documentation-scraper

Turn any documentation portal (GitBook, Mintlify, Docusaurus, ReadTheDocs) into LLM-ready Markdown, vector RAG JSONL, llms.txt, and styled offline PDFs. Zero-config CLI, desktop GUI & FastMCP server.

A documentation scraper for developers which deep crawls any website and creates a markdown context file for that site

通用高可用离线文档抓取与转换系统 (Generic High-Availability Documentation Scraper & Converter)

Private Chrome extension (MV3) to extract, compile, and export documentation from authenticated web sessions into AI-ready Markdown, JSON, and CSV bundles.

Python web scraper for BetterDocs documentation sites. Auto-discovers content and exports to JSON, Markdown & CSV. Easy to configure.

A reusable Python scraper framework for efficiently crawling documentation websites and preparing content for AI training, with async support and structured output.