---

name: trafilatura description: "Extract clean article text from websites using trafilatura. Use when you need to read web pages, articles, blog posts, or documentation. Better than WebFetch for article content. Triggers: 'read this URL', 'fetch article', 'extract text from', 'what does this page say'."

Trafilatura - Web Content Extraction

Extract clean, readable text from web pages. Use this instead of WebFetch when you need the actual article content (not a summary).

Installation

Copyuv tool install trafilatura

Basic Usage

Extract article as markdown:

Copytrafilatura -u "https://example.com/article" --markdown

Extract as plain text:

Copytrafilatura -u "https://example.com/article"

With metadata (title, author, date):

Copytrafilatura -u "https://example.com/article" --markdown --with-metadata

When to Use

Common Patterns

Read and analyze an article:

Copytrafilatura -u "https://blog.example.com/post" --markdown

Then discuss the content with the user.

Research a topic across multiple URLs:

Copy# Run for each URL, compare findings
trafilatura -u "https://site1.com/article" --markdown
trafilatura -u "https://site2.com/article" --markdown

Extract academic paper info:

Copytrafilatura -u "https://arxiv.org/abs/2512.12345" --markdown --with-metadata

Options Reference

Troubleshooting

Empty output: Page may be JS-rendered (trafilatura can't handle SPAs) Timeout: Large pages may need --timeout 60 Encoding issues: Add --encoding utf-8

vs WebFetch

• trafilatura: Gets full article text, better for reading/analysis
• WebFetch: Gets AI summary, better for quick lookups
• yomu skill: Similar to trafilatura but with different extraction engine

Use trafilatura when you need the actual content, not a summary.