This major release adds deep crawling capabilities, memory-adaptive dispatcher,
multiple crawling strategies, Docker deployment, and a new CLI. It also includes
significant improvements to proxy handling, PDF processing, and LLM integration.
BREAKING CHANGES:
- Add memory-adaptive dispatcher as default for arun_many()
- Move max_depth to CrawlerRunConfig
- Replace ScrapingMode enum with strategy pattern
- Update BrowserContext API
- Make model fields optional with defaults
- Remove content_filter parameter from CrawlerRunConfig
- Remove synchronous WebCrawler and old CLI
- Update Docker deployment configuration
- Replace FastFilterChain with FilterChain
- Change license to Apache 2.0 with attribution clause
* feature: Add LlmConfig to easily configure and pass LLM configs to different strategies
* pulled in next branch and resolved conflicts
* feat: Add gemini and deepseek providers. Make ignore_cache in llm content filter to true by default to avoid confusions
* Refactor: Update LlmConfig in LLMExtractionStrategy class and deprecate old params
* updated tests, docs and readme
- Add ignore_default_value option to to_serializable_dict
- Add viewport dict support in BrowserConfig
- Replace FastFilterChain with FilterChain
- Add deprecation warnings for unwanted properties
- Clean up unused imports
- Rename example files for consistency
- Add comprehensive Docker configuration tutorial
BREAKING CHANGE: FastFilterChain has been replaced with FilterChain
Add JWT token-based authentication to Docker server and client.
Refactor server architecture for better code organization and error handling.
Move Dockerfile to root deploy directory and update configuration.
Add comprehensive documentation and examples.
BREAKING CHANGE: Docker server now requires authentication by default.
Endpoints require JWT tokens when security.jwt_enabled is true in config.
Add supervisor configuration for managing Redis and Gunicorn processes
Replace direct process management with supervisord
Add secure and token-free API server variants
Implement JWT authentication for protected endpoints
Update datetime handling in async dispatcher
Add email domain verification
BREAKING CHANGE: Server startup now uses supervisord instead of direct process management
Implements a new AsyncHTTPCrawlerStrategy class that provides a fast, memory-efficient alternative to browser-based crawling. Features include:
- Support for HTTP/HTTPS requests with configurable methods, headers, and timeouts
- File and raw content handling capabilities
- Streaming response processing for large files
- Customizable request/response hooks
- Comprehensive error handling
Also refactors browser management code into separate module for better organization.
Add comprehensive example demonstrating Google Search Results Page (SERP) API implementation using crawl4ai. The example includes:
- Basic web crawling setup
- LLM-based extraction
- Schema generation
- Golden standard implementation
- CrawlerHub usage
The example serves as a reference for implementing SERP API functionality with various extraction strategies.
Improve configuration serialization with better handling of frozensets and slots.
Expand deep crawling module exports and documentation.
Add comprehensive API usage examples in Docker README.
- Add support for frozenset serialization
- Improve error handling in config loading
- Export additional deep crawling components
- Enhance Docker API documentation with detailed examples
- Fix ContentTypeFilter initialization
Remove content filter related code and parameters as part of simplifying the crawler configuration. This includes:
- Removing ContentFilter import and related classes
- Removing content_filter parameter from CrawlerRunConfig
- Cleaning up LLMExtractionStrategy constructor parameters
BREAKING CHANGE: Removed content_filter parameter from CrawlerRunConfig. Users should migrate to using extraction strategies for content filtering.
Implements a full-featured CLI for Crawl4AI with the following capabilities:
- Basic and advanced web crawling
- Configuration management via YAML/JSON files
- Multiple extraction strategies (CSS, XPath, LLM)
- Content filtering and optimization
- Interactive Q&A capabilities
- Various output formats
- Comprehensive documentation and examples
Also includes:
- Home directory setup for configuration and cache
- Environment variable support for API tokens
- Test suite for CLI functionality
Implements a new proxy rotation system with the following changes:
- Add ProxyRotationStrategy abstract base class
- Add RoundRobinProxyStrategy concrete implementation
- Integrate proxy rotation with AsyncWebCrawler
- Add proxy_rotation_strategy parameter to CrawlerRunConfig
- Add example script demonstrating proxy rotation usage
- Remove deprecated synchronous WebCrawler code
- Clean up rate limiting documentation
BREAKING CHANGE: Removed synchronous WebCrawler support and related rate limiting configurations
- Add HTML attribute preservation in GoogleSearchCrawler
- Fix lxml import references in utils.py
- Remove unused ssl_certificate.json
- Clean up imports and code organization in hub.py
- Update test case formatting and remove unused image search test
BREAKING CHANGE: Removed ssl_certificate.json file which might affect existing certificate validations
- Added proper return type hints for DeepCrawlStrategy.arun method
- Added __call__ method to DeepCrawlStrategy for easier usage
- Removed redundant comments and imports
- Cleaned up type hints in DFS strategy
- Removed empty docker_client.py and .continuerules
- Added .private/ to gitignore
BREAKING CHANGE: DeepCrawlStrategy.arun now returns Union[CrawlResultT, List[CrawlResultT], AsyncGenerator[CrawlResultT, None]]
refactor(docker): restructure docker-compose for modular configuration
- Added reusable base configuration block (x-base-config) for ports, environment variables, volumes, deployment resources, restart policy, and health check.
