96 lines
3.5 KiB
YAML
96 lines
3.5 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_v3
|
|
|
|
|
|
nav:
|
|
- Home: index.md
|
|
|
|
- Tutorials:
|
|
- "Getting Started": tutorials/getting-started.md
|
|
- "AsyncWebCrawler Basics": tutorials/async-webcrawler-basics.md
|
|
- "Targeted Crawling Techniques": tutorials/targeted-crawling.md
|
|
- "Link & Media Analysis": tutorials/link-media-analysis.md
|
|
- "Advanced Features (Proxy, PDF, Screenshots)": tutorials/advanced-features.md
|
|
- "Hooks & Custom Code": tutorials/hooks-custom.md
|
|
- "Markdown Generation Basics": tutorials/markdown-basics.md
|
|
- "Extracting JSON (No LLM)": tutorials/json-extraction-basic.md
|
|
- "Extracting JSON (LLM)": tutorials/json-extraction-llm.md
|
|
- "Deploying with Docker (Quickstart)": tutorials/docker-quickstart.md
|
|
|
|
- How-To Guides:
|
|
- "Advanced Browser Configuration": how-to/advanced-browser-config.md
|
|
- "Managing Browser Contexts & Remote Browsers": how-to/browser-contexts-remote.md
|
|
- "Identity-Based Crawling (Anti-Bot)": how-to/identity-anti-bot.md
|
|
- "Link & Media Analysis": how-to/link-media-analysis.md
|
|
- "Markdown Generation Customization": how-to/markdown-custom.md
|
|
- "Structured Data Extraction (Advanced)": how-to/structured-data-advanced.md
|
|
- "Deployment Options": how-to/deployment-options.md
|
|
- "Performance & Caching": how-to/performance-caching.md
|
|
|
|
- Explanations:
|
|
- "AsyncWebCrawler & Internal Flow": explanations/async-webcrawler-flow.md
|
|
- "Configuration Objects Explained": explanations/configuration-objects.md
|
|
- "Browser Context & Managed Browser": explanations/browser-management.md
|
|
- "Markdown Generation Architecture": explanations/markdown-architecture.md
|
|
- "Extraction & Chunking Strategies": explanations/extraction-chunking.md
|
|
- "Identity-Based Crawling & Anti-Bot": explanations/identity-anti-bot.md
|
|
- "Deployment Architectures": explanations/deployment-architectures.md
|
|
|
|
- Reference:
|
|
- "Configuration": reference/configuration.md
|
|
- "Core Crawler": reference/core-crawler.md
|
|
- "Browser Strategies": reference/browser-strategies.md
|
|
- "Markdown Generation": reference/markdown-generation.md
|
|
- "Content Filters": reference/content-filters.md
|
|
- "Extraction Strategies": reference/extraction-strategies.md
|
|
- "Chunking Strategies": reference/chunking-strategies.md
|
|
- "Identity & Utility": reference/identity-utilities.md
|
|
- "Models": reference/models.md
|
|
|
|
- Blog:
|
|
- "Blog Overview": blog/index.md
|
|
# You can add real-life application posts here in the future
|
|
# - "Cool Real-World E-Commerce Scraping": blog/ecommerce-case-study.md
|
|
# - "Dealing with Complex Anti-Bot Systems": blog/anti-bot-tricks.md
|
|
|
|
|
|
theme:
|
|
name: terminal
|
|
palette: dark
|
|
|
|
plugins:
|
|
- search
|
|
- mkdocstrings:
|
|
handlers:
|
|
python:
|
|
analysis:
|
|
follow_imports: true
|
|
rendering:
|
|
show_root_full_path: false
|
|
|
|
markdown_extensions:
|
|
- codehilite
|
|
- toc:
|
|
permalink: true
|
|
- 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 |