# Trafilatura — card for AI agents

Extract text and metadata from web pages; tools for web scraping and content extraction.

Category: Scraping, browsers and parsing · PyPI package `trafilatura` · latest version 2.3.1 (checked 2026-11-01)
Install: `pip install trafilatura`
License: Apache-2.0 (permissive)

In your own product (generator, app, hosted service): **yes**. Permissive license: ship it inside your own product, closed or open source, and keep its license and copyright notice.

## Numbers (AgentGid data)
- Gid Score: 59.4 (#992 of all tools, 32 of 140 in its category)
- Used in 8 public projects set up for AI coding agents (0.1%)
- Downloads last week: 4,198,957 (as of 2026-11-17), +15.3% over 4 weeks
- GitHub stars: 7,144 (as of 2026-11-17)
- Last push: 2026-11-16

## Often used with
python-dotenv 75.8%, Pydantic 64.6%, Beautiful Soup 60.6%, NumPy 55.6%, Requests 53.5%, Uvicorn 51.5%

## Checked alternatives (same job)
- Beautiful Soup: https://agentgid.com/tools/beautifulsoup4/agent.md
- lxml: https://agentgid.com/tools/lxml/agent.md
- Playwright (Python): https://agentgid.com/tools/playwright/agent.md
- Selenium: https://agentgid.com/tools/selenium/agent.md
- html5lib: https://agentgid.com/tools/html5lib/agent.md

## Links
- AgentGid page: https://agentgid.com/tools/trafilatura/
- Homepage: https://trafilatura.readthedocs.io
- Repository: https://github.com/adbar/trafilatura

---
AgentGid's catalog is curated: every entry was checked against the maker's official pages (registry, repository, license and pricing pages) on the date shown; a license value shows the quote it stands on wherever AgentGid has one. Usage numbers come from AgentGid's own scan of public repositories set up for AI coding agents. Claims by makers are reported, not tested by AgentGid.
