feat: adding test file to my branch

.gitignore

@@ -211,7 +211,5 @@ git_issues.md
 .docs/
 .issues/
 .gitboss/
-todo_executor.md
-protect-all-except-feature.sh
-manage-collab.sh
-publish.sh
+
+manage-collab.sh 

CHANGELOG.md

@@ -1,162 +1,5 @@
 # Changelog
 
-## [0.3.75] December 1, 2024
-
-### PruningContentFilter
-
-#### 1. Introduced PruningContentFilter (Dec 01, 2024) (Dec 01, 2024)
-A new content filtering strategy that removes less relevant nodes based on metrics like text and link density.
-
-**Affected Files:**
-- `crawl4ai/content_filter_strategy.py`: Enhancement of content filtering capabilities.
-```diff
-Implemented effective pruning algorithm with comprehensive scoring.
-```
-- `README.md`: Improved documentation regarding new features.
-```diff
-Updated to include usage and explanation for the PruningContentFilter.
-```
-- `docs/md_v2/basic/content_filtering.md`: Expanded documentation for users.
-```diff
-Added detailed section explaining the PruningContentFilter.
-```
-
-#### 2. Added Unit Tests for PruningContentFilter (Dec 01, 2024) (Dec 01, 2024)
-Comprehensive tests added to ensure correct functionality of PruningContentFilter
-
-**Affected Files:**
-- `tests/async/test_content_filter_prune.py`: Increased test coverage for content filtering strategies.
-```diff
-Created test cases for various scenarios using the PruningContentFilter.
-```
-
-### Development Updates
-
-#### 3. Enhanced BM25ContentFilter tests (Dec 01, 2024) (Dec 01, 2024)
-Extended testing to cover additional edge cases and performance metrics.
-
-**Affected Files:**
-- `tests/async/test_content_filter_bm25.py`: Improved reliability and performance assurance.
-```diff
-Added tests for new extraction scenarios including malformed HTML.
-```
-
-### Infrastructure & Documentation
-
-#### 4. Updated Examples (Dec 01, 2024) (Dec 01, 2024)
-Altered examples in documentation to promote the use of PruningContentFilter alongside existing strategies.
-
-**Affected Files:**
-- `docs/examples/quickstart_async.py`: Enhanced usability and clarity for new users.
-- Revised example to illustrate usage of PruningContentFilter.
-
-## [0.3.746] November 29, 2024
-
-### Major Features
-1. Enhanced Docker Support (Nov 29, 2024)
-   - Improved GPU support in Docker images.
-   - Dockerfile refactored for better platform-specific installations.
-   - Introduced new Docker commands for different platforms:
-     - `basic-amd64`, `all-amd64`, `gpu-amd64` for AMD64.
-     - `basic-arm64`, `all-arm64`, `gpu-arm64` for ARM64.
-
-### Infrastructure & Documentation
-- Enhanced README.md to improve user guidance and installation instructions.
-- Added installation instructions for Playwright setup in README.
-- Created and updated examples in `docs/examples/quickstart_async.py` to be more useful and user-friendly.
-- Updated `requirements.txt` with a new `pydantic` dependency.
-- Bumped version number in `crawl4ai/__version__.py` to 0.3.746.
-
-### Breaking Changes
-- Streamlined application structure:
-  - Removed static pages and related code from `main.py` which might affect existing deployments relying on static content.
-
-### Development Updates
-- Developed `post_install` method in `crawl4ai/install.py` to streamline post-installation setup tasks.
-- Refined migration processes in `crawl4ai/migrations.py` with enhanced logging for better error visibility.
-- Updated `docker-compose.yml` to support local and hub services for different architectures, enhancing build and deploy capabilities.
-- Refactored example test cases in `docs/examples/docker_example.py` to facilitate comprehensive testing.
-
-### README.md
-Updated README with new docker commands and setup instructions.
-Enhanced installation instructions and guidance.
-
-### crawl4ai/install.py
-Added post-install script functionality.
-Introduced `post_install` method for automation of post-installation tasks.
-
-### crawl4ai/migrations.py
-Improved migration logging.
-Refined migration processes and added better logging.
-
-### docker-compose.yml
-Refactored docker-compose for better service management.
-Updated to define services for different platforms and versions.
-
-### requirements.txt
-Updated dependencies.
-Added `pydantic` to requirements file.
-
-### crawler/__version__.py
-Updated version number.
-Bumped version number to 0.3.746.
-
-### docs/examples/quickstart_async.py
-Enhanced example scripts.
-Uncommented example usage in async guide for user functionality.
-
-### main.py
-Refactored code to improve maintainability.
-Streamlined app structure by removing static pages code.
-
-## [0.3.743] November 27, 2024
-
-Enhance features and documentation
-- Updated version to 0.3.743
-- Improved ManagedBrowser configuration with dynamic host/port
-- Implemented fast HTML formatting in web crawler
-- Enhanced markdown generation with a new generator class
-- Improved sanitization and utility functions
-- Added contributor details and pull request acknowledgments
-- Updated documentation for clearer usage scenarios
-- Adjusted tests to reflect class name changes
-
-### CONTRIBUTORS.md
-Added new contributors and pull request details.
-Updated community contributions and acknowledged pull requests.
-
-### crawl4ai/__version__.py
-Version update.
-Bumped version to 0.3.743.
-
-### crawl4ai/async_crawler_strategy.py
-Improved ManagedBrowser configuration.
-Enhanced browser initialization with configurable host and debugging port; improved hook execution.
-
-### crawl4ai/async_webcrawler.py
-Optimized HTML processing.
-Implemented 'fast_format_html' for optimized HTML formatting; applied it when 'prettiify' is enabled.
-
-### crawl4ai/content_scraping_strategy.py
-Enhanced markdown generation strategy.
-Updated to use DefaultMarkdownGenerator and improved markdown generation with filters option.
-
-### crawl4ai/markdown_generation_strategy.py
-Refactored markdown generation class.
-Renamed DefaultMarkdownGenerationStrategy to DefaultMarkdownGenerator; added content filter handling.
-
-### crawl4ai/utils.py
-Enhanced utility functions.
-Improved input sanitization and enhanced HTML formatting method.
-
-### docs/md_v2/advanced/hooks-auth.md
-Improved documentation for hooks.
-Updated code examples to include cookies in crawler strategy initialization.
-
-### tests/async/test_markdown_genertor.py
-Refactored tests to match class renaming.
-Updated tests to use renamed DefaultMarkdownGenerator class.
-
 ## [0.3.74] November 17, 2024
 
 This changelog details the updates and changes introduced in Crawl4AI version 0.3.74. It's designed to inform developers about new features, modifications to existing components, removals, and other important information.

CONTRIBUTORS.md

@@ -10,21 +10,11 @@ We would like to thank the following people for their contributions to Crawl4AI:
 
 ## Community Contributors
 
-- [aadityakanjolia4](https://github.com/aadityakanjolia4) - Fix for `CustomHTML2Text` is not defined.
 - [FractalMind](https://github.com/FractalMind) - Created the first official Docker Hub image and fixed Dockerfile errors
 - [ketonkss4](https://github.com/ketonkss4) - Identified Selenium's new capabilities, helping reduce dependencies
 - [jonymusky](https://github.com/jonymusky) - Javascript execution documentation, and wait_for
 - [datehoer](https://github.com/datehoer) - Add browser prxy support
 
-## Pull Requests
-
-- [dvschuyl](https://github.com/dvschuyl) - AsyncPlaywrightCrawlerStrategy page-evaluate context destroyed by navigation [#304](https://github.com/unclecode/crawl4ai/pull/304)
-- [nelzomal](https://github.com/nelzomal) - Enhance development installation instructions [#286](https://github.com/unclecode/crawl4ai/pull/286)
-- [HamzaFarhan](https://github.com/HamzaFarhan) - Handled the cases where markdown_with_citations, references_markdown, and filtered_html might not be defined [#293](https://github.com/unclecode/crawl4ai/pull/293)
-- [NanmiCoder](https://github.com/NanmiCoder) - fix: crawler strategy exception handling and fixes [#271](https://github.com/unclecode/crawl4ai/pull/271)
-- [paulokuong](https://github.com/paulokuong) - fix: RAWL4_AI_BASE_DIRECTORY should be Path object instead of string [#298](https://github.com/unclecode/crawl4ai/pull/298)
-
-
 ## Other Contributors
 
 - [Gokhan](https://github.com/gkhngyk) 

Dockerfile

@@ -1,9 +1,6 @@
 # syntax=docker/dockerfile:1.4
 
-ARG TARGETPLATFORM
-ARG BUILDPLATFORM
-
-# Other build arguments
+# Build arguments
 ARG PYTHON_VERSION=3.10
 
 # Base stage with system dependencies
@@ -66,13 +63,13 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     && rm -rf /var/lib/apt/lists/*
 
 # GPU support if enabled and architecture is supported
-RUN if [ "$ENABLE_GPU" = "true" ] && [ "$TARGETPLATFORM" = "linux/amd64" ] ; then \
-    apt-get update && apt-get install -y --no-install-recommends \
-    nvidia-cuda-toolkit \
-    && rm -rf /var/lib/apt/lists/* ; \
-else \
-    echo "Skipping NVIDIA CUDA Toolkit installation (unsupported platform or GPU disabled)"; \
-fi
+RUN if [ "$ENABLE_GPU" = "true" ] && [ "$(dpkg --print-architecture)" != "arm64" ] ; then \
+        apt-get update && apt-get install -y --no-install-recommends \
+        nvidia-cuda-toolkit \
+        && rm -rf /var/lib/apt/lists/* ; \
+    else \
+        echo "Skipping NVIDIA CUDA Toolkit installation (unsupported architecture or GPU disabled)"; \
+    fi
 
 # Create and set working directory
 WORKDIR /app
@@ -123,11 +120,7 @@ RUN pip install --no-cache-dir \
 RUN mkdocs build
 
 # Install Playwright and browsers
-RUN if [ "$TARGETPLATFORM" = "linux/amd64" ]; then \
-    playwright install chromium; \
-    elif [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
-    playwright install chromium; \
-    fi
+RUN playwright install
 
 # Expose port
 EXPOSE 8000 11235 9222 8080

README.md

@@ -1,4 +1,4 @@
-# 🔥🕷️ Crawl4AI: Crawl Smarter, Faster, Freely. For AI.
+# 🔥🕷️ Crawl4AI: LLM Friendly Web Crawler & Scraper
 
 <a href="https://trendshift.io/repositories/11716" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11716" alt="unclecode%2Fcrawl4ai | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 
@@ -9,119 +9,19 @@
 [![GitHub Pull Requests](https://img.shields.io/github/issues-pr/unclecode/crawl4ai)](https://github.com/unclecode/crawl4ai/pulls)
 [![License](https://img.shields.io/github/license/unclecode/crawl4ai)](https://github.com/unclecode/crawl4ai/blob/main/LICENSE)
 
-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.  
-
-
-🎉 **Version 0.4.0 is out!** Introducing our experimental PruningContentFilter - a powerful new algorithm for smarter Markdown generation. Test it out and [share your feedback](https://github.com/unclecode/crawl4ai/issues)! [Read the release notes →](https://github.com/unclecode/crawl4ai/blob/main/docs/md_v2/blog/releases/0.4.0.md)
-
-[✨ Check out latest update v0.4.0](#-recent-updates)
-
-## 🧐 Why Crawl4AI?
-
-1. **Built for LLMs**: Creates smart, concise Markdown optimized for RAG and fine-tuning applications.  
-2. **Lightning Fast**: Delivers results 6x faster with real-time, cost-efficient performance.  
-3. **Flexible Browser Control**: Offers session management, proxies, and custom hooks for seamless data access.  
-4. **Heuristic Intelligence**: Uses advanced algorithms for efficient extraction, reducing reliance on costly models.  
-5. **Open Source & Deployable**: Fully open-source with no API keys—ready for Docker and cloud integration.  
-6. **Thriving Community**: Actively maintained by a vibrant community and the #1 trending GitHub repository.
-
-## 🚀 Quick Start 
-
-1. Install Crawl4AI:
-```bash
-pip install crawl4ai
-crawl4ai-setup # Setup the browser
-```
-
-2. Run a simple web crawl:
-```python
-import asyncio
-from crawl4ai import AsyncWebCrawler, CacheMode
-
-async def main():
-    async with AsyncWebCrawler(verbose=True) as crawler:
-        result = await crawler.arun(url="https://www.nbcnews.com/business")
-        # Soone will be change to result.markdown
-        print(result.markdown_v2.raw_markdown) 
-
-if __name__ == "__main__":
-    asyncio.run(main())
-```
-
-## ✨ Features 
-
-<details>
-<summary>📝 <strong>Markdown Generation</strong></summary>
-
-- 🧹 **Clean Markdown**: Generates clean, structured Markdown with accurate formatting.
-- 🎯 **Fit Markdown**: Heuristic-based filtering to remove noise and irrelevant parts for AI-friendly processing.
-- 🔗 **Citations and References**: Converts page links into a numbered reference list with clean citations.
-- 🛠️ **Custom Strategies**: Users can create their own Markdown generation strategies tailored to specific needs.
-- 📚 **BM25 Algorithm**: Employs BM25-based filtering for extracting core information and removing irrelevant content. 
-</details>
-
-<details>
-<summary>📊 <strong>Structured Data Extraction</strong></summary>
-
-- 🤖 **LLM-Driven Extraction**: Supports all LLMs (open-source and proprietary) for structured data extraction.
-- 🧱 **Chunking Strategies**: Implements chunking (topic-based, regex, sentence-level) for targeted content processing.
-- 🌌 **Cosine Similarity**: Find relevant content chunks based on user queries for semantic extraction.
-- 🔎 **CSS-Based Extraction**: Fast schema-based data extraction using XPath and CSS selectors.
-- 🔧 **Schema Definition**: Define custom schemas for extracting structured JSON from repetitive patterns.
-
-</details>
-
-<details>
-<summary>🌐 <strong>Browser Integration</strong></summary>
-
-- 🖥️ **Managed Browser**: Use user-owned browsers with full control, avoiding bot detection.
-- 🔄 **Remote Browser Control**: Connect to Chrome Developer Tools Protocol for remote, large-scale data extraction.
-- 🔒 **Session Management**: Preserve browser states and reuse them for multi-step crawling.
-- 🧩 **Proxy Support**: Seamlessly connect to proxies with authentication for secure access.
-- ⚙️ **Full Browser Control**: Modify headers, cookies, user agents, and more for tailored crawling setups.
-- 🌍 **Multi-Browser Support**: Compatible with Chromium, Firefox, and WebKit.
-
-</details>
-
-<details>
-<summary>🔎 <strong>Crawling & Scraping</strong></summary>
-
-- 🖼️ **Media Support**: Extract images, audio, videos, and responsive image formats like `srcset` and `picture`.
-- 🚀 **Dynamic Crawling**: Execute JS and wait for async or sync for dynamic content extraction.
-- 📸 **Screenshots**: Capture page screenshots during crawling for debugging or analysis.
-- 📂 **Raw Data Crawling**: Directly process raw HTML (`raw:`) or local files (`file://`).
-- 🔗 **Comprehensive Link Extraction**: Extracts internal, external links, and embedded iframe content.
-- 🛠️ **Customizable Hooks**: Define hooks at every step to customize crawling behavior.
-- 💾 **Caching**: Cache data for improved speed and to avoid redundant fetches.
-- 📄 **Metadata Extraction**: Retrieve structured metadata from web pages.
-- 📡 **IFrame Content Extraction**: Seamless extraction from embedded iframe content.
-
-</details>
-
-<details>
-<summary>🚀 <strong>Deployment</strong></summary>
-
-- 🐳 **Dockerized Setup**: Optimized Docker image with API server for easy deployment.
-- 🔄 **API Gateway**: One-click deployment with secure token authentication for API-based workflows.
-- 🌐 **Scalable Architecture**: Designed for mass-scale production and optimized server performance.
-- ⚙️ **DigitalOcean Deployment**: Ready-to-deploy configurations for DigitalOcean and similar platforms.
-
-</details>
-
-<details>
-<summary>🎯 <strong>Additional Features</strong></summary>
-
-- 🕶️ **Stealth Mode**: Avoid bot detection by mimicking real users.
-- 🏷️ **Tag-Based Content Extraction**: Refine crawling based on custom tags, headers, or metadata.
-- 🔗 **Link Analysis**: Extract and analyze all links for detailed data exploration.
-- 🛡️ **Error Handling**: Robust error management for seamless execution.
-- 🔐 **CORS & Static Serving**: Supports filesystem-based caching and cross-origin requests.
-- 📖 **Clear Documentation**: Simplified and updated guides for onboarding and advanced usage.
-- 🙌 **Community Recognition**: Acknowledges contributors and pull requests for transparency.
-
-</details>
+Crawl4AI simplifies asynchronous web crawling and data extraction, making it accessible for large language models (LLMs) and AI applications. 🆓🌐
 
+## New in 0.3.74 ✨
 
+- 🚀 **Blazing Fast Scraping:** The scraping process is now significantly faster, often completing in under 100 milliseconds (excluding web fetch time)!
+- 📥 **Download Manager:** Integrated file crawling and downloading capabilities, with full control over file management and tracking within the `CrawlResult` object.
+- 🔎 **Markdown Filter:** Enhanced content extraction using BM25 algorithm to create cleaner markdown with only relevant webpage content.
+- 🗂️ **Local & Raw HTML:** Crawl local files (`file://`) and raw HTML strings (`raw:`) directly.
+- 🤖 **Browser Control:** Use your own browser setup for crawling, with persistent contexts and stealth integration to bypass anti-bot measures.
+- ☁️ **API & Cache Boost:** CORS support, static file serving, and a new filesystem-based cache for blazing-fast performance. Fine-tune caching with the `CacheMode` enum (ENABLED, DISABLED, READ_ONLY, WRITE_ONLY, BYPASS) and the `always_bypass_cache` parameter.
+- 🐳 **API Gateway:** Run Crawl4AI as a local or cloud API service, enabling cross-platform usage through a containerized server with secure token authentication via `CRAWL4AI_API_TOKEN`.
+- 🛠️ **Database Improvements:** Enhanced database system for handling larger content sets with improved caching and faster performance.
+- 🐛 **Squashed Bugs:** Fixed browser context issues in Docker, memory leaks, enhanced error handling, and improved HTML parsing.
 
 ## Try it Now!
 
@@ -129,27 +29,53 @@ if __name__ == "__main__":
 
 ✨ Visit our [Documentation Website](https://crawl4ai.com/mkdocs/)
 
+## Features ✨
+
+- 🆓 Completely free and open-source
+- 🚀 Blazing fast performance, outperforming many paid services
+- 🤖 LLM-friendly output formats (JSON, cleaned HTML, markdown)
+- 🌐 Multi-browser support (Chromium, Firefox, WebKit)
+- 🌍 Supports crawling multiple URLs simultaneously
+- 🎨 Extracts and returns all media tags (Images, Audio, and Video)
+- 🔗 Extracts all external and internal links
+- 📚 Extracts metadata from the page
+- 🔄 Custom hooks for authentication, headers, and page modifications
+- 🕵️ User-agent customization
+- 🖼️ Takes screenshots of pages with enhanced error handling
+- 📜 Executes multiple custom JavaScripts before crawling
+- 📊 Generates structured output without LLM using JsonCssExtractionStrategy
+- 📚 Various chunking strategies: topic-based, regex, sentence, and more
+- 🧠 Advanced extraction strategies: cosine clustering, LLM, and more
+- 🎯 CSS selector support for precise data extraction
+- 📝 Passes instructions/keywords to refine extraction
+- 🔒 Proxy support with authentication for enhanced access
+- 🔄 Session management for complex multi-page crawling
+- 🌐 Asynchronous architecture for improved performance
+- 🖼️ Improved image processing with lazy-loading detection
+- 🕰️ Enhanced handling of delayed content loading
+- 🔑 Custom headers support for LLM interactions
+- 🖼️ iframe content extraction for comprehensive analysis
+- ⏱️ Flexible timeout and delayed content retrieval options
+
 ## Installation 🛠️
 
 Crawl4AI offers flexible installation options to suit various use cases. You can install it as a Python package or use Docker.
 
-<details>
-<summary>🐍 <strong>Using pip</strong></summary>
+### Using pip 🐍
 
 Choose the installation option that best fits your needs:
 
-### Basic Installation
+#### Basic Installation
 
 For basic web crawling and scraping tasks:
 
 ```bash
 pip install crawl4ai
-crawl4ai-setup # Setup the browser
 ```
 
 By default, this will install the asynchronous version of Crawl4AI, using Playwright for web crawling.
 
-👉 **Note**: When you install Crawl4AI, the `crawl4ai-setup` should automatically install and set up Playwright. However, if you encounter any Playwright-related errors, you can manually install it using one of these methods:
+👉 Note: When you install Crawl4AI, the setup script should automatically install and set up Playwright. However, if you encounter any Playwright-related errors, you can manually install it using one of these methods:
 
 1. Through the command line:
 
@@ -165,42 +91,25 @@ By default, this will install the asynchronous version of Crawl4AI, using Playwr
 
 This second method has proven to be more reliable in some cases.
 
----
+#### Installation with Synchronous Version
 
-### Installation with Synchronous Version
-
-The sync version is deprecated and will be removed in future versions. If you need the synchronous version using Selenium:
+If you need the synchronous version using Selenium:
 
 ```bash
 pip install crawl4ai[sync]
 ```
 
----
-
-### Development Installation
+#### Development Installation
 
 For contributors who plan to modify the source code:
 
 ```bash
 git clone https://github.com/unclecode/crawl4ai.git
 cd crawl4ai
-pip install -e .                    # Basic installation in editable mode
+pip install -e .
 ```
 
-Install optional features:
-
-```bash
-pip install -e ".[torch]"           # With PyTorch features
-pip install -e ".[transformer]"     # With Transformer features
-pip install -e ".[cosine]"          # With cosine similarity features
-pip install -e ".[sync]"            # With synchronous crawling (Selenium)
-pip install -e ".[all]"             # Install all optional features
-```
-
-</details>
-
-<details>
-<summary>🚀 <strong>One-Click Deployment</strong></summary>
+## One-Click Deployment 🚀
 
 Deploy your own instance of Crawl4AI with one click:
 
@@ -211,191 +120,45 @@ Deploy your own instance of Crawl4AI with one click:
 The deploy will:
 - Set up a Docker container with Crawl4AI
 - Configure Playwright and all dependencies
-- Start the FastAPI server on port `11235`
+- Start the FastAPI server on port 11235
 - Set up health checks and auto-deployment
 
-</details>
-
-<details>
-<summary>🐳 <strong>Using Docker</strong></summary>
+### Using Docker 🐳
 
 Crawl4AI is available as Docker images for easy deployment. You can either pull directly from Docker Hub (recommended) or build from the repository.
 
----
+#### Option 1: Docker Hub (Recommended)
 
-<details>
-<summary>🐳 <strong>Option 1: Docker Hub (Recommended)</strong></summary>
-
-Choose the appropriate image based on your platform and needs:
-
-### For AMD64 (Regular Linux/Windows):
 ```bash
-# Basic version (recommended)
-docker pull unclecode/crawl4ai:basic-amd64
-docker run -p 11235:11235 unclecode/crawl4ai:basic-amd64
+# Pull and run from Docker Hub (choose one):
+docker pull unclecode/crawl4ai:basic    # Basic crawling features
+docker pull unclecode/crawl4ai:all      # Full installation (ML, LLM support)
+docker pull unclecode/crawl4ai:gpu      # GPU-enabled version
 
-# Full ML/LLM support
-docker pull unclecode/crawl4ai:all-amd64
-docker run -p 11235:11235 unclecode/crawl4ai:all-amd64
+# Run the container
+docker run -p 11235:11235 unclecode/crawl4ai:basic  # Replace 'basic' with your chosen version
 
-# With GPU support
-docker pull unclecode/crawl4ai:gpu-amd64
-docker run -p 11235:11235 unclecode/crawl4ai:gpu-amd64
+# In case to allocate more shared memory for the container
+docker run --shm-size=2gb -p 11235:11235 unclecode/crawl4ai:basic
 ```
 
-### For ARM64 (M1/M2 Macs, ARM servers):
-```bash
-# Basic version (recommended)
-docker pull unclecode/crawl4ai:basic-arm64
-docker run -p 11235:11235 unclecode/crawl4ai:basic-arm64
-
-# Full ML/LLM support
-docker pull unclecode/crawl4ai:all-arm64
-docker run -p 11235:11235 unclecode/crawl4ai:all-arm64
-
-# With GPU support
-docker pull unclecode/crawl4ai:gpu-arm64
-docker run -p 11235:11235 unclecode/crawl4ai:gpu-arm64
-```
-
-Need more memory? Add `--shm-size`:
-```bash
-docker run --shm-size=2gb -p 11235:11235 unclecode/crawl4ai:basic-amd64
-```
-
-Test the installation:
-```bash
-curl http://localhost:11235/health
-```
-
-### For Raspberry Pi (32-bit) (coming soon):
-```bash
-# Pull and run basic version (recommended for Raspberry Pi)
-docker pull unclecode/crawl4ai:basic-armv7
-docker run -p 11235:11235 unclecode/crawl4ai:basic-armv7
-
-# With increased shared memory if needed
-docker run --shm-size=2gb -p 11235:11235 unclecode/crawl4ai:basic-armv7
-```
-
-Note: Due to hardware constraints, only the basic version is recommended for Raspberry Pi.
-
-</details>
-
-<details>
-<summary>🐳 <strong>Option 2: Build from Repository</strong></summary>
-
-Build the image locally based on your platform:
+#### Option 2: Build from Repository
 
 ```bash
 # Clone the repository
 git clone https://github.com/unclecode/crawl4ai.git
 cd crawl4ai
 
-# For AMD64 (Regular Linux/Windows)
-docker build --platform linux/amd64 \
-  --tag crawl4ai:local \
-  --build-arg INSTALL_TYPE=basic \
+# Build the image
+docker build -t crawl4ai:local \
+  --build-arg INSTALL_TYPE=basic \  # Options: basic, all
   .
 
-# For ARM64 (M1/M2 Macs, ARM servers)
-docker build --platform linux/arm64 \
-  --tag crawl4ai:local \
-  --build-arg INSTALL_TYPE=basic \
-  .
-```
-
-Build options:
-- INSTALL_TYPE=basic (default): Basic crawling features
-- INSTALL_TYPE=all: Full ML/LLM support
-- ENABLE_GPU=true: Add GPU support
-
-Example with all options:
-```bash
-docker build --platform linux/amd64 \
-  --tag crawl4ai:local \
-  --build-arg INSTALL_TYPE=all \
-  --build-arg ENABLE_GPU=true \
-  .
-```
-
-Run your local build:
-```bash
-# Regular run
+# Run your local build
 docker run -p 11235:11235 crawl4ai:local
-
-# With increased shared memory
-docker run --shm-size=2gb -p 11235:11235 crawl4ai:local
 ```
 
-Test the installation:
-```bash
-curl http://localhost:11235/health
-```
-
-</details>
-
-<details>
-<summary>🐳 <strong>Option 3: Using Docker Compose</strong></summary>
-
-Docker Compose provides a more structured way to run Crawl4AI, especially when dealing with environment variables and multiple configurations.
-
-```bash
-# Clone the repository
-git clone https://github.com/unclecode/crawl4ai.git
-cd crawl4ai
-```
-
-### For AMD64 (Regular Linux/Windows):
-```bash
-# Build and run locally
-docker-compose --profile local-amd64 up
-
-# Run from Docker Hub
-VERSION=basic docker-compose --profile hub-amd64 up   # Basic version
-VERSION=all docker-compose --profile hub-amd64 up     # Full ML/LLM support
-VERSION=gpu docker-compose --profile hub-amd64 up     # GPU support
-```
-
-### For ARM64 (M1/M2 Macs, ARM servers):
-```bash
-# Build and run locally
-docker-compose --profile local-arm64 up
-
-# Run from Docker Hub
-VERSION=basic docker-compose --profile hub-arm64 up   # Basic version
-VERSION=all docker-compose --profile hub-arm64 up     # Full ML/LLM support
-VERSION=gpu docker-compose --profile hub-arm64 up     # GPU support
-```
-
-Environment variables (optional):
-```bash
-# Create a .env file
-CRAWL4AI_API_TOKEN=your_token
-OPENAI_API_KEY=your_openai_key
-CLAUDE_API_KEY=your_claude_key
-```
-
-The compose file includes:
-- Memory management (4GB limit, 1GB reserved)
-- Shared memory volume for browser support
-- Health checks
-- Auto-restart policy
-- All necessary port mappings
-
-Test the installation:
-```bash
-curl http://localhost:11235/health
-```
-
-</details>
-
----
-
-### Quick Test
-
-Run a quick test (works for both Docker options):
-
+Quick test (works for both options):
 ```python
 import requests
 
@@ -406,143 +169,149 @@ response = requests.post(
 )
 task_id = response.json()["task_id"]
 
-# Continue polling until the task is complete (status="completed")
+# Get results
 result = requests.get(f"http://localhost:11235/task/{task_id}")
 ```
 
-For more examples, see our [Docker Examples](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/docker_example.py). For advanced configuration, environment variables, and usage examples, see our [Docker Deployment Guide](https://crawl4ai.com/mkdocs/basic/docker-deployment/).
-
-</details>
+For advanced configuration, environment variables, and usage examples, see our [Docker Deployment Guide](https://crawl4ai.com/mkdocs/basic/docker-deployment/).
 
 
-## 🔬 Advanced Usage Examples 🔬
-
-You can check the project structure in the directory [https://github.com/unclecode/crawl4ai/docs/examples](docs/examples). Over there, you can find a variety of examples; here, some popular examples are shared.
-
-<details>
-<summary>📝 <strong>Heuristic Markdown Generation with Clean and Fit Markdown</strong></summary>
+## Quick Start 🚀
 
 ```python
 import asyncio
-from crawl4ai import AsyncWebCrawler, CacheMode
-from crawl4ai.content_filter_strategy import PruningContentFilter, BM25ContentFilter
-from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
+from crawl4ai import AsyncWebCrawler
 
 async def main():
-    async with AsyncWebCrawler(
-        headless=True,  
-        verbose=True,
-    ) as crawler:
-        result = await crawler.arun(
-            url="https://docs.micronaut.io/4.7.6/guide/",
-            cache_mode=CacheMode.ENABLED,
-            markdown_generator=DefaultMarkdownGenerator(
-                content_filter=PruningContentFilter(threshold=0.48, threshold_type="fixed", min_word_threshold=0)
-            ),
-            # markdown_generator=DefaultMarkdownGenerator(
-            #     content_filter=BM25ContentFilter(user_query="WHEN_WE_FOCUS_BASED_ON_A_USER_QUERY", bm25_threshold=1.0)
-            # ),
-        )
-        print(len(result.markdown))
-        print(len(result.fit_markdown))
-        print(len(result.markdown_v2.fit_markdown))
+    async with AsyncWebCrawler(verbose=True) as crawler:
+        result = await crawler.arun(url="https://www.nbcnews.com/business")
+        print(result.markdown)
 
 if __name__ == "__main__":
     asyncio.run(main())
 ```
 
-</details>
+## Advanced Usage 🔬
 
-<details>
-<summary>🖥️ <strong>Executing JavaScript & Extract Structured Data without LLMs</strong></summary>
+### Executing JavaScript and Using CSS Selectors
 
 ```python
 import asyncio
-from crawl4ai import AsyncWebCrawler, CacheMode
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
-import json
+from crawl4ai import AsyncWebCrawler
 
 async def main():
+    async with AsyncWebCrawler(verbose=True) as crawler:
+        js_code = ["const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();"]
+        result = await crawler.arun(
+            url="https://www.nbcnews.com/business",
+            js_code=js_code,
+            css_selector=".wide-tease-item__description",
+            bypass_cache=True
+        )
+        print(result.extracted_content)
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+### Using a Proxy
+
+```python
+import asyncio
+from crawl4ai import AsyncWebCrawler
+
+async def main():
+    async with AsyncWebCrawler(verbose=True, proxy="http://127.0.0.1:7890") as crawler:
+        result = await crawler.arun(
+            url="https://www.nbcnews.com/business",
+            bypass_cache=True
+        )
+        print(result.markdown)
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+### Extracting Structured Data without LLM
+
+The `JsonCssExtractionStrategy` allows for precise extraction of structured data from web pages using CSS selectors.
+
+```python
+import asyncio
+import json
+from crawl4ai import AsyncWebCrawler
+from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
+
+async def extract_news_teasers():
     schema = {
-    "name": "KidoCode Courses",
-    "baseSelector": "section.charge-methodology .w-tab-content > div",
-    "fields": [
-        {
-            "name": "section_title",
-            "selector": "h3.heading-50",
-            "type": "text",
-        },
-        {
-            "name": "section_description",
-            "selector": ".charge-content",
-            "type": "text",
-        },
-        {
-            "name": "course_name",
-            "selector": ".text-block-93",
-            "type": "text",
-        },
-        {
-            "name": "course_description",
-            "selector": ".course-content-text",
-            "type": "text",
-        },
-        {
-            "name": "course_icon",
-            "selector": ".image-92",
-            "type": "attribute",
-            "attribute": "src"
-        }
-    ]
-}
+        "name": "News Teaser Extractor",
+        "baseSelector": ".wide-tease-item__wrapper",
+        "fields": [
+            {
+                "name": "category",
+                "selector": ".unibrow span[data-testid='unibrow-text']",
+                "type": "text",
+            },
+            {
+                "name": "headline",
+                "selector": ".wide-tease-item__headline",
+                "type": "text",
+            },
+            {
+                "name": "summary",
+                "selector": ".wide-tease-item__description",
+                "type": "text",
+            },
+            {
+                "name": "time",
+                "selector": "[data-testid='wide-tease-date']",
+                "type": "text",
+            },
+            {
+                "name": "image",
+                "type": "nested",
+                "selector": "picture.teasePicture img",
+                "fields": [
+                    {"name": "src", "type": "attribute", "attribute": "src"},
+                    {"name": "alt", "type": "attribute", "attribute": "alt"},
+                ],
+            },
+            {
+                "name": "link",
+                "selector": "a[href]",
+                "type": "attribute",
+                "attribute": "href",
+            },
+        ],
+    }
 
     extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)
 
-    async with AsyncWebCrawler(
-        headless=False,
-        verbose=True
-    ) as crawler:
-        
-        # Create the JavaScript that handles clicking multiple times
-        js_click_tabs = """
-        (async () => {
-            const tabs = document.querySelectorAll("section.charge-methodology .tabs-menu-3 > div");
-            
-            for(let tab of tabs) {
-                // scroll to the tab
-                tab.scrollIntoView();
-                tab.click();
-                // Wait for content to load and animations to complete
-                await new Promise(r => setTimeout(r, 500));
-            }
-        })();
-        """     
-
+    async with AsyncWebCrawler(verbose=True) as crawler:
         result = await crawler.arun(
-            url="https://www.kidocode.com/degrees/technology",
-            extraction_strategy=JsonCssExtractionStrategy(schema, verbose=True),
-            js_code=[js_click_tabs],
-            cache_mode=CacheMode.BYPASS
+            url="https://www.nbcnews.com/business",
+            extraction_strategy=extraction_strategy,
+            bypass_cache=True,
         )
 
-        companies = json.loads(result.extracted_content)
-        print(f"Successfully extracted {len(companies)} companies")
-        print(json.dumps(companies[0], indent=2))
+        assert result.success, "Failed to crawl the page"
 
+        news_teasers = json.loads(result.extracted_content)
+        print(f"Successfully extracted {len(news_teasers)} news teasers")
+        print(json.dumps(news_teasers[0], indent=2))
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    asyncio.run(extract_news_teasers())
 ```
 
-</details>
+For more advanced usage examples, check out our [Examples](https://crawl4ai.com/mkdocs/extraction/css-advanced/) section in the documentation.
 
