83 lines
3.9 KiB
YAML
83 lines
3.9 KiB
YAML
site_name: Crawl4AI Documentation
|
|
site_description: 🔥🕷️ Crawl4AI, Open-source LLM Friendly Web Crawler & Scrapper
|
|
site_url: https://docs.crawl4ai.com
|
|
repo_url: https://github.com/unclecode/crawl4ai
|
|
repo_name: unclecode/crawl4ai
|
|
docs_dir: docs/md_v2
|
|
|
|
nav:
|
|
- Home: 'index.md'
|
|
- 'Installation': 'basic/installation.md'
|
|
- 'Quick Start': 'basic/quickstart.md'
|
|
|
|
- Basic:
|
|
- 'Simple Crawling': 'basic/simple-crawling.md'
|
|
- 'Output Formats': 'basic/output-formats.md'
|
|
- 'Browser Configuration': 'basic/browser-config.md'
|
|
- 'Page Interaction': 'basic/page-interaction.md'
|
|
- 'Content Selection': 'basic/content-selection.md'
|
|
|
|
- Advanced:
|
|
- 'Content Processing': 'advanced/content-processing.md'
|
|
- 'Magic Mode': 'advanced/magic-mode.md'
|
|
- 'Hooks & Auth': 'advanced/hooks-auth.md'
|
|
- 'Proxy & Security': 'advanced/proxy-security.md'
|
|
- 'Session Management': 'advanced/session-management.md'
|
|
- 'Session Management (Advanced)': 'advanced/session-management-advanced.md'
|
|
|
|
- Extraction:
|
|
- 'Overview': 'extraction/overview.md'
|
|
- 'LLM Strategy': 'extraction/llm.md'
|
|
- 'Json-CSS Extractor Basic': 'extraction/css.md'
|
|
- 'Json-CSS Extractor Advanced': 'extraction/css-advanced.md'
|
|
- 'Cosine Strategy': 'extraction/cosine.md'
|
|
- 'Chunking': 'extraction/chunking.md'
|
|
|
|
- Tutorial:
|
|
- 'Episode 1: Introduction to Crawl4AI and Basic Installation': 'tutorial/episode_01_Introduction_to_Crawl4AI_and_Basic_Installation.md'
|
|
- 'Episode 2: Overview of Advanced Features': 'tutorial/episode_02_Overview_of_Advanced_Features.md'
|
|
- 'Episode 3: Browser Configurations & Headless Crawling': 'tutorial/episode_03_Browser_Configurations_&_Headless_Crawling.md'
|
|
- 'Episode 4: Advanced Proxy and Security Settings': 'tutorial/episode_04_Advanced_Proxy_and_Security_Settings.md'
|
|
- 'Episode 5: JavaScript Execution and Dynamic Content Handling': 'tutorial/episode_05_JavaScript_Execution_and_Dynamic_Content_Handling.md'
|
|
- 'Episode 6: Magic Mode and Anti-Bot Protection': 'tutorial/episode_06_Magic_Mode_and_Anti-Bot_Protection.md'
|
|
- 'Episode 7: Content Cleaning and Fit Markdown': 'tutorial/episode_07_Content_Cleaning_and_Fit_Markdown.md'
|
|
- 'Episode 8: Media Handling: Images, Videos, and Audio': 'tutorial/episode_08_Media_Handling:_Images,_Videos,_and_Audio.md'
|
|
- 'Episode 9: Link Analysis and Smart Filtering': 'tutorial/episode_09_Link_Analysis_and_Smart_Filtering.md'
|
|
- 'Episode 10: Custom Headers, Identity, and User Simulation': 'tutorial/episode_10_Custom_Headers,_Identity,_and_User_Simulation.md'
|
|
- 'Episode 11.1: Extraction Strategies: JSON CSS': 'tutorial/episode_11_1_Extraction_Strategies:_JSON_CSS.md'
|
|
- 'Episode 11.2: Extraction Strategies: LLM': 'tutorial/episode_11_2_Extraction_Strategies:_LLM.md'
|
|
- 'Episode 11.3: Extraction Strategies: Cosine': 'tutorial/episode_11_3_Extraction_Strategies:_Cosine.md'
|
|
- 'Episode 12: Session-Based Crawling for Dynamic Websites': 'tutorial/episode_12_Session-Based_Crawling_for_Dynamic_Websites.md'
|
|
- 'Episode 13: Chunking Strategies for Large Text Processing': 'tutorial/episode_13_Chunking_Strategies_for_Large_Text_Processing.md'
|
|
- 'Episode 14: Hooks and Custom Workflow with AsyncWebCrawler': 'tutorial/episode_14_Hooks_and_Custom_Workflow_with_AsyncWebCrawler.md'
|
|
|
|
- API Reference:
|
|
- 'AsyncWebCrawler': 'api/async-webcrawler.md'
|
|
- 'AsyncWebCrawler.arun()': 'api/arun.md'
|
|
- 'CrawlResult': 'api/crawl-result.md'
|
|
- 'Strategies': 'api/strategies.md'
|
|
|
|
theme:
|
|
name: terminal
|
|
palette: dark
|
|
|
|
markdown_extensions:
|
|
- pymdownx.highlight:
|
|
anchor_linenums: true
|
|
- pymdownx.inlinehilite
|
|
- pymdownx.snippets
|
|
- pymdownx.superfences
|
|
- admonition
|
|
- pymdownx.details
|
|
- attr_list
|
|
- tables
|
|
|
|
extra_css:
|
|
- assets/styles.css
|
|
- assets/highlight.css
|
|
- assets/dmvendor.css
|
|
|
|
extra_javascript:
|
|
- assets/highlight.min.js
|
|
- assets/highlight_init.js
|