Data / Repositories / Data extraction
Data extraction repositories on GitHub: 12 ranked by stars
12 public repositories tagged Data extraction are on GitHub, with 428,222 stars between them; 7 had a push in the last 30 days. Most are written in Python (6), TypeScript (2), JavaScript (2). The most starred: firecrawl/firecrawl (191,485), D4Vinci/Scrapling (86,357), unclecode/crawl4ai (85,530).
SpecStream is the live web data engine for teams and agents. It reads open-source repositories on GitHub and keeps what it reads, and this page groups that reading by topic. Ask for the repositories you track by topic, language, license or activity, and new ones and changes arrive in your sheet, CRM, Slack or agent.
Every repository, most starred first
| Repository | What it is | Language | Stars | Forks | License | Last push | Read |
|---|---|---|---|---|---|---|---|
| firecrawl/firecrawl | Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. | TypeScript | 191,485 | 10,124 | AGPL-3.0 | Oct 14 | Oct 14 |
| D4Vinci/Scrapling | An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! | Python | 86,357 | 8,855 | BSD-3-Clause | Oct 8 | Oct 8 |
| unclecode/crawl4ai | Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key. | Python | 85,530 | 8,879 | Apache-2.0 | Oct 14 | Oct 14 |
| ScrapeGraphAI/Scrapegraph-ai | Python scraper based on AI | Python | 31,623 | 3,221 | MIT | Oct 6 | Oct 8 |
| browserbase/stagehand | The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more. | TypeScript | 25,666 | 1,756 | MIT | Oct 14 | Oct 14 |
| brightdata/brightdata-mcp | A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access. | JavaScript | 2,675 | 332 | MIT | Oct 14 | Oct 14 |
| raznem/parsera | Lightweight library for scraping web-sites with LLMs | Python | 1,358 | 78 | GPL-2.0 | Dec 17, 2025 | Sep 21 |
| yfedoseev/pdf_oxide | The fastest PDF library for Python and Rust. Text extraction, image extraction, markdown conversion, PDF creation & editing. 0.8ms mean, 5× faster than industry leaders, 100% pass… | Rust | 1,073 | 133 | Apache-2.0 | Oct 6 | Oct 11 |
| us/crw | Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl… | Rust | 1,059 | 84 | AGPL-3.0 | Sep 21 | Sep 21 |
| ScrapeGraphAI/scrapecraft | AI-powered web scraping editor with visual workflow builder. Build, test & deploy web scrapers using natural language. Powered by ScrapeGraphAI & LangGraph. | Python | 699 | 112 | MIT | Dec 26, 2025 | Sep 21 |
| jpjacobpadilla/Stealth-Requests | Undetected web-scraping & seamless HTML parsing in Python! | Python | 564 | 57 | MIT | Sep 19 | Sep 21 |
| umbrellaDocumentation/Web-Data-Scraper | Web Data Scraper - no-code internet scraping. Extract and export to CSV, Excel, JSON, Google Sheets, and Webhook. | JavaScript | 133 | 116 | Mar 17 | Sep 21 |
By language
- Python 6
Related topics
- Web scraping 10
- AI 7
- LLM 7
- Webscraping 7
- Python 7
- Crawler 6
- Scraping 6
- Web crawler 6
- AI agents 5
- Markdown 5
- Web scraper 5
- MCP 4
Read from GitHub by SpecStream between September 21, 2026 and October 14, 2026; each row shows the day its repository was read. Stars and pushes change every day, and the GitHub page is the current one. Forks and archived repositories are left out.