-<details>
-<summary>📚 <strong>Extracting Structured Data with LLMs</strong></summary>
+### Extracting Structured Data with OpenAI
 
 ```python
 import os
 import asyncio
-from crawl4ai import AsyncWebCrawler, CacheMode
+from crawl4ai import AsyncWebCrawler
 from crawl4ai.extraction_strategy import LLMExtractionStrategy
 from pydantic import BaseModel, Field
 
@@ -557,8 +326,6 @@ async def main():
             url='https://openai.com/api/pricing/',
             word_count_threshold=1,
             extraction_strategy=LLMExtractionStrategy(
-                # Here you can use any provider that Litellm library supports, for instance: ollama/qwen2
-                # provider="ollama/qwen2", api_token="no-token", 
                 provider="openai/gpt-4o", api_token=os.getenv('OPENAI_API_KEY'), 
                 schema=OpenAIModelFee.schema(),
                 extraction_type="schema",
@@ -566,7 +333,7 @@ async def main():
                 Do not miss any models in the entire content. One extracted model JSON format should look like this: 
                 {"model_name": "GPT-4", "input_fee": "US$10.00 / 1M tokens", "output_fee": "US$30.00 / 1M tokens"}."""
             ),            
-            cache_mode=CacheMode.BYPASS,
+            bypass_cache=True,
         )
         print(result.extracted_content)
 
@@ -574,101 +341,143 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
-</details>
+### Session Management and Dynamic Content Crawling
 
-<details>
-<summary>🤖 <strong>Using You own Browswer with Custome User Profile</strong></summary>
+Crawl4AI excels at handling complex scenarios, such as crawling multiple pages with dynamic content loaded via JavaScript. Here's an example of crawling GitHub commits across multiple pages:
 
 ```python
-import os, sys
-from pathlib import Path
-import asyncio, time
+import asyncio
+import re
+from bs4 import BeautifulSoup
 from crawl4ai import AsyncWebCrawler
 
-async def test_news_crawl():
-    # Create a persistent user data directory
-    user_data_dir = os.path.join(Path.home(), ".crawl4ai", "browser_profile")
-    os.makedirs(user_data_dir, exist_ok=True)
+async def crawl_typescript_commits():
+    first_commit = ""
+    async def on_execution_started(page):
+        nonlocal first_commit 
+        try:
+            while True:
+                await page.wait_for_selector('li.Box-sc-g0xbh4-0 h4')
+                commit = await page.query_selector('li.Box-sc-g0xbh4-0 h4')
+                commit = await commit.evaluate('(element) => element.textContent')
+                commit = re.sub(r'\s+', '', commit)
+                if commit and commit != first_commit:
+                    first_commit = commit
+                    break
+                await asyncio.sleep(0.5)
+        except Exception as e:
+            print(f"Warning: New content didn't appear after JavaScript execution: {e}")
 
