type="Code">
+      <option value="">not</option>
+      <option value="true">and</option>
+      <option value="only">only</option>
+      </select> including forks.
+    </label>
+  </fieldset>
+  <fieldset class="pb-3 mb-4 border-bottom color-border-muted min-width-0">
+    <h3>Issues options</h3>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_state">In the state</label></dt>
+      <dd><select id="search_state" class="form-select js-advanced-search-prefix" data-search-prefix="state:" data-search-type="Issues">
+      <option value="">open/closed</option>
+      <option value="open">open</option>
+      <option value="closed">closed</option>
+      </select></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_state_reason">With the reason</label></dt>
+      <dd><select id="search_state_reason" class="form-select js-advanced-search-prefix" data-search-prefix="reason:" data-search-type="Issues">
+      <option value="">any reason</option>
+      <option value="completed">completed</option>
+      <option value="not planned">not planned</option>
+      <option value="reopened">reopened</option>
+      </select></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_comments">With this many comments</label></dt>
+      <dd><input id="search_comments" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="0..100, >442" data-search-prefix="comments:" data-search-type="Issues"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_labels">With the labels</label></dt>
+      <dd><input id="search_labels" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="bug, ie6" data-search-prefix="label:" data-search-type="Issues"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_author">Opened by the author</label></dt>
+      <dd><input id="search_author" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="hubot, octocat" data-search-prefix="author:" data-search-type="Issues"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_mention">Mentioning the users</label></dt>
+      <dd><input id="search_mention" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="tpope, mattt" data-search-prefix="mentions:" data-search-type="Issues"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_assignment">Assigned to the users</label></dt>
+      <dd><input id="search_assignment" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="twp, jim" data-search-prefix="assignee:" data-search-type="Issues"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_updated_date">Updated before the date</label></dt>
+      <dd><input id="search_updated_date" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="<YYYY-MM-DD" data-search-prefix="updated:" data-search-type="Issues"></dd>
+    </dl>
+  </fieldset>
+  <fieldset class="pb-3 mb-4 border-bottom color-border-muted min-width-0">
+    <h3>Users options</h3>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_full_name">With this full name</label></dt>
+      <dd><input id="search_full_name" type="text" class="form-control js-advanced-search-prefix" placeholder="Grace Hopper" data-search-prefix="fullname:" data-search-type="Users"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_location">From this location</label></dt>
+      <dd><input id="search_location" type="text" class="form-control js-advanced-search-prefix" placeholder="San Francisco, CA" data-search-prefix="location:" data-search-type="Users"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_followers">With this many followers</label></dt>
+      <dd><input id="search_followers" type="text" class="form-control js-advanced-search-prefix" placeholder="20..50, >200, <2" data-search-prefix="followers:" data-search-type="Users"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_public_repos">With this many public repositories</label></dt>
+      <dd><input id="search_public_repos" type="text" class="form-control js-advanced-search-prefix" placeholder="0, <42, >5" data-search-prefix="repos:" data-search-type="Users"></dd>
+    </dl>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_user_language">Working in this language</label></dt>
+      <dd>
+        <select id="search_user_language" name="l" class="form-select js-advanced-search-prefix" data-search-prefix="language:">
+          <option value="">Any language</option>
+          <optgroup label="Popular">
+            <option value="C">C</option>
+<option value="C#">C#</option>
+<option value="C++">C++</option>
+<option value="CoffeeScript">CoffeeScript</option>
+<option value="CSS">CSS</option>
+<option value="Dart">Dart</option>
+<option value="DM">DM</option>
+<option value="Elixir">Elixir</option>
+<option value="Go">Go</option>
+<option value="Groovy">Groovy</option>
+<option value="HTML">HTML</option>
+<option value="Java">Java</option>
+<option value="JavaScript">JavaScript</option>
+<option value="Kotlin">Kotlin</option>
+<option value="Objective-C">Objective-C</option>
+<option value="Perl">Perl</option>
+<option value="PHP">PHP</option>
+<option value="PowerShell">PowerShell</option>
+<option value="Python">Python</option>
+<option value="Ruby">Ruby</option>
+<option value="Rust">Rust</option>
+<option value="Scala">Scala</option>
+<option value="Shell">Shell</option>
+<option value="Swift">Swift</option>
+<option value="TypeScript">TypeScript</option>
+          </optgroup>
+          <optgroup label="Everything else">
+            <option value="1C Enterprise">1C Enterprise</option>
+<option value="2-Dimensional Array">2-Dimensional Array</option>
+<option value="4D">4D</option>
+<option value="ABAP">ABAP</option>
+<option value="ABAP CDS">ABAP CDS</option>
+<option value="ABNF">ABNF</option>
+<option value="ActionScript">ActionScript</option>
+<option value="Ada">Ada</option>
+
+<option value="Yul">Yul</option>
+<option value="ZAP">ZAP</option>
+<option value="Zeek">Zeek</option>
+<option value="ZenScript">ZenScript</option>
+<option value="Zephir">Zephir</option>
+<option value="Zig">Zig</option>
+<option value="ZIL">ZIL</option>
+<option value="Zimpl">Zimpl</option>
+<option value="Zmodel">Zmodel</option>
+          </optgroup>
+        </select>
+      </dd>
+    </dl>
+  </fieldset>
+  <fieldset class="pb-3 mb-4 border-bottom color-border-muted min-width-0">
+    <h3>Wiki options</h3>
+    <dl class="form-group flattened d-flex d-md-block flex-column">
+      <dt><label for="search_wiki_updated_date">Updated before the date</label></dt>
+      <dd><input id="search_wiki_updated_date" type="text" class="form-control js-advanced-search-prefix" placeholder="<YYYY-MM-DD" data-search-prefix="updated:" data-search-type="Wiki"></dd>
+    </dl>
+  </fieldset>
+  <div class="form-group flattened">
+    <div class="d-flex d-md-block">  <button type="submit" data-view-component="true" class="btn flex-auto">    Search
+</button></div>
+  </div>
+</div>
+
+</form>

