Article Extractor

Extract main content from web articles and blog posts, removing navigation, ads, and clutter. Saves clean, readable text.

Prerequisites

This skill requires UV for dependency management. Run from the tapestry-skills project root.

Workflow

URL → Validate → Detect Tool → Extract Content → Sanitize Filename → Save

Tools (in priority order):

1. reader (Mozilla Readability) - best for most articles
2. trafilatura - excellent for blogs/news (included in dependencies)
3. Fallback (tapestry-extract-html) - works without external tools