-    async with AsyncWebCrawler(
-        verbose=True,
-        headless=True,
-        user_data_dir=user_data_dir,
-        use_persistent_context=True,
-        headers={
-            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
-            "Accept-Language": "en-US,en;q=0.5",
-            "Accept-Encoding": "gzip, deflate, br",
-            "DNT": "1",
-            "Connection": "keep-alive",
-            "Upgrade-Insecure-Requests": "1",
-            "Sec-Fetch-Dest": "document",
-            "Sec-Fetch-Mode": "navigate",
-            "Sec-Fetch-Site": "none",
-            "Sec-Fetch-User": "?1",
-            "Cache-Control": "max-age=0",
-        }
-    ) as crawler:
-        url = "ADDRESS_OF_A_CHALLENGING_WEBSITE"
-        
-        result = await crawler.arun(
-            url,
-            cache_mode=CacheMode.BYPASS,
-            magic=True,
-        )
-        
-        print(f"Successfully crawled {url}")
-        print(f"Content length: {len(result.markdown)}")
+    async with AsyncWebCrawler(verbose=True) as crawler:
+        crawler.crawler_strategy.set_hook('on_execution_started', on_execution_started)
+
+        url = "https://github.com/microsoft/TypeScript/commits/main"
+        session_id = "typescript_commits_session"
+        all_commits = []
+
+        js_next_page = """
+        const button = document.querySelector('a[data-testid="pagination-next-button"]');
+        if (button) button.click();
+        """
+
+        for page in range(3):  # Crawl 3 pages
+            result = await crawler.arun(
+                url=url,
+                session_id=session_id,
+                css_selector="li.Box-sc-g0xbh4-0",
+                js=js_next_page if page > 0 else None,
+                bypass_cache=True,
+                js_only=page > 0
+            )
+
+            assert result.success, f"Failed to crawl page {page + 1}"
+
+            soup = BeautifulSoup(result.cleaned_html, 'html.parser')
+            commits = soup.select("li")
+            all_commits.extend(commits)
+
+            print(f"Page {page + 1}: Found {len(commits)} commits")
+
+        await crawler.crawler_strategy.kill_session(session_id)
+        print(f"Successfully crawled {len(all_commits)} commits across 3 pages")
+
+if __name__ == "__main__":
+    asyncio.run(crawl_typescript_commits())
 ```
 
+This example demonstrates Crawl4AI's ability to handle complex scenarios where content is loaded asynchronously. It crawls multiple pages of GitHub commits, executing JavaScript to load new content and using custom hooks to ensure data is loaded before proceeding.
+
+For more advanced usage examples, check out our [Examples](https://crawl4ai.com/mkdocs/tutorial/episode_12_Session-Based_Crawling_for_Dynamic_Websites/) section in the documentation.
 </details>
 
 
-## ✨ Recent Updates   
+## Speed Comparison 🚀
 
-- 🔬 **PruningContentFilter**: New unsupervised filtering strategy for intelligent content extraction based on text density and relevance scoring.
-- 🧵 **Enhanced Thread Safety**: Improved multi-threaded environment handling with better locks and parallel processing support.
-- 🤖 **Smart User-Agent Generation**: Advanced user-agent generator with customization options and randomization capabilities.
-- 📝 **New Blog Launch**: Stay updated with our detailed release notes and technical deep dives at [crawl4ai.com/blog](https://crawl4ai.com/blog).
-- 🧪 **Expanded Test Coverage**: Comprehensive test suite for both PruningContentFilter and BM25ContentFilter with edge case handling.
+Crawl4AI is designed with speed as a primary focus. Our goal is to provide the fastest possible response with high-quality data extraction, minimizing abstractions between the data and the user.
 
-Read the full details of this release in our [0.4.0 Release Notes](https://github.com/unclecode/crawl4ai/blob/main/docs/md_v2/blog/releases/0.4.0.md).
+We've conducted a speed comparison between Crawl4AI and Firecrawl, a paid service. The results demonstrate Crawl4AI's superior performance:
 
-## 📖 Documentation & Roadmap 
+```bash
+Firecrawl:
+Time taken: 7.02 seconds
+Content length: 42074 characters
+Images found: 49
 
-> 🚨 **Documentation Update Alert**: We're undertaking a major documentation overhaul next week to reflect recent updates and improvements. Stay tuned for a more comprehensive and up-to-date guide!
+Crawl4AI (simple crawl):
+Time taken: 1.60 seconds
+Content length: 18238 characters
+Images found: 49
 
-For current documentation, including installation instructions, advanced features, and API reference, visit our [Documentation Website](https://crawl4ai.com/mkdocs/).
+Crawl4AI (with JavaScript execution):
+Time taken: 4.64 seconds
+Content length: 40869 characters
+Images found: 89
+```
 
-To check our development plans and upcoming features, visit our [Roadmap](https://github.com/unclecode/crawl4ai/blob/main/ROADMAP.md).
+As you can see, Crawl4AI outperforms Firecrawl significantly:
 
-<details>
-<summary>📈 <strong>Development TODOs</strong></summary>
+- Simple crawl: Crawl4AI is over 4 times faster than Firecrawl.
+- With JavaScript execution: Even when executing JavaScript to load more content (doubling the number of images found), Crawl4AI is still faster than Firecrawl's simple crawl.
 
+You can find the full comparison code in our repository at `docs/examples/crawl4ai_vs_firecrawl.py`.
+
+## Documentation 📚
+
+For detailed documentation, including installation instructions, advanced features, and API reference, visit our [Documentation Website](https://crawl4ai.com/mkdocs/).
+
+## Crawl4AI Roadmap 🗺️
+
+For detailed information on our development plans and upcoming features, check out our [Roadmap](https://github.com/unclecode/crawl4ai/blob/main/ROADMAP.md).
+
+### Advanced Crawling Systems 🔧
 - [x] 0. Graph Crawler: Smart website traversal using graph search algorithms for comprehensive nested page extraction
 - [ ] 1. Question-Based Crawler: Natural language driven web discovery and content extraction
 - [ ] 2. Knowledge-Optimal Crawler: Smart crawling that maximizes knowledge while minimizing data extraction
 - [ ] 3. Agentic Crawler: Autonomous system for complex multi-step crawling operations
+
+### Specialized Features 🛠️
 - [ ] 4. Automated Schema Generator: Convert natural language to extraction schemas
 - [ ] 5. Domain-Specific Scrapers: Pre-configured extractors for common platforms (academic, e-commerce)
 - [ ] 6. Web Embedding Index: Semantic search infrastructure for crawled content
+
+### Development Tools 🔨
 - [ ] 7. Interactive Playground: Web UI for testing, comparing strategies with AI assistance
 - [ ] 8. Performance Monitor: Real-time insights into crawler operations
 - [ ] 9. Cloud Integration: One-click deployment solutions across cloud providers
+
+### Community & Growth 🌱
 - [ ] 10. Sponsorship Program: Structured support system with tiered benefits
 - [ ] 11. Educational Content: "How to Crawl" video series and interactive tutorials
 
-</details>
-
-## 🤝 Contributing 
+## Contributing 🤝
 
 We welcome contributions from the open-source community. Check out our [contribution guidelines](https://github.com/unclecode/crawl4ai/blob/main/CONTRIBUTING.md) for more information.
 
-## 📄 License 
+## License 📄
 
 Crawl4AI is released under the [Apache 2.0 License](https://github.com/unclecode/crawl4ai/blob/main/LICENSE).
 
-## 📧 Contact 
+## Contact 📧
 
 For questions, suggestions, or feedback, feel free to reach out:
 
@@ -678,32 +487,32 @@ For questions, suggestions, or feedback, feel free to reach out:
 
 Happy Crawling! 🕸️🚀
 
-## 🗾 Mission
 
-Our mission is to unlock the value of personal and enterprise data by transforming digital footprints into structured, tradeable assets. Crawl4AI empowers individuals and organizations with open-source tools to extract and structure data, fostering a shared data economy.  
+# Mission
 
-We envision a future where AI is powered by real human knowledge, ensuring data creators directly benefit from their contributions. By democratizing data and enabling ethical sharing, we are laying the foundation for authentic AI advancement.
+Our mission is to unlock the untapped potential of personal and enterprise data in the digital age. In today's world, individuals and organizations generate vast amounts of valuable digital footprints, yet this data remains largely uncapitalized as a true asset. 
 
-<details>
-<summary>🔑 <strong>Key Opportunities</strong></summary>
- 
-- **Data Capitalization**: Transform digital footprints into measurable, valuable assets.  
-- **Authentic AI Data**: Provide AI systems with real human insights.  
-- **Shared Economy**: Create a fair data marketplace that benefits data creators.  
+Our open-source solution empowers developers and innovators to build tools for data extraction and structuring, laying the foundation for a new era of data ownership. By transforming personal and enterprise data into structured, tradeable assets, we're creating opportunities for individuals to capitalize on their digital footprints and for organizations to unlock the value of their collective knowledge.
 
-</details>
+This democratization of data represents the first step toward a shared data economy, where willing participation in data sharing drives AI advancement while ensuring the benefits flow back to data creators. Through this approach, we're building a future where AI development is powered by authentic human knowledge rather than synthetic alternatives.
 
-<details>
-<summary>🚀 <strong>Development Pathway</strong></summary>
+![Mission Diagram](./docs/assets/pitch-dark.svg)
 
-1. **Open-Source Tools**: Community-driven platforms for transparent data extraction.  
-2. **Digital Asset Structuring**: Tools to organize and value digital knowledge.  
-3. **Ethical Data Marketplace**: A secure, fair platform for exchanging structured data.  
+For a detailed exploration of our vision, opportunities, and pathway forward, please see our [full mission statement](./MISSION.md).
 
-For more details, see our [full mission statement](./MISSION.md).
-</details>
+## Key Opportunities
 
+- **Data Capitalization**: Transform digital footprints into valuable assets that can appear on personal and enterprise balance sheets
+- **Authentic Data**: Unlock the vast reservoir of real human insights and knowledge for AI advancement
+- **Shared Economy**: Create new value streams where data creators directly benefit from their contributions
 
+## Development Pathway
+
+1. **Open-Source Foundation**: Building transparent, community-driven data extraction tools
+2. **Data Capitalization Platform**: Creating tools to structure and value digital assets
+3. **Shared Data Marketplace**: Establishing an economic platform for ethical data exchange
+
+For a detailed exploration of our vision, challenges, and solutions, please see our [full mission statement](./MISSION.md).
 
 
 ## Star History

crawl4ai/__init__.py

@@ -1,9 +1,9 @@
 # __init__.py
 
 from .async_webcrawler import AsyncWebCrawler, CacheMode
-
 from .models import CrawlResult
 from .__version__ import __version__
+# __version__ = "0.3.73"
 
 __all__ = [
     "AsyncWebCrawler",

crawl4ai/__version__.py

@@ -1,2 +1,2 @@
 # crawl4ai/_version.py
-__version__ = "0.4.0"
+__version__ = "0.3.74"

crawl4ai/async_crawler_strategy.py

@@ -6,7 +6,6 @@ from typing import Callable, Dict, Any, List, Optional, Awaitable
 import os, sys, shutil
 import tempfile, subprocess
 from playwright.async_api import async_playwright, Page, Browser, Error
-from playwright.async_api import TimeoutError as PlaywrightTimeoutError
 from io import BytesIO
 from PIL import Image, ImageDraw, ImageFont
 from pathlib import Path
@@ -16,8 +15,7 @@ import hashlib
 import json
 import uuid
 from .models import AsyncCrawlResponse
-from .utils import create_box_message
-from .user_agent_generator import UserAgentGenerator
+
 from playwright_stealth import StealthConfig, stealth_async
 
 stealth_config = StealthConfig(
@@ -37,14 +35,13 @@ stealth_config = StealthConfig(
 
 
 class ManagedBrowser:
-    def __init__(self, browser_type: str = "chromium", user_data_dir: Optional[str] = None, headless: bool = False, logger = None, host: str = "localhost", debugging_port: int = 9222):
+    def __init__(self, browser_type: str = "chromium", user_data_dir: Optional[str] = None, headless: bool = False, logger = None):
         self.browser_type = browser_type
         self.user_data_dir = user_data_dir
         self.headless = headless
         self.browser_process = None
         self.temp_dir = None
-        self.debugging_port = debugging_port
-        self.host = host
+        self.debugging_port = 9222
         self.logger = logger
         self.shutting_down = False
 
@@ -73,7 +70,7 @@ class ManagedBrowser:
             # Monitor browser process output for errors
             asyncio.create_task(self._monitor_browser_process())
             await asyncio.sleep(2)  # Give browser time to start
-            return f"http://{self.host}:{self.debugging_port}"
+            return f"http://localhost:{self.debugging_port}"
         except Exception as e:
             await self.cleanup()
             raise Exception(f"Failed to start browser: {e}")
@@ -224,22 +221,14 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
         self.use_cached_html = use_cached_html
         self.user_agent = kwargs.get(
             "user_agent",
-            # "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:109.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.5845.187 Safari/604.1 Edg/117.0.2045.47"
-            "Mozilla/5.0 (Linux; Android 11; SM-G973F) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.120 Mobile Safari/537.36"
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
+            "(KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
         )
-        user_agenr_generator = UserAgentGenerator()
-        if kwargs.get("user_agent_mode") == "random":
-            self.user_agent = user_agenr_generator.generate(
-                 **kwargs.get("user_agent_generator_config", {})
-            )
         self.proxy = kwargs.get("proxy")
         self.proxy_config = kwargs.get("proxy_config")
         self.headless = kwargs.get("headless", True)
         self.browser_type = kwargs.get("browser_type", "chromium")
         self.headers = kwargs.get("headers", {})
-        self.browser_hint = user_agenr_generator.generate_client_hints(self.user_agent)
-        self.headers.setdefault("sec-ch-ua", self.browser_hint)
-        self.cookies = kwargs.get("cookies", [])
         self.sessions = {}
         self.session_ttl = 1800 
         self.js_code = js_code
@@ -306,8 +295,6 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                 # Set up the default context
                 if self.default_context:
                     await self.default_context.set_extra_http_headers(self.headers)
-                    if self.cookies:
-                        await self.default_context.add_cookies(self.cookies)                    
                     if self.accept_downloads:
                         await self.default_context.set_default_timeout(60000)
                         await self.default_context.set_default_navigation_timeout(60000)
@@ -316,9 +303,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                         
                     if self.user_agent:
                         await self.default_context.set_extra_http_headers({
-                            "User-Agent": self.user_agent,
-                            "sec-ch-ua": self.browser_hint,
-                            # **self.headers
+                            "User-Agent": self.user_agent
                         })
             else:
                 # Base browser arguments
@@ -333,11 +318,9 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                         "--window-position=0,0",
                         "--ignore-certificate-errors",
                         "--ignore-certificate-errors-spki-list",
-                        "--disable-blink-features=AutomationControlled",
-                        
                     ]
                 }
-                
+
                 # Add channel if specified (try Chrome first)
                 if self.chrome_channel:
                     browser_args["channel"] = self.chrome_channel
@@ -430,13 +413,13 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
         else:
             raise ValueError(f"Invalid hook type: {hook_type}")
 
-    async def execute_hook(self, hook_type: str, *args, **kwargs):
+    async def execute_hook(self, hook_type: str, *args):
         hook = self.hooks.get(hook_type)
         if hook:
             if asyncio.iscoroutinefunction(hook):
-                return await hook(*args, **kwargs)
+                return await hook(*args)
             else:
-                return hook(*args, **kwargs)
+                return hook(*args)
         return args[0] if args else None
 
     def update_user_agent(self, user_agent: str):
@@ -655,17 +638,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
         self._cleanup_expired_sessions()
         session_id = kwargs.get("session_id")
         
-        # Check if in kwargs we have user_agent that will override the default user_agent
-        user_agent = kwargs.get("user_agent", self.user_agent)
-        
-        # Generate random user agent if magic mode is enabled and user_agent_mode is not random
-        if kwargs.get("user_agent_mode") != "random" and kwargs.get("magic", False):
-            user_agent = UserAgentGenerator().generate(
-                **kwargs.get("user_agent_generator_config", {})
-            )
-        
         # Handle page creation differently for managed browser
-        context = None
         if self.use_managed_browser:
             if session_id:
                 # Reuse existing session if available
@@ -688,7 +661,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                     else:
                         # Normal context creation for non-persistent or non-Chrome browsers
                         context = await self.browser.new_context(
-                            user_agent=user_agent,
+                            user_agent=self.user_agent,
                             viewport={"width": 1200, "height": 800},
                             proxy={"server": self.proxy} if self.proxy else None,
                             java_script_enabled=True,
@@ -696,8 +669,6 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                             # downloads_path=self.downloads_path if self.accept_downloads else None
                         )
                         await context.add_cookies([{"name": "cookiesEnabled", "value": "true", "url": url}])
-                        if self.cookies:
-                            await context.add_cookies(self.cookies)
                         await context.set_extra_http_headers(self.headers)
                         page = await context.new_page()
                     self.sessions[session_id] = (context, page, time.time())
@@ -708,14 +679,11 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                 else:
                     # Normal context creation
                     context = await self.browser.new_context(
-                        user_agent=user_agent,
+                        user_agent=self.user_agent,
                         viewport={"width": 1920, "height": 1080},
                         proxy={"server": self.proxy} if self.proxy else None,
                         accept_downloads=self.accept_downloads,
-                        ignore_https_errors=True  # Add this line
                     )
-                    if self.cookies:
-                            await context.add_cookies(self.cookies)
                     await context.set_extra_http_headers(self.headers)
                 
                 if kwargs.get("override_navigator", False) or kwargs.get("simulate_user", False) or kwargs.get("magic", False):
@@ -785,23 +753,20 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                     return response
 
             if not kwargs.get("js_only", False):
-                await self.execute_hook('before_goto', page, context = context)
+                await self.execute_hook('before_goto', page)
                 
 
-                try:
-                    response = await page.goto(
-                        url,
-                        # wait_until=kwargs.get("wait_until", ["domcontentloaded", "networkidle"]),
-                        wait_until=kwargs.get("wait_until", "domcontentloaded"),
-                        timeout=kwargs.get("page_timeout", 60000),
-                    )
-                except Error as e:
-                    raise RuntimeError(f"Failed on navigating ACS-GOTO :\n{str(e)}")
+                response = await page.goto(
+                    url,
+                    # wait_until=kwargs.get("wait_until", ["domcontentloaded", "networkidle"]),
+                    wait_until=kwargs.get("wait_until", "domcontentloaded"),
+                    timeout=kwargs.get("page_timeout", 60000)
+                )
                 
                 # response = await page.goto("about:blank")
                 # await page.evaluate(f"window.location.href = '{url}'")
                 
-                await self.execute_hook('after_goto', page, context = context)
+                await self.execute_hook('after_goto', page)
                 
                 # Get status code and headers
                 status_code = response.status
@@ -863,10 +828,9 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                     for js in js_code:
                         await page.evaluate(js)
                 
-                # await page.wait_for_timeout(100)
-                
+                await page.wait_for_load_state('networkidle')
                 # Check for on execution event
-                await self.execute_hook('on_execution_started', page, context = context)
+                await self.execute_hook('on_execution_started', page)
                 
             if kwargs.get("simulate_user", False) or kwargs.get("magic", False):
                 # Simulate user interactions
@@ -882,9 +846,6 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                     await self.smart_wait(page, wait_for, timeout=kwargs.get("page_timeout", 60000))
                 except Exception as e:
                     raise RuntimeError(f"Wait condition failed: {str(e)}")
-            
-            # if not wait_for and js_code:
-            #     await page.wait_for_load_state('networkidle', timeout=5000)
 
             # Update image dimensions
             update_image_dimensions_js = """
@@ -943,24 +904,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                 });
             }
             """
-            
-            try:
-                try:
-                    await page.wait_for_load_state(
-                        # state="load",
-                        state="domcontentloaded",
-                        timeout=5
-                    )
-                except PlaywrightTimeoutError:
-                    pass
-                await page.evaluate(update_image_dimensions_js)
-            except Exception as e:
-                self.logger.error(
-                    message="Error updating image dimensions ACS-UPDATE_IMAGE_DIMENSIONS_JS: {error}",
-                    tag="ERROR",
-                    params={"error": str(e)}
-                )
-                # raise RuntimeError(f"Error updating image dimensions ACS-UPDATE_IMAGE_DIMENSIONS_JS: {str(e)}")
+            await page.evaluate(update_image_dimensions_js)
 
             # Wait a bit for any onload events to complete
             await page.wait_for_timeout(100)
@@ -969,7 +913,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
             if kwargs.get("process_iframes", False):
                 page = await self.process_iframes(page)
             
-            await self.execute_hook('before_retrieve_html', page, context = context)
+            await self.execute_hook('before_retrieve_html', page)
             # Check if delay_before_return_html is set then wait for that time
             delay_before_return_html = kwargs.get("delay_before_return_html")
             if delay_before_return_html:
@@ -980,7 +924,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                 await self.remove_overlay_elements(page)
             
             html = await page.content()
-            await self.execute_hook('before_return_html', page, html, context = context)
+            await self.execute_hook('before_return_html', page, html)
             
             # Check if kwargs has screenshot=True then take screenshot
             screenshot_data = None

crawl4ai/async_database.3.73.py

@@ -0,0 +1,285 @@
+import os
+from pathlib import Path
+import aiosqlite
+import asyncio
+from typing import Optional, Tuple, Dict
+from contextlib import asynccontextmanager
+import logging
+import json  # Added for serialization/deserialization
+from .utils import ensure_content_dirs, generate_content_hash
+import xxhash
+import aiofiles
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+DB_PATH = os.path.join(Path.home(), ".crawl4ai")
+os.makedirs(DB_PATH, exist_ok=True)
+DB_PATH = os.path.join(DB_PATH, "crawl4ai.db")
+
+class AsyncDatabaseManager:
+    def __init__(self, pool_size: int = 10, max_retries: int = 3):
+        self.db_path = DB_PATH
+        self.content_paths = ensure_content_dirs(os.path.dirname(DB_PATH))
+        self.pool_size = pool_size
+        self.max_retries = max_retries
+        self.connection_pool: Dict[int, aiosqlite.Connection] = {}
+        self.pool_lock = asyncio.Lock()
+        self.connection_semaphore = asyncio.Semaphore(pool_size)
+        
+    async def initialize(self):
+        """Initialize the database and connection pool"""
+        await self.ainit_db()
+        
+    async def cleanup(self):
+        """Cleanup connections when shutting down"""
+        async with self.pool_lock:
+            for conn in self.connection_pool.values():
+                await conn.close()
+            self.connection_pool.clear()
+
+    @asynccontextmanager
+    async def get_connection(self):
+        """Connection pool manager"""
+        async with self.connection_semaphore:
+            task_id = id(asyncio.current_task())
+            try:
+                async with self.pool_lock:
+                    if task_id not in self.connection_pool:
+                        conn = await aiosqlite.connect(
+                            self.db_path,
+                            timeout=30.0
+                        )
+                        await conn.execute('PRAGMA journal_mode = WAL')
+                        await conn.execute('PRAGMA busy_timeout = 5000')
+                        self.connection_pool[task_id] = conn
+                    
+                yield self.connection_pool[task_id]
+                
+            except Exception as e:
+                logger.error(f"Connection error: {e}")
+                raise
+            finally:
+                async with self.pool_lock:
+                    if task_id in self.connection_pool:
+                        await self.connection_pool[task_id].close()
+                        del self.connection_pool[task_id]
+
+    async def execute_with_retry(self, operation, *args):
+        """Execute database operations with retry logic"""
+        for attempt in range(self.max_retries):
+            try:
+                async with self.get_connection() as db:
+                    result = await operation(db, *args)
+                    await db.commit()
+                    return result
+            except Exception as e:
+                if attempt == self.max_retries - 1:
+                    logger.error(f"Operation failed after {self.max_retries} attempts: {e}")
+                    raise
+                await asyncio.sleep(1 * (attempt + 1))  # Exponential backoff
+
+    async def ainit_db(self):
+        """Initialize database schema"""
+        async def _init(db):
+            await db.execute('''
+                CREATE TABLE IF NOT EXISTS crawled_data (
+                    url TEXT PRIMARY KEY,
+                    html TEXT,
+                    cleaned_html TEXT,
+                    markdown TEXT,
+                    extracted_content TEXT,
+                    success BOOLEAN,
+                    media TEXT DEFAULT "{}",
+                    links TEXT DEFAULT "{}",
+                    metadata TEXT DEFAULT "{}",
+                    screenshot TEXT DEFAULT "",
+                    response_headers TEXT DEFAULT "{}",
+                    downloaded_files TEXT DEFAULT "{}"  -- New column added
+                )
+            ''')
+        
+        await self.execute_with_retry(_init)
+        await self.update_db_schema()
+
+    async def update_db_schema(self):
+        """Update database schema if needed"""
+        async def _check_columns(db):
+            cursor = await db.execute("PRAGMA table_info(crawled_data)")
+            columns = await cursor.fetchall()
+            return [column[1] for column in columns]
+
+        column_names = await self.execute_with_retry(_check_columns)
+        
+        # List of new columns to add
+        new_columns = ['media', 'links', 'metadata', 'screenshot', 'response_headers', 'downloaded_files']
+        
+        for column in new_columns:
+            if column not in column_names:
+                await self.aalter_db_add_column(column)
+
+    async def aalter_db_add_column(self, new_column: str):
+        """Add new column to the database"""
+        async def _alter(db):
+            if new_column == 'response_headers':
+                await db.execute(f'ALTER TABLE crawled_data ADD COLUMN {new_column} TEXT DEFAULT "{{}}"')
+            else:
+                await db.execute(f'ALTER TABLE crawled_data ADD COLUMN {new_column} TEXT DEFAULT ""')
+            logger.info(f"Added column '{new_column}' to the database.")
+
+        await self.execute_with_retry(_alter)
+
+
+    async def aget_cached_url(self, url: str) -> Optional[Tuple[str, str, str, str, str, bool, str, str, str, str]]:
+        """Retrieve cached URL data"""
+        async def _get(db):
+            async with db.execute(
+                '''
+                SELECT url, html, cleaned_html, markdown, 
+                    extracted_content, success, media, links,
+                    metadata, screenshot, response_headers,
+                    downloaded_files
+                FROM crawled_data WHERE url = ?
+                ''',
+                (url,)
+            ) as cursor:
+                row = await cursor.fetchone()
+                if row:
+                    # Load content from files using stored hashes
+                    html = await self._load_content(row[1], 'html') if row[1] else ""
+                    cleaned = await self._load_content(row[2], 'cleaned') if row[2] else ""
+                    markdown = await self._load_content(row[3], 'markdown') if row[3] else ""
+                    extracted = await self._load_content(row[4], 'extracted') if row[4] else ""
+                    screenshot = await self._load_content(row[9], 'screenshots') if row[9] else ""
+                    
+                    return (
+                        row[0],  # url
+                        html or "",  # Return empty string if file not found
+                        cleaned or "",
+                        markdown or "", 
+                        extracted or "",
+                        row[5],  # success
+                        json.loads(row[6] or '{}'),  # media
+                        json.loads(row[7] or '{}'),  # links
+                        json.loads(row[8] or '{}'),  # metadata
+                        screenshot or "",
+                        json.loads(row[10] or '{}'),  # response_headers
+                        json.loads(row[11] or '[]')  # downloaded_files
+                    )
+                return None
+
+        try:
+            return await self.execute_with_retry(_get)
+        except Exception as e:
+            logger.error(f"Error retrieving cached URL: {e}")
+            return None
+
+    async def acache_url(self, url: str, html: str, cleaned_html: str, 
+                        markdown: str, extracted_content: str, success: bool,
+                        media: str = "{}", links: str = "{}", 
+                        metadata: str = "{}", screenshot: str = "",
+                        response_headers: str = "{}", downloaded_files: str = "[]"):
+        """Cache URL data with content stored in filesystem"""
+        
+        # Store content files and get hashes
+        html_hash = await self._store_content(html, 'html')
+        cleaned_hash = await self._store_content(cleaned_html, 'cleaned')
+        markdown_hash = await self._store_content(markdown, 'markdown')
+        extracted_hash = await self._store_content(extracted_content, 'extracted')
+        screenshot_hash = await self._store_content(screenshot, 'screenshots')
+
+        async def _cache(db):
+            await db.execute('''
+                INSERT INTO crawled_data (
+                    url, html, cleaned_html, markdown,
+                    extracted_content, success, media, links, metadata,
+                    screenshot, response_headers, downloaded_files
+                )
+                VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+                ON CONFLICT(url) DO UPDATE SET
+                    html = excluded.html,
+                    cleaned_html = excluded.cleaned_html,
+                    markdown = excluded.markdown,
+                    extracted_content = excluded.extracted_content,
+                    success = excluded.success,
+                    media = excluded.media,      
+                    links = excluded.links,    
+                    metadata = excluded.metadata,      
+                    screenshot = excluded.screenshot,
+                    response_headers = excluded.response_headers,
+                    downloaded_files = excluded.downloaded_files
+            ''', (url, html_hash, cleaned_hash, markdown_hash, extracted_hash,
+                success, media, links, metadata, screenshot_hash,
+                response_headers, downloaded_files))
+
+        try:
+            await self.execute_with_retry(_cache)
+        except Exception as e:
+            logger.error(f"Error caching URL: {e}")
+
+
+
+    async def aget_total_count(self) -> int:
+        """Get total number of cached URLs"""
+        async def _count(db):
+            async with db.execute('SELECT COUNT(*) FROM crawled_data') as cursor:
+                result = await cursor.fetchone()
+                return result[0] if result else 0
+
+        try:
+            return await self.execute_with_retry(_count)
+        except Exception as e:
+            logger.error(f"Error getting total count: {e}")
+            return 0
+
+    async def aclear_db(self):
+        """Clear all data from the database"""
+        async def _clear(db):
+            await db.execute('DELETE FROM crawled_data')
+
+        try:
+            await self.execute_with_retry(_clear)
+        except Exception as e:
+            logger.error(f"Error clearing database: {e}")
+
+    async def aflush_db(self):
+        """Drop the entire table"""
+        async def _flush(db):
+            await db.execute('DROP TABLE IF EXISTS crawled_data')
+
+        try:
+            await self.execute_with_retry(_flush)
+        except Exception as e:
+            logger.error(f"Error flushing database: {e}")
+            
+                
+    async def _store_content(self, content: str, content_type: str) -> str:
+        """Store content in filesystem and return hash"""
+        if not content:
+            return ""
+            
+        content_hash = generate_content_hash(content)
+        file_path = os.path.join(self.content_paths[content_type], content_hash)
+        
+        # Only write if file doesn't exist
+        if not os.path.exists(file_path):
+            async with aiofiles.open(file_path, 'w', encoding='utf-8') as f:
+                await f.write(content)
+                
+        return content_hash
+
+    async def _load_content(self, content_hash: str, content_type: str) -> Optional[str]:
+        """Load content from filesystem by hash"""
+        if not content_hash:
+            return None
+            
+        file_path = os.path.join(self.content_paths[content_type], content_hash)
+        try:
+            async with aiofiles.open(file_path, 'r', encoding='utf-8') as f:
+                return await f.read()
+        except:
+            logger.error(f"Failed to load content: {file_path}")
+            return None
+
+# Create a singleton instance
+async_db_manager = AsyncDatabaseManager()

crawl4ai/async_webcrawler.3.73.py

@@ -0,0 +1,344 @@
+import os
+import time
+from pathlib import Path
+from typing import Optional
+import json
+import asyncio
+from .models import CrawlResult
+from .async_database import async_db_manager
+from .chunking_strategy import *
+from .extraction_strategy import *
+from .async_crawler_strategy import AsyncCrawlerStrategy, AsyncPlaywrightCrawlerStrategy, AsyncCrawlResponse
+from .content_scrapping_strategy import WebScrapingStrategy
+from .config import MIN_WORD_THRESHOLD, IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD
+from .utils import (
+    sanitize_input_encode,
+    InvalidCSSSelectorError,
+    format_html
+)
+from .__version__ import __version__ as crawl4ai_version
+
+class AsyncWebCrawler:
+    def __init__(
+        self,
+        crawler_strategy: Optional[AsyncCrawlerStrategy] = None,
+        always_by_pass_cache: bool = False,
+        base_directory: str = str(Path.home()),
+        **kwargs,
+    ):
+        self.crawler_strategy = crawler_strategy or AsyncPlaywrightCrawlerStrategy(
+            **kwargs
+        )
+        self.always_by_pass_cache = always_by_pass_cache
+        # self.crawl4ai_folder = os.path.join(Path.home(), ".crawl4ai")
+        self.crawl4ai_folder = os.path.join(base_directory, ".crawl4ai")
+        os.makedirs(self.crawl4ai_folder, exist_ok=True)
+        os.makedirs(f"{self.crawl4ai_folder}/cache", exist_ok=True)
+        self.ready = False
+        self.verbose = kwargs.get("verbose", False)
+
+    async def __aenter__(self):
+        await self.crawler_strategy.__aenter__()
+        await self.awarmup()
+        return self
+
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
+        await self.crawler_strategy.__aexit__(exc_type, exc_val, exc_tb)
+
+    async def awarmup(self):
+        # Print a message for crawl4ai and its version
+        if self.verbose:
+            print(f"[LOG] 🚀 Crawl4AI {crawl4ai_version}")
+            print("[LOG] 🌤️  Warming up the AsyncWebCrawler")
+        # await async_db_manager.ainit_db()
+        # # await async_db_manager.initialize()
+        # await self.arun(
+        #     url="https://google.com/",
+        #     word_count_threshold=5,
+        #     bypass_cache=False,
+        #     verbose=False,
+        # )
+        self.ready = True
+        if self.verbose:
+            print("[LOG] 🌞 AsyncWebCrawler is ready to crawl")
+
+    async def arun(
+        self,
+        url: str,
+        word_count_threshold=MIN_WORD_THRESHOLD,
+        extraction_strategy: ExtractionStrategy = None,
+        chunking_strategy: ChunkingStrategy = RegexChunking(),
+        bypass_cache: bool = False,
+        css_selector: str = None,
+        screenshot: bool = False,
+        user_agent: str = None,
+        verbose=True,
+        disable_cache: bool = False,
+        no_cache_read: bool = False,
+        no_cache_write: bool = False,
+        **kwargs,
+    ) -> CrawlResult:
+        """
+        Runs the crawler for a single source: URL (web, local file, or raw HTML).
+
+        Args:
+            url (str): The URL to crawl. Supported prefixes:
+                - 'http://' or 'https://': Web URL to crawl.
+                - 'file://': Local file path to process.
+                - 'raw:': Raw HTML content to process.
+            ... [other existing parameters]
+
+        Returns:
+            CrawlResult: The result of the crawling and processing.
+        """
+        try:
+            if disable_cache:
+                bypass_cache = True
+                no_cache_read = True
+                no_cache_write = True
+            
+            extraction_strategy = extraction_strategy or NoExtractionStrategy()
+            extraction_strategy.verbose = verbose
+            if not isinstance(extraction_strategy, ExtractionStrategy):
+                raise ValueError("Unsupported extraction strategy")
+            if not isinstance(chunking_strategy, ChunkingStrategy):
+                raise ValueError("Unsupported chunking strategy")
+            
+            word_count_threshold = max(word_count_threshold, MIN_WORD_THRESHOLD)
+
+            async_response: AsyncCrawlResponse = None
+            cached = None
+            screenshot_data = None
+            extracted_content = None
+            
+            is_web_url = url.startswith(('http://', 'https://'))
+            is_local_file = url.startswith("file://")
+            is_raw_html = url.startswith("raw:")
+            _url = url if not is_raw_html else "Raw HTML"
+            
+            start_time = time.perf_counter()
+            cached_result = None
+            if is_web_url and (not bypass_cache or not no_cache_read) and not self.always_by_pass_cache:
+                cached_result = await async_db_manager.aget_cached_url(url)
+                        
+            if cached_result:
+                html = sanitize_input_encode(cached_result.html)
+                extracted_content = sanitize_input_encode(cached_result.extracted_content or "")
+                if screenshot:
+                    screenshot_data = cached_result.screenshot
+                    if not screenshot_data:
+                        cached_result = None
+                if verbose:
+                    print(
+                        f"[LOG] 1️⃣  ✅ Page fetched (cache) for {_url}, success: {bool(html)}, time taken: {time.perf_counter() - start_time:.2f} seconds"
+                    )
+
+
+            if not cached or not html:
+                t1 = time.perf_counter()
+                
+                if user_agent:
+                    self.crawler_strategy.update_user_agent(user_agent)
+                async_response: AsyncCrawlResponse = await self.crawler_strategy.crawl(url, screenshot=screenshot, **kwargs)
+                html = sanitize_input_encode(async_response.html)
+                screenshot_data = async_response.screenshot
+                t2 = time.perf_counter()
+                if verbose:
+                    print(
+                        f"[LOG] 1️⃣  ✅ Page fetched (no-cache) for {_url}, success: {bool(html)}, time taken: {t2 - t1:.2f} seconds"
+                    )
+
+            t1 = time.perf_counter()
+            crawl_result = await self.aprocess_html(
+                url=url,
+                html=html,
+                extracted_content=extracted_content,
+                word_count_threshold=word_count_threshold,
+                extraction_strategy=extraction_strategy,
+                chunking_strategy=chunking_strategy,
+                css_selector=css_selector,
+                screenshot=screenshot_data,
+                verbose=verbose,
+                is_cached=bool(cached),
+                async_response=async_response,
+                bypass_cache=bypass_cache,
+                is_web_url = is_web_url,
+                is_local_file = is_local_file,
+                is_raw_html = is_raw_html,
+                **kwargs,
+            )
+            
+            if async_response:
+                crawl_result.status_code = async_response.status_code
+                crawl_result.response_headers = async_response.response_headers
+                crawl_result.downloaded_files = async_response.downloaded_files
+            else:
+                crawl_result.status_code = 200
+                crawl_result.response_headers = cached_result.response_headers if cached_result else {}
+
+            crawl_result.success = bool(html)
+            crawl_result.session_id = kwargs.get("session_id", None)
+
+            if verbose:
+                print(
+                    f"[LOG] 🔥 🚀 Crawling done for {_url}, success: {crawl_result.success}, time taken: {time.perf_counter() - start_time:.2f} seconds"
+                )
+
+            if not is_raw_html and not no_cache_write:
+                if not bool(cached_result) or kwargs.get("bypass_cache", False) or self.always_by_pass_cache:
+                    await async_db_manager.acache_url(crawl_result)
+
+
+            return crawl_result
+        
+        except Exception as e:
+            if not hasattr(e, "msg"):
+                e.msg = str(e)
+            print(f"[ERROR] 🚫 arun(): Failed to crawl {_url}, error: {e.msg}")
+            return CrawlResult(url=url, html="", markdown = f"[ERROR] 🚫 arun(): Failed to crawl {_url}, error: {e.msg}", success=False, error_message=e.msg)
+
+    async def arun_many(
+        self,
+        urls: List[str],
+        word_count_threshold=MIN_WORD_THRESHOLD,
+        extraction_strategy: ExtractionStrategy = None,
+        chunking_strategy: ChunkingStrategy = RegexChunking(),
+        bypass_cache: bool = False,
+        css_selector: str = None,
+        screenshot: bool = False,
+        user_agent: str = None,
+        verbose=True,
+        **kwargs,
+    ) -> List[CrawlResult]:
+        """
+        Runs the crawler for multiple sources: URLs (web, local files, or raw HTML).
+
+        Args:
+            urls (List[str]): A list of URLs with supported prefixes:
+                - 'http://' or 'https://': Web URL to crawl.
+                - 'file://': Local file path to process.
+                - 'raw:': Raw HTML content to process.
+            ... [other existing parameters]
+
+        Returns:
+            List[CrawlResult]: The results of the crawling and processing.
+        """
+        semaphore_count = kwargs.get('semaphore_count', 5)  # Adjust as needed
+        semaphore = asyncio.Semaphore(semaphore_count)
+
+        async def crawl_with_semaphore(url):
+            async with semaphore:
+                return await self.arun(
+                    url,
+                    word_count_threshold=word_count_threshold,
+                    extraction_strategy=extraction_strategy,
+                    chunking_strategy=chunking_strategy,
+                    bypass_cache=bypass_cache,
+                    css_selector=css_selector,
+                    screenshot=screenshot,
+                    user_agent=user_agent,
+                    verbose=verbose,
+                    **kwargs,
+                )
+
+        tasks = [crawl_with_semaphore(url) for url in urls]
+        results = await asyncio.gather(*tasks, return_exceptions=True)
+        return [result if not isinstance(result, Exception) else str(result) for result in results]
+
+    async def aprocess_html(
+        self,
+        url: str,
+        html: str,
+        extracted_content: str,
+        word_count_threshold: int,
+        extraction_strategy: ExtractionStrategy,
+        chunking_strategy: ChunkingStrategy,
+        css_selector: str,
+        screenshot: str,
+        verbose: bool,
+        **kwargs,
+    ) -> CrawlResult:
+        t = time.perf_counter()
+        # Extract content from HTML
+        try:
+            _url = url if not kwargs.get("is_raw_html", False) else "Raw HTML"
+            t1 = time.perf_counter()
+            scrapping_strategy = WebScrapingStrategy()
+            # result = await scrapping_strategy.ascrap(
+            result = scrapping_strategy.scrap(
+                url,
+                html,
+                word_count_threshold=word_count_threshold,
+                css_selector=css_selector,
+                only_text=kwargs.get("only_text", False),
+                image_description_min_word_threshold=kwargs.get(
+                    "image_description_min_word_threshold", IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD
+                ),
+                **kwargs,
+            )
+
+            if result is None:
+                raise ValueError(f"Process HTML, Failed to extract content from the website: {url}")
+        except InvalidCSSSelectorError as e:
+            raise ValueError(str(e))
+        except Exception as e:
+            raise ValueError(f"Process HTML, Failed to extract content from the website: {url}, error: {str(e)}")
+
+        cleaned_html = sanitize_input_encode(result.get("cleaned_html", ""))
+        markdown = sanitize_input_encode(result.get("markdown", ""))
+        fit_markdown = sanitize_input_encode(result.get("fit_markdown", ""))
+        fit_html = sanitize_input_encode(result.get("fit_html", ""))
+        media = result.get("media", [])
+        links = result.get("links", [])
+        metadata = result.get("metadata", {})
+        
+        if verbose:
+            print(
+                f"[LOG] 2️⃣  ✅ Scraping done for {_url}, success: True, time taken: {time.perf_counter() - t1:.2f} seconds"
+            )        
+
+        if extracted_content is None and extraction_strategy and chunking_strategy and not isinstance(extraction_strategy, NoExtractionStrategy):
+            t1 = time.perf_counter()
+            # Check if extraction strategy is type of JsonCssExtractionStrategy
+            if isinstance(extraction_strategy, JsonCssExtractionStrategy) or isinstance(extraction_strategy, JsonCssExtractionStrategy):
+                extraction_strategy.verbose = verbose
+                extracted_content = extraction_strategy.run(url, [html])
+                extracted_content = json.dumps(extracted_content, indent=4, default=str, ensure_ascii=False)
+            else:
+                sections = chunking_strategy.chunk(markdown)
+                extracted_content = extraction_strategy.run(url, sections)
+                extracted_content = json.dumps(extracted_content, indent=4, default=str, ensure_ascii=False)
+            if verbose:
+                print(
+                    f"[LOG] 3️⃣  ✅ Extraction done for {_url}, time taken: {time.perf_counter() - t1:.2f} seconds"
+                )
+
+        screenshot = None if not screenshot else screenshot
+        
+        return CrawlResult(
+            url=url,
+            html=html,
+            cleaned_html=format_html(cleaned_html),
+            markdown=markdown,
+            fit_markdown=fit_markdown,
+            fit_html= fit_html,
+            media=media,
+            links=links,
+            metadata=metadata,
+            screenshot=screenshot,
+            extracted_content=extracted_content,
+            success=True,
+            error_message="",
+        )
+
+    async def aclear_cache(self):
+        # await async_db_manager.aclear_db()
+        await async_db_manager.cleanup()
+
+    async def aflush_cache(self):
+        await async_db_manager.aflush_db()
+
+    async def aget_cache_size(self):
+        return await async_db_manager.aget_total_count()
+
+

crawl4ai/async_webcrawler.py

@@ -7,15 +7,14 @@ from pathlib import Path
 from typing import Optional, List, Union
 import json
 import asyncio
-from contextlib import nullcontext
-from .models import CrawlResult, MarkdownGenerationResult
+from .models import CrawlResult
 from .async_database import async_db_manager
 from .chunking_strategy import *
 from .content_filter_strategy import *
 from .extraction_strategy import *
 from .async_crawler_strategy import AsyncCrawlerStrategy, AsyncPlaywrightCrawlerStrategy, AsyncCrawlResponse
 from .cache_context import CacheMode, CacheContext, _legacy_to_cache_mode
-from .content_scraping_strategy import WebScrapingStrategy
+from .content_scrapping_strategy import WebScrapingStrategy
 from .async_logger import AsyncLogger
 
 from .config import (
@@ -26,11 +25,8 @@ from .config import (
 from .utils import (
     sanitize_input_encode,
     InvalidCSSSelectorError,
-    format_html,
-    fast_format_html,
-    create_box_message
+    format_html
 )
-
 from urllib.parse import urlparse
 import random
 from .__version__ import __version__ as crawl4ai_version
@@ -68,7 +64,6 @@ class AsyncWebCrawler:
         always_bypass_cache: bool = False,
         always_by_pass_cache: Optional[bool] = None,  # Deprecated parameter
         base_directory: str = str(os.getenv("CRAWL4_AI_BASE_DIRECTORY", Path.home())),
-        thread_safe: bool = False,
         **kwargs,
     ):
         """
@@ -106,8 +101,6 @@ class AsyncWebCrawler:
         else:
             self.always_bypass_cache = always_bypass_cache
 
-        self._lock = asyncio.Lock() if thread_safe else None
-        
         self.crawl4ai_folder = os.path.join(base_directory, ".crawl4ai")
         os.makedirs(self.crawl4ai_folder, exist_ok=True)
         os.makedirs(f"{self.crawl4ai_folder}/cache", exist_ok=True)
@@ -182,169 +175,168 @@ class AsyncWebCrawler:
         Returns:
             CrawlResult: The result of crawling and processing
         """
-        async with self._lock or nullcontext():
-            try:
-                # Handle deprecated parameters
-                if any([bypass_cache, disable_cache, no_cache_read, no_cache_write]):
-                    if kwargs.get("warning", True):
-                        warnings.warn(
-                            "Cache control boolean flags are deprecated and will be removed in version X.X.X. "
-                            "Use 'cache_mode' parameter instead. Examples:\n"
-                            "- For bypass_cache=True, use cache_mode=CacheMode.BYPASS\n"
-                            "- For disable_cache=True, use cache_mode=CacheMode.DISABLED\n"
-                            "- For no_cache_read=True, use cache_mode=CacheMode.WRITE_ONLY\n"
-                            "- For no_cache_write=True, use cache_mode=CacheMode.READ_ONLY\n"
-                            "Pass warning=False to suppress this warning.",
-                            DeprecationWarning,
-                            stacklevel=2
-                        )
-                    
-                    # Convert legacy parameters if cache_mode not provided
-                    if cache_mode is None:
-                        cache_mode = _legacy_to_cache_mode(
-                            disable_cache=disable_cache,
-                            bypass_cache=bypass_cache,
-                            no_cache_read=no_cache_read,
-                            no_cache_write=no_cache_write
-                        )
-                
-                # Default to ENABLED if no cache mode specified
-                if cache_mode is None:
-                    cache_mode = CacheMode.ENABLED
-
-                # Create cache context
-                cache_context = CacheContext(url, cache_mode, self.always_bypass_cache)
-
-                extraction_strategy = extraction_strategy or NoExtractionStrategy()
-                extraction_strategy.verbose = verbose
-                if not isinstance(extraction_strategy, ExtractionStrategy):
-                    raise ValueError("Unsupported extraction strategy")
-                if not isinstance(chunking_strategy, ChunkingStrategy):
-                    raise ValueError("Unsupported chunking strategy")
-                
-                word_count_threshold = max(word_count_threshold, MIN_WORD_THRESHOLD)
-
-                async_response: AsyncCrawlResponse = None
-                cached_result = None
-                screenshot_data = None
-                extracted_content = None
-                
-                start_time = time.perf_counter()
-                
-                # Try to get cached result if appropriate
-                if cache_context.should_read():
-                    cached_result = await async_db_manager.aget_cached_url(url)
-                            
-                if cached_result:
-                    html = sanitize_input_encode(cached_result.html)
-                    extracted_content = sanitize_input_encode(cached_result.extracted_content or "")
-                    if screenshot:
-                        screenshot_data = cached_result.screenshot
-                        if not screenshot_data:
-                            cached_result = None
-                    # if verbose:
-                    #     print(f"{Fore.BLUE}{self.tag_format('FETCH')} {self.log_icons['FETCH']} Cache hit for {cache_context.display_url} | Status: {Fore.GREEN if bool(html) else Fore.RED}{bool(html)}{Style.RESET_ALL} | Time: {time.perf_counter() - start_time:.2f}s")
-                    self.logger.url_status(