docs/examples/c4a_script/script_samples/add_to_cart.c4a

@@ -0,0 +1,7 @@
+GO https://store.example.com/product/laptop
+WAIT `.product-details` 8
+CLICK `button.add-to-cart`
+WAIT `.cart-notification` 3
+CLICK `.cart-icon`
+WAIT `.checkout-btn` 5
+CLICK `.checkout-btn`

docs/examples/c4a_script/script_samples/advanced_control_flow.c4a

@@ -0,0 +1,43 @@
+# Advanced control flow with IF, EXISTS, and REPEAT
+
+# Define reusable procedures
+PROC handle_cookie_banner
+  IF (EXISTS `.cookie-banner`) THEN CLICK `.accept-cookies`
+  IF (EXISTS `.privacy-notice`) THEN CLICK `.dismiss-privacy`
+ENDPROC
+
+PROC scroll_to_load
+  SCROLL DOWN 500
+  WAIT 0.5
+ENDPROC
+
+PROC try_login
+  CLICK `#email`
+  TYPE "user@example.com"
+  CLICK `#password`
+  TYPE "secure123"
+  CLICK `button[type="submit"]`
+  WAIT 2
+ENDPROC
+
+# Main script
+GO https://example.com
+WAIT 2
+
+# Handle popups
+handle_cookie_banner
+
+# Conditional navigation based on login state
+IF (EXISTS `.user-menu`) THEN CLICK `.dashboard-link` ELSE try_login
+
+# Repeat scrolling based on content count
+REPEAT (scroll_to_load, 5)
+
+# Load more content while button exists
+REPEAT (CLICK `.load-more`, `document.querySelector('.load-more') && !document.querySelector('.no-more-content')`)
+
+# Process items conditionally
+IF (`document.querySelectorAll('.item').length > 10`) THEN EVAL `console.log('Found ' + document.querySelectorAll('.item').length + ' items')`
+
+# Complex condition with viewport check
+IF (`window.innerWidth < 768 && document.querySelector('.mobile-menu')`) THEN CLICK `.mobile-menu-toggle`

docs/examples/c4a_script/script_samples/conditional_login.c4a

@@ -0,0 +1,8 @@
+GO https://myapp.com
+WAIT 2
+IF (EXISTS `.user-avatar`) THEN CLICK `.logout` ELSE CLICK `.login`
+WAIT `#auth-form` 5
+IF (EXISTS `#auth-form`) THEN TYPE "user@example.com"
+IF (EXISTS `#auth-form`) THEN PRESS Tab
+IF (EXISTS `#auth-form`) THEN TYPE "password123"
+IF (EXISTS `#auth-form`) THEN CLICK `button[type="submit"]`