- Updated services to include base configuration directly using `<<: *base-config` syntax.
- Removed redundant `base-config` service definition.
Split deep crawling code into separate strategy files for better organization and maintainability. Added new BFF (Best First) and DFS crawling strategies. Introduced base strategy class and common types.
BREAKING CHANGE: Deep crawling implementation has been split into multiple files. Import paths for deep crawling strategies have changed.
Restructure deep crawling code into a dedicated module with improved organization:
- Move deep crawl logic from async_deep_crawl.py to deep_crawling/
- Create separate files for BFS strategy, filters, and scorers
- Improve code organization and maintainability
- Add optimized implementations for URL filtering and scoring
- Rename DeepCrawlHandler to DeepCrawlDecorator for clarity
BREAKING CHANGE: DeepCrawlStrategy and BreadthFirstSearchStrategy imports need to be updated to new package structure
Implements deep crawling functionality with a new BreadthFirstSearch strategy:
- Add DeepCrawlStrategy base class and BFS implementation
- Integrate deep crawling with AsyncWebCrawler via decorator pattern
- Update CrawlerRunConfig to support deep crawling parameters
- Add pagination support for Google Search crawler
BREAKING CHANGE: AsyncWebCrawler.arun and arun_many return types now include deep crawl results
Changes cache mode from BYPASS to WRITE_ONLY when cache is disabled to ensure
results are still cached for future use. Also adds error handling for non-JSON
LLM responses and comprehensive API test suite.
- Changes default cache fallback from BYPASS to WRITE_ONLY
- Adds error handling for LLM JSON parsing
- Introduces new test suite for API endpoints
Complete overhaul of Docker deployment setup with improved architecture:
- Add Redis integration for task management
- Implement rate limiting and security middleware
- Add Prometheus metrics and health checks
- Improve error handling and logging
- Add support for streaming responses
- Implement proper configuration management
- Add platform-specific optimizations for ARM64/AMD64
BREAKING CHANGE: Docker deployment now requires Redis and new config.yml structure
Add comprehensive Docker deployment configuration with:
- New .dockerignore and .llm.env.example files
- Enhanced Dockerfile with multi-stage build and optimizations
- Detailed README with setup instructions and environment configurations
- Improved requirements.txt with Gunicorn
- Better error handling in async_configs.py
BREAKING CHANGE: Docker deployment now requires .llm.env file for API keys
Add Docker service integration with FastAPI server and client implementation.
Implement serialization utilities for BrowserConfig and CrawlerRunConfig to support
Docker service communication. Clean up imports and improve error handling.
- Add Crawl4aiDockerClient class
- Implement config serialization/deserialization
- Add FastAPI server with streaming support
- Add health check endpoint
- Clean up imports and type hints
Add Docker deployment setup with FastAPI server implementation for Crawl4AI:
- Create Dockerfile with Python 3.10 and Playwright dependencies
- Implement FastAPI server with streaming and non-streaming endpoints
- Add request/response models and JSON serialization
- Include test script for API verification
Also includes:
- Update .gitignore for Continue development files
- Add project rules in .continuerules
- Clean up async_dispatcher.py formatting
Major reorganization of the project structure:
- Moved legacy synchronous crawler code to legacy folder
- Removed deprecated CLI and docs manager
- Consolidated version manager into utils.py
- Added CrawlerHub to __init__.py exports
- Fixed type hints in async_webcrawler.py
- Fixed minor bugs in chunking and crawler strategies
BREAKING CHANGE: Removed synchronous WebCrawler, CLI, and docs management functionality. Users should migrate to AsyncWebCrawler.