-                            url=cache_context.display_url,
-                            success=bool(html),
-                            timing=time.perf_counter() - start_time,
-                            tag="FETCH"
-                        )                    
-
-
-                # Fetch fresh content if needed
-                if not cached_result or not html:
-                    t1 = time.perf_counter()
-                    
-                    if user_agent:
-                        self.crawler_strategy.update_user_agent(user_agent)
-                    async_response: AsyncCrawlResponse = await self.crawler_strategy.crawl(
-                        url, 
-                        screenshot=screenshot, 
-                        **kwargs
+        try:
+            # Handle deprecated parameters
+            if any([bypass_cache, disable_cache, no_cache_read, no_cache_write]):
+                if kwargs.get("warning", True):
+                    warnings.warn(
+                        "Cache control boolean flags are deprecated and will be removed in version X.X.X. "
+                        "Use 'cache_mode' parameter instead. Examples:\n"
+                        "- For bypass_cache=True, use cache_mode=CacheMode.BYPASS\n"
+                        "- For disable_cache=True, use cache_mode=CacheMode.DISABLED\n"
+                        "- For no_cache_read=True, use cache_mode=CacheMode.WRITE_ONLY\n"
+                        "- For no_cache_write=True, use cache_mode=CacheMode.READ_ONLY\n"
+                        "Pass warning=False to suppress this warning.",
+                        DeprecationWarning,
+                        stacklevel=2
                     )
-                    html = sanitize_input_encode(async_response.html)
-                    screenshot_data = async_response.screenshot
-                    t2 = time.perf_counter()
-                    self.logger.url_status(
+                
+                # Convert legacy parameters if cache_mode not provided
+                if cache_mode is None:
+                    cache_mode = _legacy_to_cache_mode(
+                        disable_cache=disable_cache,
+                        bypass_cache=bypass_cache,
+                        no_cache_read=no_cache_read,
+                        no_cache_write=no_cache_write
+                    )
+            
+            # Default to ENABLED if no cache mode specified
+            if cache_mode is None:
+                cache_mode = CacheMode.ENABLED
+
+            # Create cache context
+            cache_context = CacheContext(url, cache_mode, self.always_bypass_cache)
+
+            extraction_strategy = extraction_strategy or NoExtractionStrategy()
+            extraction_strategy.verbose = verbose
+            if not isinstance(extraction_strategy, ExtractionStrategy):
+                raise ValueError("Unsupported extraction strategy")
+            if not isinstance(chunking_strategy, ChunkingStrategy):
+                raise ValueError("Unsupported chunking strategy")
+            
+            word_count_threshold = max(word_count_threshold, MIN_WORD_THRESHOLD)
+
+            async_response: AsyncCrawlResponse = None
+            cached_result = None
+            screenshot_data = None
+            extracted_content = None
+            
+            start_time = time.perf_counter()
+            
+            # Try to get cached result if appropriate
+            if cache_context.should_read():
+                cached_result = await async_db_manager.aget_cached_url(url)
+                        
+            if cached_result:
+                html = sanitize_input_encode(cached_result.html)
+                extracted_content = sanitize_input_encode(cached_result.extracted_content or "")
+                if screenshot:
+                    screenshot_data = cached_result.screenshot
+                    if not screenshot_data:
+                        cached_result = None
+                # if verbose:
+                #     print(f"{Fore.BLUE}{self.tag_format('FETCH')} {self.log_icons['FETCH']} Cache hit for {cache_context.display_url} | Status: {Fore.GREEN if bool(html) else Fore.RED}{bool(html)}{Style.RESET_ALL} | Time: {time.perf_counter() - start_time:.2f}s")
+                self.logger.url_status(
                         url=cache_context.display_url,
                         success=bool(html),
-                        timing=t2 - t1,
+                        timing=time.perf_counter() - start_time,
                         tag="FETCH"
-                    )
-                    # if verbose:
-                    #     print(f"{Fore.BLUE}{self.tag_format('FETCH')} {self.log_icons['FETCH']} Live fetch for {cache_context.display_url}... | Status: {Fore.GREEN if bool(html) else Fore.RED}{bool(html)}{Style.RESET_ALL} | Time: {t2 - t1:.2f}s")
+                    )                    
 
-                # Process the HTML content
-                crawl_result = await self.aprocess_html(
-                    url=url,
-                    html=html,
-                    extracted_content=extracted_content,
-                    word_count_threshold=word_count_threshold,
-                    extraction_strategy=extraction_strategy,
-                    chunking_strategy=chunking_strategy,
-                    content_filter=content_filter,
-                    css_selector=css_selector,
-                    screenshot=screenshot_data,
-                    verbose=verbose,
-                    is_cached=bool(cached_result),
-                    async_response=async_response,
-                    is_web_url=cache_context.is_web_url,
-                    is_local_file=cache_context.is_local_file,
-                    is_raw_html=cache_context.is_raw_html,
-                    **kwargs,
+
+            # Fetch fresh content if needed
+            if not cached_result or not html:
+                t1 = time.perf_counter()
+                
+                if user_agent:
+                    self.crawler_strategy.update_user_agent(user_agent)
+                async_response: AsyncCrawlResponse = await self.crawler_strategy.crawl(
+                    url, 
+                    screenshot=screenshot, 
+                    **kwargs
                 )
-                
-                # Set response data
-                if async_response:
-                    crawl_result.status_code = async_response.status_code
-                    crawl_result.response_headers = async_response.response_headers
-                    crawl_result.downloaded_files = async_response.downloaded_files
-                else:
-                    crawl_result.status_code = 200
-                    crawl_result.response_headers = cached_result.response_headers if cached_result else {}
-
-                crawl_result.success = bool(html)
-                crawl_result.session_id = kwargs.get("session_id", None)
-
-                # if verbose:
-                #     print(f"{Fore.GREEN}{self.tag_format('COMPLETE')} {self.log_icons['COMPLETE']} {cache_context.display_url[:URL_LOG_SHORTEN_LENGTH]}... | Status: {Fore.GREEN if crawl_result.success else Fore.RED}{crawl_result.success} | {Fore.YELLOW}Total: {time.perf_counter() - start_time:.2f}s{Style.RESET_ALL}")
-                self.logger.success(
-                        message="{url:.50}... | Status: {status} | Total: {timing}",
-                        tag="COMPLETE",
-                        params={
-                            "url": cache_context.display_url,
-                            "status": crawl_result.success,
-                            "timing": f"{time.perf_counter() - start_time:.2f}s"
-                        },
-                        colors={
-                            "status": Fore.GREEN if crawl_result.success else Fore.RED,
-                            "timing": Fore.YELLOW
-                        }
-                    )
-
-                # Update cache if appropriate
-                if cache_context.should_write() and not bool(cached_result):
-                    await async_db_manager.acache_url(crawl_result)
-
-                return crawl_result
-            
-            except Exception as e:
-                if not hasattr(e, "msg"):
-                    e.msg = str(e)
-                # print(f"{Fore.RED}{self.tag_format('ERROR')} {self.log_icons['ERROR']} Failed to crawl {cache_context.display_url[:URL_LOG_SHORTEN_LENGTH]}... | {e.msg}{Style.RESET_ALL}")
-                
-                self.logger.error_status(
+                html = sanitize_input_encode(async_response.html)
+                screenshot_data = async_response.screenshot
+                t2 = time.perf_counter()
+                self.logger.url_status(
                     url=cache_context.display_url,
-                    error=create_box_message(e.msg, type = "error"),
-                    tag="ERROR"
-                )            
-                return CrawlResult(
-                    url=url, 
-                    html="", 
-                    success=False, 
-                    error_message=e.msg
+                    success=bool(html),
+                    timing=t2 - t1,
+                    tag="FETCH"
                 )
+                # if verbose:
+                #     print(f"{Fore.BLUE}{self.tag_format('FETCH')} {self.log_icons['FETCH']} Live fetch for {cache_context.display_url}... | Status: {Fore.GREEN if bool(html) else Fore.RED}{bool(html)}{Style.RESET_ALL} | Time: {t2 - t1:.2f}s")
+
+            # Process the HTML content
+            crawl_result = await self.aprocess_html(
+                url=url,
+                html=html,
+                extracted_content=extracted_content,
+                word_count_threshold=word_count_threshold,
+                extraction_strategy=extraction_strategy,
+                chunking_strategy=chunking_strategy,
+                content_filter=content_filter,
+                css_selector=css_selector,
+                screenshot=screenshot_data,
+                verbose=verbose,
+                is_cached=bool(cached_result),
+                async_response=async_response,
+                is_web_url=cache_context.is_web_url,
+                is_local_file=cache_context.is_local_file,
+                is_raw_html=cache_context.is_raw_html,
+                **kwargs,
+            )
+            
+            # Set response data
+            if async_response:
+                crawl_result.status_code = async_response.status_code
+                crawl_result.response_headers = async_response.response_headers
+                crawl_result.downloaded_files = async_response.downloaded_files
+            else:
+                crawl_result.status_code = 200
+                crawl_result.response_headers = cached_result.response_headers if cached_result else {}
+
+            crawl_result.success = bool(html)
+            crawl_result.session_id = kwargs.get("session_id", None)
+
+            # if verbose:
+            #     print(f"{Fore.GREEN}{self.tag_format('COMPLETE')} {self.log_icons['COMPLETE']} {cache_context.display_url[:URL_LOG_SHORTEN_LENGTH]}... | Status: {Fore.GREEN if crawl_result.success else Fore.RED}{crawl_result.success} | {Fore.YELLOW}Total: {time.perf_counter() - start_time:.2f}s{Style.RESET_ALL}")
+            self.logger.success(
+                    message="{url:.50}... | Status: {status} | Total: {timing}",
+                    tag="COMPLETE",
+                    params={
+                        "url": cache_context.display_url,
+                        "status": crawl_result.success,
+                        "timing": f"{time.perf_counter() - start_time:.2f}s"
+                    },
+                    colors={
+                        "status": Fore.GREEN if crawl_result.success else Fore.RED,
+                        "timing": Fore.YELLOW
+                    }
+                )
+
+            # Update cache if appropriate
+            if cache_context.should_write() and not bool(cached_result):
+                await async_db_manager.acache_url(crawl_result)
+
+            return crawl_result
+        
+        except Exception as e:
+            if not hasattr(e, "msg"):
+                e.msg = str(e)
+            # print(f"{Fore.RED}{self.tag_format('ERROR')} {self.log_icons['ERROR']} Failed to crawl {cache_context.display_url[:URL_LOG_SHORTEN_LENGTH]}... | {e.msg}{Style.RESET_ALL}")
+            self.logger.error_status(
+                url=cache_context.display_url,
+                error=e.msg,
+                tag="ERROR"
+            )            
+            return CrawlResult(
+                url=url, 
+                html="", 
+                markdown=f"[ERROR] 🚫 arun(): Failed to crawl {cache_context.display_url}, error: {e.msg}", 
+                success=False, 
+                error_message=e.msg
+            )
 
     async def arun_many(
         self,
@@ -477,17 +469,15 @@ class AsyncWebCrawler:
         try:
             _url = url if not kwargs.get("is_raw_html", False) else "Raw HTML"
             t1 = time.perf_counter()
-            scrapping_strategy = WebScrapingStrategy(
-                logger=self.logger,
-            )
+            scrapping_strategy = WebScrapingStrategy()
             # result = await scrapping_strategy.ascrap(
             result = scrapping_strategy.scrap(
                 url,
                 html,
                 word_count_threshold=word_count_threshold,
                 css_selector=css_selector,
-                only_text=kwargs.pop("only_text", False),
-                image_description_min_word_threshold=kwargs.pop(
+                only_text=kwargs.get("only_text", False),
+                image_description_min_word_threshold=kwargs.get(
                     "image_description_min_word_threshold", IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD
                 ),
                 content_filter = content_filter,
@@ -501,8 +491,6 @@ class AsyncWebCrawler:
         except Exception as e:
             raise ValueError(f"Process HTML, Failed to extract content from the website: {url}, error: {str(e)}")
 
-        markdown_v2: MarkdownGenerationResult = result.get("markdown_v2", None)
-        
         cleaned_html = sanitize_input_encode(result.get("cleaned_html", ""))
         markdown = sanitize_input_encode(result.get("markdown", ""))
         fit_markdown = sanitize_input_encode(result.get("fit_markdown", ""))
@@ -544,18 +532,16 @@ class AsyncWebCrawler:
                     "timing": time.perf_counter() - t1
                 }
             )
+        
+
+                
 
         screenshot = None if not screenshot else screenshot
         
-        
-        if kwargs.get("prettiify", False):
-            cleaned_html = fast_format_html(cleaned_html)
-        
         return CrawlResult(
             url=url,
             html=html,
-            cleaned_html=cleaned_html,
-            markdown_v2=markdown_v2,
+            cleaned_html=format_html(cleaned_html),
             markdown=markdown,
             fit_markdown=fit_markdown,
             fit_html= fit_html,

crawl4ai/content_filter_strategy.py

@@ -4,19 +4,12 @@ from typing import List, Tuple, Dict
 from rank_bm25 import BM25Okapi
 from time import perf_counter
 from collections import deque
-from bs4 import BeautifulSoup, NavigableString, Tag, Comment
+from bs4 import BeautifulSoup, NavigableString, Tag
 from .utils import clean_tokens
 from abc import ABC, abstractmethod
-import math
+
 from snowballstemmer import stemmer
 
-
-# import regex
-# def tokenize_text(text):
-#     # Regular expression to match words or CJK (Chinese, Japanese, Korean) characters
-#     pattern = r'\p{L}+|\p{N}+|[\p{Script=Han}\p{Script=Hiragana}\p{Script=Katakana}ー]|[\p{P}]'
-#     return regex.findall(pattern, text)
-
 # from nltk.stem import PorterStemmer
 # ps = PorterStemmer()
 class RelevantContentFilter(ABC):
@@ -64,14 +57,9 @@ class RelevantContentFilter(ABC):
         query_parts = []
         
         # Title
-        try:
-            title = soup.title.string
-            if title:
-                query_parts.append(title)
-        except Exception:
-            pass
-
-        if soup.find('h1'):
+        if soup.title:
+            query_parts.append(soup.title.string)
+        elif soup.find('h1'):
             query_parts.append(soup.find('h1').get_text())
             
         # Meta tags
@@ -93,7 +81,7 @@ class RelevantContentFilter(ABC):
         return ' '.join(filter(None, query_parts))
 
 
-    def extract_text_chunks(self, body: Tag, min_word_threshold: int = None) -> List[Tuple[str, str]]:
+    def extract_text_chunks(self, body: Tag) -> List[Tuple[str, str]]:
         """
         Extracts text chunks from a BeautifulSoup body element while preserving order.
         Returns list of tuples (text, tag_name) for classification.
@@ -167,9 +155,6 @@ class RelevantContentFilter(ABC):
             if text:
                 chunks.append((chunk_index, text, 'content', body))
         
-        if min_word_threshold:
-            chunks = [chunk for chunk in chunks if len(chunk[1].split()) >= min_word_threshold]
-        
         return chunks    
     
 
@@ -289,26 +274,15 @@ class BM25ContentFilter(RelevantContentFilter):
         }
         self.stemmer = stemmer(language)
 
-    def filter_content(self, html: str, min_word_threshold: int = None) -> List[str]:
+    def filter_content(self, html: str) -> List[str]:
         """Implements content filtering using BM25 algorithm with priority tag handling"""
         if not html or not isinstance(html, str):
             return []
 
         soup = BeautifulSoup(html, 'lxml')
-        
-        # Check if body is present
-        if not soup.body:
-            # Wrap in body tag if missing
-            soup = BeautifulSoup(f'<body>{html}</body>', 'lxml')        
         body = soup.find('body')
-        
-        query = self.extract_page_query(soup, body)
-        
-        if not query:
-            return []
-            # return [self.clean_element(soup)]
-            
-        candidates = self.extract_text_chunks(body, min_word_threshold)
+        query = self.extract_page_query(soup.find('head'), body)
+        candidates = self.extract_text_chunks(body)
 
         if not candidates:
             return []
@@ -325,10 +299,6 @@ class BM25ContentFilter(RelevantContentFilter):
                    for _, chunk, _, _ in candidates]
         tokenized_query = [self.stemmer.stemWord(word) for word in query.lower().split()]
 
-        # tokenized_corpus = [[self.stemmer.stemWord(word) for word in tokenize_text(chunk.lower())] 
-        #            for _, chunk, _, _ in candidates]
-        # tokenized_query = [self.stemmer.stemWord(word) for word in tokenize_text(query.lower())]
-
         # Clean from stop words and noise
         tokenized_corpus = [clean_tokens(tokens) for tokens in tokenized_corpus]
         tokenized_query = clean_tokens(tokenized_query)
@@ -356,188 +326,3 @@ class BM25ContentFilter(RelevantContentFilter):
         selected_candidates.sort(key=lambda x: x[0])
 
         return [self.clean_element(tag) for _, _, tag in selected_candidates]
-
-
-
-
-
-
-class PruningContentFilter(RelevantContentFilter):
-    def __init__(self, user_query: str = None, min_word_threshold: int = None, 
-                 threshold_type: str = 'fixed', threshold: float = 0.48):
-        super().__init__(user_query)
-        self.min_word_threshold = min_word_threshold
-        self.threshold_type = threshold_type
-        self.threshold = threshold
-        
-        # Add tag importance for dynamic threshold
-        self.tag_importance = {
-            'article': 1.5,
-            'main': 1.4,
-            'section': 1.3,
-            'p': 1.2,
-            'h1': 1.4,
-            'h2': 1.3,
-            'h3': 1.2,
-            'div': 0.7,
-            'span': 0.6
-        }
-        
-        # Metric configuration
-        self.metric_config = {
-            'text_density': True,
-            'link_density': True,
-            'tag_weight': True,
-            'class_id_weight': True,
-            'text_length': True,
-        }
-        
-        self.metric_weights = {
-            'text_density': 0.4,
-            'link_density': 0.2,
-            'tag_weight': 0.2,
-            'class_id_weight': 0.1,
-            'text_length': 0.1,
-        }
-        
-        self.tag_weights = {
-            'div': 0.5,
-            'p': 1.0,
-            'article': 1.5,
-            'section': 1.0,
-            'span': 0.3,
-            'li': 0.5,
-            'ul': 0.5,
-            'ol': 0.5,
-            'h1': 1.2,
-            'h2': 1.1,
-            'h3': 1.0,
-            'h4': 0.9,
-            'h5': 0.8,
-            'h6': 0.7,
-        }
-
-    def filter_content(self, html: str, min_word_threshold: int = None) -> List[str]:
-        if not html or not isinstance(html, str):
-            return []
-            
-        soup = BeautifulSoup(html, 'lxml')
-        if not soup.body:
-            soup = BeautifulSoup(f'<body>{html}</body>', 'lxml')
-        
-        # Remove comments and unwanted tags
-        self._remove_comments(soup)
-        self._remove_unwanted_tags(soup)
-        
-        # Prune tree starting from body
-        body = soup.find('body')
-        self._prune_tree(body)
-        
-        # Extract remaining content as list of HTML strings
-        content_blocks = []
-        for element in body.children:
-            if isinstance(element, str) or not hasattr(element, 'name'):
-                continue
-            if len(element.get_text(strip=True)) > 0:
-                content_blocks.append(str(element))
-                
-        return content_blocks
-
-    def _remove_comments(self, soup):
-        for element in soup(text=lambda text: isinstance(text, Comment)):
-            element.extract()
-
-    def _remove_unwanted_tags(self, soup):
-        for tag in self.excluded_tags:
-            for element in soup.find_all(tag):
-                element.decompose()
-
-    def _prune_tree(self, node):
-        if not node or not hasattr(node, 'name') or node.name is None:
-            return
-
-        text_len = len(node.get_text(strip=True))
-        tag_len = len(node.encode_contents().decode('utf-8'))
-        link_text_len = sum(len(s.strip()) for s in (a.string for a in node.find_all('a', recursive=False)) if s)
-
-        metrics = {
-            'node': node,
-            'tag_name': node.name,
-            'text_len': text_len,
-            'tag_len': tag_len,
-            'link_text_len': link_text_len
-        }
-
-        score = self._compute_composite_score(metrics, text_len, tag_len, link_text_len)
-
-        if self.threshold_type == 'fixed':
-            should_remove = score < self.threshold
-        else:  # dynamic
-            tag_importance = self.tag_importance.get(node.name, 0.7)
-            text_ratio = text_len / tag_len if tag_len > 0 else 0
-            link_ratio = link_text_len / text_len if text_len > 0 else 1
-            
-            threshold = self.threshold  # base threshold
-            if tag_importance > 1:
-                threshold *= 0.8
-            if text_ratio > 0.4:
-                threshold *= 0.9
-            if link_ratio > 0.6:
-                threshold *= 1.2
-                
-            should_remove = score < threshold
-
-        if should_remove:
-            node.decompose()
-        else:
-            children = [child for child in node.children if hasattr(child, 'name')]
-            for child in children:
-                self._prune_tree(child)
-
-    def _compute_composite_score(self, metrics, text_len, tag_len, link_text_len):
-        if self.min_word_threshold:
-            # Get raw text from metrics node - avoid extra processing
-            text = metrics['node'].get_text(strip=True)
-            word_count = text.count(' ') + 1
-            if word_count < self.min_word_threshold:
-                return -1.0  # Guaranteed removal
-        score = 0.0
-        total_weight = 0.0
-
-        if self.metric_config['text_density']:
-            density = text_len / tag_len if tag_len > 0 else 0
-            score += self.metric_weights['text_density'] * density
-            total_weight += self.metric_weights['text_density']
-
-        if self.metric_config['link_density']:
-            density = 1 - (link_text_len / text_len if text_len > 0 else 0)
-            score += self.metric_weights['link_density'] * density
-            total_weight += self.metric_weights['link_density']
-
-        if self.metric_config['tag_weight']:
-            tag_score = self.tag_weights.get(metrics['tag_name'], 0.5)
-            score += self.metric_weights['tag_weight'] * tag_score
-            total_weight += self.metric_weights['tag_weight']
-
-        if self.metric_config['class_id_weight']:
-            class_score = self._compute_class_id_weight(metrics['node'])
-            score += self.metric_weights['class_id_weight'] * max(0, class_score)
-            total_weight += self.metric_weights['class_id_weight']
-
-        if self.metric_config['text_length']:
-            score += self.metric_weights['text_length'] * math.log(text_len + 1)
-            total_weight += self.metric_weights['text_length']
-
-        return score / total_weight if total_weight > 0 else 0
-
-    def _compute_class_id_weight(self, node):
-        class_id_score = 0
-        if 'class' in node.attrs:
-            classes = ' '.join(node['class'])
-            if self.negative_patterns.match(classes):
-                class_id_score -= 0.5
-        if 'id' in node.attrs:
-            element_id = node['id']
-            if self.negative_patterns.match(element_id):
-                class_id_score -= 0.5
-        return class_id_score

crawl4ai/content_scrapping_strategy.py

@@ -1,6 +1,6 @@
 import re  # Point 1: Pre-Compile Regular Expressions
 from abc import ABC, abstractmethod
-from typing import Dict, Any, Optional
+from typing import Dict, Any
 from bs4 import BeautifulSoup
 from concurrent.futures import ThreadPoolExecutor
 import asyncio, requests, re, os
@@ -9,19 +9,103 @@ from bs4 import element, NavigableString, Comment
 from urllib.parse import urljoin
 from requests.exceptions import InvalidSchema
 # from .content_cleaning_strategy import ContentCleaningStrategy
-from .content_filter_strategy import RelevantContentFilter, BM25ContentFilter, PruningContentFilter
-from .markdown_generation_strategy import MarkdownGenerationStrategy, DefaultMarkdownGenerator
-from .models import MarkdownGenerationResult
+from .content_filter_strategy import RelevantContentFilter, BM25ContentFilter
+
 from .utils import (
     sanitize_input_encode,
     sanitize_html,
     extract_metadata,
     InvalidCSSSelectorError,
-    CustomHTML2Text,
+    # CustomHTML2Text,
     normalize_url,
-    is_external_url    
+    is_external_url
+    
 )
-from .tools import profile_and_time
+
+from .html2text import HTML2Text
+class CustomHTML2Text(HTML2Text):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.inside_pre = False
+        self.inside_code = False
+        self.preserve_tags = set()  # Set of tags to preserve
+        self.current_preserved_tag = None
+        self.preserved_content = []
+        self.preserve_depth = 0
+        
+        # Configuration options
+        self.skip_internal_links = False
+        self.single_line_break = False
+        self.mark_code = False
+        self.include_sup_sub = False
+        self.body_width = 0
+        self.ignore_mailto_links = True
+        self.ignore_links = False
+        self.escape_backslash = False
+        self.escape_dot = False
+        self.escape_plus = False
+        self.escape_dash = False
+        self.escape_snob = False
+
+    def update_params(self, **kwargs):
+        """Update parameters and set preserved tags."""
+        for key, value in kwargs.items():
+            if key == 'preserve_tags':
+                self.preserve_tags = set(value)
+            else:
+                setattr(self, key, value)
+
+    def handle_tag(self, tag, attrs, start):
+        # Handle preserved tags
+        if tag in self.preserve_tags:
+            if start:
+                if self.preserve_depth == 0:
+                    self.current_preserved_tag = tag
+                    self.preserved_content = []
+                    # Format opening tag with attributes
+                    attr_str = ''.join(f' {k}="{v}"' for k, v in attrs.items() if v is not None)
+                    self.preserved_content.append(f'<{tag}{attr_str}>')
+                self.preserve_depth += 1
+                return
+            else:
+                self.preserve_depth -= 1
+                if self.preserve_depth == 0:
+                    self.preserved_content.append(f'</{tag}>')
+                    # Output the preserved HTML block with proper spacing
+                    preserved_html = ''.join(self.preserved_content)
+                    self.o('\n' + preserved_html + '\n')
+                    self.current_preserved_tag = None
+                return
+
+        # If we're inside a preserved tag, collect all content
+        if self.preserve_depth > 0:
+            if start:
+                # Format nested tags with attributes
+                attr_str = ''.join(f' {k}="{v}"' for k, v in attrs.items() if v is not None)
+                self.preserved_content.append(f'<{tag}{attr_str}>')
+            else:
+                self.preserved_content.append(f'</{tag}>')
+            return
+
+        # Handle pre tags
+        if tag == 'pre':
+            if start:
+                self.o('```\n')
+                self.inside_pre = True
+            else:
+                self.o('\n```')
+                self.inside_pre = False
+        # elif tag in ["h1", "h2", "h3", "h4", "h5", "h6"]:
+        #     pass
+        else:
+            super().handle_tag(tag, attrs, start)
+
+    def handle_data(self, data, entity_char=False):
+        """Override handle_data to capture content within preserved tags."""
+        if self.preserve_depth > 0:
+            self.preserved_content.append(data)
+            return
+        super().handle_data(data, entity_char)
 
 # Pre-compile regular expressions for Open Graph and Twitter metadata
 OG_REGEX = re.compile(r'^og:')
@@ -80,109 +164,6 @@ class WebScrapingStrategy(ContentScrapingStrategy):
     async def ascrap(self, url: str, html: str, **kwargs) -> Dict[str, Any]:
         return await asyncio.to_thread(self._get_content_of_website_optimized, url, html, **kwargs)
 
-
-    def _generate_markdown_content(self, 
-                                 cleaned_html: str,
-                                 html: str,
-                                 url: str,
-                                 success: bool,
-                                 **kwargs) -> Dict[str, Any]:
-        """Generate markdown content using either new strategy or legacy method.
-        
-        Args:
-            cleaned_html: Sanitized HTML content
-            html: Original HTML content
-            url: Base URL of the page
-            success: Whether scraping was successful
-            **kwargs: Additional options including:
-                - markdown_generator: Optional[MarkdownGenerationStrategy]
-                - html2text: Dict[str, Any] options for HTML2Text
-                - content_filter: Optional[RelevantContentFilter]
-                - fit_markdown: bool
-                - fit_markdown_user_query: Optional[str]
-                - fit_markdown_bm25_threshold: float
-        
-        Returns:
-            Dict containing markdown content in various formats
-        """
-        markdown_generator: Optional[MarkdownGenerationStrategy] = kwargs.get('markdown_generator', DefaultMarkdownGenerator())
-        
-        if markdown_generator:
-            try:
-                if kwargs.get('fit_markdown', False) and not markdown_generator.content_filter:
-                        markdown_generator.content_filter = PruningContentFilter(
-                            threshold_type=kwargs.get('fit_markdown_treshold_type', 'fixed'),
-                            threshold=kwargs.get('fit_markdown_treshold', 0.48),
-                            min_word_threshold=kwargs.get('fit_markdown_min_word_threshold', ),
-                        )
-                        # markdown_generator.content_filter = BM25ContentFilter(
-                        #     user_query=kwargs.get('fit_markdown_user_query', None),
-                        #     bm25_threshold=kwargs.get('fit_markdown_bm25_threshold', 1.0)
-                        # )
-                
-                markdown_result: MarkdownGenerationResult = markdown_generator.generate_markdown(
-                    cleaned_html=cleaned_html,
-                    base_url=url,
-                    html2text_options=kwargs.get('html2text', {})
-                )
-                
-                help_message = """"""
-                
-                return {
-                    'markdown': markdown_result.raw_markdown,  
-                    'fit_markdown': markdown_result.fit_markdown,
-                    'fit_html': markdown_result.fit_html, 
-                    'markdown_v2': markdown_result
-                }
-            except Exception as e:
-                self._log('error',
-                    message="Error using new markdown generation strategy: {error}",
-                    tag="SCRAPE",
-                    params={"error": str(e)}
-                )
-                markdown_generator = None
-                return {
-                    'markdown': f"Error using new markdown generation strategy: {str(e)}",
-                    'fit_markdown': "Set flag 'fit_markdown' to True to get cleaned HTML content.",
-                    'fit_html': "Set flag 'fit_markdown' to True to get cleaned HTML content.",
-                    'markdown_v2': None                    
-                }
-
-        # Legacy method
-        h = CustomHTML2Text()
-        h.update_params(**kwargs.get('html2text', {}))            
-        markdown = h.handle(cleaned_html)
-        markdown = markdown.replace('    ```', '```')
-        
-        fit_markdown = "Set flag 'fit_markdown' to True to get cleaned HTML content."
-        fit_html = "Set flag 'fit_markdown' to True to get cleaned HTML content."
-        
-        if kwargs.get('content_filter', None) or kwargs.get('fit_markdown', False):
-            content_filter = kwargs.get('content_filter', None)
-            if not content_filter:
-                content_filter = BM25ContentFilter(
-                    user_query=kwargs.get('fit_markdown_user_query', None),
-                    bm25_threshold=kwargs.get('fit_markdown_bm25_threshold', 1.0)
-                )
-            fit_html = content_filter.filter_content(html)
-            fit_html = '\n'.join('<div>{}</div>'.format(s) for s in fit_html)
-            fit_markdown = h.handle(fit_html)
-
-        markdown_v2 = MarkdownGenerationResult(
-            raw_markdown=markdown,
-            markdown_with_citations=markdown,
-            references_markdown=markdown,
-            fit_markdown=fit_markdown
-        )
-        
-        return {
-            'markdown': markdown,
-            'fit_markdown': fit_markdown,
-            'fit_html': fit_html,
-            'markdown_v2' : markdown_v2
-        }
-
-
     def _get_content_of_website_optimized(self, url: str, html: str, word_count_threshold: int = MIN_WORD_THRESHOLD, css_selector: str = None, **kwargs) -> Dict[str, Any]:
         success = True
         if not html:
@@ -245,9 +226,7 @@ class WebScrapingStrategy(ContentScrapingStrategy):
                             return text_content
                 return None
 
-        def process_image_old(img, url, index, total_images):
-                   
-            
+        def process_image(img, url, index, total_images):
             #Check if an image has valid display and inside undesired html elements
             def is_valid_image(img, parent, parent_classes):
                 style = img.get('style', '')
@@ -263,6 +242,8 @@ class WebScrapingStrategy(ContentScrapingStrategy):
 
             #Score an image for it's usefulness
             def score_image_for_usefulness(img, base_url, index, images_count):
+
+
                 image_height = img.get('height')
                 height_value, height_unit = parse_dimension(image_height)
                 image_width =  img.get('width')
@@ -296,14 +277,14 @@ class WebScrapingStrategy(ContentScrapingStrategy):
                     score+=1
                 return score
 
+            
+            
             if not is_valid_image(img, img.parent, img.parent.get('class', [])):
                 return None
-                
             score = score_image_for_usefulness(img, url, index, total_images)
-            if score <= kwargs.get('image_score_threshold', IMAGE_SCORE_THRESHOLD):
+            if score <= IMAGE_SCORE_THRESHOLD:
                 return None
-
-            base_result = {
+            return {
                 'src': img.get('src', ''),
                 'data-src': img.get('data-src', ''),
                 'alt': img.get('alt', ''),
@@ -312,113 +293,6 @@ class WebScrapingStrategy(ContentScrapingStrategy):
                 'type': 'image'
             }
 
-            sources = []
-            srcset = img.get('srcset', '')
-            if srcset:
-                sources = parse_srcset(srcset)
-                if sources:
-                    return [dict(base_result, src=source['url'], width=source['width']) 
-                        for source in sources]
-
-            return [base_result]  # Always return a list
-
-        def process_image(img, url, index, total_images):
-            parse_srcset = lambda s: [{'url': u.strip().split()[0], 'width': u.strip().split()[-1].rstrip('w') 
-                          if ' ' in u else None} 
-                         for u in [f"http{p}" for p in s.split("http") if p]]
-            
-            # Constants for checks
-            classes_to_check = frozenset(['button', 'icon', 'logo'])
-            tags_to_check = frozenset(['button', 'input'])
-            
-            # Pre-fetch commonly used attributes
-            style = img.get('style', '')
-            alt = img.get('alt', '')
-            src = img.get('src', '')
-            data_src = img.get('data-src', '')
-            width = img.get('width')
-            height = img.get('height')
-            parent = img.parent
-            parent_classes = parent.get('class', [])
-
-            # Quick validation checks
-            if ('display:none' in style or
-                parent.name in tags_to_check or
-                any(c in cls for c in parent_classes for cls in classes_to_check) or
-                any(c in src for c in classes_to_check) or
-                any(c in alt for c in classes_to_check)):
-                return None
-
-            # Quick score calculation
-            score = 0
-            if width and width.isdigit():
-                width_val = int(width)
-                score += 1 if width_val > 150 else 0
-            if height and height.isdigit():
-                height_val = int(height)
-                score += 1 if height_val > 150 else 0
-            if alt:
-                score += 1
-            score += index/total_images < 0.5
-            
-            image_format = ''
-            if "data:image/" in src:
-                image_format = src.split(',')[0].split(';')[0].split('/')[1].split(';')[0]
-            else:
-                image_format = os.path.splitext(src)[1].lower().strip('.').split('?')[0]
-            
-            if image_format in ('jpg', 'png', 'webp', 'avif'):
-                score += 1
-
-            if score <= kwargs.get('image_score_threshold', IMAGE_SCORE_THRESHOLD):
-                return None
-
-            # Use set for deduplication
-            unique_urls = set()
-            image_variants = []
-            
-            # Generate a unique group ID for this set of variants
-            group_id = index 
-            
-            # Base image info template
-            base_info = {
-                'alt': alt,
-                'desc': find_closest_parent_with_useful_text(img),
-                'score': score,
-                'type': 'image',
-                'group_id': group_id # Group ID for this set of variants
-            }
-
-            # Inline function for adding variants
-            def add_variant(src, width=None):
-                if src and not src.startswith('data:') and src not in unique_urls:
-                    unique_urls.add(src)
-                    image_variants.append({**base_info, 'src': src, 'width': width})
-
-            # Process all sources
-            add_variant(src)
-            add_variant(data_src)
-            
-            # Handle srcset and data-srcset in one pass
-            for attr in ('srcset', 'data-srcset'):
-                if value := img.get(attr):
-                    for source in parse_srcset(value):
-                        add_variant(source['url'], source['width'])
-
-            # Quick picture element check
-            if picture := img.find_parent('picture'):
-                for source in picture.find_all('source'):
-                    if srcset := source.get('srcset'):
-                        for src in parse_srcset(srcset):
-                            add_variant(src['url'], src['width'])
-
-            # Framework-specific attributes in one pass
-            for attr, value in img.attrs.items():
-                if attr.startswith('data-') and ('src' in attr or 'srcset' in attr) and 'http' in value:
-                    add_variant(value)
-
-            return image_variants if image_variants else None
-
         def remove_unwanted_attributes(element, important_attrs, keep_data_attributes=False):
             attrs_to_remove = []
             for attr in element.attrs:
@@ -610,16 +484,13 @@ class WebScrapingStrategy(ContentScrapingStrategy):
         links['internal'] = list(internal_links_dict.values())
         links['external'] = list(external_links_dict.values())
 
+
         # # Process images using ThreadPoolExecutor
         imgs = body.find_all('img')
         
-        # For test we use for loop instead of thread
-        media['images'] = [
-            img for result in (process_image(img, url, i, len(imgs)) 
-                            for i, img in enumerate(imgs))
-            if result is not None
-            for img in result
-        ]
+        with ThreadPoolExecutor() as executor:
+            image_results = list(executor.map(process_image, imgs, [url]*len(imgs), range(len(imgs)), [len(imgs)]*len(imgs)))
+        media['images'] = [result for result in image_results if result is not None]
 
         def flatten_nested_elements(node):
             if isinstance(node, NavigableString):
@@ -674,16 +545,41 @@ class WebScrapingStrategy(ContentScrapingStrategy):
 
         cleaned_html = str_body.replace('\n\n', '\n').replace('  ', ' ')
 
-        markdown_content = self._generate_markdown_content(
-            cleaned_html=cleaned_html,
-            html=html,
-            url=url,
-            success=success,
-            **kwargs
-        )
+        try:
+            h = CustomHTML2Text()
+            h.update_params(**kwargs.get('html2text', {}))            
+            markdown = h.handle(cleaned_html)
+        except Exception as e:
+            if not h:
+                h = CustomHTML2Text()
+            self._log('error',
+                message="Error converting HTML to markdown: {error}",
+                tag="SCRAPE",
+                params={"error": str(e)}
+            )
+            markdown = h.handle(sanitize_html(cleaned_html))
+        markdown = markdown.replace('    ```', '```')
+
         
+            
+        fit_markdown = "Set flag 'fit_markdown' to True to get cleaned HTML content."
+        fit_html = "Set flag 'fit_markdown' to True to get cleaned HTML content."
+        if kwargs.get('content_filter', None) or kwargs.get('fit_markdown', False):
+            content_filter = kwargs.get('content_filter', None)
+            if not content_filter:
+                content_filter = BM25ContentFilter(
+                    user_query= kwargs.get('fit_markdown_user_query', None),
+                    bm25_threshold= kwargs.get('fit_markdown_bm25_threshold', 1.0)
+                )
+            fit_html = content_filter.filter_content(html)
+            fit_html = '\n'.join('<div>{}</div>'.format(s) for s in fit_html)
+            fit_markdown = h.handle(fit_html)
+
+        cleaned_html = sanitize_html(cleaned_html)
         return {
-            **markdown_content,
+            'markdown': markdown,
+            'fit_markdown': fit_markdown,
+            'fit_html': fit_html,
             'cleaned_html': cleaned_html,
             'success': success,
             'media': media,

crawl4ai/crawler_strategy.py

@@ -283,7 +283,7 @@ class LocalSeleniumCrawlerStrategy(CrawlerStrategy):
                 print(f"[LOG] ✅ Crawled {url} successfully!")
             
             return html
-        except InvalidArgumentException as e:
+        except InvalidArgumentException:
             if not hasattr(e, 'msg'):
                 e.msg = sanitize_input_encode(str(e))
             raise InvalidArgumentException(f"Failed to crawl {url}: {e.msg}")

crawl4ai/install.py

@@ -1,44 +0,0 @@
-import subprocess
-import sys
-import asyncio
-from .async_logger import AsyncLogger, LogLevel
-
-# Initialize logger
-logger = AsyncLogger(log_level=LogLevel.DEBUG, verbose=True)
-
-def post_install():
-    """Run all post-installation tasks"""
-    logger.info("Running post-installation setup...", tag="INIT")
-    install_playwright()
-    run_migration()
-    logger.success("Post-installation setup completed!", tag="COMPLETE")
-    
-def install_playwright():
-    logger.info("Installing Playwright browsers...", tag="INIT")
-    try:
-        subprocess.check_call([sys.executable, "-m", "playwright", "install"])
-        logger.success("Playwright installation completed successfully.", tag="COMPLETE")
-    except subprocess.CalledProcessError as e:
-        logger.error(f"Error during Playwright installation: {e}", tag="ERROR")
-        logger.warning(
-            "Please run 'python -m playwright install' manually after the installation."
-        )
-    except Exception as e:
-        logger.error(f"Unexpected error during Playwright installation: {e}", tag="ERROR")
-        logger.warning(
-            "Please run 'python -m playwright install' manually after the installation."
-        )
-
-def run_migration():
-    """Initialize database during installation"""
-    try:
-        logger.info("Starting database initialization...", tag="INIT")
-        from crawl4ai.async_database import async_db_manager
-
-        asyncio.run(async_db_manager.initialize())
-        logger.success("Database initialization completed successfully.", tag="COMPLETE")
-    except ImportError:
-        logger.warning("Database module not found. Will initialize on first use.")
-    except Exception as e:
-        logger.warning(f"Database initialization failed: {e}")
-        logger.warning("Database will be initialized on first use")

crawl4ai/markdown_generation_strategy.py

@@ -1,130 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import Optional, Dict, Any, Tuple
-from .models import MarkdownGenerationResult
-from .utils import CustomHTML2Text
-from .content_filter_strategy import RelevantContentFilter, BM25ContentFilter
-import re
-from urllib.parse import urljoin
-
-# Pre-compile the regex pattern
-LINK_PATTERN = re.compile(r'!?\[([^\]]+)\]\(([^)]+?)(?:\s+"([^"]*)")?\)')
-
-class MarkdownGenerationStrategy(ABC):
-    """Abstract base class for markdown generation strategies."""
-    def __init__(self, content_filter: Optional[RelevantContentFilter] = None, options: Optional[Dict[str, Any]] = None):
-        self.content_filter = content_filter
-        self.options = options or {}
-    
-    @abstractmethod
-    def generate_markdown(self, 
-                         cleaned_html: str, 
-                         base_url: str = "",
-                         html2text_options: Optional[Dict[str, Any]] = None,
-                         content_filter: Optional[RelevantContentFilter] = None,
-                         citations: bool = True,
-                         **kwargs) -> MarkdownGenerationResult:
-        """Generate markdown from cleaned HTML."""
-        pass
-
-class DefaultMarkdownGenerator(MarkdownGenerationStrategy):
-    """Default implementation of markdown generation strategy."""
-    def __init__(self, content_filter: Optional[RelevantContentFilter] = None, options: Optional[Dict[str, Any]] = None):
-        super().__init__(content_filter, options)
-    
-    def convert_links_to_citations(self, markdown: str, base_url: str = "") -> Tuple[str, str]:
-        link_map = {}
-        url_cache = {}  # Cache for URL joins
-        parts = []
-        last_end = 0
-        counter = 1
-        
-        for match in LINK_PATTERN.finditer(markdown):
-            parts.append(markdown[last_end:match.start()])
-            text, url, title = match.groups()
-            
-            # Use cached URL if available, otherwise compute and cache
-            if base_url and not url.startswith(('http://', 'https://', 'mailto:')):
-                if url not in url_cache:
-                    url_cache[url] = fast_urljoin(base_url, url)
-                url = url_cache[url]
-                
-            if url not in link_map:
-                desc = []
-                if title: desc.append(title)
-                if text and text != title: desc.append(text)
-                link_map[url] = (counter, ": " + " - ".join(desc) if desc else "")
-                counter += 1
-                
-            num = link_map[url][0]
-            parts.append(f"{text}⟨{num}⟩" if not match.group(0).startswith('!') else f"![{text}⟨{num}⟩]")
-            last_end = match.end()
-        
-        parts.append(markdown[last_end:])
-        converted_text = ''.join(parts)
-        
-        # Pre-build reference strings
-        references = ["\n\n## References\n\n"]
-        references.extend(
-            f"⟨{num}⟩ {url}{desc}\n" 
-            for url, (num, desc) in sorted(link_map.items(), key=lambda x: x[1][0])
-        )
-        
-        return converted_text, ''.join(references)
-
-    def generate_markdown(self, 
-                         cleaned_html: str, 
-                         base_url: str = "",
-                         html2text_options: Optional[Dict[str, Any]] = None,
-                         options: Optional[Dict[str, Any]] = None,
-                         content_filter: Optional[RelevantContentFilter] = None,
-                         citations: bool = True,
-                         **kwargs) -> MarkdownGenerationResult:
-        """Generate markdown with citations from cleaned HTML."""
-        # Initialize HTML2Text with options
-        h = CustomHTML2Text()
-        if html2text_options:
-            h.update_params(**html2text_options)
-        elif options:
-            h.update_params(**options)
-        elif self.options:
-            h.update_params(**self.options)
-
-        # Generate raw markdown
-        raw_markdown = h.handle(cleaned_html)
-        raw_markdown = raw_markdown.replace('    ```', '```')
-
-        # Convert links to citations
-        markdown_with_citations: str = ""
-        references_markdown: str = ""
-        if citations:
-            markdown_with_citations, references_markdown = self.convert_links_to_citations(
-                raw_markdown, base_url
-            )
-
-        # Generate fit markdown if content filter is provided
-        fit_markdown: Optional[str] = ""
-        filtered_html: Optional[str] = ""
-        if content_filter or self.content_filter:
-            content_filter = content_filter or self.content_filter
-            filtered_html = content_filter.filter_content(cleaned_html)
-            filtered_html = '\n'.join('<div>{}</div>'.format(s) for s in filtered_html)
-            fit_markdown = h.handle(filtered_html)
-
-        return MarkdownGenerationResult(
-            raw_markdown=raw_markdown,
-            markdown_with_citations=markdown_with_citations,
-            references_markdown=references_markdown,
-            fit_markdown=fit_markdown,
-            fit_html=filtered_html,
-        )
-
-def fast_urljoin(base: str, url: str) -> str:
-    """Fast URL joining for common cases."""
-    if url.startswith(('http://', 'https://', 'mailto:', '//')):
-        return url
-    if url.startswith('/'):
-        # Handle absolute paths
-        if base.endswith('/'):
-            return base[:-1] + url
-        return base + url
-    return urljoin(base, url)

crawl4ai/migrations.py

@@ -9,13 +9,9 @@ import aiofiles
 import shutil
 import time
 from datetime import datetime
-from .async_logger import AsyncLogger, LogLevel
 
-# Initialize logger
-logger = AsyncLogger(log_level=LogLevel.DEBUG, verbose=True)
-
-# logging.basicConfig(level=logging.INFO)
-# logger = logging.getLogger(__name__)
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
 
 class DatabaseMigration:
     def __init__(self, db_path: str):
@@ -59,8 +55,7 @@ class DatabaseMigration:
 
     async def migrate_database(self):
         """Migrate existing database to file-based storage"""
-        # logger.info("Starting database migration...")
-        logger.info("Starting database migration...", tag="INIT")
+        logger.info("Starting database migration...")
         
         try:
             async with aiosqlite.connect(self.db_path) as db:
@@ -96,25 +91,19 @@ class DatabaseMigration:
                     
                     migrated_count += 1
                     if migrated_count % 100 == 0:
-                        logger.info(f"Migrated {migrated_count} records...", tag="INIT")
-                        
+                        logger.info(f"Migrated {migrated_count} records...")
 
                 await db.commit()
-                logger.success(f"Migration completed. {migrated_count} records processed.", tag="COMPLETE")
+                logger.info(f"Migration completed. {migrated_count} records processed.")
 
         except Exception as e:
-            # logger.error(f"Migration failed: {e}")
-            logger.error(
-                message="Migration failed: {error}",
-                tag="ERROR",
-                params={"error": str(e)}
-            )
-            raise e
+            logger.error(f"Migration failed: {e}")
+            raise
 
 async def backup_database(db_path: str) -> str:
     """Create backup of existing database"""
     if not os.path.exists(db_path):
-        logger.info("No existing database found. Skipping backup.", tag="INIT")
+        logger.info("No existing database found. Skipping backup.")
         return None
         
     # Create backup with timestamp
@@ -127,16 +116,11 @@ async def backup_database(db_path: str) -> str:
         
         # Create backup
         shutil.copy2(db_path, backup_path)
-        logger.info(f"Database backup created at: {backup_path}", tag="COMPLETE")
+        logger.info(f"Database backup created at: {backup_path}")
         return backup_path
     except Exception as e:
-        # logger.error(f"Backup failed: {e}")
-        logger.error(
-                message="Migration failed: {error}",
-                tag="ERROR",
-                params={"error": str(e)}
-            )
-        raise e
+        logger.error(f"Backup failed: {e}")
+        raise
     
 async def run_migration(db_path: Optional[str] = None):
     """Run database migration"""
@@ -144,7 +128,7 @@ async def run_migration(db_path: Optional[str] = None):
         db_path = os.path.join(Path.home(), ".crawl4ai", "crawl4ai.db")
     
     if not os.path.exists(db_path):
-        logger.info("No existing database found. Skipping migration.", tag="INIT")
+        logger.info("No existing database found. Skipping migration.")
         return
         
     # Create backup first

crawl4ai/models.py

@@ -1,5 +1,5 @@
 from pydantic import BaseModel, HttpUrl
-from typing import List, Dict, Optional, Callable, Awaitable, Union
+from typing import List, Dict, Optional, Callable, Awaitable
 
 
 
@@ -7,13 +7,6 @@ class UrlModel(BaseModel):
     url: HttpUrl
     forced: bool = False
 
-class MarkdownGenerationResult(BaseModel):
-    raw_markdown: str
-    markdown_with_citations: str
-    references_markdown: str
-    fit_markdown: Optional[str] = None
-    fit_html: Optional[str] = None
-
 class CrawlResult(BaseModel):
     url: str
     html: str
@@ -23,8 +16,7 @@ class CrawlResult(BaseModel):
     links: Dict[str, List[Dict]] = {}
     downloaded_files: Optional[List[str]] = None
     screenshot: Optional[str] = None