docs/examples/c4a_script/script_samples/data_extraction.c4a

@@ -0,0 +1,56 @@
+# Data extraction example
+# Scrapes product information from an e-commerce site
+
+# Navigate to products page
+GO https://shop.example.com/products
+WAIT `.product-list` 10
+
+# Scroll to load lazy-loaded content
+SCROLL DOWN 500
+WAIT 1
+SCROLL DOWN 500
+WAIT 1
+SCROLL DOWN 500
+WAIT 2
+
+# Extract product data
+EVAL `
+  // Extract all product information
+  const products = Array.from(document.querySelectorAll('.product-card')).map((card, index) => {
+    return {
+      id: index + 1,
+      name: card.querySelector('.product-title')?.textContent?.trim() || 'N/A',
+      price: card.querySelector('.price')?.textContent?.trim() || 'N/A',
+      rating: card.querySelector('.rating')?.textContent?.trim() || 'N/A',
+      availability: card.querySelector('.in-stock') ? 'In Stock' : 'Out of Stock',
+      image: card.querySelector('img')?.src || 'N/A'
+    };
+  });
+
+  // Log results
+  console.log('=== Product Extraction Results ===');
+  console.log('Total products found:', products.length);
+  console.log(JSON.stringify(products, null, 2));
+  
+  // Save to localStorage for retrieval
+  localStorage.setItem('scraped_products', JSON.stringify(products));
+`
+
+# Optional: Click on first product for details
+CLICK `.product-card:first-child`
+WAIT `.product-details` 5
+
+# Extract detailed information
+EVAL `
+  const details = {
+    description: document.querySelector('.product-description')?.textContent?.trim(),
+    specifications: Array.from(document.querySelectorAll('.spec-item')).map(spec => ({
+      label: spec.querySelector('.spec-label')?.textContent,
+      value: spec.querySelector('.spec-value')?.textContent
+    })),
+    reviews: document.querySelector('.review-count')?.textContent
+  };
+  
+  console.log('=== Product Details ===');
+  console.log(JSON.stringify(details, null, 2));
+`

docs/examples/c4a_script/script_samples/fill_contact.c4a

@@ -0,0 +1,8 @@
+GO https://company.com/contact
+WAIT `form#contact` 10
+TYPE "John Smith"
+PRESS Tab
+TYPE "john@email.com"
+PRESS Tab
+TYPE "Need help with my order"
+CLICK `button[type="submit"]`

docs/examples/c4a_script/script_samples/load_more_content.c4a

@@ -0,0 +1,7 @@
+GO https://news.example.com
+WAIT `.article-list` 5
+REPEAT (SCROLL DOWN 500, 3)
+WAIT 1
+REPEAT (CLICK `.load-more`, `document.querySelector('.load-more') !== null`)
+WAIT 2
+IF (`document.querySelectorAll('.article').length > 20`) THEN EVAL `console.log('Loaded enough articles')`

docs/examples/c4a_script/script_samples/login_flow.c4a

@@ -0,0 +1,36 @@
+# Login flow with error handling
+# Demonstrates procedures, variables, and conditional checks
+
+# Define login procedure
+PROC perform_login
+  CLICK `input#email`
+  TYPE $email
+  CLICK `input#password`
+  TYPE $password
+  CLICK `button.login-submit`
+ENDPROC
+
+# Set credentials
+SET email = "user@example.com"
+SET password = "securePassword123"
+
+# Navigate to login page
+GO https://app.example.com/login
+WAIT `.login-container` 15
+
+# Attempt login
+perform_login
+
+# Wait for page to load
+WAIT 3
+
+# Check if login was successful
+EVAL `
+  if (document.querySelector('.dashboard')) {
+    console.log('Login successful - on dashboard');
+  } else if (document.querySelector('.error-message')) {
+    console.log('Login failed:', document.querySelector('.error-message').textContent);
+  } else {
+    console.log('Unknown state after login');
+  }
+`