Add JavaScript execution result handling and improve PDF processing capabilities:
- Add js_execution_result to CrawlResult and AsyncCrawlResponse models
- Implement execution result capture in AsyncPlaywrightCrawlerStrategy
- Add batch processing for PDF pages with configurable batch size
- Enhance JsonElementExtractionStrategy with better schema generation
- Add HTML optimization utilities
BREAKING CHANGE: PDF processing now uses batch processing by default
Add new PDF processing module with the following features:
- PDF text extraction and formatting to HTML/Markdown
- Image extraction with multiple format support (JPEG, PNG, TIFF)
- Link extraction from PDF documents
- Metadata extraction including title, author, dates
- Support for both local and remote PDF files
Also includes:
- New configuration options for HTML attribute handling
- Internal/external link filtering improvements
- Version bump to 0.4.300b4
Enhanced markdown formatting, fixed list indentation, and improved readability across multiple API documentation files:
- arun.md
- arun_many.md
- async-webcrawler.md
- parameters.md
Changes include:
- Consistent list formatting and indentation
- Better spacing between sections
- Clearer separation of content blocks
- Fixed quotation marks and code block formatting
Uncomments demonstration code for memory dispatcher, streaming support,
content scraping, JSON schema generation, LLM markdown, and robots compliance
in the v0.4.3b2 features demo file. Also adds fake-useragent package as a
project dependency.
This change makes all feature demonstrations active by default and ensures
proper user agent handling capabilities.
Modify proxy rotation example to include empty user agent setting and comment out other demo functions for focused testing. This change simplifies the demo file to focus specifically on proxy rotation functionality.
No breaking changes.
Redesign user agent generation to be more modular and reliable:
- Add abstract base class UAGen for user agent generation
- Implement ValidUAGenerator using fake-useragent library
- Add OnlineUAGenerator for fetching real-world user agents
- Update browser configurations to use new UA generation system
- Improve client hints generation
This change makes the user agent system more maintainable and provides better real-world user agent coverage.
Add support for direct CDP URL configuration in BrowserConfig and ManagedBrowser classes. This allows connecting to remote browser instances using custom CDP endpoints instead of always launching a local browser.
- Added cdp_url parameter to BrowserConfig
- Added cdp_url support in ManagedBrowser.start() method
- Updated documentation for new parameters
Update the demo script to use the new crawler.arun_many() API instead of dispatcher.run_urls()
and fix result access patterns. Also improve code formatting and remove
extra whitespace.
- Replace dispatcher.run_urls with crawler.arun_many
- Update streaming demo to use new API and correct result access
- Clean up whitespace and formatting
- Simplify result property access patterns
Clean up whitespace and improve readability in v0_4_3b2_features_demo.py:
- Remove excessive blank lines between functions
- Improve config formatting for better readability
- Uncomment memory dispatcher demo in main function
No breaking changes.
- Restructure multi-URL crawling documentation with better formatting and examples
- Update code examples to use new API syntax (arun_many)
- Add detailed parameter explanations for RateLimiter and Dispatchers
- Enhance CSS styling for better documentation readability
- Fix outdated method calls in feature demo script
BREAKING CHANGE: Updated dispatcher.run_urls() to crawler.arun_many() in examples
- Add RelevantContentFilter to __init__.py exports
- Update version to 0.4.3b3
- Enhance type hints in async_configs.py
- Remove empty utils.scraping.py file
- Update mkdocs configuration with version info and GitHub integration
BREAKING CHANGE: None
Resolves merge conflict in README.md by removing outdated version 0.4.24x information and keeping current version 0.4.3bx details. Updates release notes description to reflect current features including Memory Dispatcher System, Streaming Support, and other improvements.
No breaking changes.
Update version numbers to v0.4.3bx throughout README.md
Fix contributing guidelines link to point to CONTRIBUTORS.md
Update Aravind's role in CONTRIBUTORS.md to Head of Community and Product
Add pre-release installation instructions
Fix minor formatting in personal story section
No breaking changes
Rename and replace the features demo file to reflect the beta 2 version number.
The old v0.4.3 demo file is removed and replaced with a new beta 2 version.
Renames:
- docs/examples/v0_4_3_features_demo.py -> docs/examples/v0_4_3b2_features_demo.py
Update example scripts to reflect latest API changes and improve demonstrations:
- Increase test URLs in dispatcher example from 20 to 40 pages
- Comment out unused dispatcher strategies for cleaner output
- Fix scraping strategies performance script to use correct object notation
- Update v0_4_3_features_demo with additional feature mentions and uncomment demo sections
These changes make the examples more current and better aligned with the actual API.