-    markdown: Optional[Union[str, MarkdownGenerationResult]] = None
-    markdown_v2: Optional[MarkdownGenerationResult] = None
+    markdown: Optional[str] = None
     fit_markdown: Optional[str] = None
     fit_html: Optional[str] = None
     extracted_content: Optional[str] = None
@@ -44,5 +36,3 @@ class AsyncCrawlResponse(BaseModel):
 
     class Config:
         arbitrary_types_allowed = True
-
-

crawl4ai/tools.py

@@ -1,34 +0,0 @@
-import time
-import cProfile
-import pstats
-from functools import wraps
-
-def profile_and_time(func):
-    @wraps(func)
-    def wrapper(self, *args, **kwargs):
-        # Start timer
-        start_time = time.perf_counter()
-        
-        # Setup profiler
-        profiler = cProfile.Profile()
-        profiler.enable()
-        
-        # Run function
-        result = func(self, *args, **kwargs)
-        
-        # Stop profiler
-        profiler.disable()
-        
-        # Calculate elapsed time
-        elapsed_time = time.perf_counter() - start_time
-        
-        # Print timing
-        print(f"[PROFILER] Scraping completed in {elapsed_time:.2f} seconds")
-        
-        # Print profiling stats
-        stats = pstats.Stats(profiler)
-        stats.sort_stats('cumulative')  # Sort by cumulative time
-        stats.print_stats(20)  # Print top 20 time-consuming functions
-        
-        return result
-    return wrapper

crawl4ai/user_agent_generator.py

@@ -1,263 +0,0 @@
-import random
-from typing import Optional, Literal, List, Dict, Tuple
-import re
-
-
-class UserAgentGenerator:
-    def __init__(self):
-        # Previous platform definitions remain the same...
-        self.desktop_platforms = {
-            "windows": {
-                "10_64": "(Windows NT 10.0; Win64; x64)",
-                "10_32": "(Windows NT 10.0; WOW64)",
-            },
-            "macos": {
-                "intel": "(Macintosh; Intel Mac OS X 10_15_7)",
-                "newer": "(Macintosh; Intel Mac OS X 10.15; rv:109.0)",
-            },
-            "linux": {
-                "generic": "(X11; Linux x86_64)",
-                "ubuntu": "(X11; Ubuntu; Linux x86_64)",
-                "chrome_os": "(X11; CrOS x86_64 14541.0.0)",
-            }
-        }
-
-        self.mobile_platforms = {
-            "android": {
-                "samsung": "(Linux; Android 13; SM-S901B)",
-                "pixel": "(Linux; Android 12; Pixel 6)",
-                "oneplus": "(Linux; Android 13; OnePlus 9 Pro)",
-                "xiaomi": "(Linux; Android 12; M2102J20SG)",
-            },
-            "ios": {
-                "iphone": "(iPhone; CPU iPhone OS 16_5 like Mac OS X)",
-                "ipad": "(iPad; CPU OS 16_5 like Mac OS X)",
-            }
-        }
-
-        # Browser Combinations
-        self.browser_combinations = {
-            1: [
-                ["chrome"],
-                ["firefox"],
-                ["safari"],
-                ["edge"]
-            ],
-            2: [
-                ["gecko", "firefox"],
-                ["chrome", "safari"],
-                ["webkit", "safari"]
-            ],
-            3: [
-                ["chrome", "safari", "edge"],
-                ["webkit", "chrome", "safari"]
-            ]
-        }
-
-        # Rendering Engines with versions
-        self.rendering_engines = {
-            "chrome_webkit": "AppleWebKit/537.36",
-            "safari_webkit": "AppleWebKit/605.1.15",
-            "gecko": [  # Added Gecko versions
-                "Gecko/20100101",
-                "Gecko/20100101",  # Firefox usually uses this constant version
-                "Gecko/2010010",
-            ]
-        }
-
-        # Browser Versions
-        self.chrome_versions = [
-            "Chrome/119.0.6045.199",
-            "Chrome/118.0.5993.117",
-            "Chrome/117.0.5938.149",
-            "Chrome/116.0.5845.187",
-            "Chrome/115.0.5790.171",
-        ]
-
-        self.edge_versions = [
-            "Edg/119.0.2151.97",
-            "Edg/118.0.2088.76",
-            "Edg/117.0.2045.47",
-            "Edg/116.0.1938.81",
-            "Edg/115.0.1901.203",
-        ]
-
-        self.safari_versions = [
-            "Safari/537.36",  # For Chrome-based
-            "Safari/605.1.15",
-            "Safari/604.1",
-            "Safari/602.1",
-            "Safari/601.5.17",
-        ]
-
-        # Added Firefox versions
-        self.firefox_versions = [
-            "Firefox/119.0",
-            "Firefox/118.0.2",
-            "Firefox/117.0.1",
-            "Firefox/116.0",
-            "Firefox/115.0.3",
-            "Firefox/114.0.2",
-            "Firefox/113.0.1",
-            "Firefox/112.0",
-            "Firefox/111.0.1",
-            "Firefox/110.0",
-        ]
-
-    def get_browser_stack(self, num_browsers: int = 1) -> List[str]:
-        """Get a valid combination of browser versions"""
-        if num_browsers not in self.browser_combinations:
-            raise ValueError(f"Unsupported number of browsers: {num_browsers}")
-        
-        combination = random.choice(self.browser_combinations[num_browsers])
-        browser_stack = []
-        
-        for browser in combination:
-            if browser == "chrome":
-                browser_stack.append(random.choice(self.chrome_versions))
-            elif browser == "firefox":
-                browser_stack.append(random.choice(self.firefox_versions))
-            elif browser == "safari":
-                browser_stack.append(random.choice(self.safari_versions))
-            elif browser == "edge":
-                browser_stack.append(random.choice(self.edge_versions))
-            elif browser == "gecko":
-                browser_stack.append(random.choice(self.rendering_engines["gecko"]))
-            elif browser == "webkit":
-                browser_stack.append(self.rendering_engines["chrome_webkit"])
-        
-        return browser_stack
-
-    def generate(self, 
-                device_type: Optional[Literal['desktop', 'mobile']] = None,
-                os_type: Optional[str] = None,
-                device_brand: Optional[str] = None,
-                browser_type: Optional[Literal['chrome', 'edge', 'safari', 'firefox']] = None,
-                num_browsers: int = 3) -> str:
-        """
-        Generate a random user agent with specified constraints.
-        
-        Args:
-            device_type: 'desktop' or 'mobile'
-            os_type: 'windows', 'macos', 'linux', 'android', 'ios'
-            device_brand: Specific device brand
-            browser_type: 'chrome', 'edge', 'safari', or 'firefox'
-            num_browsers: Number of browser specifications (1-3)
-        """
-        # Get platform string
-        platform = self.get_random_platform(device_type, os_type, device_brand)
-        
-        # Start with Mozilla
-        components = ["Mozilla/5.0", platform]
-        
-        # Add browser stack
-        browser_stack = self.get_browser_stack(num_browsers)
-        
-        # Add appropriate legacy token based on browser stack
-        if "Firefox" in str(browser_stack):
-            components.append(random.choice(self.rendering_engines["gecko"]))
-        elif "Chrome" in str(browser_stack) or "Safari" in str(browser_stack):
-            components.append(self.rendering_engines["chrome_webkit"])
-            components.append("(KHTML, like Gecko)")
-        
-        # Add browser versions
-        components.extend(browser_stack)
-        
-        return " ".join(components)
-
-    def generate_with_client_hints(self, **kwargs) -> Tuple[str, str]:
-        """Generate both user agent and matching client hints"""
-        user_agent = self.generate(**kwargs)
-        client_hints = self.generate_client_hints(user_agent)
-        return user_agent, client_hints
-
-    def get_random_platform(self, device_type, os_type, device_brand):
-        """Helper method to get random platform based on constraints"""
-        platforms = self.desktop_platforms if device_type == 'desktop' else \
-                   self.mobile_platforms if device_type == 'mobile' else \
-                   {**self.desktop_platforms, **self.mobile_platforms}
-        
-        if os_type:
-            for platform_group in [self.desktop_platforms, self.mobile_platforms]:
-                if os_type in platform_group:
-                    platforms = {os_type: platform_group[os_type]}
-                    break
-        
-        os_key = random.choice(list(platforms.keys()))
-        if device_brand and device_brand in platforms[os_key]:
-            return platforms[os_key][device_brand]
-        return random.choice(list(platforms[os_key].values()))
-
-    def parse_user_agent(self, user_agent: str) -> Dict[str, str]:
-        """Parse a user agent string to extract browser and version information"""
-        browsers = {
-            'chrome': r'Chrome/(\d+)',
-            'edge': r'Edg/(\d+)',
-            'safari': r'Version/(\d+)',
-            'firefox': r'Firefox/(\d+)'
-        }
-        
-        result = {}
-        for browser, pattern in browsers.items():
-            match = re.search(pattern, user_agent)
-            if match:
-                result[browser] = match.group(1)
-        
-        return result
-
-    def generate_client_hints(self, user_agent: str) -> str:
-        """Generate Sec-CH-UA header value based on user agent string"""
-        browsers = self.parse_user_agent(user_agent)
-        
-        # Client hints components
-        hints = []
-        
-        # Handle different browser combinations
-        if 'chrome' in browsers:
-            hints.append(f'"Chromium";v="{browsers["chrome"]}"')
-            hints.append('"Not_A Brand";v="8"')
-            
-            if 'edge' in browsers:
-                hints.append(f'"Microsoft Edge";v="{browsers["edge"]}"')
-            else:
-                hints.append(f'"Google Chrome";v="{browsers["chrome"]}"')
-                
-        elif 'firefox' in browsers:
-            # Firefox doesn't typically send Sec-CH-UA
-            return '""'
-            
-        elif 'safari' in browsers:
-            # Safari's format for client hints
-            hints.append(f'"Safari";v="{browsers["safari"]}"')
-            hints.append('"Not_A Brand";v="8"')
-        
-        return ', '.join(hints)
-
-# Example usage:
-if __name__ == "__main__":
-    generator = UserAgentGenerator()
-    print(generator.generate())
-    
-    print("\nSingle browser (Chrome):")
-    print(generator.generate(num_browsers=1, browser_type='chrome'))
-    
-    print("\nTwo browsers (Gecko/Firefox):")
-    print(generator.generate(num_browsers=2))
-    
-    print("\nThree browsers (Chrome/Safari/Edge):")
-    print(generator.generate(num_browsers=3))
-    
-    print("\nFirefox on Linux:")
-    print(generator.generate(
-        device_type='desktop',
-        os_type='linux',
-        browser_type='firefox',
-        num_browsers=2
-    ))
-    
-    print("\nChrome/Safari/Edge on Windows:")
-    print(generator.generate(
-        device_type='desktop',
-        os_type='windows',
-        num_browsers=3
-    ))

crawl4ai/utils.py

@@ -17,154 +17,10 @@ from requests.exceptions import InvalidSchema
 import hashlib
 from typing import Optional, Tuple, Dict, Any
 import xxhash
-from colorama import Fore, Style, init
-import textwrap
 
-from .html2text import HTML2Text
-class CustomHTML2Text(HTML2Text):
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.inside_pre = False
-        self.inside_code = False
-        self.preserve_tags = set()  # Set of tags to preserve
-        self.current_preserved_tag = None
-        self.preserved_content = []
-        self.preserve_depth = 0
-        
-        # Configuration options
-        self.skip_internal_links = False
-        self.single_line_break = False
-        self.mark_code = False
-        self.include_sup_sub = False
-        self.body_width = 0
-        self.ignore_mailto_links = True
-        self.ignore_links = False
-        self.escape_backslash = False
-        self.escape_dot = False
-        self.escape_plus = False
-        self.escape_dash = False
-        self.escape_snob = False
-
-    def update_params(self, **kwargs):
-        """Update parameters and set preserved tags."""
-        for key, value in kwargs.items():
-            if key == 'preserve_tags':
-                self.preserve_tags = set(value)
-            else:
-                setattr(self, key, value)
-
-    def handle_tag(self, tag, attrs, start):
-        # Handle preserved tags
-        if tag in self.preserve_tags:
-            if start:
-                if self.preserve_depth == 0:
-                    self.current_preserved_tag = tag
-                    self.preserved_content = []
-                    # Format opening tag with attributes
-                    attr_str = ''.join(f' {k}="{v}"' for k, v in attrs.items() if v is not None)
-                    self.preserved_content.append(f'<{tag}{attr_str}>')
-                self.preserve_depth += 1
-                return
-            else:
-                self.preserve_depth -= 1
-                if self.preserve_depth == 0:
-                    self.preserved_content.append(f'</{tag}>')
-                    # Output the preserved HTML block with proper spacing
-                    preserved_html = ''.join(self.preserved_content)
-                    self.o('\n' + preserved_html + '\n')
-                    self.current_preserved_tag = None
-                return
-
-        # If we're inside a preserved tag, collect all content
-        if self.preserve_depth > 0:
-            if start:
-                # Format nested tags with attributes
-                attr_str = ''.join(f' {k}="{v}"' for k, v in attrs.items() if v is not None)
-                self.preserved_content.append(f'<{tag}{attr_str}>')
-            else:
-                self.preserved_content.append(f'</{tag}>')
-            return
-
-        # Handle pre tags
-        if tag == 'pre':
-            if start:
-                self.o('```\n')
-                self.inside_pre = True
-            else:
-                self.o('\n```')
-                self.inside_pre = False
-        # elif tag in ["h1", "h2", "h3", "h4", "h5", "h6"]:
-        #     pass
-        else:
-            super().handle_tag(tag, attrs, start)
-
-    def handle_data(self, data, entity_char=False):
-        """Override handle_data to capture content within preserved tags."""
-        if self.preserve_depth > 0:
-            self.preserved_content.append(data)
-            return
-        super().handle_data(data, entity_char)
 class InvalidCSSSelectorError(Exception):
     pass
 
-
-def create_box_message(
-   message: str, 
-   type: str = "info", 
-   width: int = 80, 
-   add_newlines: bool = True,
-   double_line: bool = False
-) -> str:
-   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, "×"),
-   }
-   
-   border_color, text_color, prefix = styles.get(type.lower(), styles["info"])
-   
-   # Define box characters based on line style
-   box_chars = {
-       "single": ("─", "│", "┌", "┐", "└", "┘"),
-       "double": ("═", "║", "╔", "╗", "╚", "╝")
-   }
-   line_style = "double" if double_line else "single"
-   h_line, v_line, tl, tr, bl, br = box_chars[line_style]
-   
-   # Process lines with lighter text color
-   formatted_lines = []
-   raw_lines = message.split('\n')
-   
-   if raw_lines:
-       first_line = f"{prefix} {raw_lines[0].strip()}"
-       wrapped_first = textwrap.fill(first_line, width=width-4)
-       formatted_lines.extend(wrapped_first.split('\n'))
-       
-       for line in raw_lines[1:]:
-           if line.strip():
-               wrapped = textwrap.fill(f"  {line.strip()}", width=width-4)
-               formatted_lines.extend(wrapped.split('\n'))
-           else:
-               formatted_lines.append("")
-   
-   # 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}{v_line}{text_color} {line:<{width-2}}{border_color}{v_line}" for line in formatted_lines],
-       f"{border_color}{bl}{horizontal_line}{br}{Style.RESET_ALL}"
-   ]
-   
-   result = "\n".join(box)
-   if add_newlines:
-       result = f"\n{result}\n"
-   
-   return result
-
 def calculate_semaphore_count():
     cpu_count = os.cpu_count()
     memory_gb = get_system_memory() / (1024 ** 3)  # Convert to GB
@@ -289,17 +145,12 @@ def sanitize_html(html):
 def sanitize_input_encode(text: str) -> str:
     """Sanitize input to handle potential encoding issues."""
     try:
-        try:
-            if not text:
-                return ''
-            # Attempt to encode and decode as UTF-8 to handle potential encoding issues
-            return text.encode('utf-8', errors='ignore').decode('utf-8')
-        except UnicodeEncodeError as e:
-            print(f"Warning: Encoding issue detected. Some characters may be lost. Error: {e}")
-            # Fall back to ASCII if UTF-8 fails
-            return text.encode('ascii', errors='ignore').decode('ascii')
-    except Exception as e:
-        raise ValueError(f"Error sanitizing input: {str(e)}") from e
+        # Attempt to encode and decode as UTF-8 to handle potential encoding issues
+        return text.encode('utf-8', errors='ignore').decode('utf-8')
+    except UnicodeEncodeError as e:
+        print(f"Warning: Encoding issue detected. Some characters may be lost. Error: {e}")
+        # Fall back to ASCII if UTF-8 fails
+        return text.encode('ascii', errors='ignore').decode('ascii')
 
 def escape_json_string(s):
     """
@@ -1140,54 +991,9 @@ def wrap_text(draw, text, font, max_width):
     return '\n'.join(lines)
 
 def format_html(html_string):
-    soup = BeautifulSoup(html_string, 'lxml.parser')
+    soup = BeautifulSoup(html_string, 'html.parser')
     return soup.prettify()
 
-def fast_format_html(html_string):
-    """
-    A fast HTML formatter that uses string operations instead of parsing.
-    
-    Args:
-        html_string (str): The HTML string to format
-        
-    Returns:
-        str: The formatted HTML string
-    """
-    # Initialize variables
-    indent = 0
-    indent_str = "  "  # Two spaces for indentation
-    formatted = []
-    in_content = False
-    
-    # Split by < and > to separate tags and content
-    parts = html_string.replace('>', '>\n').replace('<', '\n<').split('\n')
-    
-    for part in parts:
-        if not part.strip():
-            continue
-            
-        # Handle closing tags
-        if part.startswith('</'):
-            indent -= 1
-            formatted.append(indent_str * indent + part)
-            
-        # Handle self-closing tags
-        elif part.startswith('<') and part.endswith('/>'):
-            formatted.append(indent_str * indent + part)
-            
-        # Handle opening tags
-        elif part.startswith('<'):
-            formatted.append(indent_str * indent + part)
-            indent += 1
-            
-        # Handle content between tags
-        else:
-            content = part.strip()
-            if content:
-                formatted.append(indent_str * indent + content)
-    
-    return '\n'.join(formatted)
-
 def normalize_url(href, base_url):
     """Normalize URLs to ensure consistent format"""
     from urllib.parse import urljoin, urlparse

crawl4ai/web_crawler.py

@@ -10,7 +10,7 @@ from .extraction_strategy import *
 from .crawler_strategy import *
 from typing import List
 from concurrent.futures import ThreadPoolExecutor
-from .content_scraping_strategy import WebScrapingStrategy
+from .content_scrapping_strategy import WebScrapingStrategy
 from .config import *
 import warnings
 import json

deploy/railway/README.md

@@ -0,0 +1,19 @@
+# Railway Deployment
+
+## Quick Deploy
+[![Deploy on Railway](https://railway.app/button.svg)](https://railway.app/template/crawl4ai)
+
+## Manual Setup
+1. Fork this repository
+2. Create a new Railway project 
+3. Configure environment variables:
+   - `INSTALL_TYPE`: basic or all
+   - `ENABLE_GPU`: true/false
+4. Deploy!
+
+## Configuration
+See `railway.toml` for:
+- Memory limits
+- Health checks
+- Restart policies
+- Scaling options

deploy/railway/button.json

@@ -0,0 +1,33 @@
+{
+    "name": "Crawl4AI",
+    "description": "LLM Friendly Web Crawler & Scraper",
+    "render": {
+      "dockerfile": {
+        "path": "Dockerfile"
+      }
+    },
+    "env": [
+      {
+        "key": "INSTALL_TYPE",
+        "description": "Installation type (basic/all)",
+        "default": "basic",
+        "required": true
+      },
+      {
+        "key": "ENABLE_GPU",
+        "description": "Enable GPU support",
+        "default": "false",
+        "required": false
+      }
+    ],
+    "services": [
+      {
+        "name": "web",
+        "dockerfile": "./Dockerfile",
+        "healthcheck": {
+          "path": "/health",
+          "port": 11235
+        }
+      }
+    ]
+  }

deploy/railway/railway.toml

@@ -0,0 +1,18 @@
+# railway.toml
+[build]
+builder = "DOCKERFILE"
+dockerfilePath = "Dockerfile"
+
+[deploy]
+startCommand = "uvicorn main:app --host 0.0.0.0 --port $PORT"
+healthcheckPath = "/health"
+restartPolicyType = "ON_FAILURE"
+restartPolicyMaxRetries = 3
+
+[deploy.memory]
+soft = 2048 # 2GB min for Playwright
+hard = 4096 # 4GB max
+
+[deploy.scaling]
+min = 1
+max = 1

docker-compose.hub.yml

@@ -0,0 +1,27 @@
+services:
+  crawl4ai:
+    image: unclecode/crawl4ai:basic  # Pull image from Docker Hub
+    ports:
+      - "11235:11235"  # FastAPI server
+      - "8000:8000"    # Alternative port
+      - "9222:9222"    # Browser debugging
+      - "8080:8080"    # Additional port
+    environment:
+      - CRAWL4AI_API_TOKEN=${CRAWL4AI_API_TOKEN:-}  # Optional API token
+      - OPENAI_API_KEY=${OPENAI_API_KEY:-}          # Optional OpenAI API key
+      - CLAUDE_API_KEY=${CLAUDE_API_KEY:-}          # Optional Claude API key
+    volumes:
+      - /dev/shm:/dev/shm  # Shared memory for browser operations
+    deploy:
+      resources:
+        limits:
+          memory: 4G
+        reservations:
+          memory: 1G
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:11235/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s

docker-compose.local.yml

@@ -0,0 +1,33 @@
+services:
+  crawl4ai:
+    build:
+      context: .
+      dockerfile: Dockerfile
+      args:
+        PYTHON_VERSION: 3.10
+        INSTALL_TYPE: all
+        ENABLE_GPU: false
+    ports:
+      - "11235:11235"  # FastAPI server
+      - "8000:8000"    # Alternative port
+      - "9222:9222"    # Browser debugging
+      - "8080:8080"    # Additional port
+    environment:
+      - CRAWL4AI_API_TOKEN=${CRAWL4AI_API_TOKEN:-}  # Optional API token
+      - OPENAI_API_KEY=${OPENAI_API_KEY:-}          # Optional OpenAI API key
+      - CLAUDE_API_KEY=${CLAUDE_API_KEY:-}          # Optional Claude API key
+    volumes:
+      - /dev/shm:/dev/shm  # Shared memory for browser operations
+    deploy:
+      resources:
+        limits:
+          memory: 4G
+        reservations:
+          memory: 1G
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:11235/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s

docker-compose.yml

@@ -1,46 +1,13 @@
 services:
-  # Local build services for different platforms
-  crawl4ai-amd64:
+  crawl4ai:
     build:
       context: .
       dockerfile: Dockerfile
       args:
-        PYTHON_VERSION: "3.10"
-        INSTALL_TYPE: ${INSTALL_TYPE:-basic}
+        PYTHON_VERSION: 3.10
+        INSTALL_TYPE: all
         ENABLE_GPU: false
-      platforms:
-        - linux/amd64
-    profiles: ["local-amd64"]
-    extends: &base-config
-      file: docker-compose.yml
-      service: base-config
-
-  crawl4ai-arm64:
-    build:
-      context: .
-      dockerfile: Dockerfile
-      args:
-        PYTHON_VERSION: "3.10"
-        INSTALL_TYPE: ${INSTALL_TYPE:-basic}
-        ENABLE_GPU: false
-      platforms:
-        - linux/arm64
-    profiles: ["local-arm64"]
-    extends: *base-config
-
-  # Hub services for different platforms and versions
-  crawl4ai-hub-amd64:
-    image: unclecode/crawl4ai:${VERSION:-basic}-amd64
-    profiles: ["hub-amd64"]
-    extends: *base-config
-
-  crawl4ai-hub-arm64:
-    image: unclecode/crawl4ai:${VERSION:-basic}-arm64
-    profiles: ["hub-arm64"]
-    extends: *base-config
-
-  # Base configuration to be extended
-  base-config:
+    profiles: ["local"]
     ports:
       - "11235:11235"
       - "8000:8000"
@@ -64,4 +31,32 @@ services:
       interval: 30s
       timeout: 10s
       retries: 3
-      start_period: 40s
+      start_period: 40s
+
+  crawl4ai-hub:
+    image: unclecode/crawl4ai:basic
+    profiles: ["hub"]
+    ports:
+      - "11235:11235"
+      - "8000:8000"
+      - "9222:9222"
+      - "8080:8080"
+    environment:
+      - CRAWL4AI_API_TOKEN=${CRAWL4AI_API_TOKEN:-}
+      - OPENAI_API_KEY=${OPENAI_API_KEY:-}
+      - CLAUDE_API_KEY=${CLAUDE_API_KEY:-}
+    volumes:
+      - /dev/shm:/dev/shm
+    deploy:
+      resources:
+        limits:
+          memory: 4G
+        reservations:
+          memory: 1G
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:11235/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s

docs/examples/docker_example.py

@@ -78,20 +78,20 @@ def test_docker_deployment(version="basic"):
             time.sleep(5)
     
     # Test cases based on version
+    # test_basic_crawl(tester)
+    # test_basic_crawl(tester)
+    # test_basic_crawl_sync(tester)
     test_basic_crawl_direct(tester)
-    test_basic_crawl(tester)
-    test_basic_crawl(tester)
-    test_basic_crawl_sync(tester)
     
-    if version in ["full", "transformer"]:
-        test_cosine_extraction(tester)
+    # if version in ["full", "transformer"]:
+    #     test_cosine_extraction(tester)
 
-    test_js_execution(tester)
-    test_css_selector(tester)
-    test_structured_extraction(tester)
-    test_llm_extraction(tester)
-    test_llm_with_ollama(tester)
-    test_screenshot(tester)
+    # test_js_execution(tester)
+    # test_css_selector(tester)
+    # test_structured_extraction(tester)
+    # test_llm_extraction(tester)
+    # test_llm_with_ollama(tester)
+    # test_screenshot(tester)
     
 
 def test_basic_crawl(tester: Crawl4AiTester):

docs/examples/quickstart_async.py

@@ -13,9 +13,7 @@ import re
 from typing import Dict, List
 from bs4 import BeautifulSoup
 from pydantic import BaseModel, Field
-from crawl4ai import AsyncWebCrawler, CacheMode
-from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
-from crawl4ai.content_filter_strategy import BM25ContentFilter, PruningContentFilter
+from crawl4ai import AsyncWebCrawler
 from crawl4ai.extraction_strategy import (
     JsonCssExtractionStrategy,
     LLMExtractionStrategy,
@@ -32,7 +30,7 @@ print("Website: https://crawl4ai.com")
 async def simple_crawl():
     print("\n--- Basic Usage ---")
     async with AsyncWebCrawler(verbose=True) as crawler:
-        result = await crawler.arun(url="https://www.nbcnews.com/business", cache_mode= CacheMode.BYPASS)
+        result = await crawler.arun(url="https://www.nbcnews.com/business")
         print(result.markdown[:500])  # Print first 500 characters
 
 async def simple_example_with_running_js_code():
@@ -53,7 +51,7 @@ async def simple_example_with_running_js_code():
             url="https://www.nbcnews.com/business",
             js_code=js_code,
             # wait_for=wait_for,
-            cache_mode=CacheMode.BYPASS,
+            bypass_cache=True,
         )
         print(result.markdown[:500])  # Print first 500 characters
 
@@ -63,7 +61,7 @@ async def simple_example_with_css_selector():
         result = await crawler.arun(
             url="https://www.nbcnews.com/business",
             css_selector=".wide-tease-item__description",
-            cache_mode=CacheMode.BYPASS,
+            bypass_cache=True,
         )
         print(result.markdown[:500])  # Print first 500 characters
 
@@ -76,17 +74,16 @@ async def use_proxy():
     async with AsyncWebCrawler(verbose=True, proxy="http://your-proxy-url:port") as crawler:
         result = await crawler.arun(
             url="https://www.nbcnews.com/business",
-            cache_mode= CacheMode.BYPASS
+            bypass_cache=True
         )
-        if result.success:
-            print(result.markdown[:500])  # Print first 500 characters
+        print(result.markdown[:500])  # Print first 500 characters
 
 async def capture_and_save_screenshot(url: str, output_path: str):
     async with AsyncWebCrawler(verbose=True) as crawler:
         result = await crawler.arun(
             url=url,
             screenshot=True,
-            cache_mode= CacheMode.BYPASS
+            bypass_cache=True
         )
         
         if result.success and result.screenshot:
@@ -135,75 +132,48 @@ async def extract_structured_data_using_llm(provider: str, api_token: str = None
                 {"model_name": "GPT-4", "input_fee": "US$10.00 / 1M tokens", "output_fee": "US$30.00 / 1M tokens"}.""",
                 extra_args=extra_args
             ),
-            cache_mode=CacheMode.BYPASS,
+            bypass_cache=True,
         )
         print(result.extracted_content)
 
 async def extract_structured_data_using_css_extractor():
     print("\n--- Using JsonCssExtractionStrategy for Fast Structured Output ---")
     schema = {
-    "name": "KidoCode Courses",
-    "baseSelector": "section.charge-methodology .w-tab-content > div",
-    "fields": [
-        {
-            "name": "section_title",
-            "selector": "h3.heading-50",
-            "type": "text",
-        },
-        {
-            "name": "section_description",
-            "selector": ".charge-content",
-            "type": "text",
-        },
-        {
-            "name": "course_name",
-            "selector": ".text-block-93",
-            "type": "text",
-        },
-        {
-            "name": "course_description",
-            "selector": ".course-content-text",
-            "type": "text",
-        },
-        {
-            "name": "course_icon",
-            "selector": ".image-92",
-            "type": "attribute",
-            "attribute": "src"
-        }
-    ]
-}
-
-    async with AsyncWebCrawler(
-        headless=True,
-        verbose=True
-    ) as crawler:
-        
-        # Create the JavaScript that handles clicking multiple times
-        js_click_tabs = """
-        (async () => {
-            const tabs = document.querySelectorAll("section.charge-methodology .tabs-menu-3 > div");
-            
-            for(let tab of tabs) {
-                // scroll to the tab
-                tab.scrollIntoView();
-                tab.click();
-                // Wait for content to load and animations to complete
-                await new Promise(r => setTimeout(r, 500));
+        "name": "Coinbase Crypto Prices",
+        "baseSelector": ".cds-tableRow-t45thuk",
+        "fields": [
+            {
+                "name": "crypto",
+                "selector": "td:nth-child(1) h2",
+                "type": "text",
+            },
+            {
+                "name": "symbol",
+                "selector": "td:nth-child(1) p",
+                "type": "text",
+            },
+            {
+                "name": "price",
+                "selector": "td:nth-child(2)",
+                "type": "text",
             }
-        })();
-        """     
+        ],
+    }
 
+    extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)
+
+    async with AsyncWebCrawler(verbose=True) as crawler:
         result = await crawler.arun(
-            url="https://www.kidocode.com/degrees/technology",
-            extraction_strategy=JsonCssExtractionStrategy(schema, verbose=True),
-            js_code=[js_click_tabs],
-            cache_mode=CacheMode.BYPASS
+            url="https://www.coinbase.com/explore",
+            extraction_strategy=extraction_strategy,
+            bypass_cache=True,
         )
 
-        companies = json.loads(result.extracted_content)
-        print(f"Successfully extracted {len(companies)} companies")
-        print(json.dumps(companies[0], indent=2))
+        assert result.success, "Failed to crawl the page"
+
+        news_teasers = json.loads(result.extracted_content)
+        print(f"Successfully extracted {len(news_teasers)} news teasers")
+        print(json.dumps(news_teasers[0], indent=2))
 
 # Advanced Session-Based Crawling with Dynamic Content 🔄
 async def crawl_dynamic_content_pages_method_1():
@@ -243,7 +213,7 @@ async def crawl_dynamic_content_pages_method_1():
                 session_id=session_id,
                 css_selector="li.Box-sc-g0xbh4-0",
                 js=js_next_page if page > 0 else None,
-                cache_mode=CacheMode.BYPASS,
+                bypass_cache=True,
                 js_only=page > 0,
                 headless=False,
             )
@@ -312,7 +282,7 @@ async def crawl_dynamic_content_pages_method_2():
                 extraction_strategy=extraction_strategy,
                 js_code=js_next_page_and_wait if page > 0 else None,
                 js_only=page > 0,
-                cache_mode=CacheMode.BYPASS,
+                bypass_cache=True,
                 headless=False,
             )
 
@@ -373,7 +343,7 @@ async def crawl_dynamic_content_pages_method_3():
                 js_code=js_next_page if page > 0 else None,
                 wait_for=wait_for if page > 0 else None,
                 js_only=page > 0,
-                cache_mode=CacheMode.BYPASS,
+                bypass_cache=True,
                 headless=False,
             )
 
@@ -391,21 +361,21 @@ async def crawl_custom_browser_type():
     # Use Firefox
     start = time.time()
     async with AsyncWebCrawler(browser_type="firefox", verbose=True, headless = True) as crawler:
-        result = await crawler.arun(url="https://www.example.com", cache_mode= CacheMode.BYPASS)
+        result = await crawler.arun(url="https://www.example.com", bypass_cache=True)
         print(result.markdown[:500])
         print("Time taken: ", time.time() - start)
 
     # Use WebKit
     start = time.time()
     async with AsyncWebCrawler(browser_type="webkit", verbose=True, headless = True) as crawler:
-        result = await crawler.arun(url="https://www.example.com", cache_mode= CacheMode.BYPASS)
+        result = await crawler.arun(url="https://www.example.com", bypass_cache=True)
         print(result.markdown[:500])
         print("Time taken: ", time.time() - start)
 
     # Use Chromium (default)
     start = time.time()
     async with AsyncWebCrawler(verbose=True, headless = True) as crawler:
-        result = await crawler.arun(url="https://www.example.com", cache_mode= CacheMode.BYPASS)
+        result = await crawler.arun(url="https://www.example.com", bypass_cache=True)
         print(result.markdown[:500])
         print("Time taken: ", time.time() - start)
 
@@ -414,7 +384,7 @@ async def crawl_with_user_simultion():
         url = "YOUR-URL-HERE"
         result = await crawler.arun(
             url=url,            
-            cache_mode=CacheMode.BYPASS,
+            bypass_cache=True,
             magic = True, # Automatically detects and removes overlays, popups, and other elements that block content
             # simulate_user = True,# Causes a series of random mouse movements and clicks to simulate user interaction
             # override_navigator = True # Overrides the navigator object to make it look like a real user
@@ -438,7 +408,7 @@ async def speed_comparison():
     params={'formats': ['markdown', 'html']}
     )
     end = time.time()
-    print("Firecrawl:")
+    print("Firecrawl (simulated):")
     print(f"Time taken: {end - start:.2f} seconds")
     print(f"Content length: {len(scrape_status['markdown'])} characters")
     print(f"Images found: {scrape_status['markdown'].count('cldnry.s-nbcnews.com')}")
@@ -450,7 +420,7 @@ async def speed_comparison():
         result = await crawler.arun(
             url="https://www.nbcnews.com/business",
             word_count_threshold=0,
-            cache_mode=CacheMode.BYPASS,
+            bypass_cache=True,
             verbose=False,
         )
         end = time.time()
@@ -460,26 +430,6 @@ async def speed_comparison():
         print(f"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}")
         print()
 
-        # Crawl4AI with advanced content filtering
-        start = time.time()
-        result = await crawler.arun(
-            url="https://www.nbcnews.com/business",
-            word_count_threshold=0,
-            markdown_generator=DefaultMarkdownGenerator(
-                content_filter = PruningContentFilter(threshold=0.48, threshold_type="fixed", min_word_threshold=0)
-                # content_filter=BM25ContentFilter(user_query=None, bm25_threshold=1.0)
-            ),
-            cache_mode=CacheMode.BYPASS,
-            verbose=False,
-        )
-        end = time.time()
-        print("Crawl4AI (Markdown Plus):")
-        print(f"Time taken: {end - start:.2f} seconds")
-        print(f"Content length: {len(result.markdown_v2.raw_markdown)} characters")
-        print(f"Fit Markdown: {len(result.markdown_v2.fit_markdown)} characters")
-        print(f"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}")
-        print()
-
         # Crawl4AI with JavaScript execution
         start = time.time()
         result = await crawler.arun(
@@ -488,18 +438,13 @@ async def speed_comparison():
                 "const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();"
             ],
             word_count_threshold=0,
-            cache_mode=CacheMode.BYPASS,
-            markdown_generator=DefaultMarkdownGenerator(
-                content_filter = PruningContentFilter(threshold=0.48, threshold_type="fixed", min_word_threshold=0)
-                # content_filter=BM25ContentFilter(user_query=None, bm25_threshold=1.0)
-            ),
+            bypass_cache=True,
             verbose=False,
         )
         end = time.time()
         print("Crawl4AI (with JavaScript execution):")
         print(f"Time taken: {end - start:.2f} seconds")
         print(f"Content length: {len(result.markdown)} characters")
-        print(f"Fit Markdown: {len(result.markdown_v2.fit_markdown)} characters")
         print(f"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}")
 
     print("\nNote on Speed Comparison:")
@@ -538,7 +483,7 @@ async def generate_knowledge_graph():
         url = "https://paulgraham.com/love.html"
         result = await crawler.arun(
             url=url,
-            cache_mode=CacheMode.BYPASS,
+            bypass_cache=True,
             extraction_strategy=extraction_strategy,
             # magic=True
         )
@@ -547,50 +492,19 @@ async def generate_knowledge_graph():
             f.write(result.extracted_content)
 
 async def fit_markdown_remove_overlay():
-    async with AsyncWebCrawler(
-            headless=True,  # Set to False to see what is happening
-            verbose=True,
-            user_agent_mode="random",
-            user_agent_generator_config={
-                "device_type": "mobile",
-                "os_type": "android"
-            },
-    ) as crawler:
+    async with AsyncWebCrawler(headless = False) as crawler:
+        url = "https://janineintheworld.com/places-to-visit-in-central-mexico"
         result = await crawler.arun(
-            url='https://www.kidocode.com/degrees/technology',
-            cache_mode=CacheMode.BYPASS,
-            markdown_generator=DefaultMarkdownGenerator(
-                content_filter=PruningContentFilter(threshold=0.48, threshold_type="fixed", min_word_threshold=0),
-                options={
-                    "ignore_links": True
-                }
-            ),
-            # markdown_generator=DefaultMarkdownGenerator(
-            #     content_filter=BM25ContentFilter(user_query=None, bm25_threshold=1.0),
-            #     options={
-            #         "ignore_links": True
-            #     }
-            # ),
+            url=url,
+            bypass_cache=True,
+            word_count_threshold = 10,
+            remove_overlay_elements=True,
+            screenshot = True
         )
-        
-        if result.success:
-            print(len(result.markdown_v2.raw_markdown))
-            print(len(result.markdown_v2.markdown_with_citations))
-            print(len(result.markdown_v2.fit_markdown))
-            
-            # Save clean html
-            with open(os.path.join(__location__, "output/cleaned_html.html"), "w") as f:
-                f.write(result.cleaned_html)
-            
-            with open(os.path.join(__location__, "output/output_raw_markdown.md"), "w") as f:
-                f.write(result.markdown_v2.raw_markdown)
-                
-            with open(os.path.join(__location__, "output/output_markdown_with_citations.md"), "w") as f:
-                f.write(result.markdown_v2.markdown_with_citations) 
-                
-            with open(os.path.join(__location__, "output/output_fit_markdown.md"), "w") as f:   
-                f.write(result.markdown_v2.fit_markdown)
-        
+        # Save markdown to file
+        with open(os.path.join(__location__, "mexico_places.md"), "w") as f:
+            f.write(result.fit_markdown)
+
     print("Done")
 
 
@@ -598,25 +512,25 @@ async def main():
     await simple_crawl()
     await simple_example_with_running_js_code()
     await simple_example_with_css_selector()
-    # await use_proxy()
+    await use_proxy()
     await capture_and_save_screenshot("https://www.example.com", os.path.join(__location__, "tmp/example_screenshot.jpg"))
     await extract_structured_data_using_css_extractor()
 
     # LLM extraction examples
-    # await extract_structured_data_using_llm()
-    # await extract_structured_data_using_llm("huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct", os.getenv("HUGGINGFACE_API_KEY"))
-    # await extract_structured_data_using_llm("ollama/llama3.2")    
+    await extract_structured_data_using_llm()
+    await extract_structured_data_using_llm("huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct", os.getenv("HUGGINGFACE_API_KEY"))
     await extract_structured_data_using_llm("openai/gpt-4o", os.getenv("OPENAI_API_KEY"))
+    await extract_structured_data_using_llm("ollama/llama3.2")    
 
     # You always can pass custom headers to the extraction strategy
-    # custom_headers = {
-    #     "Authorization": "Bearer your-custom-token",
-    #     "X-Custom-Header": "Some-Value"
-    # }
-    # await extract_structured_data_using_llm(extra_headers=custom_headers)
+    custom_headers = {
+        "Authorization": "Bearer your-custom-token",
+        "X-Custom-Header": "Some-Value"
+    }
+    await extract_structured_data_using_llm(extra_headers=custom_headers)
     
-    await crawl_dynamic_content_pages_method_1()
-    await crawl_dynamic_content_pages_method_2()
+    # await crawl_dynamic_content_pages_method_1()
+    # await crawl_dynamic_content_pages_method_2()
     await crawl_dynamic_content_pages_method_3()
     
     await crawl_custom_browser_type()

docs/examples/v0.3.74.overview.py

@@ -52,7 +52,34 @@ async def download_example():
         else:
             print("\nNo files were downloaded")
 
-# 2. Local File and Raw HTML Processing Example
+# 2. Content Filtering with BM25 Example
+async def content_filtering_example():
+    """Example of using the new BM25 content filtering"""
+    async with AsyncWebCrawler(verbose=True) as crawler:
+        # Create filter with custom query for OpenAI's blog
+        content_filter = BM25ContentFilter(
+            # user_query="Investment and fundraising",
+            # user_query="Robotic",
+            bm25_threshold=1.0
+        )
+        
+        result = await crawler.arun(
+            url="https://techcrunch.com/",
+            content_filter=content_filter,
+            cache_mode=CacheMode.BYPASS
+        )
+        
+        print(f"Filtered content: {len(result.fit_markdown)}")
+        print(f"Filtered content: {result.fit_markdown}")
+        
+        # Save html 
+        with open(os.path.join(__data__, "techcrunch.html"), "w") as f:
+            f.write(result.fit_html)
+        
+        with open(os.path.join(__data__, "filtered_content.md"), "w") as f:
+            f.write(result.fit_markdown)
+
+# 3. Local File and Raw HTML Processing Example
 async def local_and_raw_html_example():
     """Example of processing local files and raw HTML"""
     # Create a sample HTML file
@@ -88,68 +115,6 @@ async def local_and_raw_html_example():
         print("Local file content:", local_result.markdown)
         print("\nRaw HTML content:", raw_result.markdown)
 
-# 3. Enhanced Markdown Generation Example
-async def markdown_generation_example():
-    """Example of enhanced markdown generation with citations and LLM-friendly features"""
-    async with AsyncWebCrawler(verbose=True) as crawler:
-        # Create a content filter (optional)
-        content_filter = BM25ContentFilter(
-            # user_query="History and cultivation",
-            bm25_threshold=1.0
-        )
-        
-        result = await crawler.arun(
-            url="https://en.wikipedia.org/wiki/Apple",
-            css_selector="main div#bodyContent",
-            content_filter=content_filter,
-            cache_mode=CacheMode.BYPASS
-        )
-        
-        from crawl4ai import AsyncWebCrawler
-        from crawl4ai.content_filter_strategy import BM25ContentFilter
-        
-        result = await crawler.arun(
-            url="https://en.wikipedia.org/wiki/Apple",
-            css_selector="main div#bodyContent",
-            content_filter=BM25ContentFilter()
-        )
-        print(result.markdown_v2.fit_markdown)
-        
-        print("\nMarkdown Generation Results:")
-        print(f"1. Original markdown length: {len(result.markdown)}")
-        print(f"2. New markdown versions (markdown_v2):")
-        print(f"   - Raw markdown length: {len(result.markdown_v2.raw_markdown)}")
-        print(f"   - Citations markdown length: {len(result.markdown_v2.markdown_with_citations)}")
-        print(f"   - References section length: {len(result.markdown_v2.references_markdown)}")
-        if result.markdown_v2.fit_markdown:
-            print(f"   - Filtered markdown length: {len(result.markdown_v2.fit_markdown)}")
-        
-        # Save examples to files
-        output_dir = os.path.join(__data__, "markdown_examples")
-        os.makedirs(output_dir, exist_ok=True)
-        
-        # Save different versions
-        with open(os.path.join(output_dir, "1_raw_markdown.md"), "w") as f:
-            f.write(result.markdown_v2.raw_markdown)
-            
-        with open(os.path.join(output_dir, "2_citations_markdown.md"), "w") as f:
-            f.write(result.markdown_v2.markdown_with_citations)
-            
-        with open(os.path.join(output_dir, "3_references.md"), "w") as f:
-            f.write(result.markdown_v2.references_markdown)
-            
-        if result.markdown_v2.fit_markdown:
-            with open(os.path.join(output_dir, "4_filtered_markdown.md"), "w") as f:
-                f.write(result.markdown_v2.fit_markdown)
-                
-        print(f"\nMarkdown examples saved to: {output_dir}")
-        
-        # Show a sample of citations and references
-        print("\nSample of markdown with citations:")
-        print(result.markdown_v2.markdown_with_citations[:500] + "...\n")
-        print("Sample of references:")
-        print('\n'.join(result.markdown_v2.references_markdown.split('\n')[:10]) + "...")
-
 # 4. Browser Management Example
 async def browser_management_example():
     """Example of using enhanced browser management features"""
@@ -243,13 +208,9 @@ async def api_example():
                     headers=headers
                 ) as status_response:
                     result = await status_response.json()
-                    print(f"Task status: {result['status']}")
+                    print(f"Task result: {result}")
                     
                     if result["status"] == "completed":
-                        print("Task completed!")
-                        print("Results:")
-                        news = json.loads(result["results"][0]['extracted_content'])
-                        print(json.dumps(news[:4], indent=2))
                         break
                     else:
                         await asyncio.sleep(1)
@@ -259,15 +220,15 @@ async def main():
     # print("Running Crawl4AI feature examples...")
     
     # print("\n1. Running Download Example:")
-    # await download_example()
+    await download_example()
     
-    # print("\n2. Running Markdown Generation Example:")
-    # await markdown_generation_example()
+    # print("\n2. Running Content Filtering Example:")
+    await content_filtering_example()
     
-    # # print("\n3. Running Local and Raw HTML Example:")
-    # await local_and_raw_html_example()
+    # print("\n3. Running Local and Raw HTML Example:")
+    await local_and_raw_html_example()
     
-    # # print("\n4. Running Browser Management Example:")
+    # print("\n4. Running Browser Management Example:")
     await browser_management_example()
     
     # print("\n5. Running API Example:")

docs/md_v2/advanced/hooks-auth.md

@@ -18,7 +18,7 @@ Let's see how we can customize the AsyncWebCrawler using hooks! In this example,
 import asyncio
 from crawl4ai import AsyncWebCrawler
 from crawl4ai.async_crawler_strategy import AsyncPlaywrightCrawlerStrategy
-from playwright.async_api import Page, Browser, BrowserContext
+from playwright.async_api import Page, Browser
 
 async def on_browser_created(browser: Browser):
     print("[HOOK] on_browser_created")
@@ -71,11 +71,7 @@ from crawl4ai.async_crawler_strategy import AsyncPlaywrightCrawlerStrategy
 async def main():
     print("\n🔗 Using Crawler Hooks: Let's see how we can customize the AsyncWebCrawler using hooks!")
     
-    initial_cookies = [
-        {"name": "sessionId", "value": "abc123", "domain": ".example.com"},
-        {"name": "userId", "value": "12345", "domain": ".example.com"}
-    ]
-    crawler_strategy = AsyncPlaywrightCrawlerStrategy(verbose=True, cookies=initial_cookies)
+    crawler_strategy = AsyncPlaywrightCrawlerStrategy(verbose=True)
     crawler_strategy.set_hook('on_browser_created', on_browser_created)
     crawler_strategy.set_hook('before_goto', before_goto)
     crawler_strategy.set_hook('after_goto', after_goto)

docs/md_v2/advanced/managed_browser.md

@@ -4,59 +4,7 @@ This guide explains how to use content filtering strategies in Crawl4AI to extra
 
 ## Relevance Content Filter
 
-The `RelevanceContentFilter` is an abstract class that provides a common interface for content filtering strategies. Specific filtering algorithms, like `PruningContentFilter` or `BM25ContentFilter`, inherit from this class and implement the `filter_content` method. This method takes the HTML content as input and returns a list of filtered text blocks.
-
-
-## Pruning Content Filter
-
-The `PruningContentFilter` is a tree-shaking algorithm that analyzes the HTML DOM structure and removes less relevant nodes based on various metrics like text density, link density, and tag importance. It evaluates each node using a composite scoring system and "prunes" nodes that fall below a certain threshold.
-
-### Usage
-
-```python
-from crawl4ai import AsyncWebCrawler
-from crawl4ai.content_filter_strategy import PruningContentFilter
-
-async def filter_content(url):
-    async with AsyncWebCrawler() as crawler:
-        content_filter = PruningContentFilter(
-            min_word_threshold=5,
-            threshold_type='dynamic',
-            threshold=0.45
-        )
-        result = await crawler.arun(url=url, extraction_strategy=content_filter, fit_markdown=True)
-        if result.success:
-            print(f"Cleaned Markdown:\n{result.fit_markdown}")
-```
-
-### Parameters
-
-- **`min_word_threshold`**: (Optional) Minimum number of words a node must contain to be considered relevant. Nodes with fewer words are automatically pruned.
-
-- **`threshold_type`**: (Optional, default 'fixed') Controls how pruning thresholds are calculated:
-  - `'fixed'`: Uses a constant threshold value for all nodes
-  - `'dynamic'`: Adjusts threshold based on node characteristics like tag importance and text/link ratios
-
-- **`threshold`**: (Optional, default 0.48) Base threshold value for node pruning:
-  - For fixed threshold: Nodes scoring below this value are removed
-  - For dynamic threshold: This value is adjusted based on node properties
-
-### How It Works
-
-The pruning algorithm evaluates each node using multiple metrics:
-- Text density: Ratio of actual text to overall node content
-- Link density: Proportion of text within links
-- Tag importance: Weight based on HTML tag type (e.g., article, p, div)
-- Content quality: Metrics like text length and structural importance
-
-Nodes scoring below the threshold are removed, effectively "shaking" less relevant content from the DOM tree. This results in a cleaner document containing only the most relevant content blocks.
-
-The algorithm is particularly effective for:
-- Removing boilerplate content
-- Eliminating navigation menus and sidebars
-- Preserving main article content
-- Maintaining document structure while removing noise
-
+The `RelevanceContentFilter` is an abstract class that provides a common interface for content filtering strategies. Specific filtering algorithms, like `BM25ContentFilter`, inherit from this class and implement the `filter_content` method. This method takes the HTML content as input and returns a list of filtered text blocks.
 
 ## BM25 Algorithm
 

docs/md_v2/basic/content_filtering.md

@@ -4,59 +4,7 @@ This guide explains how to use content filtering strategies in Crawl4AI to extra
 
 ## Relevance Content Filter
 
-The `RelevanceContentFilter` is an abstract class that provides a common interface for content filtering strategies. Specific filtering algorithms, like `PruningContentFilter` or `BM25ContentFilter`, inherit from this class and implement the `filter_content` method. This method takes the HTML content as input and returns a list of filtered text blocks.
-
-
-## Pruning Content Filter
-
-The `PruningContentFilter` is a tree-shaking algorithm that analyzes the HTML DOM structure and removes less relevant nodes based on various metrics like text density, link density, and tag importance. It evaluates each node using a composite scoring system and "prunes" nodes that fall below a certain threshold.
-
-### Usage
-
-```python
-from crawl4ai import AsyncWebCrawler
-from crawl4ai.content_filter_strategy import PruningContentFilter
-
-async def filter_content(url):
-    async with AsyncWebCrawler() as crawler:
-        content_filter = PruningContentFilter(
-            min_word_threshold=5,
-            threshold_type='dynamic',
-            threshold=0.45
-        )
-        result = await crawler.arun(url=url, extraction_strategy=content_filter, fit_markdown=True)
-        if result.success:
-            print(f"Cleaned Markdown:\n{result.fit_markdown}")
-```
-
-### Parameters
-
-- **`min_word_threshold`**: (Optional) Minimum number of words a node must contain to be considered relevant. Nodes with fewer words are automatically pruned.
-
-- **`threshold_type`**: (Optional, default 'fixed') Controls how pruning thresholds are calculated:
-  - `'fixed'`: Uses a constant threshold value for all nodes
-  - `'dynamic'`: Adjusts threshold based on node characteristics like tag importance and text/link ratios
-
-- **`threshold`**: (Optional, default 0.48) Base threshold value for node pruning:
-  - For fixed threshold: Nodes scoring below this value are removed
-  - For dynamic threshold: This value is adjusted based on node properties
-
-### How It Works
-
-The pruning algorithm evaluates each node using multiple metrics:
-- Text density: Ratio of actual text to overall node content
-- Link density: Proportion of text within links
-- Tag importance: Weight based on HTML tag type (e.g., article, p, div)
-- Content quality: Metrics like text length and structural importance
-
-Nodes scoring below the threshold are removed, effectively "shaking" less relevant content from the DOM tree. This results in a cleaner document containing only the most relevant content blocks.
-
-The algorithm is particularly effective for:
-- Removing boilerplate content
-- Eliminating navigation menus and sidebars
-- Preserving main article content
-- Maintaining document structure while removing noise
-
+The `RelevanceContentFilter` is an abstract class that provides a common interface for content filtering strategies. Specific filtering algorithms, like `BM25ContentFilter`, inherit from this class and implement the `filter_content` method. This method takes the HTML content as input and returns a list of filtered text blocks.
 
 ## BM25 Algorithm
 
@@ -73,7 +21,7 @@ from crawl4ai.content_filter_strategy import BM25ContentFilter