docs/examples/c4a_script/script_samples/multi_step_workflow.c4a

@@ -0,0 +1,106 @@
+# Multi-step e-commerce workflow
+# Complete purchase flow with procedures and error handling
+
+# Reusable procedures
+PROC search_product
+  CLICK `input.search-bar`
+  TYPE $search_term
+  PRESS Enter
+  WAIT `.search-results` 10
+ENDPROC
+
+PROC add_first_item_to_cart
+  CLICK `.product-item:first-child .add-to-cart`
+  WAIT ".added-to-cart-notification" 3
+ENDPROC
+
+PROC go_to_checkout
+  CLICK `.cart-icon`
+  WAIT `.cart-drawer` 5
+  CLICK `button.proceed-to-checkout`
+  WAIT `.checkout-page` 10
+ENDPROC
+
+PROC fill_customer_info
+  # Billing information
+  CLICK `#billing-firstname`
+  TYPE $first_name
+  CLICK `#billing-lastname`
+  TYPE $last_name
+  CLICK `#billing-email`
+  TYPE $email
+  CLICK `#billing-phone`
+  TYPE $phone
+  
+  # Address
+  CLICK `#billing-address`
+  TYPE $address
+  CLICK `#billing-city`
+  TYPE $city
+  CLICK `#billing-state`
+  TYPE $state
+  CLICK `#billing-zip`
+  TYPE $zip
+ENDPROC
+
+PROC select_shipping
+  CLICK `input[value="standard"]`
+  WAIT 1
+ENDPROC
+
+# Set all required variables
+SET search_term = "wireless headphones"
+SET first_name = "John"
+SET last_name = "Doe"
+SET email = "john.doe@example.com"
+SET phone = "555-0123"
+SET address = "123 Main Street"
+SET city = "San Francisco"
+SET state = "CA"
+SET zip = "94105"
+
+# Main workflow starts here
+GO https://shop.example.com
+WAIT `.homepage-loaded` 10
+
+# Step 1: Search and add to cart
+search_product
+EVAL `console.log('Found', document.querySelectorAll('.product-item').length, 'products')`
+add_first_item_to_cart
+
+# Add a second item
+CLICK `.product-item:nth-child(2) .add-to-cart`
+WAIT 2
+
+# Step 2: Go to checkout
+go_to_checkout
+
+# Step 3: Fill customer information
+fill_customer_info
+
+# Step 4: Select shipping method
+select_shipping
+
+# Step 5: Continue to payment
+CLICK `button.continue-to-payment`
+WAIT `.payment-section` 10
+
+# Log order summary
+EVAL `
+  const orderTotal = document.querySelector('.order-total')?.textContent;
+  const itemCount = document.querySelectorAll('.order-item').length;
+  console.log('=== Order Summary ===');
+  console.log('Items:', itemCount);
+  console.log('Total:', orderTotal);
+  
+  // Get all items
+  const items = Array.from(document.querySelectorAll('.order-item')).map(item => ({
+    name: item.querySelector('.item-name')?.textContent,
+    quantity: item.querySelector('.item-quantity')?.textContent,
+    price: item.querySelector('.item-price')?.textContent
+  }));
+  console.log('Items:', JSON.stringify(items, null, 2));
+`
+
+# Note: Stopping here before actual payment submission
+EVAL `console.log('Workflow completed - stopped before payment submission')`

docs/examples/c4a_script/script_samples/navigate_tabs.c4a

@@ -0,0 +1,8 @@
+GO https://app.example.com
+WAIT `.nav-menu` 8
+CLICK `a[href="/products"]`
+WAIT 2
+CLICK `a[href="/about"]`
+WAIT 2
+BACK
+WAIT 1

docs/examples/c4a_script/script_samples/quick_login.c4a

@@ -0,0 +1,8 @@
+GO https://myapp.com/login
+WAIT `input#email` 5
+CLICK `input#email`
+TYPE "user@example.com"
+PRESS Tab
+TYPE "password123"
+CLICK `button.login-btn`
+WAIT `.dashboard` 10

docs/examples/c4a_script/script_samples/responsive_actions.c4a

@@ -0,0 +1,7 @@
+GO https://responsive.site.com
+WAIT 2
+IF (`window.innerWidth < 768`) THEN CLICK `.mobile-menu`
+IF (`window.innerWidth < 768`) THEN WAIT `.mobile-nav` 3
+IF (`window.innerWidth >= 768`) THEN CLICK `.desktop-menu li:nth-child(2)`
+REPEAT (CLICK `.next-slide`, 5)
+IF (EXISTS `.cookie-banner`) THEN CLICK `.accept-cookies`

