# Trafilatura Web Text Extraction and Crawling Toolkit

> Trafilatura is a Python package and CLI tool for gathering text from the web. It handles crawling, downloading, and extracting main text content, metadata, and comments from raw HTML, outputting clean structured data in CSV, JSON, Markdown, XML, and TXT formats.

- Skill: `agentskillexchange/trafilatura-web-text-extraction-and-crawling-toolkit` (Agent Skill)
- Install (CLI): `npx skillmds@latest add agentskillexchange/trafilatura-web-text-extraction-and-crawling-toolkit`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/trafilatura-web-text-extraction-and-crawling-toolkit/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/agentskillexchange/trafilatura-web-text-extraction-and-crawling-toolkit

---


# Trafilatura Web Text Extraction and Crawling Toolkit

Trafilatura is a Python package and CLI tool for gathering text from the web. It handles crawling, downloading, and extracting main text content, metadata, and comments from raw HTML, outputting clean structured data in CSV, JSON, Markdown, XML, and TXT formats.

## Installation

Requirements and caveats from upstream:
- [![Python package](https://img.shields.io/pypi/v/trafilatura.svg)](https://pypi.python.org/pypi/trafilatura)
- [![Python versions](https://img.shields.io/pypi/pyversions/trafilatura.svg)](https://pypi.python.org/pypi/trafilatura)
- Trafilatura is a cutting-edge **Python package and command-line tool**

Basic usage or getting-started notes:
- to run the evaluation with the latest data and packages.
- [Getting started with Trafilatura](https://trafilatura.readthedocs.io/en/latest/quickstart.html)
- is straightforward. For more information and detailed guides, visit

- Source: https://github.com/adbar/trafilatura
- Extracted from upstream docs: https://raw.githubusercontent.com/adbar/trafilatura/HEAD/README.md

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/trafilatura-web-text-extraction-crawling/)