 async def filter_content(url, query=None):
     async with AsyncWebCrawler() as crawler:
         content_filter = BM25ContentFilter(user_query=query)
-        result = await crawler.arun(url=url, extraction_strategy=content_filter, fit_markdown=True) # Set fit_markdown flag to True to trigger BM25 filtering
+        result = await crawler.arun(url=url, content_filter=content_filter, fit_markdown=True) # Set fit_markdown flag to True to trigger BM25 filtering
         if result.success:
             print(f"Filtered Content (JSON):\n{result.extracted_content}")
             print(f"\nFiltered Markdown:\n{result.fit_markdown}") # New field in CrawlResult object
@@ -123,7 +71,7 @@ class MyCustomFilter(RelevantContentFilter):
 async def custom_filter_demo(url: str):
     async with AsyncWebCrawler() as crawler:
         custom_filter = MyCustomFilter()
-        result = await crawler.arun(url, extraction_strategy=custom_filter)
+        result = await crawler.arun(url, content_filter=custom_filter)
         if result.success:
             print(result.extracted_content)
 

docs/md_v2/blog/index.md

@@ -1,28 +0,0 @@
-# Crawl4AI Blog
-
-Welcome to the Crawl4AI blog! Here you'll find detailed release notes, technical deep dives, and news about the project.
-
-## Latest Release
-
-### [0.4.0 - Major Content Filtering Update](releases/0.4.0.md)
-*December 1, 2024*
-
-Introducing significant improvements to content filtering, multi-threaded environment handling, and user-agent generation. This release features the new PruningContentFilter, enhanced thread safety, and improved test coverage.
-
-[Read full release notes →](releases/0.4.0.md)
-
-## Project History
-
-Want to see how we got here? Check out our [complete changelog](https://github.com/unclecode/crawl4ai/blob/main/CHANGELOG.md) covering all previous versions and the evolution of Crawl4AI.
-
-## Categories
-
-- [Technical Deep Dives](/blog/technical) - Coming soon
-- [Tutorials & Guides](/blog/tutorials) - Coming soon
-- [Community Updates](/blog/community) - Coming soon
-
-## Stay Updated
-
-- Star us on [GitHub](https://github.com/unclecode/crawl4ai)
-- Follow [@unclecode](https://twitter.com/unclecode) on Twitter
-- Join our community discussions on GitHub

docs/md_v2/blog/releases/0.4.0.md

@@ -1,62 +0,0 @@
-# Release Summary for Version 0.4.0 (December 1, 2024)
-
-## Overview
-The 0.4.0 release introduces significant improvements to content filtering, multi-threaded environment handling, user-agent generation, and test coverage. Key highlights include the introduction of the PruningContentFilter, designed to automatically identify and extract the most valuable parts of an HTML document, as well as enhancements to the BM25ContentFilter to extend its versatility and effectiveness.
-
-## Major Features and Enhancements
-
-### 1. PruningContentFilter
-- Introduced a new unsupervised content filtering strategy that scores and prunes less relevant nodes in an HTML document based on metrics like text and link density.
-- Focuses on retaining the most valuable parts of the content, making it highly effective for extracting relevant information from complex web pages.
-- Fully documented with updated README and expanded user guides.
-
-### 2. User-Agent Generator
-- Added a user-agent generator utility that resolves compatibility issues and supports customizable user-agent strings.
-- By default, the generator randomizes user agents for each request, adding diversity, but users can customize it for tailored scenarios.
-
-### 3. Enhanced Thread Safety
-- Improved handling of multi-threaded environments by adding better thread locks for parallel processing, ensuring consistency and stability when running multiple threads.
-
-### 4. Extended Content Filtering Strategies
-- Users now have access to both the PruningContentFilter for unsupervised extraction and the BM25ContentFilter for supervised filtering based on user queries.
-- Enhanced BM25ContentFilter with improved capabilities to process page titles, meta tags, and descriptions, allowing for more effective classification and clustering of text chunks.
-
-### 5. Documentation Updates
-- Updated examples and tutorials to promote the use of the PruningContentFilter alongside the BM25ContentFilter, providing clear instructions for selecting the appropriate filter for each use case.
-
-### 6. Unit Test Enhancements
-- Added unit tests for PruningContentFilter to ensure accuracy and reliability.
-- Enhanced BM25ContentFilter tests to cover additional edge cases and performance metrics, particularly for malformed HTML inputs.
-
-## Revised Change Logs for Version 0.4.0
-
-### PruningContentFilter (Dec 01, 2024)
-- Introduced the PruningContentFilter to optimize content extraction by pruning less relevant HTML nodes.
-  - **Affected Files:**
-    - **crawl4ai/content_filter_strategy.py**: Added a scoring-based pruning algorithm.
-    - **README.md**: Updated to include PruningContentFilter usage.
-    - **docs/md_v2/basic/content_filtering.md**: Expanded user documentation, detailing the use and benefits of PruningContentFilter.
-
-### Unit Tests for PruningContentFilter (Dec 01, 2024)
-- Added comprehensive unit tests for PruningContentFilter to ensure correctness and efficiency.
-  - **Affected Files:**
-    - **tests/async/test_content_filter_prune.py**: Created tests covering different pruning scenarios to ensure stability and correctness.
-
-### Enhanced BM25ContentFilter Tests (Dec 01, 2024)
-- Expanded tests to cover additional extraction scenarios and performance metrics, improving robustness.
-  - **Affected Files:**
-    - **tests/async/test_content_filter_bm25.py**: Added tests for edge cases, including malformed HTML inputs.
-
-### Documentation and Example Updates (Dec 01, 2024)
-- Revised examples to illustrate the use of PruningContentFilter alongside existing content filtering methods.
-  - **Affected Files:**
-    - **docs/examples/quickstart_async.py**: Enhanced example clarity and usability for new users.
-
-## Experimental Features
-- The PruningContentFilter is still under experimental development, and we continue to gather feedback for further refinements.
-
-## Conclusion
-This release significantly enhances the content extraction capabilities of Crawl4ai with the introduction of the PruningContentFilter, improved supervised filtering with BM25ContentFilter, and robust multi-threaded handling. Additionally, the user-agent generator provides much-needed versatility, resolving compatibility issues faced by many users.
-
-Users are encouraged to experiment with the new content filtering methods to determine which best suits their needs.
-

main.py

@@ -340,6 +340,9 @@ app.add_middleware(
     allow_headers=["*"],  # Allows all headers
 )
 
+# Mount the pages directory as a static directory
+app.mount("/pages", StaticFiles(directory=__location__ + "/pages"), name="pages")
+
 # API token security
 security = HTTPBearer()
 CRAWL4AI_API_TOKEN = os.getenv("CRAWL4AI_API_TOKEN") or "test_api_code"
@@ -361,6 +364,7 @@ if os.path.exists(__location__ + "/site"):
     app.mount("/mkdocs", StaticFiles(directory="site", html=True), name="mkdocs")
 
 site_templates = Jinja2Templates(directory=__location__ + "/site")
+templates = Jinja2Templates(directory=__location__ + "/pages")
 
 crawler_service = CrawlerService()
 

mkdocs.yml

@@ -10,11 +10,7 @@ nav:
   - 'Installation': 'basic/installation.md'
   - 'Docker Deplotment': 'basic/docker-deploymeny.md'
   - 'Quick Start': 'basic/quickstart.md'
-  - Changelog & Blog:
-    - 'Blog Home': 'blog/index.md'
-    - 'Latest (0.4.0)': 'blog/releases/0.4.0.md'
-    - 'Changelog': 'https://github.com/unclecode/crawl4ai/blob/main/CHANGELOG.md'
-
+  
   - Basic:
     - 'Simple Crawling': 'basic/simple-crawling.md'
     - 'Output Formats': 'basic/output-formats.md'
@@ -54,12 +50,12 @@ nav:
     - '5. Dynamic Content': 'tutorial/episode_05_JavaScript_Execution_and_Dynamic_Content_Handling.md'
     - '6. Magic Mode': 'tutorial/episode_06_Magic_Mode_and_Anti-Bot_Protection.md'
     - '7. Content Cleaning': 'tutorial/episode_07_Content_Cleaning_and_Fit_Markdown.md'
-    - '8. Media Handling': 'tutorial/episode_08_Media_Handling_Images_Videos_and_Audio.md'
+    - '8. Media Handling': 'tutorial/episode_08_Media_Handling:_Images,_Videos,_and_Audio.md'
     - '9. Link Analysis': 'tutorial/episode_09_Link_Analysis_and_Smart_Filtering.md'
     - '10. User Simulation': 'tutorial/episode_10_Custom_Headers,_Identity,_and_User_Simulation.md'
-    - '11.1. JSON CSS': 'tutorial/episode_11_1_Extraction_Strategies_JSON_CSS.md'
-    - '11.2. LLM Strategy': 'tutorial/episode_11_2_Extraction_Strategies_LLM.md'
-    - '11.3. Cosine Strategy': 'tutorial/episode_11_3_Extraction_Strategies_Cosine.md'
+    - '11.1. JSON CSS': 'tutorial/episode_11_1_Extraction_Strategies:_JSON_CSS.md'
+    - '11.2. LLM Strategy': 'tutorial/episode_11_2_Extraction_Strategies:_LLM.md'
+    - '11.3. Cosine Strategy': 'tutorial/episode_11_3_Extraction_Strategies:_Cosine.md'
     - '12. Session Crawling': 'tutorial/episode_12_Session-Based_Crawling_for_Dynamic_Websites.md'
     - '13. Text Chunking': 'tutorial/episode_13_Chunking_Strategies_for_Large_Text_Processing.md'
     - '14. Custom Workflows': 'tutorial/episode_14_Hooks_and_Custom_Workflow_with_AsyncWebCrawler.md'

pages/app.css

@@ -0,0 +1,131 @@
+:root {
+    --ifm-font-size-base: 100%;
+    --ifm-line-height-base: 1.65;
+    --ifm-font-family-base: system-ui, -apple-system, Segoe UI, Roboto, Ubuntu, Cantarell, Noto Sans, sans-serif,
+        BlinkMacSystemFont, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji",
+        "Segoe UI Symbol";
+}
+html {
+    -webkit-font-smoothing: antialiased;
+    -webkit-text-size-adjust: 100%;
+    text-size-adjust: 100%;
+    font: var(--ifm-font-size-base) / var(--ifm-line-height-base) var(--ifm-font-family-base);
+}
+body {
+    background-color: #1a202c;
+    color: #fff;
+}
+.tab-content {
+    max-height: 400px;
+    overflow: auto;
+}
+pre {
+    white-space: pre-wrap;
+    font-size: 14px;
+}
+pre code {
+    width: 100%;
+}
+
+/* Custom styling for docs-item class and Markdown generated elements */
+.docs-item {
+    background-color: #2d3748; /* bg-gray-800 */
+    padding: 1rem; /* p-4 */
+    border-radius: 0.375rem; /* rounded */
+    box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1); /* shadow-md */
+    margin-bottom: 1rem; /* space between items */
+    line-height: 1.5; /* leading-normal */
+}
+
+.docs-item h3,
+.docs-item h4 {
+    color: #ffffff; /* text-white */
+    font-size: 1.25rem; /* text-xl */
+    font-weight: 700; /* font-bold */
+    margin-bottom: 0.5rem; /* mb-2 */
+}
+.docs-item h4 {
+    font-size: 1rem; /* text-xl */
+}
+
+.docs-item p {
+    color: #e2e8f0; /* text-gray-300 */
+    margin-bottom: 0.5rem; /* mb-2 */
+}
+
+.docs-item code {
+    background-color: #1a202c; /* bg-gray-900 */
+    color: #e2e8f0; /* text-gray-300 */
+    padding: 0.25rem 0.5rem; /* px-2 py-1 */
+    border-radius: 0.25rem; /* rounded */
+    font-size: 0.875rem; /* text-sm */
+}
+
+.docs-item pre {
+    background-color: #1a202c; /* bg-gray-900 */
+    color: #e2e8f0; /* text-gray-300 */
+    padding: 0.5rem; /* p-2 */
+    border-radius: 0.375rem; /* rounded */
+    overflow: auto; /* overflow-auto */
+    margin-bottom: 0.5rem; /* mb-2 */
+}
+
+.docs-item div {
+    color: #e2e8f0; /* text-gray-300 */
+    font-size: 1rem; /* prose prose-sm */
+    line-height: 1.25rem; /* line-height for readability */
+}
+
+/* Adjustments to make prose class more suitable for dark mode */
+.prose {
+    max-width: none; /* max-w-none */
+}
+
+.prose p,
+.prose ul {
+    margin-bottom: 1rem; /* mb-4 */
+}
+
+.prose code {
+    /* background-color: #4a5568; */ /* bg-gray-700 */
+    color: #65a30d; /* text-white */
+    padding: 0.25rem 0.5rem; /* px-1 py-0.5 */
+    border-radius: 0.25rem; /* rounded */
+    display: inline-block; /* inline-block */
+}
+
+.prose pre {
+    background-color: #1a202c; /* bg-gray-900 */
+    color: #ffffff; /* text-white */
+    padding: 0.5rem; /* p-2 */
+    border-radius: 0.375rem; /* rounded */
+}
+
+.prose h3 {
+    color: #65a30d; /* text-white */
+    font-size: 1.25rem; /* text-xl */
+    font-weight: 700; /* font-bold */
+    margin-bottom: 0.5rem; /* mb-2 */
+}
+
+body {
+    background-color: #1a1a1a;
+    color: #b3ff00;
+}
+.sidebar {
+    color: #b3ff00;
+    border-right: 1px solid #333;
+}
+.sidebar a {
+    color: #b3ff00;
+    text-decoration: none;
+}
+.sidebar a:hover {
+    background-color: #555;
+}
+.content-section {
+    display: none;
+}
+.content-section.active {
+    display: block;
+}

pages/app.js

@@ -0,0 +1,356 @@
+// JavaScript to manage dynamic form changes and logic
+document.getElementById("extraction-strategy-select").addEventListener("change", function () {
+    const strategy = this.value;
+    const providerModelSelect = document.getElementById("provider-model-select");
+    const tokenInput = document.getElementById("token-input");
+    const instruction = document.getElementById("instruction");
+    const semantic_filter = document.getElementById("semantic_filter");
+    const instruction_div = document.getElementById("instruction_div");
+    const semantic_filter_div = document.getElementById("semantic_filter_div");
+    const llm_settings = document.getElementById("llm_settings");
+
+    if (strategy === "LLMExtractionStrategy") {
+        // providerModelSelect.disabled = false;
+        // tokenInput.disabled = false;
+        // semantic_filter.disabled = true;
+        // instruction.disabled = false;
+        llm_settings.classList.remove("hidden");
+        instruction_div.classList.remove("hidden");
+        semantic_filter_div.classList.add("hidden");
+    } else if (strategy === "NoExtractionStrategy") {
+        semantic_filter_div.classList.add("hidden");
+        instruction_div.classList.add("hidden");
+        llm_settings.classList.add("hidden");
+    } else {
+        // providerModelSelect.disabled = true;
+        // tokenInput.disabled = true;
+        // semantic_filter.disabled = false;
+        // instruction.disabled = true;
+        llm_settings.classList.add("hidden");
+        instruction_div.classList.add("hidden");
+        semantic_filter_div.classList.remove("hidden");
+    }
+
+
+});
+
+// Get the selected provider model and token from local storage
+const storedProviderModel = localStorage.getItem("provider_model");
+const storedToken = localStorage.getItem(storedProviderModel);
+
+if (storedProviderModel) {
+    document.getElementById("provider-model-select").value = storedProviderModel;
+}
+
+if (storedToken) {
+    document.getElementById("token-input").value = storedToken;
+}
+
+// Handle provider model dropdown change
+document.getElementById("provider-model-select").addEventListener("change", () => {
+    const selectedProviderModel = document.getElementById("provider-model-select").value;
+    const storedToken = localStorage.getItem(selectedProviderModel);
+
+    if (storedToken) {
+        document.getElementById("token-input").value = storedToken;
+    } else {
+        document.getElementById("token-input").value = "";
+    }
+});
+
+// Fetch total count from the database
+axios
+    .get("/total-count")
+    .then((response) => {
+        document.getElementById("total-count").textContent = response.data.count;
+    })
+    .catch((error) => console.error(error));
+
+// Handle crawl button click
+document.getElementById("crawl-btn").addEventListener("click", () => {
+    // validate input to have both URL and API token
+    // if selected extraction strategy is LLMExtractionStrategy, then API token is required
+    if (document.getElementById("extraction-strategy-select").value === "LLMExtractionStrategy") {
+        if (!document.getElementById("url-input").value || !document.getElementById("token-input").value) {
+            alert("Please enter both URL(s) and API token.");
+            return;
+        }
+    }
+
+    const selectedProviderModel = document.getElementById("provider-model-select").value;
+    const apiToken = document.getElementById("token-input").value;
+    const extractBlocks = document.getElementById("extract-blocks-checkbox").checked;
+    const bypassCache = document.getElementById("bypass-cache-checkbox").checked;
+
+    // Save the selected provider model and token to local storage
+    localStorage.setItem("provider_model", selectedProviderModel);
+    localStorage.setItem(selectedProviderModel, apiToken);
+
+    const urlsInput = document.getElementById("url-input").value;
+    const urls = urlsInput.split(",").map((url) => url.trim());
+    const data = {
+        urls: urls,
+        include_raw_html: true,
+        bypass_cache: bypassCache,
+        extract_blocks: extractBlocks,
+        word_count_threshold: parseInt(document.getElementById("threshold").value),
+        extraction_strategy: document.getElementById("extraction-strategy-select").value,
+        extraction_strategy_args: {
+            provider: selectedProviderModel,
+            api_token: apiToken,
+            instruction: document.getElementById("instruction").value,
+            semantic_filter: document.getElementById("semantic_filter").value,
+        },
+        chunking_strategy: document.getElementById("chunking-strategy-select").value,
+        chunking_strategy_args: {},
+        css_selector: document.getElementById("css-selector").value,
+        screenshot: document.getElementById("screenshot-checkbox").checked,
+        // instruction: document.getElementById("instruction").value,
+        // semantic_filter: document.getElementById("semantic_filter").value,
+        verbose: true,
+    };
+
+    // import requests
+
+    // data = {
+    //   "urls": [
+    //     "https://www.nbcnews.com/business"
+    //   ],
+    //   "word_count_threshold": 10,
+    //   "extraction_strategy": "NoExtractionStrategy",
+    // }
+    
+    // response = requests.post("https://crawl4ai.com/crawl", json=data) # OR local host if your run locally 
+    // print(response.json())
+
+    // save api token to local storage
+    localStorage.setItem("api_token", document.getElementById("token-input").value);
+
+    document.getElementById("loading").classList.remove("hidden");
+    document.getElementById("result").style.visibility = "hidden";
+    document.getElementById("code_help").style.visibility = "hidden";
+
+    axios
+        .post("/crawl", data)
+        .then((response) => {
+            const result = response.data.results[0];
+            const parsedJson = JSON.parse(result.extracted_content);
+            document.getElementById("json-result").textContent = JSON.stringify(parsedJson, null, 2);
+            document.getElementById("cleaned-html-result").textContent = result.cleaned_html;
+            document.getElementById("markdown-result").textContent = result.markdown;
+            document.getElementById("media-result").textContent = JSON.stringify( result.media, null, 2);
+            if (result.screenshot){
+                const imgElement = document.createElement("img");
+                // Set the src attribute with the base64 data
+                imgElement.src = `data:image/png;base64,${result.screenshot}`;
+                document.getElementById("screenshot-result").innerHTML = "";
+                document.getElementById("screenshot-result").appendChild(imgElement);
+            }
+            
+            // Update code examples dynamically
+            const extractionStrategy = data.extraction_strategy;
+            const isLLMExtraction = extractionStrategy === "LLMExtractionStrategy";
+
+            // REMOVE API TOKEN FROM CODE EXAMPLES
+            data.extraction_strategy_args.api_token = "your_api_token";
+
+            if (data.extraction_strategy === "NoExtractionStrategy") {
+                delete data.extraction_strategy_args;
+                delete data.extrac_blocks;
+            }
+
+            if (data.chunking_strategy === "RegexChunking") {
+                delete data.chunking_strategy_args;
+            }
+
+            delete data.verbose;
+
+            if (data.css_selector === "") {
+                delete data.css_selector;
+            }
+
+            if (!data.bypass_cache) {
+                delete data.bypass_cache;
+            }
+
+            if (!data.extract_blocks) {
+                delete data.extract_blocks;
+            }
+
+            if (!data.include_raw_html) {
+                delete data.include_raw_html;
+            }
+
+            document.getElementById(
+                "curl-code"
+            ).textContent = `curl -X POST -H "Content-Type: application/json" -d '${JSON.stringify({
+                ...data,
+                api_token: isLLMExtraction ? "your_api_token" : undefined,
+            }, null, 2)}' https://crawl4ai.com/crawl`;
+
+            document.getElementById("python-code").textContent = `import requests\n\ndata = ${JSON.stringify(
+                { ...data, api_token: isLLMExtraction ? "your_api_token" : undefined },
+                null,
+                2
+            )}\n\nresponse = requests.post("https://crawl4ai.com/crawl", json=data) # OR local host if your run locally \nprint(response.json())`;
+
+            document.getElementById(
+                "nodejs-code"
+            ).textContent = `const axios = require('axios');\n\nconst data = ${JSON.stringify(
+                { ...data, api_token: isLLMExtraction ? "your_api_token" : undefined },
+                null,
+                2
+            )};\n\naxios.post("https://crawl4ai.com/crawl", data) // OR local host if your run locally \n    .then(response => console.log(response.data))\n    .catch(error => console.error(error));`;
+
+            document.getElementById(
+                "library-code"
+            ).textContent = `from crawl4ai.web_crawler import WebCrawler\nfrom crawl4ai.extraction_strategy import *\nfrom crawl4ai.chunking_strategy import *\n\ncrawler = WebCrawler()\ncrawler.warmup()\n\nresult = crawler.run(\n    url='${
+                urls[0]
+            }',\n    word_count_threshold=${data.word_count_threshold},\n    extraction_strategy=${
+                isLLMExtraction
+                    ? `${extractionStrategy}(provider="${data.provider_model}", api_token="${data.api_token}")`
+                    : extractionStrategy + "()"
+            },\n    chunking_strategy=${data.chunking_strategy}(),\n    bypass_cache=${
+                data.bypass_cache
+            },\n    css_selector="${data.css_selector}"\n)\nprint(result)`;
+
+            // Highlight code syntax
+            hljs.highlightAll();
+
+            // Select JSON tab by default
+            document.querySelector('.tab-btn[data-tab="json"]').click();
+
+            document.getElementById("loading").classList.add("hidden");
+
+            document.getElementById("result").style.visibility = "visible";
+            document.getElementById("code_help").style.visibility = "visible";
+
+            // increment the total count
+            document.getElementById("total-count").textContent =
+                parseInt(document.getElementById("total-count").textContent) + 1;
+        })
+        .catch((error) => {
+            console.error(error);
+            document.getElementById("loading").classList.add("hidden");
+        });
+});
+
+// Handle tab clicks
+document.querySelectorAll(".tab-btn").forEach((btn) => {
+    btn.addEventListener("click", () => {
+        const tab = btn.dataset.tab;
+        document.querySelectorAll(".tab-btn").forEach((b) => b.classList.remove("bg-lime-700", "text-white"));
+        btn.classList.add("bg-lime-700", "text-white");
+        document.querySelectorAll(".tab-content.code pre").forEach((el) => el.classList.add("hidden"));
+        document.getElementById(`${tab}-result`).parentElement.classList.remove("hidden");
+    });
+});
+
+// Handle code tab clicks
+document.querySelectorAll(".code-tab-btn").forEach((btn) => {
+    btn.addEventListener("click", () => {
+        const tab = btn.dataset.tab;
+        document.querySelectorAll(".code-tab-btn").forEach((b) => b.classList.remove("bg-lime-700", "text-white"));
+        btn.classList.add("bg-lime-700", "text-white");
+        document.querySelectorAll(".tab-content.result pre").forEach((el) => el.classList.add("hidden"));
+        document.getElementById(`${tab}-code`).parentElement.classList.remove("hidden");
+    });
+});
+
+// Handle copy to clipboard button clicks
+
+async function copyToClipboard(text) {
+    if (navigator.clipboard && navigator.clipboard.writeText) {
+        return navigator.clipboard.writeText(text);
+    } else {
+        return fallbackCopyTextToClipboard(text);
+    }
+}
+
+function fallbackCopyTextToClipboard(text) {
+    return new Promise((resolve, reject) => {
+        const textArea = document.createElement("textarea");
+        textArea.value = text;
+
+        // Avoid scrolling to bottom
+        textArea.style.top = "0";
+        textArea.style.left = "0";
+        textArea.style.position = "fixed";
+
+        document.body.appendChild(textArea);
+        textArea.focus();
+        textArea.select();
+
+        try {
+            const successful = document.execCommand("copy");
+            if (successful) {
+                resolve();
+            } else {
+                reject();
+            }
+        } catch (err) {
+            reject(err);
+        }
+
+        document.body.removeChild(textArea);
+    });
+}
+
+document.querySelectorAll(".copy-btn").forEach((btn) => {
+    btn.addEventListener("click", () => {
+        const target = btn.dataset.target;
+        const code = document.getElementById(target).textContent;
+        //navigator.clipboard.writeText(code).then(() => {
+        copyToClipboard(code).then(() => {
+            btn.textContent = "Copied!";
+            setTimeout(() => {
+                btn.textContent = "Copy";
+            }, 2000);
+        });
+    });
+});
+
+document.addEventListener("DOMContentLoaded", async () => {
+    try {
+        const extractionResponse = await fetch("/strategies/extraction");
+        const extractionStrategies = await extractionResponse.json();
+
+        const chunkingResponse = await fetch("/strategies/chunking");
+        const chunkingStrategies = await chunkingResponse.json();
+
+        renderStrategies("extraction-strategies", extractionStrategies);
+        renderStrategies("chunking-strategies", chunkingStrategies);
+    } catch (error) {
+        console.error("Error fetching strategies:", error);
+    }
+});
+
+function renderStrategies(containerId, strategies) {
+    const container = document.getElementById(containerId);
+    container.innerHTML = ""; // Clear any existing content
+    strategies = JSON.parse(strategies);
+    Object.entries(strategies).forEach(([strategy, description]) => {
+        const strategyElement = document.createElement("div");
+        strategyElement.classList.add("bg-zinc-800", "p-4", "rounded", "shadow-md", "docs-item");
+
+        const strategyDescription = document.createElement("div");
+        strategyDescription.classList.add("text-gray-300", "prose", "prose-sm");
+        strategyDescription.innerHTML = marked.parse(description);
+
+        strategyElement.appendChild(strategyDescription);
+
+        container.appendChild(strategyElement);
+    });
+}
+document.querySelectorAll(".sidebar a").forEach((link) => {
+    link.addEventListener("click", function (event) {
+        event.preventDefault();
+        document.querySelectorAll(".content-section").forEach((section) => {
+            section.classList.remove("active");
+        });
+        const target = event.target.getAttribute("data-target");
+        document.getElementById(target).classList.add("active");
+    });
+});
+// Highlight code syntax
+hljs.highlightAll();

pages/index copy.html

@@ -0,0 +1,971 @@
+<!DOCTYPE html>
+<html lang="en">
+    <head>
+        <meta charset="UTF-8" />
+        <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+        <title>Crawl4AI</title>
+
+        <link rel="preconnect" href="https://fonts.googleapis.com" />
+        <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+        <link href="https://fonts.googleapis.com/css2?family=Inter:wght@100..900&display=swap" rel="stylesheet" />
+
+        <!-- <link href="https://cdn.jsdelivr.net/npm/tailwindcss@3.4.3/dist/tailwind.min.css" rel="stylesheet" /> -->
+        <script src="https://cdn.tailwindcss.com"></script>
+        <script src="https://cdn.jsdelivr.net/npm/axios/dist/axios.min.js"></script>
+        <link
+            rel="stylesheet"
+            href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.7.0/styles/monokai.min.css"
+        />
+        <script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script>
+
+        <script src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.7.0/highlight.min.js"></script>
+        <style>
+            :root {
+                --ifm-font-size-base: 100%;
+                --ifm-line-height-base: 1.65;
+                --ifm-font-family-base: system-ui, -apple-system, Segoe UI, Roboto, Ubuntu, Cantarell, Noto Sans,
+                    sans-serif, BlinkMacSystemFont, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji",
+                    "Segoe UI Emoji", "Segoe UI Symbol";
+            }
+            html {
+                -webkit-font-smoothing: antialiased;
+                -webkit-text-size-adjust: 100%;
+                text-size-adjust: 100%;
+                font: var(--ifm-font-size-base) / var(--ifm-line-height-base) var(--ifm-font-family-base);
+            }
+            body {
+                background-color: #1a202c;
+                color: #fff;
+            }
+            .tab-content {
+                max-height: 400px;
+                overflow: auto;
+            }
+            pre {
+                white-space: pre-wrap;
+                font-size: 14px;
+            }
+            pre code {
+                width: 100%;
+            }
+        </style>
+        <style>
+            /* Custom styling for docs-item class and Markdown generated elements */
+            .docs-item {
+                background-color: #2d3748; /* bg-gray-800 */
+                padding: 1rem; /* p-4 */
+                border-radius: 0.375rem; /* rounded */
+                box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1); /* shadow-md */
+                margin-bottom: 1rem; /* space between items */
+            }
+
+            .docs-item h3,
+            .docs-item h4 {
+                color: #ffffff; /* text-white */
+                font-size: 1.25rem; /* text-xl */
+                font-weight: 700; /* font-bold */
+                margin-bottom: 0.5rem; /* mb-2 */
+            }
+
+            .docs-item p {
+                color: #e2e8f0; /* text-gray-300 */
+                margin-bottom: 0.5rem; /* mb-2 */
+            }
+
+            .docs-item code {
+                background-color: #1a202c; /* bg-gray-900 */
+                color: #e2e8f0; /* text-gray-300 */
+                padding: 0.25rem 0.5rem; /* px-2 py-1 */
+                border-radius: 0.25rem; /* rounded */
+            }
+
+            .docs-item pre {
+                background-color: #1a202c; /* bg-gray-900 */
+                color: #e2e8f0; /* text-gray-300 */
+                padding: 0.5rem; /* p-2 */
+                border-radius: 0.375rem; /* rounded */
+                overflow: auto; /* overflow-auto */
+                margin-bottom: 0.5rem; /* mb-2 */
+            }
+
+            .docs-item div {
+                color: #e2e8f0; /* text-gray-300 */
+                font-size: 1rem; /* prose prose-sm */
+                line-height: 1.25rem; /* line-height for readability */
+            }
+
+            /* Adjustments to make prose class more suitable for dark mode */
+            .prose {
+                max-width: none; /* max-w-none */
+            }
+
+            .prose p,
+            .prose ul {
+                margin-bottom: 1rem; /* mb-4 */
+            }
+
+            .prose code {
+                /* background-color: #4a5568; */ /* bg-gray-700 */
+                color: #65a30d; /* text-white */
+                padding: 0.25rem 0.5rem; /* px-1 py-0.5 */
+                border-radius: 0.25rem; /* rounded */
+                display: inline-block; /* inline-block */
+            }
+
+            .prose pre {
+                background-color: #1a202c; /* bg-gray-900 */
+                color: #ffffff; /* text-white */
+                padding: 0.5rem; /* p-2 */
+                border-radius: 0.375rem; /* rounded */
+            }
+
+            .prose h3 {
+                color: #65a30d; /* text-white */
+                font-size: 1.25rem; /* text-xl */
+                font-weight: 700; /* font-bold */
+                margin-bottom: 0.5rem; /* mb-2 */
+            }
+        </style>
+    </head>
+    <body class="bg-black text-gray-200">
+        <header class="bg-zinc-950 text-white py-4 flex">
+            <div class="mx-auto px-4">
+                <h1 class="text-2xl font-bold">🔥🕷️ Crawl4AI: Web Data for your Thoughts</h1>
+            </div>
+            <div class="mx-auto px-4 flex font-bold text-xl gap-2">
+                <span>📊 Total Website Processed</span>
+                <span id="total-count" class="text-lime-400">2</span>
+            </div>
+        </header>
+
+        <section class="try-it py-8 px-16 pb-20">
+            <div class="container mx-auto px-4">
+                <h2 class="text-2xl font-bold mb-4">Try It Now</h2>
+                <div class="grid grid-cols-1 lg:grid-cols-3 gap-4">
+                    <div class="space-y-4">
+                        <div class="flex flex-col">
+                            <label for="url-input" class="text-lime-500 font-bold text-xs">URL(s)</label>
+                            <input
+                                type="text"
+                                id="url-input"
+                                value="https://www.nbcnews.com/business"
+                                class="border border-zinc-700 rounded px-4 py-0 bg-zinc-900 text-lime-500"
+                                placeholder="Enter URL(s) separated by commas"
+                            />
+                        </div>
+                        <div class="flex flex-col">
+                            <label for="threshold" class="text-lime-500 font-bold text-xs">Min Words Threshold</label>
+                            <select
+                                id="threshold"
+                                class="border border-zinc-700 rounded px-4 py-0 bg-zinc-900 text-lime-500"
+                            >
+                                <option value="5">5</option>
+                                <option value="10" selected>10</option>
+                                <option value="15">15</option>
+                                <option value="20">20</option>
+                                <option value="25">25</option>
+                            </select>
+                        </div>
+                        <div class="flex flex-col">
+                            <label for="css-selector" class="text-lime-500 font-bold text-xs">CSS Selector</label>
+                            <input
+                                type="text"
+                                id="css-selector"
+                                class="border border-zinc-700 rounded px-4 py-0 bg-zinc-900 text-lime-500"
+                                placeholder="Enter CSS Selector"
+                            />
+                        </div>
+                        <div class="flex flex-col">
+                            <label for="extraction-strategy-select" class="text-lime-500 font-bold text-xs"
+                                >Extraction Strategy</label
+                            >
+                            <select
+                                id="extraction-strategy-select"
+                                class="border border-zinc-700 rounded px-4 py-1 bg-zinc-900 text-lime-500"
+                            >
+                                <option value="CosineStrategy">CosineStrategy</option>
+                                <option value="LLMExtractionStrategy">LLMExtractionStrategy</option>
+                                <option value="NoExtractionStrategy">NoExtractionStrategy</option>
+                            </select>
+                        </div>
+                        <div class="flex flex-col">
+                            <label for="chunking-strategy-select" class="text-lime-500 font-bold text-xs"
+                                >Chunking Strategy</label
+                            >
+                            <select
+                                id="chunking-strategy-select"
+                                class="border border-zinc-700 rounded px-4 py-1 bg-zinc-900 text-lime-500"
+                            >
+                                <option value="RegexChunking">RegexChunking</option>
+                                <option value="NlpSentenceChunking">NlpSentenceChunking</option>
+                                <option value="TopicSegmentationChunking">TopicSegmentationChunking</option>
+                                <option value="FixedLengthWordChunking">FixedLengthWordChunking</option>
+                                <option value="SlidingWindowChunking">SlidingWindowChunking</option>
+                            </select>
+                        </div>
+                        <div class="flex flex-col">
+                            <label for="provider-model-select" class="text-lime-500 font-bold text-xs"
+                                >Provider Model</label
+                            >
+                            <select
+                                id="provider-model-select"
+                                class="border border-zinc-700 rounded px-4 py-0 bg-zinc-900 text-lime-500"
+                                disabled
+                            >
+                                <option value="groq/llama3-70b-8192">groq/llama3-70b-8192</option>
+                                <option value="groq/llama3-8b-8192">groq/llama3-8b-8192</option>
+                                <option value="openai/gpt-4-turbo">gpt-4-turbo</option>
+                                <option value="openai/gpt-3.5-turbo">gpt-3.5-turbo</option>
+                                <option value="anthropic/claude-3-haiku-20240307">claude-3-haiku</option>
+                                <option value="anthropic/claude-3-opus-20240229">claude-3-opus</option>
+                                <option value="anthropic/claude-3-sonnet-20240229">claude-3-sonnet</option>
+                            </select>
+                        </div>
+                        <div class="flex flex-col">
+                            <label for="token-input" class="text-lime-500 font-bold text-xs">API Token</label>
+                            <input
+                                type="password"
+                                id="token-input"
+                                class="border border-zinc-700 rounded px-4 py-0 bg-zinc-900 text-lime-500"
+                                placeholder="Enter Groq API token"
+                                disabled
+                            />
+                        </div>
+                        <div class="flex gap-3">
+                            <div class="flex items-center gap-2">
+                                <input type="checkbox" id="bypass-cache-checkbox" />
+                                <label for="bypass-cache-checkbox" class="text-lime-500 font-bold">Bypass Cache</label>
+                            </div>
+                            <div class="flex items-center gap-2">
+                                <input type="checkbox" id="extract-blocks-checkbox" checked />
+                                <label for="extract-blocks-checkbox" class="text-lime-500 font-bold"
+                                    >Extract Blocks</label
+                                >
+                            </div>
+                            <button id="crawl-btn" class="bg-lime-600 text-black font-bold px-4 py-0 rounded">
+                                Crawl
+                            </button>
+                        </div>
+                    </div>
+
+                    <div id="result" class=" ">
+                        <div id="loading" class="hidden">
+                            <p class="text-white">Loading... Please wait.</p>
+                        </div>
+                        <div class="tab-buttons flex gap-2">
+                            <button
+                                class="tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500"
+                                data-tab="json"
+                            >
+                                JSON
+                            </button>
+                            <button
+                                class="tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500"
+                                data-tab="cleaned-html"
+                            >
+                                Cleaned HTML
+                            </button>
+                            <button
+                                class="tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500"
+                                data-tab="markdown"
+                            >
+                                Markdown
+                            </button>
+                        </div>
+                        <div class="tab-content code bg-zinc-900 p-2 rounded h-full border border-zinc-700 text-sm">
+                            <pre class="h-full flex"><code id="json-result" class="language-json"></code></pre>
+                            <pre
+                                class="hidden h-full flex"
+                            ><code id="cleaned-html-result" class="language-html"></code></pre>
+                            <pre
+                                class="hidden h-full flex"
+                            ><code id="markdown-result" class="language-markdown"></code></pre>
+                        </div>
+                    </div>
+
+                    <div id="code_help" class=" ">
+                        <div class="tab-buttons flex gap-2">
+                            <button
+                                class="code-tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500"
+                                data-tab="curl"
+                            >
+                                cURL
+                            </button>
+                            <button
+                                class="code-tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500"
+                                data-tab="library"
+                            >
+                                Python Library
+                            </button>
+                            <button
+                                class="code-tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500"
+                                data-tab="python"
+                            >
+                                Python (Request)
+                            </button>
+                            <button
+                                class="code-tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500"
+                                data-tab="nodejs"
+                            >
+                                Node.js
+                            </button>
+                        </div>
+                        <div class="tab-content result bg-zinc-900 p-2 rounded h-full border border-zinc-700 text-sm">
+                            <pre class="h-full flex relative">
+                                <code id="curl-code" class="language-bash"></code>
+                                <button class="absolute top-2 right-2 bg-zinc-700 text-white px-2 py-1 rounded copy-btn" data-target="curl-code">Copy</button>
+                            </pre>
+                            <pre class="hidden h-full flex relative">
+                                <code id="python-code" class="language-python"></code>
+                                <button class="absolute top-2 right-2 bg-zinc-700 text-white px-2 py-1 rounded copy-btn" data-target="python-code">Copy</button>
+                            </pre>
+                            <pre class="hidden h-full flex relative">
+                                <code id="nodejs-code" class="language-javascript"></code>
+                                <button class="absolute top-2 right-2 bg-zinc-700 text-white px-2 py-1 rounded copy-btn" data-target="nodejs-code">Copy</button>
+                            </pre>
+                            <pre class="hidden h-full flex relative">
+                                <code id="library-code" class="language-python"></code>
+                                <button class="absolute top-2 right-2 bg-zinc-700 text-white px-2 py-1 rounded copy-btn" data-target="library-code">Copy</button>
+                            </pre>
+                        </div>
+                    </div>
+                </div>
+            </div>
+        </section>
+        <section class="bg-zinc-900 text-zinc-300 p-6 px-20">
+            <div class="grid grid-cols-2 gap-4 p-4 bg-zinc-900 text-lime-500">
+                <!-- Step 1 -->
+                <div class="col-span-2 bg-yellow-500 p-2 rounded text-zinc-900">
+                    🌟 <strong>Welcome to the Crawl4ai Quickstart Guide! Let's dive into some web crawling fun!</strong>
+                </div>
+                <div class="bg-zinc-800 p-2 rounded">
+                    First Step: Create an instance of WebCrawler and call the <code>warmup()</code> function.
+                </div>
+                <div>
+                    <pre><code class="language-python">crawler = WebCrawler()
+            crawler.warmup()</code></pre>
+                </div>
+
+                <!-- Step 2 -->
+                <div class="col-span-2 bg-yellow-500 p-2 rounded text-zinc-900">
+                    🧠 <strong>Understanding 'bypass_cache' and 'include_raw_html' parameters:</strong>
+                </div>
+                <div class="bg-zinc-800 p-2 rounded">First crawl (caches the result):</div>
+                <div>
+                    <pre><code class="language-python">result = crawler.run(url="https://www.nbcnews.com/business")</code></pre>
+                </div>
+                <div class="bg-zinc-800 p-2 rounded">Second crawl (Force to crawl again):</div>
+                <div>
+                    <pre><code class="language-python">result = crawler.run(url="https://www.nbcnews.com/business", bypass_cache=True)</code></pre>
+                </div>
+                <div class="bg-zinc-800 p-2 rounded">Crawl result without raw HTML content:</div>
+                <div>
+                    <pre><code class="language-python">result = crawler.run(url="https://www.nbcnews.com/business", include_raw_html=False)</code></pre>
+                </div>
+
+                <!-- Step 3 -->
+                <div class="col-span-2 bg-yellow-500 p-2 rounded text-zinc-900">
+                    📄
+                    <strong
+                        >The 'include_raw_html' parameter, when set to True, includes the raw HTML content in the
+                        response. By default, it is set to True.</strong
+                    >
+                </div>
+                <div class="bg-zinc-800 p-2 rounded">Set <code>always_by_pass_cache</code> to True:</div>
+                <div>
+                    <pre><code class="language-python">crawler.always_by_pass_cache = True</code></pre>
+                </div>
+
+                <!-- Step 4 -->
+                <div class="col-span-2 bg-yellow-500 p-2 rounded text-zinc-900">
+                    🧩 <strong>Let's add a chunking strategy: RegexChunking!</strong>
+                </div>
+                <div class="bg-zinc-800 p-2 rounded">Using RegexChunking:</div>
+                <div>
+                    <pre><code class="language-python">result = crawler.run(
+                url="https://www.nbcnews.com/business",
+                chunking_strategy=RegexChunking(patterns=["\n\n"])
+            )</code></pre>
+                </div>
+                <div class="bg-zinc-800 p-2 rounded">Using NlpSentenceChunking:</div>
+                <div>
+                    <pre><code class="language-python">result = crawler.run(
+                url="https://www.nbcnews.com/business",
+                chunking_strategy=NlpSentenceChunking()
+            )</code></pre>
+                </div>
+
+                <!-- Step 5 -->
+                <div class="col-span-2 bg-yellow-500 p-2 rounded text-zinc-900">
+                    🧠 <strong>Let's get smarter with an extraction strategy: CosineStrategy!</strong>
+                </div>
+                <div class="bg-zinc-800 p-2 rounded">Using CosineStrategy:</div>
+                <div>
+                    <pre><code class="language-python">result = crawler.run(
+                url="https://www.nbcnews.com/business",
+                extraction_strategy=CosineStrategy(word_count_threshold=10, max_dist=0.2, linkage_method="ward", top_k=3)
+            )</code></pre>
+                </div>
+
+                <!-- Step 6 -->
+                <div class="col-span-2 bg-yellow-500 p-2 rounded text-zinc-900">
+                    🤖 <strong>Time to bring in the big guns: LLMExtractionStrategy without instructions!</strong>
+                </div>
+                <div class="bg-zinc-800 p-2 rounded">Using LLMExtractionStrategy without instructions:</div>
+                <div>
+                    <pre><code class="language-python">result = crawler.run(
+                url="https://www.nbcnews.com/business",
+                extraction_strategy=LLMExtractionStrategy(provider="openai/gpt-4o", api_token=os.getenv('OPENAI_API_KEY'))
+            )</code></pre>
+                </div>
+
+                <!-- Step 7 -->
+                <div class="col-span-2 bg-yellow-500 p-2 rounded text-zinc-900">
+                    📜 <strong>Let's make it even more interesting: LLMExtractionStrategy with instructions!</strong>
+                </div>
+                <div class="bg-zinc-800 p-2 rounded">Using LLMExtractionStrategy with instructions:</div>
+                <div>
+                    <pre><code class="language-python">result = crawler.run(
+                url="https://www.nbcnews.com/business",
+                extraction_strategy=LLMExtractionStrategy(
+                    provider="openai/gpt-4o",
+                    api_token=os.getenv('OPENAI_API_KEY'),
+                    instruction="I am interested in only financial news"
+                )
+            )</code></pre>
+                </div>
+
+                <!-- Step 8 -->
+                <div class="col-span-2 bg-yellow-500 p-2 rounded text-zinc-900">
+                    🎯 <strong>Targeted extraction: Let's use a CSS selector to extract only H2 tags!</strong>
+                </div>
+                <div class="bg-zinc-800 p-2 rounded">Using CSS selector to extract H2 tags:</div>
+                <div>
+                    <pre><code class="language-python">result = crawler.run(
+                url="https://www.nbcnews.com/business",
+                css_selector="h2"
+            )</code></pre>
+                </div>
+
+                <!-- Step 9 -->
+                <div class="col-span-2 bg-yellow-500 p-2 rounded text-zinc-900">
+                    🖱️ <strong>Let's get interactive: Passing JavaScript code to click 'Load More' button!</strong>
+                </div>
+                <div class="bg-zinc-800 p-2 rounded">Using JavaScript to click 'Load More' button:</div>
+                <div>
+                    <pre><code class="language-python">js_code = """
+            const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More'));
+            loadMoreButton && loadMoreButton.click();
+            """
+            crawler_strategy = LocalSeleniumCrawlerStrategy(js_code=js_code)
+            crawler = WebCrawler(crawler_strategy=crawler_strategy, always_by_pass_cache=True)
+            result = crawler.run(url="https://www.nbcnews.com/business")</code></pre>
+                </div>
+
+                <!-- Conclusion -->
+                <div class="col-span-2 bg-yellow-500 p-2 rounded text-zinc-900">
+                    🎉
+                    <strong
+                        >Congratulations! You've made it through the Crawl4ai Quickstart Guide! Now go forth and crawl
+                        the web like a pro! 🕸️</strong
+                    >
+                </div>
+            </div>
+        </section>
+        <section class="bg-zinc-900 text-zinc-300 p-6 px-20">
+            <h1 class="text-3xl font-bold mb-4">Installation 💻</h1>
+            <p class="mb-4">
+                There are two ways to use Crawl4AI: as a library in your Python projects or as a standalone local
+                server.
+            </p>
+
+            <p class="mb-4">
+                You can also try Crawl4AI in a Google Colab
+                <a href="https://colab.research.google.com/drive/1wz8u30rvbq6Scodye9AGCw8Qg_Z8QGsk"
+                    ><img
+                        src="https://colab.research.google.com/assets/colab-badge.svg"
+                        alt="Open In Colab"
+                        style="display: inline-block; width: 100px; height: 20px"
+                /></a>
+            </p>
+
+            <h2 class="text-2xl font-bold mb-2">Using Crawl4AI as a Library 📚</h2>
+            <p class="mb-4">To install Crawl4AI as a library, follow these steps:</p>
+
+            <ol class="list-decimal list-inside mb-4">
+                <li class="mb-2">
+                    Install the package from GitHub:
+                    <pre
+                        class="bg-zinc-800 p-4 rounded mt-2 text-zinc-100"
+                    ><code>pip install git+https://github.com/unclecode/crawl4ai.git</code></pre>
+                </li>
+                <li class="mb-2">
+                    Alternatively, you can clone the repository and install the package locally:
+                    <pre
+                        class="bg-zinc-800 p-4 rounded mt-2 text-zinc-100"
+                    ><code  class = "language-python bash">virtualenv venv
+source venv/bin/activate
+git clone https://github.com/unclecode/crawl4ai.git
+cd crawl4ai
+pip install -e .
+        </code></pre>
+                </li>
+                <li>
+                    Import the necessary modules in your Python script:
+                    <pre
+                        class="bg-zinc-800 p-4 rounded mt-2 text-zinc-100"
+                    ><code class = "language-python hljs">from crawl4ai.web_crawler import WebCrawler
+from crawl4ai.chunking_strategy import *
+from crawl4ai.extraction_strategy import *
+import os
+
+crawler = WebCrawler()
+
+# Single page crawl
+single_url = UrlModel(url='https://www.nbcnews.com/business', forced=False)
+result = crawl4ai.fetch_page(
+    url='https://www.nbcnews.com/business',
+    word_count_threshold=5, # Minimum word count for a HTML tag to be considered as a worthy block
+    chunking_strategy= RegexChunking( patterns = ["\\n\\n"]), # Default is RegexChunking
+    extraction_strategy= CosineStrategy(word_count_threshold=10, max_dist=0.2, linkage_method='ward', top_k=3) # Default is CosineStrategy
+    # extraction_strategy= LLMExtractionStrategy(provider= "openai/gpt-4o", api_token = os.getenv('OPENAI_API_KEY')),
+    bypass_cache=False,
+    extract_blocks =True, # Whether to extract semantical blocks of text from the HTML
+    css_selector = "", # Eg: "div.article-body"
+    verbose=True,
+    include_raw_html=True, # Whether to include the raw HTML content in the response
+)
+print(result.model_dump())
+        </code></pre>
+                </li>
+            </ol>
+            <p class="mb-4">
+                For more information about how to run Crawl4AI as a local server, please refer to the
+                <a href="https://github.com/unclecode/crawl4ai" class="text-blue-400">GitHub repository</a>.
+            </p>
+            
+        </section>
+
+        <section class="bg-zinc-900 text-zinc-300 p-6 px-20">
+            <h1 class="text-3xl font-bold mb-4">📖 Parameters</h1>
+            <div class="overflow-x-auto">
+                <table class="min-w-full bg-zinc-800 border border-zinc-700">
+                    <thead>
+                        <tr>
+                            <th class="py-2 px-4 border-b border-zinc-700">Parameter</th>
+                            <th class="py-2 px-4 border-b border-zinc-700">Description</th>
+                            <th class="py-2 px-4 border-b border-zinc-700">Required</th>