docs/examples/c4a_script/script_samples/scroll_and_click.c4a

@@ -0,0 +1,8 @@
+GO https://news.site.com
+WAIT `.article-list` 10
+SCROLL DOWN 500
+WAIT 1
+SCROLL DOWN 500
+WAIT 1
+CLICK `.article:nth-child(5)`
+WAIT `.article-content` 5

docs/examples/c4a_script/script_samples/search_product.c4a

@@ -0,0 +1,7 @@
+GO https://shop.example.com
+WAIT `.search-bar` 10
+CLICK `.search-bar`
+TYPE "wireless headphones"
+PRESS Enter
+WAIT `.results` 5
+CLICK `.product-card:first-child`

docs/examples/c4a_script/script_samples/simple_form.c4a

@@ -0,0 +1,19 @@
+# Simple form submission example
+# This script fills out a contact form and submits it
+
+GO https://example.com/contact
+WAIT `form#contact-form` 10
+
+# Fill out the form fields
+CLICK `input[name="name"]`
+TYPE "Alice Smith"
+PRESS Tab
+TYPE "alice@example.com"
+PRESS Tab
+TYPE "I'd like to learn more about your services"
+
+# Submit the form
+CLICK `button[type="submit"]`
+
+# Wait for success message
+WAIT "Thank you for your message" 5

docs/examples/c4a_script/script_samples/smart_form_fill.c4a

@@ -0,0 +1,11 @@
+PROC fill_field
+  TYPE "test@example.com"
+  PRESS Tab
+ENDPROC
+
+GO https://forms.example.com
+WAIT `form` 5
+IF (EXISTS `input[type="email"]`) THEN CLICK `input[type="email"]`
+IF (EXISTS `input[type="email"]`) THEN fill_field
+REPEAT (PRESS Tab, `document.activeElement.type !== 'submit'`)
+CLICK `button[type="submit"]`

