refactor(docs): reorganize documentation structure and update styles

Reorganize documentation into core/advanced/extraction sections for better navigation. Update terminal theme styles and add rich library for better CLI output. Remove redundant tutorial files and consolidate content into core sections. Add personal story to index page for project context. BREAKING CHANGE: Documentation structure has been significantly reorganized
2025-01-07 20:49:50 +08:00
parent ae376f15fb
commit ca3e33122e
87 changed files with 4869 additions and 8951 deletions
--- a/copy.yml
+++ b/copy.yml
@@ -0,0 +1,94 @@
+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'
+  - 'Docker Deplotment': 'basic/docker-deploymeny.md'
+  - 'Quick Start': 'basic/quickstart.md'
+  - Changelog & Blog:
+    - 'Blog Home': 'blog/index.md'
+    - 'Latest (0.4.1)': 'blog/releases/0.4.1.md'
+    - 'Changelog': 'https://github.com/unclecode/crawl4ai/blob/main/CHANGELOG.md'
+
+  - Core:
+    - 'Simple Crawling': 'basic/simple-crawling.md'
+    - 'Crawler Result': 'basic/crawler-result.md'
+    - 'Crawler & Browser Params': 'basic/browser-crawler-config.md'
+    - 'Markdown Generation': 'basic/markdown-generation.md'
+    - 'Fit Markdown': 'basic/fit-markdown.md'
+    - 'Page Interaction': 'basic/page-interaction.md'
+    - 'Content Selection': 'basic/content-selection.md'
+    - 'Cache Modes': 'basic/cache-modes.md'
+    - 'Local files & Raw HTML': 'basic/local-files.md'
+    - 'File Downloading': 'basic/file-downloading.md'
+
+  - Advanced:
+    - 'Link & Media Handling': 'advanced/link-media.md'
+    - 'Hooks & Auth': 'advanced/hooks-auth.md'
+    - 'Lazy Loading': 'advanced/lazy-loading.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'
+
+  - API Reference:
+    - 'Parameters Table': 'api/parameters.md'
+    - 'AsyncWebCrawler': 'api/async-webcrawler.md'
+    - 'AsyncWebCrawler.arun()': 'api/arun.md'
+    - 'CrawlResult': 'api/crawl-result.md'
+    - 'Strategies': 'api/strategies.md'
+    
+  - Tutorial:
+    - '1. Getting Started': 'tutorial/episode_01_Introduction_to_Crawl4AI_and_Basic_Installation.md'
+    - '2. Advanced Features': 'tutorial/episode_02_Overview_of_Advanced_Features.md'
+    - '3. Browser Setup': 'tutorial/episode_03_Browser_Configurations_&_Headless_Crawling.md'
+    - '4. Proxy Settings': 'tutorial/episode_04_Advanced_Proxy_and_Security_Settings.md'
+    - '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'
+    - '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'
+    - '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'
+
+
+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