+                            <th class="py-2 px-4 border-b border-zinc-700">Default Value</th>
+                        </tr>
+                    </thead>
+                    <tbody>
+                        <tr>
+                            <td class="py-2 px-4 border-b border-zinc-700">urls</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">
+                                A list of URLs to crawl and extract data from.
+                            </td>
+                            <td class="py-2 px-4 border-b border-zinc-700">Yes</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">-</td>
+                        </tr>
+                        <tr>
+                            <td class="py-2 px-4 border-b border-zinc-700">include_raw_html</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">
+                                Whether to include the raw HTML content in the response.
+                            </td>
+                            <td class="py-2 px-4 border-b border-zinc-700">No</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">false</td>
+                        </tr>
+                        <tr>
+                            <td class="py-2 px-4 border-b border-zinc-700">bypass_cache</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">
+                                Whether to force a fresh crawl even if the URL has been previously crawled.
+                            </td>
+                            <td class="py-2 px-4 border-b border-zinc-700">No</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">false</td>
+                        </tr>
+                        <tr>
+                            <td class="py-2 px-4 border-b border-zinc-700">extract_blocks</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">
+                                Whether to extract semantical blocks of text from the HTML.
+                            </td>
+                            <td class="py-2 px-4 border-b border-zinc-700">No</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">true</td>
+                        </tr>
+                        <tr>
+                            <td class="py-2 px-4 border-b border-zinc-700">word_count_threshold</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">
+                                The minimum number of words a block must contain to be considered meaningful (minimum
+                                value is 5).
+                            </td>
+                            <td class="py-2 px-4 border-b border-zinc-700">No</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">5</td>
+                        </tr>
+                        <tr>
+                            <td class="py-2 px-4 border-b border-zinc-700">extraction_strategy</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">
+                                The strategy to use for extracting content from the HTML (e.g., "CosineStrategy").
+                            </td>
+                            <td class="py-2 px-4 border-b border-zinc-700">No</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">CosineStrategy</td>
+                        </tr>
+                        <tr>
+                            <td class="py-2 px-4 border-b border-zinc-700">chunking_strategy</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">
+                                The strategy to use for chunking the text before processing (e.g., "RegexChunking").
+                            </td>
+                            <td class="py-2 px-4 border-b border-zinc-700">No</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">RegexChunking</td>
+                        </tr>
+                        <tr>
+                            <td class="py-2 px-4 border-b border-zinc-700">css_selector</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">
+                                The CSS selector to target specific parts of the HTML for extraction.
+                            </td>
+                            <td class="py-2 px-4 border-b border-zinc-700">No</td>
+                            <td class="py-2 px-4 border-b border-zinc-700">None</td>
+                        </tr>
+                        <tr>
+                            <td class="py-2 px-4">verbose</td>
+                            <td class="py-2 px-4">Whether to enable verbose logging.</td>
+                            <td class="py-2 px-4">No</td>
+                            <td class="py-2 px-4">true</td>
+                        </tr>
+                    </tbody>
+                </table>
+            </div>
+        </section>
+
+        <section id="extraction" class="py-8 px-20">
+            <div class="overflow-x-auto mx-auto px-6">
+                <h2 class="text-2xl font-bold mb-4">Extraction Strategies</h2>
+                <div id="extraction-strategies" class="space-y-4"></div>
+            </div>
+        </section>
+
+        <section id="chunking" class="py-8 px-20">
+            <div class="overflow-x-auto mx-auto px-6">
+                <h2 class="text-2xl font-bold mb-4">Chunking Strategies</h2>
+                <div id="chunking-strategies" class="space-y-4"></div>
+            </div>
+        </section>
+
+        <section class="hero bg-zinc-900 py-8 px-20">
+            <div class="container mx-auto px-4">
+                <h2 class="text-3xl font-bold mb-4">🤔 Why building this?</h2>
+                <p class="text-lg mb-4">
+                    In recent times, we've witnessed a surge of startups emerging, riding the AI hype wave and charging
+                    for services that should rightfully be accessible to everyone. 🌍💸 One such example is scraping and
+                    crawling web pages and transforming them into a format suitable for Large Language Models (LLMs).
+                    🕸️🤖 We believe that building a business around this is not the right approach; instead, it should
+                    definitely be open-source. 🆓🌟 So, if you possess the skills to build such tools and share our
+                    philosophy, we invite you to join our "Robinhood" band and help set these products free for the
+                    benefit of all. 🤝💪
+                </p>
+            </div>
+        </section>
+
+        <section class="installation py-8 px-20">
+            <div class="container mx-auto px-4">
+                <h2 class="text-2xl font-bold mb-4">⚙️ Installation</h2>
+                <p class="mb-4">
+                    To install and run Crawl4AI as a library or a local server, please refer to the 📚
+                    <a href="https://github.com/unclecode/crawl4ai" class="text-blue-400">GitHub repository</a>.
+                </p>
+            </div>
+        </section>
+
+        <footer class="bg-zinc-900 text-white py-4">
+            <div class="container mx-auto px-4">
+                <div class="flex justify-between items-center">
+                    <p>© 2024 Crawl4AI. All rights reserved.</p>
+                    <div class="social-links">
+                        <a
+                            href="https://github.com/unclecode/crawl4ai"
+                            class="text-white hover:text-gray-300 mx-2"
+                            target="_blank"
+                            >😺 GitHub</a
+                        >
+                        <a
+                            href="https://twitter.com/unclecode"
+                            class="text-white hover:text-gray-300 mx-2"
+                            target="_blank"
+                            >🐦 Twitter</a
+                        >
+                    </div>
+                </div>
+            </div>
+        </footer>
+
+        <script>
+            // JavaScript to manage dynamic form changes and logic
+            document.getElementById("extraction-strategy-select").addEventListener("change", function () {
+                const strategy = this.value;
+                const providerModelSelect = document.getElementById("provider-model-select");
+                const tokenInput = document.getElementById("token-input");
+
+                if (strategy === "LLMExtractionStrategy") {
+                    providerModelSelect.disabled = false;
+                    tokenInput.disabled = false;
+                } else {
+                    providerModelSelect.disabled = true;
+                    tokenInput.disabled = true;
+                }
+            });
+
+            // Get the selected provider model and token from local storage
+            const storedProviderModel = localStorage.getItem("provider_model");
+            const storedToken = localStorage.getItem(storedProviderModel);
+
+            if (storedProviderModel) {
+                document.getElementById("provider-model-select").value = storedProviderModel;
+            }
+
+            if (storedToken) {
+                document.getElementById("token-input").value = storedToken;
+            }
+
+            // Handle provider model dropdown change
+            document.getElementById("provider-model-select").addEventListener("change", () => {
+                const selectedProviderModel = document.getElementById("provider-model-select").value;
+                const storedToken = localStorage.getItem(selectedProviderModel);
+
+                if (storedToken) {
+                    document.getElementById("token-input").value = storedToken;
+                } else {
+                    document.getElementById("token-input").value = "";
+                }
+            });
+
+            // Fetch total count from the database
+            axios
+                .get("/total-count")
+                .then((response) => {
+                    document.getElementById("total-count").textContent = response.data.count;
+                })
+                .catch((error) => console.error(error));
+
+            // Handle crawl button click
+            document.getElementById("crawl-btn").addEventListener("click", () => {
+                // validate input to have both URL and API token
+                if (!document.getElementById("url-input").value || !document.getElementById("token-input").value) {
+                    alert("Please enter both URL(s) and API token.");
+                    return;
+                }
+
+                const selectedProviderModel = document.getElementById("provider-model-select").value;
+                const apiToken = document.getElementById("token-input").value;
+                const extractBlocks = document.getElementById("extract-blocks-checkbox").checked;
+                const bypassCache = document.getElementById("bypass-cache-checkbox").checked;
+
+                // Save the selected provider model and token to local storage
+                localStorage.setItem("provider_model", selectedProviderModel);
+                localStorage.setItem(selectedProviderModel, apiToken);
+
+                const urlsInput = document.getElementById("url-input").value;
+                const urls = urlsInput.split(",").map((url) => url.trim());
+                const data = {
+                    urls: urls,
+                    provider_model: selectedProviderModel,
+                    api_token: apiToken,
+                    include_raw_html: true,
+                    bypass_cache: bypassCache,
+                    extract_blocks: extractBlocks,
+                    word_count_threshold: parseInt(document.getElementById("threshold").value),
+                    extraction_strategy: document.getElementById("extraction-strategy-select").value,
+                    chunking_strategy: document.getElementById("chunking-strategy-select").value,
+                    css_selector: document.getElementById("css-selector").value,
+                    verbose: true,
+                };
+
+                // save api token to local storage
+                localStorage.setItem("api_token", document.getElementById("token-input").value);
+
+                document.getElementById("loading").classList.remove("hidden");
+                //document.getElementById("result").classList.add("hidden");
+                //document.getElementById("code_help").classList.add("hidden");
+
+                axios
+                    .post("/crawl", data)
+                    .then((response) => {
+                        const result = response.data.results[0];
+                        const parsedJson = JSON.parse(result.extracted_content);
+                        document.getElementById("json-result").textContent = JSON.stringify(parsedJson, null, 2);
+                        document.getElementById("cleaned-html-result").textContent = result.cleaned_html;
+                        document.getElementById("markdown-result").textContent = result.markdown;
+
+                        // Update code examples dynamically
+                        const extractionStrategy = data.extraction_strategy;
+                        const isLLMExtraction = extractionStrategy === "LLMExtractionStrategy";
+
+                        document.getElementById(
+                            "curl-code"
+                        ).textContent = `curl -X POST -H "Content-Type: application/json" -d '${JSON.stringify({
+                            ...data,
+                            api_token: isLLMExtraction ? "your_api_token" : undefined,
+                        })}' http://crawl4ai.uccode.io/crawl`;
+
+                        document.getElementById(
+                            "python-code"
+                        ).textContent = `import requests\n\ndata = ${JSON.stringify(
+                            { ...data, api_token: isLLMExtraction ? "your_api_token" : undefined },
+                            null,
+                            2
+                        )}\n\nresponse = requests.post("http://crawl4ai.uccode.io/crawl", json=data) # OR local host if your run locally \nprint(response.json())`;
+
+                        document.getElementById(
+                            "nodejs-code"
+                        ).textContent = `const axios = require('axios');\n\nconst data = ${JSON.stringify(
+                            { ...data, api_token: isLLMExtraction ? "your_api_token" : undefined },
+                            null,
+                            2
+                        )};\n\naxios.post("http://crawl4ai.uccode.io/crawl", data) // OR local host if your run locally \n    .then(response => console.log(response.data))\n    .catch(error => console.error(error));`;
+
+                        document.getElementById(
+                            "library-code"
+                        ).textContent = `from crawl4ai.web_crawler import WebCrawler\nfrom crawl4ai.extraction_strategy import *\nfrom crawl4ai.chunking_strategy import *\n\ncrawler = WebCrawler()\ncrawler.warmup()\n\nresult = crawler.run(\n    url='${
+                            urls[0]
+                        }',\n    word_count_threshold=${data.word_count_threshold},\n    extraction_strategy=${
+                            isLLMExtraction
+                                ? `${extractionStrategy}(provider="${data.provider_model}", api_token="${data.api_token}")`
+                                : extractionStrategy + "()"
+                        },\n    chunking_strategy=${data.chunking_strategy}(),\n    bypass_cache=${
+                            data.bypass_cache
+                        },\n    css_selector="${data.css_selector}"\n)\nprint(result)`;
+
+                        // Highlight code syntax
+                        hljs.highlightAll();
+
+                        // Select JSON tab by default
+                        document.querySelector('.tab-btn[data-tab="json"]').click();
+
+                        document.getElementById("loading").classList.add("hidden");
+                        document.getElementById("result").classList.remove("hidden");
+                        document.getElementById("code_help").classList.remove("hidden");
+
+                        // increment the total count
+                        document.getElementById("total-count").textContent =
+                            parseInt(document.getElementById("total-count").textContent) + 1;
+                    })
+                    .catch((error) => {
+                        console.error(error);
+                        document.getElementById("loading").classList.add("hidden");
+                    });
+            });
+
+            // Handle tab clicks
+            document.querySelectorAll(".tab-btn").forEach((btn) => {
+                btn.addEventListener("click", () => {
+                    const tab = btn.dataset.tab;
+                    document
+                        .querySelectorAll(".tab-btn")
+                        .forEach((b) => b.classList.remove("bg-lime-700", "text-white"));
+                    btn.classList.add("bg-lime-700", "text-white");
+                    document.querySelectorAll(".tab-content.code pre").forEach((el) => el.classList.add("hidden"));
+                    document.getElementById(`${tab}-result`).parentElement.classList.remove("hidden");
+                });
+            });
+
+            // Handle code tab clicks
+            document.querySelectorAll(".code-tab-btn").forEach((btn) => {
+                btn.addEventListener("click", () => {
+                    const tab = btn.dataset.tab;
+                    document
+                        .querySelectorAll(".code-tab-btn")
+                        .forEach((b) => b.classList.remove("bg-lime-700", "text-white"));
+                    btn.classList.add("bg-lime-700", "text-white");
+                    document.querySelectorAll(".tab-content.result pre").forEach((el) => el.classList.add("hidden"));
+                    document.getElementById(`${tab}-code`).parentElement.classList.remove("hidden");
+                });
+            });
+
+            // Handle copy to clipboard button clicks
+
+            async function copyToClipboard(text) {
+                if (navigator.clipboard && navigator.clipboard.writeText) {
+                    return navigator.clipboard.writeText(text);
+                } else {
+                    return fallbackCopyTextToClipboard(text);
+                }
+            }
+
+            function fallbackCopyTextToClipboard(text) {
+                return new Promise((resolve, reject) => {
+                    const textArea = document.createElement("textarea");
+                    textArea.value = text;
+
+                    // Avoid scrolling to bottom
+                    textArea.style.top = "0";
+                    textArea.style.left = "0";
+                    textArea.style.position = "fixed";
+
+                    document.body.appendChild(textArea);
+                    textArea.focus();
+                    textArea.select();
+
+                    try {
+                        const successful = document.execCommand("copy");
+                        if (successful) {
+                            resolve();
+                        } else {
+                            reject();
+                        }
+                    } catch (err) {
+                        reject(err);
+                    }
+
+                    document.body.removeChild(textArea);
+                });
+            }
+
+            document.querySelectorAll(".copy-btn").forEach((btn) => {
+                btn.addEventListener("click", () => {
+                    const target = btn.dataset.target;
+                    const code = document.getElementById(target).textContent;
+                    //navigator.clipboard.writeText(code).then(() => {
+                    copyToClipboard(code).then(() => {
+                        btn.textContent = "Copied!";
+                        setTimeout(() => {
+                            btn.textContent = "Copy";
+                        }, 2000);
+                    });
+                });
+            });
+
+            document.addEventListener("DOMContentLoaded", async () => {
+                try {
+                    const extractionResponse = await fetch("/strategies/extraction");
+                    const extractionStrategies = await extractionResponse.json();
+
+                    const chunkingResponse = await fetch("/strategies/chunking");
+                    const chunkingStrategies = await chunkingResponse.json();
+
+                    renderStrategies("extraction-strategies", extractionStrategies);
+                    renderStrategies("chunking-strategies", chunkingStrategies);
+                } catch (error) {
+                    console.error("Error fetching strategies:", error);
+                }
+            });
+
+            function renderStrategies(containerId, strategies) {
+                const container = document.getElementById(containerId);
+                container.innerHTML = ""; // Clear any existing content
+                strategies = JSON.parse(strategies);
+                Object.entries(strategies).forEach(([strategy, description]) => {
+                    const strategyElement = document.createElement("div");
+                    strategyElement.classList.add("bg-zinc-800", "p-4", "rounded", "shadow-md", "docs-item");
+
+                    const strategyDescription = document.createElement("div");
+                    strategyDescription.classList.add("text-gray-300", "prose", "prose-sm");
+                    strategyDescription.innerHTML = marked.parse(description);
+
+                    strategyElement.appendChild(strategyDescription);
+
+                    container.appendChild(strategyElement);
+                });
+            }
+
+            // Highlight code syntax
+            hljs.highlightAll();
+        </script>
+    </body>
+</html>

pages/index.html

@@ -0,0 +1,73 @@
+<!DOCTYPE html>
+<html lang="en">
+    <head>
+        <meta charset="UTF-8" />
+        <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+        <title>Crawl4AI</title>
+
+        <link rel="preconnect" href="https://fonts.googleapis.com" />
+        <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+        <link href="https://fonts.googleapis.com/css2?family=Inter:wght@100..900&display=swap" rel="stylesheet" />
+
+        <!-- <link href="https://cdn.jsdelivr.net/npm/tailwindcss@3.4.3/dist/tailwind.min.css" rel="stylesheet" /> -->
+        <script src="https://cdn.tailwindcss.com"></script>
+        <script src="https://cdn.jsdelivr.net/npm/axios/dist/axios.min.js"></script>
+        <link rel="stylesheet" href="/pages/app.css" />
+        <link
+            rel="stylesheet"
+            href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.7.0/styles/monokai.min.css"
+        />
+        <script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script>
+
+        <script src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.7.0/highlight.min.js"></script>
+    </head>
+    <body class="bg-black text-gray-200">
+        <header class="bg-zinc-950 text-lime-500 py-4 flex">
+            
+            <div class="mx-auto px-4">
+                <h1 class="text-2xl font-bold">🔥🕷️ Crawl4AI: Web Data for your Thoughts</h1>
+            </div>
+            <div class="mx-auto px-4 flex font-bold text-xl gap-2">
+                <span>📊 Total Website Processed</span>
+                <span id="total-count" class="text-lime-400">2</span>
+            </div>
+        </header>
+        
+            {{ try_it | safe }}
+
+            <div class="mx-auto p-4 bg-zinc-950 text-lime-500 min-h-screen">
+                <div class="container mx-auto">
+                <div class="flex h-full px-20">
+                    <div class="sidebar w-1/4 p-4">
+                        <h2 class="text-lg font-bold mb-4">Outline</h2>
+                        <ul>
+                            <li class="mb-2"><a href="#" data-target="installation">Installation</a></li>
+                            <li class="mb-2"><a href="#" data-target="how-to-guide">How to Guide</a></li>
+                            <li class="mb-2"><a href="#" data-target="chunking-strategies">Chunking Strategies</a></li>
+                            <li class="mb-2">
+                                <a href="#" data-target="extraction-strategies">Extraction Strategies</a>
+                            </li>
+                        </ul>
+                    </div>
+
+                    <!-- Main Content -->
+                    <div class="w-3/4 p-4">
+                        {{installation | safe}} {{how_to_guide | safe}}
+
+                        <section id="chunking-strategies" class="content-section">
+                            <h1 class="text-2xl font-bold">Chunking Strategies</h1>
+                            <p>Content for chunking strategies...</p>
+                        </section>
+                        <section id="extraction-strategies" class="content-section">
+                            <h1 class="text-2xl font-bold">Extraction Strategies</h1>
+                            <p>Content for extraction strategies...</p>
+                        </section>
+                    </div>
+                </div>
+            </div>
+            </div>
+        
+        {{ footer | safe }}
+        <script script src="/pages/app.js"></script>
+    </body>
+</html>

pages/index_pooling.html

@@ -0,0 +1,425 @@
+<!DOCTYPE html>
+<html lang="en">
+    <head>
+        <meta charset="UTF-8" />
+        <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+        <title>Crawl4AI</title>
+
+        <link rel="preconnect" href="https://fonts.googleapis.com" />
+        <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+        <link href="https://fonts.googleapis.com/css2?family=Inter:wght@100..900&display=swap" rel="stylesheet" />
+
+        <link href="https://cdn.jsdelivr.net/npm/tailwindcss@2.2.19/dist/tailwind.min.css" rel="stylesheet" />
+        <script src="https://cdn.jsdelivr.net/npm/axios/dist/axios.min.js"></script>
+        <link
+            rel="stylesheet"
+            href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.7.0/styles/vs2015.min.css"
+        />
+        <script src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.7.0/highlight.min.js"></script>
+        <style>
+            :root {
+                --ifm-font-size-base: 100%;
+                --ifm-line-height-base: 1.65;
+                --ifm-font-family-base: system-ui, -apple-system, Segoe UI, Roboto, Ubuntu, Cantarell, Noto Sans,
+                    sans-serif, BlinkMacSystemFont, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji",
+                    "Segoe UI Emoji", "Segoe UI Symbol";
+            }
+            html {
+                -webkit-font-smoothing: antialiased;
+                -webkit-text-size-adjust: 100%;
+                text-size-adjust: 100%;
+                font: var(--ifm-font-size-base) / var(--ifm-line-height-base) var(--ifm-font-family-base);
+            }
+            body {
+                background-color: #1a202c;
+                color: #fff;
+            }
+            .tab-content {
+                max-height: 400px;
+                overflow: auto;
+            }
+            pre {
+                white-space: pre-wrap;
+                font-size: 14px;
+            }
+            pre code {
+                width: 100%;
+            }
+        </style>
+    </head>
+    <body>
+        <header class="bg-gray-900 text-white py-4">
+            <div class="container mx-auto px-4">
+                <h1 class="text-2xl font-bold">🔥🕷️ Crawl4AI: Open-source LLM Friendly Web scraper</h1>
+            </div>
+        </header>
+
+        <section class="try-it py-8 pb-20">
+            <div class="container mx-auto px-4">
+                <h2 class="text-2xl font-bold mb-4">Try It Now</h2>
+                <div class="mb-4 flex w-full gap-2">
+                    <input
+                        type="text"
+                        id="url-input"
+                        value="https://kidocode.com"
+                        class="border border-gray-600 rounded px-4 py-2 flex-grow bg-gray-800 text-white"
+                        placeholder="Enter URL(s) separated by commas"
+                    />
+                    <select
+                        id="provider-model-select"
+                        class="border border-gray-600 rounded px-4 py-2 bg-gray-800 text-white"
+                    >
+                        <!-- Add your option values here -->
+                        <option value="groq/llama3-70b-8192">groq/llama3-70b-8192</option>
+                        <option value="groq/llama3-8b-8192">groq/llama3-8b-8192</option>
+                        <option value="openai/gpt-4-turbo">gpt-4-turbo</option>
+                        <option value="openai/gpt-3.5-turbo">gpt-3.5-turbo</option>
+                        <option value="anthropic/claude-3-haiku-20240307">claude-3-haiku</option>
+                        <option value="anthropic/claude-3-opus-20240229">claude-3-opus</option>
+                        <option value="anthropic/claude-3-sonnet-20240229">claude-3-sonnet</option>
+                    </select>
+                    <input
+                        type="password"
+                        id="token-input"
+                        class="border border-gray-600 rounded px-4 py-2 flex-grow bg-gray-800 text-white"
+                        placeholder="Enter Groq API token"
+                    />
+                    <div class="flex items-center justify-center">
+                        <input type="checkbox" id="extract-blocks-checkbox" class="mr-2" checked>
+                        <label for="extract-blocks-checkbox" class="text-white">Extract Blocks</label>
+                    </div>
+                    <button id="crawl-btn" class="bg-blue-600 text-white px-4 py-2 rounded">Crawl</button>
+                </div>
+                <div class="grid grid-cols-1 md:grid-cols-2 gap-8">
+                    <div id="loading" class="hidden mt-4">
+                        <p>Loading...</p>
+                    </div>
+                    <div id="result" class="tab-container flex-1 h-full flex-col">
+                        <div class="tab-buttons flex gap-2">
+                            <button class="tab-btn px-4 py-2 bg-gray-700 rounded-t" data-tab="json">JSON</button>
+                            <button class="tab-btn px-4 py-2 bg-gray-700 rounded-t" data-tab="cleaned-html">
+                                Cleaned HTML
+                            </button>
+                            <button class="tab-btn px-4 py-2 bg-gray-700 rounded-t" data-tab="markdown">
+                                Markdown
+                            </button>
+                        </div>
+                        <div class="tab-content code bg-gray-800 p-2 rounded  h-full  flex-1 border border-gray-600">
+                            <pre class="h-full flex"><code id="json-result" class="language-json "></code></pre>
+                            <pre
+                                class="hidden h-full flex"
+                            ><code id="cleaned-html-result" class="language-html "></code></pre>
+                            <pre
+                                class="hidden h-full flex"
+                            ><code id="markdown-result" class="language-markdown "></code></pre>
+                        </div>
+                    </div>
+                    <div id="code_help" class="tab-container flex-1 h-full">
+                        <div class="tab-buttons flex gap-2">
+                            <button class="code-tab-btn px-4 py-2 bg-gray-700 rounded-t" data-tab="curl">cURL</button>
+                            <button class="code-tab-btn px-4 py-2 bg-gray-700 rounded-t" data-tab="python">
+                                Python
+                            </button>
+                            <button class="code-tab-btn px-4 py-2 bg-gray-700 rounded-t" data-tab="nodejs">
+                                Node.js
+                            </button>
+                        </div>
+                        <div class="tab-content result bg-gray-800 p-2 rounded h-full  flex-1 border border-gray-600">
+                            <pre class="h-full flex relative">
+                                    <code id="curl-code" class="language-bash"></code>
+                                    <button class="absolute top-2 right-2 bg-gray-700 text-white px-2 py-1 rounded copy-btn" data-target="curl-code">Copy</button>
+                                </pre>
+                            <pre class="hidden h-full flex relative">
+                                    <code id="python-code" class="language-python"></code>
+                                    <button class="absolute top-2 right-2 bg-gray-700 text-white px-2 py-1 rounded copy-btn" data-target="python-code">Copy</button>
+                                </pre>
+                            <pre class="hidden h-full flex relative">
+                                    <code id="nodejs-code" class="language-javascript"></code>
+                                    <button class="absolute top-2 right-2 bg-gray-700 text-white px-2 py-1 rounded copy-btn" data-target="nodejs-code">Copy</button>
+                                </pre>
+                        </div>
+                    </div>
+                </div>
+            </div>
+        </section>
+
+        <section class="hero bg-gray-900 py-8">
+            <div class="container mx-auto px-4">
+                <h2 class="text-3xl font-bold mb-4">🤔 Why building this?</h2>
+                <p class="text-lg mb-4">
+                    In recent times, we've seen numerous startups emerging, riding the AI hype wave and charging for
+                    services that should rightfully be accessible to everyone. 🌍💸 One for example is to scrap and crawl 
+                    a web page, and transform it o a form suitable for LLM. We don't think one should build a business
+                    out of this, but definilty should be opened source. So if you possess the skills to build such things 
+                    and you have such philosphy you should join our "Robinhood" band and help set
+                    these products free. 🆓🤝
+                </p>
+            </div>
+        </section>
+
+        <section class="installation py-8">
+            <div class="container mx-auto px-4">
+                <h2 class="text-2xl font-bold mb-4">⚙️ Installation</h2>
+                <p class="mb-4">
+                    To install and run Crawl4AI locally or on your own service, the best way is to use Docker. 🐳 Follow
+                    these steps:
+                </p>
+                <ol class="list-decimal list-inside mb-4">
+                    <li>
+                        Clone the GitHub repository: 📥
+                        <code>git clone https://github.com/unclecode/crawl4ai.git</code>
+                    </li>
+                    <li>Navigate to the project directory: 📂 <code>cd crawl4ai</code></li>
+                    <li>
+                        Build the Docker image: 🛠️ <code>docker build -t crawl4ai .</code> On Mac, follow: 🍎
+                        <code>docker build --platform linux/amd64 -t crawl4ai .</code>
+                    </li>
+                    <li>Run the Docker container: ▶️ <code>docker run -p 8000:80 crawl4ai</code></li>
+                </ol>
+                <p>
+                    For more detailed instructions and advanced configuration options, please refer to the 📚
+                    <a href="https://github.com/unclecode/crawl4ai" class="text-blue-400">GitHub repository</a>.
+                </p>
+            </div>
+        </section>
+
+        <footer class="bg-gray-900 text-white py-4">
+            <div class="container mx-auto px-4">
+                <div class="flex justify-between items-center">
+                    <p>© 2024 Crawl4AI. All rights reserved.</p>
+                    <div class="social-links">
+                        <a
+                            href="https://github.com/unclecode/crawl4ai"
+                            class="text-white hover:text-gray-300 mx-2"
+                            target="_blank"
+                            >😺 GitHub</a
+                        >
+                        <a
+                            href="https://twitter.com/unclecode"
+                            class="text-white hover:text-gray-300 mx-2"
+                            target="_blank"
+                            >🐦 Twitter</a
+                        >
+                        <a
+                            href="https://discord.gg/your-invite-link"
+                            class="text-white hover:text-gray-300 mx-2"
+                            target="_blank"
+                            >💬 Discord</a
+                        >
+                    </div>
+                </div>
+            </div>
+        </footer>
+
+        <script>
+            // Get the selected provider model and token from local storage
+            const storedProviderModel = localStorage.getItem("provider_model");
+            const storedToken = localStorage.getItem(storedProviderModel);
+
+            if (storedProviderModel) {
+                document.getElementById("provider-model-select").value = storedProviderModel;
+            }
+
+            if (storedToken) {
+                document.getElementById("token-input").value = storedToken;
+            }
+
+            // Handle provider model dropdown change
+            document.getElementById("provider-model-select").addEventListener("change", () => {
+                const selectedProviderModel = document.getElementById("provider-model-select").value;
+                const storedToken = localStorage.getItem(selectedProviderModel);
+
+                if (storedToken) {
+                    document.getElementById("token-input").value = storedToken;
+                } else {
+                    document.getElementById("token-input").value = "";
+                }
+            });
+
+            // Fetch total count from the database
+            axios
+                .get("/total-count")
+                .then((response) => {
+                    document.getElementById("total-count").textContent = response.data.count;
+                })
+                .catch((error) => console.error(error));
+
+            // Handle crawl button click
+            document.getElementById("crawl-btn").addEventListener("click", () => {
+                // validate input to have both URL and API token
+                if (!document.getElementById("url-input").value || !document.getElementById("token-input").value) {
+                    alert("Please enter both URL(s) and API token.");
+                    return;
+                }
+
+                const selectedProviderModel = document.getElementById("provider-model-select").value;
+                const apiToken = document.getElementById("token-input").value;
+                const extractBlocks = document.getElementById("extract-blocks-checkbox").checked;
+
+
+                // Save the selected provider model and token to local storage
+                localStorage.setItem("provider_model", selectedProviderModel);
+                localStorage.setItem(selectedProviderModel, apiToken);
+
+                const urlsInput = document.getElementById("url-input").value;
+                const urls = urlsInput.split(",").map((url) => url.trim());
+                const data = {
+                    urls: urls,
+                    provider_model: selectedProviderModel,
+                    api_token: apiToken,
+                    include_raw_html: true,
+                    forced: false,
+                    extract_blocks: extractBlocks,
+                };
+
+                // save api token to local storage
+                localStorage.setItem("api_token", document.getElementById("token-input").value);
+
+                document.getElementById("loading").classList.remove("hidden");
+                document.getElementById("result").classList.add("hidden");
+                document.getElementById("code_help").classList.add("hidden");
+
+                axios
+                    .post("/crawl", data)
+                    .then((response) => {
+                        const result = response.data.results[0];
+                        const parsedJson = JSON.parse(result.extracted_content);
+                        document.getElementById("json-result").textContent = JSON.stringify(parsedJson, null, 2);
+                        document.getElementById("cleaned-html-result").textContent = result.cleaned_html;
+                        document.getElementById("markdown-result").textContent = result.markdown;
+
+                        // Update code examples dynamically
+                        // Update code examples dynamically
+                        document.getElementById(
+                            "curl-code"
+                        ).textContent = `curl -X POST -H "Content-Type: application/json" -d '${JSON.stringify({
+                            ...data,
+                            api_token: "your_api_token",
+                        })}' http://localhost:8000/crawl`;
+
+                        document.getElementById(
+                            "python-code"
+                        ).textContent = `import requests\n\ndata = ${JSON.stringify(
+                            { ...data, api_token: "your_api_token" },
+                            null,
+                            2
+                        )}\n\nresponse = requests.post("http://localhost:8000/crawl", json=data)\nprint(response.json())`;
+
+                        document.getElementById(
+                            "nodejs-code"
+                        ).textContent = `const axios = require('axios');\n\nconst data = ${JSON.stringify(
+                            { ...data, api_token: "your_api_token" },
+                            null,
+                            2
+                        )};\n\naxios.post("http://localhost:8000/crawl", data)\n    .then(response => console.log(response.data))\n    .catch(error => console.error(error));`;
+                        // Highlight code syntax
+                        hljs.highlightAll();
+
+                        // Select JSON tab by default
+                        document.querySelector('.tab-btn[data-tab="json"]').click();
+
+                        document.getElementById("loading").classList.add("hidden");
+                        document.getElementById("result").classList.remove("hidden");
+                        document.getElementById("code_help").classList.remove("hidden");
+                    })
+                    .catch((error) => {
+                        console.error(error);
+                        document.getElementById("loading").classList.add("hidden");
+                    });
+            });
+
+            // Handle tab clicks
+            document.querySelectorAll(".tab-btn").forEach((btn) => {
+                btn.addEventListener("click", () => {
+                    const tab = btn.dataset.tab;
+                    document
+                        .querySelectorAll(".tab-btn")
+                        .forEach((b) => b.classList.remove("bg-blue-600", "text-white"));
+                    btn.classList.add("bg-blue-600", "text-white");
+                    document.querySelectorAll(".tab-content.code pre").forEach((el) => el.classList.add("hidden"));
+                    document.getElementById(`${tab}-result`).parentElement.classList.remove("hidden");
+                });
+            });
+
+            // Handle code tab clicks
+            document.querySelectorAll(".code-tab-btn").forEach((btn) => {
+                btn.addEventListener("click", () => {
+                    const tab = btn.dataset.tab;
+                    document
+                        .querySelectorAll(".code-tab-btn")
+                        .forEach((b) => b.classList.remove("bg-blue-600", "text-white"));
+                    btn.classList.add("bg-blue-600", "text-white");
+                    document.querySelectorAll(".tab-content.result pre").forEach((el) => el.classList.add("hidden"));
+                    document.getElementById(`${tab}-code`).parentElement.classList.remove("hidden");
+                });
+            });
+
+            // Handle copy to clipboard button clicks
+            document.querySelectorAll(".copy-btn").forEach((btn) => {
+                btn.addEventListener("click", () => {
+                    const target = btn.dataset.target;
+                    const code = document.getElementById(target).textContent;
+                    navigator.clipboard.writeText(code).then(() => {
+                        btn.textContent = "Copied!";
+                        setTimeout(() => {
+                            btn.textContent = "Copy";
+                        }, 2000);
+                    });
+                });
+            });
+
+
+            document.getElementById("crawl-btn").addEventListener("click", () => {
+                const urlsInput = document.getElementById("url-input").value;
+                const urls = urlsInput.split(",").map(url => url.trim());
+                const apiToken = document.getElementById("token-input").value;
+                const selectedProviderModel = document.getElementById("provider-model-select").value;
+                const extractBlocks = document.getElementById("extract-blocks-checkbox").checked;
+            
+                const data = {
+                    urls: urls,
+                    provider_model: selectedProviderModel,
+                    api_token: apiToken,
+                    include_raw_html: true,
+                    forced: false,
+                    extract_blocks: extractBlocks
+                };
+            
+                localStorage.setItem("api_token", apiToken);
+            
+                document.getElementById("loading").classList.remove("hidden");
+                document.getElementById("result").classList.add("hidden");
+                document.getElementById("code_help").classList.add("hidden");
+            
+                axios.post("/crawl", data)
+                    .then(response => {
+                        const taskId = response.data.task_id;
+                        pollTaskStatus(taskId);
+                    })
+                    .catch(error => {
+                        console.error('Error during fetch:', error);
+                        document.getElementById("loading").classList.add("hidden");
+                    });
+            });
+            
+            function pollTaskStatus(taskId) {
+                axios.get(`/task/${taskId}`)
+                    .then(response => {
+                        const task = response.data;
+                        if (task.status === 'done') {
+                            displayResults(task.results[0]);
+                        } else if (task.status === 'pending') {
+                            setTimeout(() => pollTaskStatus(taskId), 2000);  // Poll every 2 seconds
+                        } else {
+                            console.error('Task failed:', task.error);
+                            document.getElementById("loading").classList.add("hidden");
+                        }
+                    })
+                    .catch(error => {
+                        console.error('Error polling task status:', error);
+                        document.getElementById("loading").classList.add("hidden");
+                    });
+            }
+        </script>
+    </body>
+</html>

pages/partial/footer.html

@@ -0,0 +1,36 @@
+<section class="hero bg-zinc-900 py-8 px-20 text-zinc-400">
+    <div class="container mx-auto px-4">
+        <h2 class="text-3xl font-bold mb-4">🤔 Why building this?</h2>
+        <p class="text-lg mb-4">
+            In recent times, we've witnessed a surge of startups emerging, riding the AI hype wave and charging
+            for services that should rightfully be accessible to everyone. 🌍💸 One such example is scraping and
+            crawling web pages and transforming them into a format suitable for Large Language Models (LLMs).
+            🕸️🤖 We believe that building a business around this is not the right approach; instead, it should
+            definitely be open-source. 🆓🌟 So, if you possess the skills to build such tools and share our
+            philosophy, we invite you to join our "Robinhood" band and help set these products free for the
+            benefit of all. 🤝💪
+        </p>
+    </div>
+</section>
+
+<footer class="bg-zinc-900 text-zinc-400 py-4">
+    <div class="container mx-auto px-4">
+        <div class="flex justify-between items-center">
+            <p>© 2024 Crawl4AI. All rights reserved.</p>
+            <div class="social-links">
+                <a
+                    href="https://github.com/unclecode/crawl4ai"
+                    class="text-zinc-400 hover:text-gray-300 mx-2"
+                    target="_blank"
+                    >😺 GitHub</a
+                >
+                <a
+                    href="https://twitter.com/unclecode"
+                    class="text-zinc-400 hover:text-gray-300 mx-2"
+                    target="_blank"
+                    >🐦 Twitter</a
+                >
+            </div>
+        </div>
+    </div>
+</footer>

pages/partial/how_to_guide.html

@@ -0,0 +1,174 @@
+<section id="how-to-guide" class="content-section">
+    <h1 class="text-2xl font-bold">How to Guide</h1>
+    <div class="flex flex-col gap-4 p-4 bg-zinc-900 text-lime-500">
+        <!-- Step 1 -->
+        <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+            🌟
+            <strong
+                >Welcome to the Crawl4ai Quickstart Guide! Let's dive into some web crawling
+                fun!</strong
+            >
+        </div>
+        <div class="">
+            First Step: Create an instance of WebCrawler and call the
+            <code>warmup()</code> function.
+        </div>
+        <div>
+            <pre><code class="language-python">crawler = WebCrawler()
+crawler.warmup()</code></pre>
+        </div>
+
+        <!-- Step 2 -->
+        <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+            🧠 <strong>Understanding 'bypass_cache' and 'include_raw_html' parameters:</strong>
+        </div>
+        <div class="">First crawl (caches the result):</div>
+        <div>
+            <pre><code class="language-python">result = crawler.run(url="https://www.nbcnews.com/business")</code></pre>
+        </div>
+        <div class="">Second crawl (Force to crawl again):</div>
+        <div>
+            <pre><code class="language-python">result = crawler.run(url="https://www.nbcnews.com/business", bypass_cache=True)</code></pre>
+            <div class="bg-red-900 p-2 text-zinc-50">
+                ⚠️ Don't forget to set <code>`bypass_cache`</code> to True if you want to try different strategies for the same URL. Otherwise, the cached result will be returned. You can also set <code>`always_by_pass_cache`</code> in constructor to True to always bypass the cache.
+            </div>
+        </div>
+        <div class="">Crawl result without raw HTML content:</div>
+        <div>
+            <pre><code class="language-python">result = crawler.run(url="https://www.nbcnews.com/business", include_raw_html=False)</code></pre>
+        </div>
+
+        <!-- Step 3 -->
+        <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+            📄
+            <strong
+                >The 'include_raw_html' parameter, when set to True, includes the raw HTML content
+                in the response. By default, it is set to True.</strong
+            >
+        </div>
+        <div class="">Set <code>always_by_pass_cache</code> to True:</div>
+        <div>
+            <pre><code class="language-python">crawler.always_by_pass_cache = True</code></pre>
+        </div>
+        <!-- Step 3.5 Screenshot -->
+        <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+            📸
+            <strong>Let's take a screenshot of the page!</strong>
+        </div>
+        <div>
+            <pre><code class="language-python">result = crawler.run(
+    url="https://www.nbcnews.com/business",
+    screenshot=True
+)
+with open("screenshot.png", "wb") as f:
+    f.write(base64.b64decode(result.screenshot))</code></pre>
+        </div>
+
+
+        <!-- Step 4 -->
+        <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+            🧩 <strong>Let's add a chunking strategy: RegexChunking!</strong>
+        </div>
+        <div class="">Using RegexChunking:</div>
+        <div>
+            <pre><code class="language-python">result = crawler.run(
+    url="https://www.nbcnews.com/business",
+    chunking_strategy=RegexChunking(patterns=["\n\n"])
+)</code></pre>
+        </div>
+        <div class="">Using NlpSentenceChunking:</div>
+        <div>
+            <pre><code class="language-python">result = crawler.run(
+    url="https://www.nbcnews.com/business",
+    chunking_strategy=NlpSentenceChunking()
+)</code></pre>
+        </div>
+
+        <!-- Step 5 -->
+        <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+            🧠 <strong>Let's get smarter with an extraction strategy: CosineStrategy!</strong>
+        </div>
+        <div class="">Using CosineStrategy:</div>
+        <div>
+            <pre><code class="language-python">result = crawler.run(
+    url="https://www.nbcnews.com/business",
+    extraction_strategy=CosineStrategy(word_count_threshold=10, max_dist=0.2, linkage_method="ward", top_k=3)
+)</code></pre>
+        </div>
+
+        <!-- Step 6 -->
+        <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+            🤖
+            <strong
+                >Time to bring in the big guns: LLMExtractionStrategy without instructions!</strong
+            >
+        </div>
+        <div class="">Using LLMExtractionStrategy without instructions:</div>
+        <div>
+            <pre><code class="language-python">result = crawler.run(
+    url="https://www.nbcnews.com/business",
+    extraction_strategy=LLMExtractionStrategy(provider="openai/gpt-4o", api_token=os.getenv('OPENAI_API_KEY'))
+)</code></pre>
+        </div>
+
+        <!-- Step 7 -->
+        <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+            📜
+            <strong
+                >Let's make it even more interesting: LLMExtractionStrategy with
+                instructions!</strong
+            >
+        </div>
+        <div class="">Using LLMExtractionStrategy with instructions:</div>
+        <div>
+            <pre><code class="language-python">result = crawler.run(
+    url="https://www.nbcnews.com/business",
+    extraction_strategy=LLMExtractionStrategy(
+    provider="openai/gpt-4o",
+    api_token=os.getenv('OPENAI_API_KEY'),
+    instruction="I am interested in only financial news"
+)
+)</code></pre>
+        </div>
+
+        <!-- Step 8 -->
+        <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+            🎯
+            <strong>Targeted extraction: Let's use a CSS selector to extract only H2 tags!</strong>
+        </div>
+        <div class="">Using CSS selector to extract H2 tags:</div>
+        <div>
+            <pre><code class="language-python">result = crawler.run(
+    url="https://www.nbcnews.com/business",
+    css_selector="h2"
+)</code></pre>
+        </div>
+
+        <!-- Step 9 -->
+        <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+            🖱️
+            <strong
+                >Let's get interactive: Passing JavaScript code to click 'Load More' button!</strong
+            >
+        </div>
+        <div class="">Using JavaScript to click 'Load More' button:</div>
+        <div>
+            <pre><code class="language-python">js_code = ["""
+const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More'));
+loadMoreButton && loadMoreButton.click();
+"""]
+crawler = WebCrawler(verbos=crawler_strategy, always_by_pass_cache=True)
+result = crawler.run(url="https://www.nbcnews.com/business", js = js_code)</code></pre>
+        <div class="">Remember that you can pass multiple JavaScript code snippets in the list. They all will be executed in the order they are passed.</div>
+        </div>
+
+        <!-- Conclusion -->
+        <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+            🎉
+            <strong
+                >Congratulations! You've made it through the Crawl4ai Quickstart Guide! Now go forth
+                and crawl the web like a pro! 🕸️</strong
+            >
+        </div>
+    </div>
+</section>

pages/partial/installation.html

@@ -0,0 +1,65 @@
+<section id="installation" class="content-section active">
+    <h1 class="text-2xl font-bold">Installation 💻</h1>
+    <p class="mb-4">