docs/examples/c4a_script/tutorial/README.md

@@ -0,0 +1,396 @@
+# C4A-Script Interactive Tutorial
+
+A comprehensive web-based tutorial for learning and experimenting with C4A-Script - Crawl4AI's visual web automation language.
+
+## 🚀 Quick Start
+
+### Prerequisites
+- Python 3.7+
+- Modern web browser (Chrome, Firefox, Safari, Edge)
+
+### Running the Tutorial
+
+1. **Clone and Navigate**
+   ```bash
+   git clone https://github.com/unclecode/crawl4ai.git
+   cd crawl4ai/docs/examples/c4a_script/tutorial/
+   ```
+
+2. **Install Dependencies**
+   ```bash
+   pip install flask
+   ```
+
+3. **Launch the Server**
+   ```bash
+   python server.py
+   ```
+
+4. **Open in Browser**
+   ```
+   http://localhost:8080
+   ```
+
+**🌐 Try Online**: [Live Demo](https://docs.crawl4ai.com/c4a-script/demo)
+
+### 2. Try Your First Script
+
+```c4a
+# Basic interaction
+GO playground/
+WAIT `body` 2
+IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
+CLICK `#start-tutorial`
+```
+
+## 🎯 What You'll Learn
+
+### Core Features
+- **📝 Text Editor**: Write C4A-Script with syntax highlighting
+- **🧩 Visual Editor**: Build scripts using drag-and-drop Blockly interface  
+- **🎬 Recording Mode**: Capture browser actions and auto-generate scripts
+- **⚡ Live Execution**: Run scripts in real-time with instant feedback
+- **📊 Timeline View**: Visualize and edit automation steps
+
+## 📚 Tutorial Content
+
+### Basic Commands
+- **Navigation**: `GO url`
+- **Waiting**: `WAIT selector timeout` or `WAIT seconds`
+- **Clicking**: `CLICK selector`
+- **Typing**: `TYPE "text"`
+- **Scrolling**: `SCROLL DOWN/UP amount`
+
+### Control Flow
+- **Conditionals**: `IF (condition) THEN action`
+- **Loops**: `REPEAT (action, condition)`
+- **Procedures**: Define reusable command sequences
+
+### Advanced Features
+- **JavaScript evaluation**: `EVAL code`
+- **Variables**: `SET name = "value"`
+- **Complex selectors**: CSS selectors in backticks
+
+## 🎮 Interactive Playground Features
+
+The tutorial includes a fully interactive web app with:
+
+### 1. **Authentication System**
+- Login form with validation
+- Session management
+- Protected content
+
+### 2. **Dynamic Content**
+- Infinite scroll products
+- Pagination controls
+- Load more buttons
+
+### 3. **Complex Forms**
+- Multi-step wizards
+- Dynamic field visibility
+- Form validation
+
+### 4. **Interactive Elements**
+- Tabs and accordions
+- Modals and popups
+- Expandable content
+
+### 5. **Data Tables**
+- Sortable columns
+- Search functionality
+- Export options
+
+## 🛠️ Tutorial Features
+
+### Live Code Editor
+- Syntax highlighting
+- Real-time compilation
+- Error messages with suggestions
+
+### JavaScript Output Viewer
+- See generated JavaScript code
+- Edit and test JS directly
+- Understand the compilation
+
+### Visual Execution
+- Step-by-step progress
+- Element highlighting
+- Console output
+
+### Example Scripts
+Load pre-written examples demonstrating:
+- Cookie banner handling
+- Login workflows
+- Infinite scroll automation
+- Multi-step form completion
+- Complex interaction sequences
+
+## 📖 Tutorial Sections
+
+### 1. Getting Started
+Learn basic commands and syntax:
+```c4a
+GO https://example.com
+WAIT `.content` 5
+CLICK `.button`
+```
+
+### 2. Handling Dynamic Content
+Master waiting strategies and conditionals:
+```c4a
+IF (EXISTS `.popup`) THEN CLICK `.close`
+WAIT `.results` 10
+```
+
+### 3. Form Automation
+Fill and submit forms:
+```c4a
+CLICK `#email`
+TYPE "user@example.com"
+CLICK `button[type="submit"]`
+```
+
+### 4. Advanced Workflows
+Build complex automation flows:
+```c4a
+PROC login
+  CLICK `#username`
+  TYPE $username
+  CLICK `#password`
+  TYPE $password
+  CLICK `#login-btn`
+ENDPROC
+
+SET username = "demo"
+SET password = "pass123"
+login
+```
+
+## 🎯 Practice Challenges
+
+### Challenge 1: Cookie & Popups
+Handle the cookie banner and newsletter popup that appear on page load.
+
+### Challenge 2: Complete Login
+Successfully log into the application using the demo credentials.
+
+### Challenge 3: Load All Products
+Use infinite scroll to load all 100 products in the catalog.
+
+### Challenge 4: Multi-step Survey
+Complete the entire multi-step survey form.
+
+### Challenge 5: Full Workflow
+Create a script that logs in, browses products, and exports data.
+
+## 💡 Tips & Tricks
+
+### 1. Use Specific Selectors
+```c4a
+# Good - specific
+CLICK `button.submit-order`
+
+# Bad - too generic
+CLICK `button`
+```
+
+### 2. Always Handle Popups
+```c4a
+# Check for common popups
+IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
+IF (EXISTS `.newsletter-modal`) THEN CLICK `.close`
+```
+
+### 3. Add Appropriate Waits
+```c4a
+# Wait for elements before interacting
+WAIT `.form` 5
+CLICK `#submit`
+```
+
+### 4. Use Procedures for Reusability
+```c4a
+PROC handle_popups
+  IF (EXISTS `.popup`) THEN CLICK `.close`
+  IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
+ENDPROC
+
+# Use anywhere