+        There are three ways to use Crawl4AI: 
+        <ol class="list-decimal list-inside mb-4">
+            <li class="">
+                As a library
+            </li>
+            <li class="">
+                As a local server (Docker)
+            </li>
+            <li class="">
+                As a Google Colab notebook. <a href="https://colab.research.google.com/drive/1wz8u30rvbq6Scodye9AGCw8Qg_Z8QGsk"
+                ><img
+                    src="https://colab.research.google.com/assets/colab-badge.svg"
+                    alt="Open In Colab"
+                    style="display: inline-block; width: 100px; height: 20px"
+            /></a>
+            </li>
+    </p>
+
+
+    <p class="my-4">To install Crawl4AI as a library, follow these steps:</p>
+
+    <ol class="list-decimal list-inside mb-4">
+        <li class="mb-4">
+            Install the package from GitHub:
+            <pre
+                class="bg-zinc-800 p-4 rounded mt-2 text-zinc-100"
+            ><code>virtualenv venv
+source venv/bin/activate
+pip install "crawl4ai[all] @ git+https://github.com/unclecode/crawl4ai.git"
+            </code></pre>
+        </li>
+        <li class="mb-4">
+            Run the following command to load the required models. This is optional, but it will boost the performance and speed of the crawler. You need to do this only once.
+            <pre
+                class="bg-zinc-800 p-4 rounded mt-2 text-zinc-100"
+            ><code>crawl4ai-download-models</code></pre>
+        </li>
+        <li class="mb-4">
+            Alternatively, you can clone the repository and install the package locally:
+            <pre
+                class="bg-zinc-800 p-4 rounded mt-2 text-zinc-100"
+            ><code  class = "language-python bash">virtualenv venv
+source venv/bin/activate
+git clone https://github.com/unclecode/crawl4ai.git
+cd crawl4ai
+pip install -e .[all]
+</code></pre>
+        </li>
+        <li class="">
+            Use docker to run the local server:
+            <pre
+                class="bg-zinc-800 p-4 rounded mt-2 text-zinc-100"
+            ><code  class = "language-python bash">docker build -t crawl4ai . 
+# docker build --platform linux/amd64 -t crawl4ai . For Mac users
+docker run -d -p 8000:80 crawl4ai</code></pre>
+        </li>
+    </ol>
+    <p class="mb-4">
+        For more information about how to run Crawl4AI as a local server, please refer to the
+        <a href="https://github.com/unclecode/crawl4ai" class="text-blue-400">GitHub repository</a>.
+    </p>
+</section>

pages/partial/try_it.html

@@ -0,0 +1,217 @@
+<section class="try-it py-8 px-16 pb-20 bg-zinc-900 overflow-hidden">
+    <div class="container mx-auto ">
+        <h2 class="text-2xl font-bold mb-4 text-lime-500">Try It Now</h2>
+        <div class="flex gap-4">
+            <div class="flex flex-col flex-1 gap-2">
+                <div class="flex flex-col">
+                    <label for="url-input" class="text-lime-500 font-bold text-xs">URL(s)</label>
+                    <input
+                        type="text"
+                        id="url-input"
+                        value="https://www.nbcnews.com/business"
+                        class="border border-zinc-700 rounded px-4 py-0 bg-zinc-900 text-zinc-300"
+                        placeholder="Enter URL(s) separated by commas"
+                    />
+                </div>
+                <div class="flex gap-2">
+                    <div class="flex flex-col">
+                        <label for="threshold" class="text-lime-500 font-bold text-xs">Min Words Threshold</label>
+                        <select
+                            id="threshold"
+                            class="border border-zinc-700 rounded px-4 py-1 bg-zinc-900 text-zinc-300"
+                        >
+                            <option value="1">1</option>
+                            <option value="5">5</option>
+                            <option value="10" selected>10</option>
+                            <option value="15">15</option>
+                            <option value="20">20</option>
+                            <option value="25">25</option>
+                        </select>
+                    </div>
+                    <div class="flex flex-col flex-1">
+                        <label for="css-selector" class="text-lime-500 font-bold text-xs">CSS Selector</label>
+                        <input
+                            type="text"
+                            id="css-selector"
+                            class="border border-zinc-700 rounded px-4 py-0 bg-zinc-900 text-zinc-300 placeholder-lime-700"
+                            placeholder="CSS Selector (e.g. .content, #main, article)"
+                        />
+                    </div>
+                </div>
+                <div class="flex gap-2">
+                    <div class="flex flex-col">
+                        <label for="extraction-strategy-select" class="text-lime-500 font-bold text-xs"
+                            >Extraction Strategy</label
+                        >
+                        <select
+                            id="extraction-strategy-select"
+                            class="border border-zinc-700 rounded px-4 py-1 bg-zinc-900 text-zinc-300"
+                        >
+                            <option value="NoExtractionStrategy" selected>NoExtractionStrategy</option>
+                            <option value="CosineStrategy">CosineStrategy</option>
+                            <option value="LLMExtractionStrategy">LLMExtractionStrategy</option>
+                        </select>
+                    </div>
+                    <div class="flex flex-col">
+                        <label for="chunking-strategy-select" class="text-lime-500 font-bold text-xs"
+                            >Chunking Strategy</label
+                        >
+                        <select
+                            id="chunking-strategy-select"
+                            class="border border-zinc-700 rounded px-4 py-1 bg-zinc-900 text-zinc-300"
+                        >
+                            <option value="RegexChunking">RegexChunking</option>
+                            <option value="NlpSentenceChunking">NlpSentenceChunking</option>
+                            <option value="TopicSegmentationChunking">TopicSegmentationChunking</option>
+                            <option value="FixedLengthWordChunking">FixedLengthWordChunking</option>
+                            <option value="SlidingWindowChunking">SlidingWindowChunking</option>
+                        </select>
+                    </div>
+                </div>
+                <div id = "llm_settings" class="flex gap-2 hidden hidden">
+                    <div class="flex flex-col">
+                        <label for="provider-model-select" class="text-lime-500 font-bold text-xs"
+                            >Provider Model</label
+                        >
+                        <select
+                            id="provider-model-select"
+                            class="border border-zinc-700 rounded px-4 py-1 bg-zinc-900 text-zinc-300"
+                        >
+                            <option value="groq/llama3-70b-8192">groq/llama3-70b-8192</option>
+                            <option value="groq/llama3-8b-8192">groq/llama3-8b-8192</option>
+                            <option value="groq/mixtral-8x7b-32768">groq/mixtral-8x7b-32768</option>
+                            <option value="openai/gpt-4-turbo">gpt-4-turbo</option>
+                            <option value="openai/gpt-3.5-turbo">gpt-3.5-turbo</option>
+                            <option value="openai/gpt-4o">gpt-4o</option>
+                            <option value="anthropic/claude-3-haiku-20240307">claude-3-haiku</option>
+                            <option value="anthropic/claude-3-opus-20240229">claude-3-opus</option>
+                            <option value="anthropic/claude-3-sonnet-20240229">claude-3-sonnet</option>
+                        </select>
+                    </div>
+                    <div class="flex flex-col flex-1">
+                        <label for="token-input" class="text-lime-500 font-bold text-xs">API Token</label>
+                        <input
+                            type="password"
+                            id="token-input"
+                            class="border border-zinc-700 rounded px-4 py-0 bg-zinc-900 text-zinc-300"
+                            placeholder="Enter Groq API token"
+                        />
+                    </div>
+                </div>
+                <div  class="flex gap-2">
+                    <!-- Add two textarea one for getting Keyword Filter and another one Instruction, make both grow whole with-->
+                    <div id = "semantic_filter_div" class="flex flex-col flex-1 hidden">
+                        <label for="keyword-filter" class="text-lime-500 font-bold text-xs">Keyword Filter</label>
+                        <textarea
+                            id="semantic_filter"
+                            rows="3"
+                            class="border border-zinc-700 rounded px-4 py-0 bg-zinc-900 text-zinc-300 placeholder-zinc-700"
+                            placeholder="Enter keywords for CosineStrategy to narrow down the content."
+                        ></textarea>
+                    </div>
+                    <div id = "instruction_div" class="flex flex-col flex-1 hidden">
+                        <label for="instruction" class="text-lime-500 font-bold text-xs">Instruction</label>
+                        <textarea
+                            id="instruction"
+                            rows="3"
+                            class="border border-zinc-700 rounded px-4 py-0 bg-zinc-900 text-zinc-300 placeholder-zinc-700"
+                            placeholder="Enter instruction for the LLMEstrategy to instruct the model."
+                        ></textarea>
+                    </div>
+                </div>
+                <div class="flex gap-3">
+                    <div class="flex items-center gap-2">
+                        <input type="checkbox" id="bypass-cache-checkbox" />
+                        <label for="bypass-cache-checkbox" class="text-lime-500 font-bold">Bypass Cache</label>
+                    </div>
+                    <div class="flex items-center gap-2">
+                        <input type="checkbox" id="screenshot-checkbox" checked />
+                        <label for="screenshot-checkbox" class="text-lime-500 font-bold">Screenshot</label>
+                    </div>
+                    <div class="flex items-center gap-2 hidden">
+                        <input type="checkbox" id="extract-blocks-checkbox" />
+                        <label for="extract-blocks-checkbox" class="text-lime-500 font-bold">Extract Blocks</label>
+                    </div>
+                    <button id="crawl-btn" class="bg-lime-600 text-black font-bold px-4 py-0 rounded">Crawl</button>
+                </div>
+            </div>
+
+            <div id="loading" class="hidden">
+                <p class="text-white">Loading... Please wait.</p>
+            </div>
+            <div id="result" class="flex-1  overflow-x-auto">
+                <div class="tab-buttons flex gap-2">
+                    <button class="tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500" data-tab="json">
+                        JSON
+                    </button>
+                    <button
+                        class="tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500"
+                        data-tab="cleaned-html"
+                    >
+                        Cleaned HTML
+                    </button>
+                    <button class="tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500" data-tab="markdown">
+                        Markdown
+                    </button>
+                    <button class="tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500" data-tab="media">
+                        Medias
+                    </button>
+                    <button class="tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500" data-tab="screenshot">
+                        Screenshot
+                    </button>
+                </div>
+                <div class="tab-content code bg-zinc-900 p-2 rounded h-full border border-zinc-700 text-sm">
+                    <pre class="h-full flex"><code id="json-result" class="language-json"></code></pre>
+                    <pre class="hidden h-full flex"><code id="cleaned-html-result" class="language-html"></code></pre>
+                    <pre class="hidden h-full flex"><code id="markdown-result" class="language-markdown"></code></pre>
+                    <pre class="hidden h-full flex"><code id="media-result" class="language-json"></code></pre>
+                    <pre class="hidden h-full flex"><code id="screenshot-result"></code></pre>
+                </div>
+            </div>
+
+            <div id="code_help" class="flex-1  overflow-x-auto">
+                <div class="tab-buttons flex gap-2">
+                    <button class="code-tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500" data-tab="curl">
+                        cURL
+                    </button>
+                    <button
+                        class="code-tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500"
+                        data-tab="library"
+                    >
+                        Python
+                    </button>
+                    <button
+                        class="code-tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500"
+                        data-tab="python"
+                    >
+                        REST API
+                    </button>
+                    <!-- <button
+                        class="code-tab-btn px-4 py-1 text-sm bg-zinc-700 rounded-t text-lime-500"
+                        data-tab="nodejs"
+                    >
+                        Node.js
+                    </button> -->
+                </div>
+                <div class="tab-content result bg-zinc-900 p-2 rounded h-full border border-zinc-700 text-sm">
+                    <pre class="h-full flex relative overflow-x-auto">
+                        <code id="curl-code" class="language-bash"></code>
+                        <button class="absolute top-2 right-2 bg-zinc-700 text-white px-2 py-1 rounded copy-btn" data-target="curl-code">Copy</button>
+                    </pre>
+                    <pre class="hidden h-full flex relative overflow-x-auto">
+                        <code id="python-code" class="language-python"></code>
+                        <button class="absolute top-2 right-2 bg-zinc-700 text-white px-2 py-1 rounded copy-btn" data-target="python-code">Copy</button>
+                    </pre>
+                    <pre class="hidden h-full flex relative overflow-x-auto">
+                        <code id="nodejs-code" class="language-javascript"></code>
+                        <button class="absolute top-2 right-2 bg-zinc-700 text-white px-2 py-1 rounded copy-btn" data-target="nodejs-code">Copy</button>
+                    </pre>
+                    <pre class="hidden h-full flex relative overflow-x-auto">
+                        <code id="library-code" class="language-python"></code>
+                        <button class="absolute top-2 right-2 bg-zinc-700 text-white px-2 py-1 rounded copy-btn" data-target="library-code">Copy</button>
+                    </pre>
+                </div>
+            </div>
+        </div>
+    </div>
+</section>

pages/tmp.html

@@ -0,0 +1,434 @@
+<div class="w-3/4 p-4">
+    <section id="installation" class="content-section active">
+        <h1 class="text-2xl font-bold">Installation 💻</h1>
+        <p class="mb-4">There are three ways to use Crawl4AI:</p>
+        <ol class="list-decimal list-inside mb-4">
+            <li class="">As a library</li>
+            <li class="">As a local server (Docker)</li>
+            <li class="">
+                As a Google Colab notebook.
+                <a href="https://colab.research.google.com/drive/1wz8u30rvbq6Scodye9AGCw8Qg_Z8QGsk"
+                    ><img
+                        src="https://colab.research.google.com/assets/colab-badge.svg"
+                        alt="Open In Colab"
+                        style="display: inline-block; width: 100px; height: 20px"
+                /></a>
+            </li>
+            <p></p>
+
+            <p class="my-4">To install Crawl4AI as a library, follow these steps:</p>
+
+            <ol class="list-decimal list-inside mb-4">
+                <li class="mb-4">
+                    Install the package from GitHub:
+                    <pre
+                        class="bg-zinc-800 p-4 rounded mt-2 text-zinc-100"
+                    ><code class="hljs language-bash">pip install git+https://github.com/unclecode/crawl4ai.git</code></pre>
+                </li>
+                <li class="mb-4">
+                    Alternatively, you can clone the repository and install the package locally:
+                    <pre
+                        class="bg-zinc-800 p-4 rounded mt-2 text-zinc-100"
+                    ><code class="language-python bash hljs">virtualenv venv
+source venv/<span class="hljs-built_in">bin</span>/activate
+git clone https://github.com/unclecode/crawl4ai.git
+cd crawl4ai
+pip install -e .
+</code></pre>
+                </li>
+                <li class="">
+                    Use docker to run the local server:
+                    <pre
+                        class="bg-zinc-800 p-4 rounded mt-2 text-zinc-100"
+                    ><code class="language-python bash hljs">docker build -t crawl4ai . 
+<span class="hljs-comment"># docker build --platform linux/amd64 -t crawl4ai . For Mac users</span>
+docker run -d -p <span class="hljs-number">8000</span>:<span class="hljs-number">80</span> crawl4ai</code></pre>
+                </li>
+            </ol>
+            <p class="mb-4">
+                For more information about how to run Crawl4AI as a local server, please refer to the
+                <a href="https://github.com/unclecode/crawl4ai" class="text-blue-400">GitHub repository</a>.
+            </p>
+        </ol>
+    </section>
+    <section id="how-to-guide" class="content-section">
+        <h1 class="text-2xl font-bold">How to Guide</h1>
+        <div class="flex flex-col gap-4 p-4 bg-zinc-900 text-lime-500">
+            <!-- Step 1 -->
+            <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+                🌟
+                <strong>Welcome to the Crawl4ai Quickstart Guide! Let's dive into some web crawling fun!</strong>
+            </div>
+            <div class="">
+                First Step: Create an instance of WebCrawler and call the
+                <code>warmup()</code> function.
+            </div>
+            <div>
+                <pre><code class="language-python hljs">crawler = WebCrawler()
+crawler.warmup()</code></pre>
+            </div>
+
+            <!-- Step 2 -->
+            <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+                🧠 <strong>Understanding 'bypass_cache' and 'include_raw_html' parameters:</strong>
+            </div>
+            <div class="">First crawl (caches the result):</div>
+            <div>
+                <pre><code class="language-python hljs">result = crawler.run(url=<span class="hljs-string">"https://www.nbcnews.com/business"</span>)</code></pre>
+            </div>
+            <div class="">Second crawl (Force to crawl again):</div>
+            <div>
+                <pre><code class="language-python hljs">result = crawler.run(url=<span class="hljs-string">"https://www.nbcnews.com/business"</span>, bypass_cache=<span class="hljs-literal">True</span>)</code></pre>
+                <div class="bg-red-900 p-2 text-zinc-50">
+                    ⚠️ Don't forget to set <code>`bypass_cache`</code> to True if you want to try different strategies
+                    for the same URL. Otherwise, the cached result will be returned. You can also set
+                    <code>`always_by_pass_cache`</code> in constructor to True to always bypass the cache.
+                </div>
+            </div>
+            <div class="">Crawl result without raw HTML content:</div>
+            <div>
+                <pre><code class="language-python hljs">result = crawler.run(url=<span class="hljs-string">"https://www.nbcnews.com/business"</span>, include_raw_html=<span class="hljs-literal">False</span>)</code></pre>
+            </div>
+
+            <!-- Step 3 -->
+            <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+                📄
+                <strong
+                    >The 'include_raw_html' parameter, when set to True, includes the raw HTML content in the response.
+                    By default, it is set to True.</strong
+                >
+            </div>
+            <div class="">Set <code>always_by_pass_cache</code> to True:</div>
+            <div>
+                <pre><code class="language-python hljs">crawler.always_by_pass_cache = <span class="hljs-literal">True</span></code></pre>
+            </div>
+
+            <!-- Step 4 -->
+            <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+                🧩 <strong>Let's add a chunking strategy: RegexChunking!</strong>
+            </div>
+            <div class="">Using RegexChunking:</div>
+            <div>
+                <pre><code class="language-python hljs">result = crawler.run(
+url=<span class="hljs-string">"https://www.nbcnews.com/business"</span>,
+chunking_strategy=RegexChunking(patterns=[<span class="hljs-string">"\n\n"</span>])
+)</code></pre>
+            </div>
+            <div class="">Using NlpSentenceChunking:</div>
+            <div>
+                <pre><code class="language-python hljs">result = crawler.run(
+url=<span class="hljs-string">"https://www.nbcnews.com/business"</span>,
+chunking_strategy=NlpSentenceChunking()
+)</code></pre>
+            </div>
+
+            <!-- Step 5 -->
+            <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+                🧠 <strong>Let's get smarter with an extraction strategy: CosineStrategy!</strong>
+            </div>
+            <div class="">Using CosineStrategy:</div>
+            <div>
+                <pre><code class="language-python hljs">result = crawler.run(
+url=<span class="hljs-string">"https://www.nbcnews.com/business"</span>,
+extraction_strategy=CosineStrategy(word_count_threshold=<span class="hljs-number">20</span>, max_dist=<span class="hljs-number">0.2</span>, linkage_method=<span class="hljs-string">"ward"</span>, top_k=<span class="hljs-number">3</span>)
+)</code></pre>
+            </div>
+
+            <!-- Step 6 -->
+            <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+                🤖
+                <strong>Time to bring in the big guns: LLMExtractionStrategy without instructions!</strong>
+            </div>
+            <div class="">Using LLMExtractionStrategy without instructions:</div>
+            <div>
+                <pre><code class="language-python hljs">result = crawler.run(
+url=<span class="hljs-string">"https://www.nbcnews.com/business"</span>,
+extraction_strategy=LLMExtractionStrategy(provider=<span class="hljs-string">"openai/gpt-4o"</span>, api_token=os.getenv(<span class="hljs-string">'OPENAI_API_KEY'</span>))
+)</code></pre>
+            </div>
+
+            <!-- Step 7 -->
+            <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+                📜
+                <strong>Let's make it even more interesting: LLMExtractionStrategy with instructions!</strong>
+            </div>
+            <div class="">Using LLMExtractionStrategy with instructions:</div>
+            <div>
+                <pre><code class="language-python hljs">result = crawler.run(
+url=<span class="hljs-string">"https://www.nbcnews.com/business"</span>,
+extraction_strategy=LLMExtractionStrategy(
+provider=<span class="hljs-string">"openai/gpt-4o"</span>,
+api_token=os.getenv(<span class="hljs-string">'OPENAI_API_KEY'</span>),
+instruction=<span class="hljs-string">"I am interested in only financial news"</span>
+)
+)</code></pre>
+            </div>
+
+            <!-- Step 8 -->
+            <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+                🎯
+                <strong>Targeted extraction: Let's use a CSS selector to extract only H2 tags!</strong>
+            </div>
+            <div class="">Using CSS selector to extract H2 tags:</div>
+            <div>
+                <pre><code class="language-python hljs">result = crawler.run(
+url=<span class="hljs-string">"https://www.nbcnews.com/business"</span>,
+css_selector=<span class="hljs-string">"h2"</span>
+)</code></pre>
+            </div>
+
+            <!-- Step 9 -->
+            <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+                🖱️
+                <strong>Let's get interactive: Passing JavaScript code to click 'Load More' button!</strong>
+            </div>
+            <div class="">Using JavaScript to click 'Load More' button:</div>
+            <div>
+                <pre><code class="language-python hljs">js_code = <span class="hljs-string">"""
+const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button =&gt; button.textContent.includes('Load More'));
+loadMoreButton &amp;&amp; loadMoreButton.click();
+"""</span>
+crawler_strategy = LocalSeleniumCrawlerStrategy(js_code=js_code)
+crawler = WebCrawler(crawler_strategy=crawler_strategy, always_by_pass_cache=<span class="hljs-literal">True</span>)
+result = crawler.run(url=<span class="hljs-string">"https://www.nbcnews.com/business"</span>)</code></pre>
+            </div>
+
+            <!-- Conclusion -->
+            <div class="col-span-2 bg-lime-800 p-2 rounded text-zinc-50">
+                🎉
+                <strong
+                    >Congratulations! You've made it through the Crawl4ai Quickstart Guide! Now go forth and crawl the
+                    web like a pro! 🕸️</strong
+                >
+            </div>
+        </div>
+    </section>
+
+    <section id="chunking-strategies" class="content-section">
+        <div class="bg-zinc-800 p-4 rounded shadow-md docs-item">
+            <div class="text-gray-300 prose prose-sm">
+                <h3>RegexChunking</h3>
+                <p>
+                    <code>RegexChunking</code> is a text chunking strategy that splits a given text into smaller parts
+                    using regular expressions. This is useful for preparing large texts for processing by language
+                    models, ensuring they are divided into manageable segments.
+                </p>
+                <h4>Constructor Parameters:</h4>
+                <ul>
+                    <li>
+                        <code>patterns</code> (list, optional): A list of regular expression patterns used to split the
+                        text. Default is to split by double newlines (<code>['\n\n']</code>).
+                    </li>
+                </ul>
+                <h4>Example usage:</h4>
+                <pre><code class="language-python">chunker = RegexChunking(patterns=[r'\n\n', r'\. '])
+chunks = chunker.chunk("This is a sample text. It will be split into chunks.")
+</code></pre>
+            </div>
+        </div>
+        <div class="bg-zinc-800 p-4 rounded shadow-md docs-item">
+            <div class="text-gray-300 prose prose-sm">
+                <h3>NlpSentenceChunking</h3>
+                <p>
+                    <code>NlpSentenceChunking</code> uses a natural language processing model to chunk a given text into
+                    sentences. This approach leverages SpaCy to accurately split text based on sentence boundaries.
+                </p>
+                <h4>Constructor Parameters:</h4>
+                <ul>
+                    <li>
+                        None.
+                    </li>
+                </ul>
+                <h4>Example usage:</h4>
+                <pre><code class="language-python">chunker = NlpSentenceChunking()
+chunks = chunker.chunk("This is a sample text. It will be split into sentences.")
+</code></pre>
+            </div>
+        </div>
+        <div class="bg-zinc-800 p-4 rounded shadow-md docs-item">
+            <div class="text-gray-300 prose prose-sm">
+                <h3>TopicSegmentationChunking</h3>
+                <p>
+                    <code>TopicSegmentationChunking</code> uses the TextTiling algorithm to segment a given text into
+                    topic-based chunks. This method identifies thematic boundaries in the text.
+                </p>
+                <h4>Constructor Parameters:</h4>
+                <ul>
+                    <li>
+                        <code>num_keywords</code> (int, optional): The number of keywords to extract for each topic
+                        segment. Default is <code>3</code>.
+                    </li>
+                </ul>
+                <h4>Example usage:</h4>
+                <pre><code class="language-python">chunker = TopicSegmentationChunking(num_keywords=3)
+chunks = chunker.chunk("This is a sample text. It will be split into topic-based segments.")
+</code></pre>
+            </div>
+        </div>
+        <div class="bg-zinc-800 p-4 rounded shadow-md docs-item">
+            <div class="text-gray-300 prose prose-sm">
+                <h3>FixedLengthWordChunking</h3>
+                <p>
+                    <code>FixedLengthWordChunking</code> splits a given text into chunks of fixed length, based on the
+                    number of words.
+                </p>
+                <h4>Constructor Parameters:</h4>
+                <ul>
+                    <li>
+                        <code>chunk_size</code> (int, optional): The number of words in each chunk. Default is
+                        <code>100</code>.
+                    </li>
+                </ul>
+                <h4>Example usage:</h4>
+                <pre><code class="language-python">chunker = FixedLengthWordChunking(chunk_size=100)
+chunks = chunker.chunk("This is a sample text. It will be split into fixed-length word chunks.")
+</code></pre>
+            </div>
+        </div>
+        <div class="bg-zinc-800 p-4 rounded shadow-md docs-item">
+            <div class="text-gray-300 prose prose-sm">
+                <h3>SlidingWindowChunking</h3>
+                <p>
+                    <code>SlidingWindowChunking</code> uses a sliding window approach to chunk a given text. Each chunk
+                    has a fixed length, and the window slides by a specified step size.
+                </p>
+                <h4>Constructor Parameters:</h4>
+                <ul>
+                    <li>
+                        <code>window_size</code> (int, optional): The number of words in each chunk. Default is
+                        <code>100</code>.
+                    </li>
+                    <li>
+                        <code>step</code> (int, optional): The number of words to slide the window. Default is
+                        <code>50</code>.
+                    </li>
+                </ul>
+                <h4>Example usage:</h4>
+                <pre><code class="language-python">chunker = SlidingWindowChunking(window_size=100, step=50)
+chunks = chunker.chunk("This is a sample text. It will be split using a sliding window approach.")
+</code></pre>
+            </div>
+        </div>
+    </section>
+    <section id="extraction-strategies" class="content-section">
+        <div class="bg-zinc-800 p-4 rounded shadow-md docs-item">
+            <div class="text-gray-300 prose prose-sm">
+                <h3>NoExtractionStrategy</h3>
+                <p>
+                    <code>NoExtractionStrategy</code> is a basic extraction strategy that returns the entire HTML
+                    content without any modification. It is useful for cases where no specific extraction is required.
+                    Only clean html, and amrkdown.
+                </p>
+                <h4>Constructor Parameters:</h4>
+                <p>None.</p>
+                <h4>Example usage:</h4>
+                <pre><code class="language-python">extractor = NoExtractionStrategy()
+extracted_content = extractor.extract(url, html)
+</code></pre>
+            </div>
+        </div>
+        <div class="bg-zinc-800 p-4 rounded shadow-md docs-item">
+            <div class="text-gray-300 prose prose-sm">
+                <h3>LLMExtractionStrategy</h3>
+                <p>
+                    <code>LLMExtractionStrategy</code> uses a Language Model (LLM) to extract meaningful blocks or
+                    chunks from the given HTML content. This strategy leverages an external provider for language model
+                    completions.
+                </p>
+                <h4>Constructor Parameters:</h4>
+                <ul>
+                    <li>
+                        <code>provider</code> (str, optional): The provider to use for the language model completions.
+                        Default is <code>DEFAULT_PROVIDER</code> (e.g., openai/gpt-4).
+                    </li>
+                    <li>
+                        <code>api_token</code> (str, optional): The API token for the provider. If not provided, it will
+                        try to load from the environment variable <code>OPENAI_API_KEY</code>.
+                    </li>
+                    <li>
+                        <code>instruction</code> (str, optional): An instruction to guide the LLM on how to perform the
+                        extraction. This allows users to specify the type of data they are interested in or set the tone
+                        of the response. Default is <code>None</code>.
+                    </li>
+                </ul>
+                <h4>Example usage:</h4>
+                <pre><code class="language-python">extractor = LLMExtractionStrategy(provider='openai', api_token='your_api_token', instruction='Extract only news about AI.')
+extracted_content = extractor.extract(url, html)
+</code></pre>
+                <p>
+                    By providing clear instructions, users can tailor the extraction process to their specific needs,
+                    enhancing the relevance and utility of the extracted content.
+                </p>
+            </div>
+        </div>
+        <div class="bg-zinc-800 p-4 rounded shadow-md docs-item">
+            <div class="text-gray-300 prose prose-sm">
+                <h3>CosineStrategy</h3>
+                <p>
+                    <code>CosineStrategy</code> uses hierarchical clustering based on cosine similarity to extract
+                    clusters of text from the given HTML content. This strategy is suitable for identifying related
+                    content sections.
+                </p>
+                <h4>Constructor Parameters:</h4>
+                <ul>
+                    <li>
+                        <code>semantic_filter</code> (str, optional): A string containing keywords for filtering relevant
+                        documents before clustering. If provided, documents are filtered based on their cosine
+                        similarity to the keyword filter embedding. Default is <code>None</code>.
+                    </li>
+                    <li>
+                        <code>word_count_threshold</code> (int, optional): Minimum number of words per cluster. Default
+                        is <code>20</code>.
+                    </li>
+                    <li>
+                        <code>max_dist</code> (float, optional): The maximum cophenetic distance on the dendrogram to
+                        form clusters. Default is <code>0.2</code>.
+                    </li>
+                    <li>
+                        <code>linkage_method</code> (str, optional): The linkage method for hierarchical clustering.
+                        Default is <code>'ward'</code>.
+                    </li>
+                    <li>
+                        <code>top_k</code> (int, optional): Number of top categories to extract. Default is
+                        <code>3</code>.
+                    </li>
+                    <li>
+                        <code>model_name</code> (str, optional): The model name for embedding generation. Default is
+                        <code>'BAAI/bge-small-en-v1.5'</code>.
+                    </li>
+                </ul>
+                <h4>Example usage:</h4>
+                <pre><code class="language-python">extractor = CosineStrategy(semantic_filter='artificial intelligence', word_count_threshold=10, max_dist=0.2, linkage_method='ward', top_k=3, model_name='BAAI/bge-small-en-v1.5')
+extracted_content = extractor.extract(url, html)
+</code></pre>
+                <h4>Cosine Similarity Filtering</h4>
+                <p>
+                    When a <code>semantic_filter</code> is provided, the <code>CosineStrategy</code> applies an
+                    embedding-based filtering process to select relevant documents before performing hierarchical
+                    clustering.
+                </p>
+            </div>
+        </div>
+        <div class="bg-zinc-800 p-4 rounded shadow-md docs-item">
+            <div class="text-gray-300 prose prose-sm">
+                <h3>TopicExtractionStrategy</h3>
+                <p>
+                    <code>TopicExtractionStrategy</code> uses the TextTiling algorithm to segment the HTML content into
+                    topics and extracts keywords for each segment. This strategy is useful for identifying and
+                    summarizing thematic content.
+                </p>
+                <h4>Constructor Parameters:</h4>
+                <ul>
+                    <li>
+                        <code>num_keywords</code> (int, optional): Number of keywords to represent each topic segment.
+                        Default is <code>3</code>.
+                    </li>
+                </ul>
+                <h4>Example usage:</h4>
+                <pre><code class="language-python">extractor = TopicExtractionStrategy(num_keywords=3)
+extracted_content = extractor.extract(url, html)
+</code></pre>
+            </div>
+        </div>
+    </section>
+</div>

requirements.txt

@@ -1,16 +1,16 @@
 aiosqlite~=0.20
+html2text~=2024.2
 lxml~=5.3
-litellm>=1.53.1
+litellm~=1.48
 numpy>=1.26.0,<3
 pillow~=10.4
-playwright>=1.49.0
+playwright>=1.47,<1.48
 python-dotenv~=1.0
 requests~=2.26
 beautifulsoup4~=4.12
-tf-playwright-stealth>=1.1.0
+tf-playwright-stealth~=1.0
 xxhash~=3.4
 rank-bm25~=0.2
-aiofiles>=24.1.0
+aiofiles~=24.0
 colorama~=0.4
-snowballstemmer~=2.2
-pydantic>=2.10
+snowballstemmer~=2.2

setup.py

@@ -1,22 +1,18 @@
 from setuptools import setup, find_packages
+from setuptools.command.install import install
 import os
 from pathlib import Path
 import shutil
-
+import subprocess
+import sys
+import asyncio
 
 # Create the .crawl4ai folder in the user's home directory if it doesn't exist
 # If the folder already exists, remove the cache folder
-base_dir = os.getenv("CRAWL4_AI_BASE_DIRECTORY")
-crawl4ai_folder = Path(base_dir) if base_dir else Path.home()
-crawl4ai_folder = crawl4ai_folder / ".crawl4ai"
+crawl4ai_folder = os.getenv("CRAWL4_AI_BASE_DIRECTORY", Path.home()) / ".crawl4ai"
 cache_folder = crawl4ai_folder / "cache"
-content_folders = [
-    "html_content",
-    "cleaned_html",
-    "markdown_content",
-    "extracted_content",
-    "screenshots",
-]
+content_folders = ['html_content', 'cleaned_html', 'markdown_content', 
+                  'extracted_content', 'screenshots']
 
 # Clean up old cache if exists
 if cache_folder.exists():
@@ -32,7 +28,7 @@ for folder in content_folders:
 __location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
 with open(os.path.join(__location__, "requirements.txt")) as f:
     requirements = f.read().splitlines()
-
+    
 with open("crawl4ai/__version__.py") as f:
     for line in f:
         if line.startswith("__version__"):
@@ -41,11 +37,42 @@ with open("crawl4ai/__version__.py") as f:
 
 # Define requirements
 default_requirements = requirements
-torch_requirements = ["torch", "nltk", "scikit-learn"]
+torch_requirements = ["torch", "nltk",  "scikit-learn"]
 transformer_requirements = ["transformers", "tokenizers"]
-cosine_similarity_requirements = ["torch", "transformers", "nltk"]
+cosine_similarity_requirements = ["torch", "transformers", "nltk" ]
 sync_requirements = ["selenium"]
 
+def install_playwright():
+    print("Installing Playwright browsers...")
+    try:
+        subprocess.check_call([sys.executable, "-m", "playwright", "install"])
+        print("Playwright installation completed successfully.")
+    except subprocess.CalledProcessError as e:
+        print(f"Error during Playwright installation: {e}")
+        print("Please run 'python -m playwright install' manually after the installation.")
+    except Exception as e:
+        print(f"Unexpected error during Playwright installation: {e}")
+        print("Please run 'python -m playwright install' manually after the installation.")
+
+def run_migration():
+    """Initialize database during installation"""
+    try:
+        print("Starting database initialization...")
+        from crawl4ai.async_database import async_db_manager
+        asyncio.run(async_db_manager.initialize())
+        print("Database initialization completed successfully.")
+    except ImportError:
+        print("Warning: Database module not found. Will initialize on first use.")
+    except Exception as e:
+        print(f"Warning: Database initialization failed: {e}")
+        print("Database will be initialized on first use")
+
+class PostInstallCommand(install):
+    def run(self):
+        install.run(self)
+        install_playwright()
+        # run_migration()
+
 setup(
     name="Crawl4AI",
     version=version,
@@ -57,24 +84,18 @@ setup(
     author_email="unclecode@kidocode.com",
     license="MIT",
     packages=find_packages(),
-    install_requires=default_requirements
-    + ["playwright", "aiofiles"],  # Added aiofiles
+    install_requires=default_requirements + ["playwright", "aiofiles"],  # Added aiofiles
     extras_require={
         "torch": torch_requirements,
         "transformer": transformer_requirements,
         "cosine": cosine_similarity_requirements,
         "sync": sync_requirements,
-        "all": default_requirements
-        + torch_requirements
-        + transformer_requirements
-        + cosine_similarity_requirements
-        + sync_requirements,
+        "all": default_requirements + torch_requirements + transformer_requirements + cosine_similarity_requirements + sync_requirements,
     },
     entry_points={
-        "console_scripts": [
-            "crawl4ai-download-models=crawl4ai.model_loader:main",
-            "crawl4ai-migrate=crawl4ai.migrations:main",  
-            'crawl4ai-setup=crawl4ai.install:post_install', 
+        'console_scripts': [
+            'crawl4ai-download-models=crawl4ai.model_loader:main',
+            'crawl4ai-migrate=crawl4ai.migrations:main',  # Added migration command
         ],
     },
     classifiers=[
@@ -88,4 +109,7 @@ setup(
         "Programming Language :: Python :: 3.10",
     ],
     python_requires=">=3.7",
-)
+    cmdclass={
+        'install': PostInstallCommand,
+    },
+)

tests/async/test_content_filter_prune.py

@@ -1,159 +0,0 @@
-import os, sys
-import pytest
-from bs4 import BeautifulSoup
-
-parent_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
-sys.path.append(parent_dir)
-
-from crawl4ai.content_filter_strategy import PruningContentFilter
-
-@pytest.fixture
-def basic_html():
-    return """
-    <html>
-        <body>
-            <article>
-                <h1>Main Article</h1>
-                <p>This is a high-quality paragraph with substantial text content. It contains enough words to pass the threshold and has good text density without too many links. This kind of content should survive the pruning process.</p>
-                <div class="sidebar">Low quality sidebar content</div>
-                <div class="social-share">Share buttons</div>
-            </article>
-        </body>
-    </html>
-    """
-
-@pytest.fixture
-def link_heavy_html():
-    return """
-    <html>
-        <body>
-            <div class="content">
-                <p>Good content paragraph that should remain.</p>
-                <div class="links">
-                    <a href="#">Link 1</a>
-                    <a href="#">Link 2</a>
-                    <a href="#">Link 3</a>
-                    <a href="#">Link 4</a>
-                </div>
-            </div>
-        </body>
-    </html>
-    """
-
-@pytest.fixture
-def mixed_content_html():
-    return """
-    <html>
-        <body>
-            <article>
-                <h1>Article Title</h1>
-                <p class="summary">Short summary.</p>
-                <div class="content">
-                    <p>Long high-quality paragraph with substantial content that should definitely survive the pruning process. This content has good text density and proper formatting which makes it valuable for retention.</p>
-                </div>
-                <div class="comments">
-                    <p>Short comment 1</p>
-                    <p>Short comment 2</p>
-                </div>
-            </article>
-        </body>
-    </html>
-    """
-
-class TestPruningContentFilter:
-    def test_basic_pruning(self, basic_html):
-        """Test basic content pruning functionality"""
-        filter = PruningContentFilter(min_word_threshold=5)
-        contents = filter.filter_content(basic_html)
-        
-        combined_content = ' '.join(contents).lower()
-        assert "high-quality paragraph" in combined_content
-        assert "sidebar content" not in combined_content
-        assert "share buttons" not in combined_content
-
-    def test_min_word_threshold(self, mixed_content_html):
-        """Test minimum word threshold filtering"""
-        filter = PruningContentFilter(min_word_threshold=10)
-        contents = filter.filter_content(mixed_content_html)
-        
-        combined_content = ' '.join(contents).lower()
-        assert "short summary" not in combined_content
-        assert "long high-quality paragraph" in combined_content
-        assert "short comment" not in combined_content
-
-    def test_threshold_types(self, basic_html):
-        """Test fixed vs dynamic thresholds"""
-        fixed_filter = PruningContentFilter(threshold_type='fixed', threshold=0.48)
-        dynamic_filter = PruningContentFilter(threshold_type='dynamic', threshold=0.45)
-        
-        fixed_contents = fixed_filter.filter_content(basic_html)
-        dynamic_contents = dynamic_filter.filter_content(basic_html)
-        
-        assert len(fixed_contents) != len(dynamic_contents), \
-            "Fixed and dynamic thresholds should yield different results"
-
-    def test_link_density_impact(self, link_heavy_html):
-        """Test handling of link-heavy content"""
-        filter = PruningContentFilter(threshold_type='dynamic')
-        contents = filter.filter_content(link_heavy_html)
-        
-        combined_content = ' '.join(contents).lower()
-        assert "good content paragraph" in combined_content
-        assert len([c for c in contents if 'href' in c]) < 2, \
-            "Should prune link-heavy sections"
-
-    def test_tag_importance(self, mixed_content_html):
-        """Test tag importance in scoring"""
-        filter = PruningContentFilter(threshold_type='dynamic')
-        contents = filter.filter_content(mixed_content_html)
-        
-        has_article = any('article' in c.lower() for c in contents)
-        has_h1 = any('h1' in c.lower() for c in contents)
-        assert has_article or has_h1, "Should retain important tags"
-
-    def test_empty_input(self):
-        """Test handling of empty input"""
-        filter = PruningContentFilter()
-        assert filter.filter_content("") == []
-        assert filter.filter_content(None) == []
-
-    def test_malformed_html(self):
-        """Test handling of malformed HTML"""
-        malformed_html = "<div>Unclosed div<p>Nested<span>content</div>"
-        filter = PruningContentFilter()
-        contents = filter.filter_content(malformed_html)
-        assert isinstance(contents, list)
-
-    def test_performance(self, basic_html):
-        """Test performance with timer"""
-        filter = PruningContentFilter()
-        
-        import time
-        start = time.perf_counter()
-        filter.filter_content(basic_html)
-        duration = time.perf_counter() - start
-        
-        # Extra strict on performance since you mentioned milliseconds matter
-        assert duration < 0.1, f"Processing took too long: {duration:.3f} seconds"
-
-    @pytest.mark.parametrize("threshold,expected_count", [
-        (0.3, 4),  # Very lenient
-        (0.48, 2), # Default
-        (0.7, 1),  # Very strict
-    ])
-    def test_threshold_levels(self, mixed_content_html, threshold, expected_count):
-        """Test different threshold levels"""
-        filter = PruningContentFilter(threshold_type='fixed', threshold=threshold)
-        contents = filter.filter_content(mixed_content_html)
-        assert len(contents) <= expected_count, \
-            f"Expected {expected_count} or fewer elements with threshold {threshold}"
-
-    def test_consistent_output(self, basic_html):
-        """Test output consistency across multiple runs"""
-        filter = PruningContentFilter()
-        first_run = filter.filter_content(basic_html)
-        second_run = filter.filter_content(basic_html)
-        assert first_run == second_run, "Output should be consistent"
-
-if __name__ == "__main__":
-    pytest.main([__file__])

tests/async/test_content_scraper_strategy.py

@@ -13,8 +13,8 @@ parent_dir = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__f
 sys.path.append(parent_dir)
 __location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
 
-from crawl4ai.content_scraping_strategy import WebScrapingStrategy
-from crawl4ai.content_scraping_strategy import WebScrapingStrategy as WebScrapingStrategyCurrent
+from crawl4ai.content_scrapping_strategy import WebScrapingStrategy
+from crawl4ai.content_scrapping_strategy import WebScrapingStrategy as WebScrapingStrategyCurrent
 # from crawl4ai.content_scrapping_strategy_current import WebScrapingStrategy as WebScrapingStrategyCurrent
 
 @dataclass

tests/async/test_markdown_genertor.py

@@ -1,165 +0,0 @@
-# ## Issue #236
-# - **Last Updated:** 2024-11-11 01:42:14
-# - **Title:** [user data crawling opens two windows, unable to control correct user browser](https://github.com/unclecode/crawl4ai/issues/236)
-# - **State:** open
-
-import os, sys, time
-parent_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
-sys.path.append(parent_dir)
-__location__ = os.path.realpath(    os.path.join(os.getcwd(), os.path.dirname(__file__)))
-import asyncio
-import os
-import time
-from typing import Dict, Any
-from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
-
-# Get current directory
-__location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
-
-def print_test_result(name: str, result: Dict[str, Any], execution_time: float):
-    """Helper function to print test results."""
-    print(f"\n{'='*20} {name} {'='*20}")
-    print(f"Execution time: {execution_time:.4f} seconds")
-    
-    
-    # Save markdown to files
-    for key, content in result.items():
-        if isinstance(content, str):
-            with open(__location__ + f"/output/{name.lower()}_{key}.md", "w") as f:
-                f.write(content)
-    
-    # # Print first few lines of each markdown version
-    # for key, content in result.items():
-    #     if isinstance(content, str):
-    #         preview = '\n'.join(content.split('\n')[:3])
-    #         print(f"\n{key} (first 3 lines):")
-    #         print(preview)
-    #         print(f"Total length: {len(content)} characters")
-
-def test_basic_markdown_conversion():
-    """Test basic markdown conversion with links."""
-    with open(__location__ + "/data/wikipedia.html", "r") as f:
-        cleaned_html = f.read()
-
-    generator = DefaultMarkdownGenerator()
-    
-    start_time = time.perf_counter()
-    result = generator.generate_markdown(
-        cleaned_html=cleaned_html,
-        base_url="https://en.wikipedia.org"
-    )
-    execution_time = time.perf_counter() - start_time
-    
-    print_test_result("Basic Markdown Conversion", {
-        'raw': result.raw_markdown,
-        'with_citations': result.markdown_with_citations,
-        'references': result.references_markdown
-    }, execution_time)
-    
-    # Basic assertions
-    assert result.raw_markdown, "Raw markdown should not be empty"
-    assert result.markdown_with_citations, "Markdown with citations should not be empty"
-    assert result.references_markdown, "References should not be empty"
-    assert "⟨" in result.markdown_with_citations, "Citations should use ⟨⟩ brackets"
-    assert "## References" in result.references_markdown, "Should contain references section"
-
-def test_relative_links():
-    """Test handling of relative links with base URL."""
-    markdown = """
-    Here's a [relative link](/wiki/Apple) and an [absolute link](https://example.com).
-    Also an [image](/images/test.png) and another [page](/wiki/Banana).
-    """
-    
-    generator = DefaultMarkdownGenerator()
-    result = generator.generate_markdown(
-        cleaned_html=markdown,
-        base_url="https://en.wikipedia.org"
-    )
-    
-    assert "https://en.wikipedia.org/wiki/Apple" in result.references_markdown
-    assert "https://example.com" in result.references_markdown
-    assert "https://en.wikipedia.org/images/test.png" in result.references_markdown
-
-def test_duplicate_links():
-    """Test handling of duplicate links."""
-    markdown = """
-    Here's a [link](/test) and another [link](/test) and a [different link](/other).
-    """
-    
-    generator = DefaultMarkdownGenerator()
-    result = generator.generate_markdown(
-        cleaned_html=markdown,
-        base_url="https://example.com"
-    )
-    
-    # Count citations in markdown
-    citations = result.markdown_with_citations.count("⟨1⟩")
-    assert citations == 2, "Same link should use same citation number"
-
-def test_link_descriptions():
-    """Test handling of link titles and descriptions."""
-    markdown = """
-    Here's a [link with title](/test "Test Title") and a [link with description](/other) to test.
-    """
-    
-    generator = DefaultMarkdownGenerator()
-    result = generator.generate_markdown(
-        cleaned_html=markdown,
-        base_url="https://example.com"
-    )
-    
-    assert "Test Title" in result.references_markdown, "Link title should be in references"
-    assert "link with description" in result.references_markdown, "Link text should be in references"
-
-def test_performance_large_document():
-    """Test performance with large document."""
-    with open(__location__ + "/data/wikipedia.md", "r") as f:
-        markdown = f.read()
-    
-    # Test with multiple iterations
-    iterations = 5
-    times = []
-    
-    generator = DefaultMarkdownGenerator()
-    
-    for i in range(iterations):
-        start_time = time.perf_counter()
-        result = generator.generate_markdown(
-            cleaned_html=markdown,
-            base_url="https://en.wikipedia.org"
-        )
-        end_time = time.perf_counter()
-        times.append(end_time - start_time)
-    
-    avg_time = sum(times) / len(times)
-    print(f"\n{'='*20} Performance Test {'='*20}")
-    print(f"Average execution time over {iterations} iterations: {avg_time:.4f} seconds")
-    print(f"Min time: {min(times):.4f} seconds")
-    print(f"Max time: {max(times):.4f} seconds")
-
-def test_image_links():
-    """Test handling of image links."""
-    markdown = """
-    Here's an ![image](/image.png "Image Title") and another ![image](/other.jpg).
-    And a regular [link](/page).
-    """
-    
-    generator = DefaultMarkdownGenerator()
-    result = generator.generate_markdown(
-        cleaned_html=markdown,
-        base_url="https://example.com"
-    )
-    
-    assert "![" in result.markdown_with_citations, "Image markdown syntax should be preserved"
-    assert "Image Title" in result.references_markdown, "Image title should be in references"
-
-if __name__ == "__main__":
-    print("Running markdown generation strategy tests...")
-    
-    test_basic_markdown_conversion()
-    test_relative_links()
-    test_duplicate_links()
-    test_link_descriptions()
-    test_performance_large_document()
-    test_image_links()
-