+handle_popups
+```
+
+## 🔧 Troubleshooting
+
+### Common Issues
+
+1. **"Element not found"**
+   - Add a WAIT before clicking
+   - Check selector specificity
+   - Verify element exists with IF
+
+2. **"Timeout waiting for selector"**
+   - Increase timeout value
+   - Check if element is dynamically loaded
+   - Verify selector is correct
+
+3. **"Missing THEN keyword"**
+   - All IF statements need THEN
+   - Format: `IF (condition) THEN action`
+
+## 🚀 Using with Crawl4AI
+
+Once you've mastered C4A-Script in the tutorial, use it with Crawl4AI:
+
+```python
+from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
+
+config = CrawlerRunConfig(
+    url="https://example.com",
+    c4a_script="""
+    WAIT `.content` 5
+    IF (EXISTS `.load-more`) THEN CLICK `.load-more`
+    WAIT `.new-content` 3
+    """
+)
+
+async with AsyncWebCrawler() as crawler:
+    result = await crawler.arun(config=config)
+```
+
+## 📝 Example Scripts
+
+Check the `scripts/` folder for complete examples:
+- `01-basic-interaction.c4a` - Getting started
+- `02-login-flow.c4a` - Authentication
+- `03-infinite-scroll.c4a` - Dynamic content
+- `04-multi-step-form.c4a` - Complex forms
+- `05-complex-workflow.c4a` - Full automation
+
+## 🏗️ Developer Guide
+
+### Project Architecture
+
+```
+tutorial/
+├── server.py              # Flask application server
+├── assets/               # Tutorial-specific assets
+│   ├── app.js            # Main application logic
+│   ├── c4a-blocks.js     # Custom Blockly blocks
+│   ├── c4a-generator.js  # Code generation
+│   ├── blockly-manager.js # Blockly integration
+│   └── styles.css        # Main styling
+├── playground/           # Interactive demo environment
+│   ├── index.html        # Demo web application
+│   ├── app.js           # Demo app logic
+│   └── styles.css       # Demo styling
+├── scripts/             # Example C4A scripts
+└── index.html           # Main tutorial interface
+```
+
+### Key Components
+
+#### 1. TutorialApp (`assets/app.js`)
+Main application controller managing:
+- Code editor integration (CodeMirror)
+- Script execution and browser preview
+- Tutorial navigation and lessons
+- State management and persistence
+
+#### 2. BlocklyManager (`assets/blockly-manager.js`)
+Visual programming interface:
+- Custom C4A-Script block definitions
+- Bidirectional sync between visual blocks and text
+- Real-time code generation
+- Dark theme integration
+
+#### 3. Recording System
+Powers the recording functionality:
+- Browser event capture
+- Smart event grouping and filtering
+- Automatic C4A-Script generation
+- Timeline visualization
+
+### Customization
+
+#### Adding New Commands
+1. **Define Block** (`assets/c4a-blocks.js`)
+2. **Add Generator** (`assets/c4a-generator.js`)
+3. **Update Parser** (`assets/blockly-manager.js`)
+
+#### Themes and Styling
+- Main styles: `assets/styles.css`
+- Theme variables: CSS custom properties
+- Dark mode: Auto-applied based on system preference
+
+### Configuration
+```python
+# server.py configuration
+PORT = 8080
+DEBUG = True
+THREADED = True
+```
+
+### API Endpoints
+- `GET /` - Main tutorial interface
+- `GET /playground/` - Interactive demo environment
+- `POST /execute` - Script execution endpoint
+- `GET /examples/<script>` - Load example scripts
+
+## 🔧 Troubleshooting
+
+### Common Issues
+
+**Port Already in Use**
+```bash
+# Kill existing process
+lsof -ti:8080 | xargs kill -9
+# Or use different port
+python server.py --port 8081
+```
+
+**Blockly Not Loading**
+- Check browser console for JavaScript errors
+- Verify all static files are served correctly
+- Ensure proper script loading order
+
+**Recording Issues**
+- Verify iframe permissions
+- Check cross-origin communication
+- Ensure event listeners are attached
+
+### Debug Mode
+Enable detailed logging by setting `DEBUG = True` in `assets/app.js`
+
+## 📚 Additional Resources
+
+- **[C4A-Script Documentation](../../md_v2/core/c4a-script.md)** - Complete language guide
+- **[API Reference](../../md_v2/api/c4a-script-reference.md)** - Detailed command documentation
+- **[Live Demo](https://docs.crawl4ai.com/c4a-script/demo)** - Try without installation
+- **[Example Scripts](../)** - More automation examples
+
+## 🤝 Contributing
+
+### Bug Reports
+1. Check existing issues on GitHub
+2. Provide minimal reproduction steps
+3. Include browser and system information
+4. Add relevant console logs
+
+### Feature Requests
+1. Fork the repository
+2. Create feature branch: `git checkout -b feature/my-feature`
+3. Test thoroughly with different browsers
+4. Update documentation
+5. Submit pull request
+
+### Code Style
+- Use consistent indentation (2 spaces for JS, 4 for Python)
+- Add comments for complex logic
+- Follow existing naming conventions
+- Test with multiple browsers
+
+---
+
+**Happy Automating!** 🎉
+
+Need help? Check our [documentation](https://docs.crawl4ai.com) or open an issue on [GitHub](https://github.com/unclecode/crawl4ai).