article-extractor

Extract and clean article text from URLs using Bash, trafilatura, or curl.

Updated Jan 2, 2026

Search Tags:#web scraping #text extraction #article extraction #article analysis #clean content

Ready to run

npx skills add https://github.com/cooopmac/nourish --skill article-extractor-cooopmac

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: article-extractor
Source: https://github.com/cooopmac/nourish/tree/main/.claude/project/skills/article-extractor
Command: npx skills add https://github.com/cooopmac/nourish --skill article-extractor-cooopmac

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @mozilla/readability-cli, trafilatura, curl, python3, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the problem of extracting clean article content from URLs (blog posts, articles, tutorials) into readable text format without ads, navigation, or clutter.

Core Features & Use Cases

URL Extraction: Extracts main content from any provided URL.
Clutter Removal: Removes navigation, ads, newsletter signups, and other clutter.
Save and Preview: Saves content as text file with a preview.

Quick Start

Use the article-extractor skill with the command: article-extractor "http://example.com/blog-post"

Frequently Asked Questions about article-extractor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract clean text from a web article URL?▼

To extract clean text from a web article, provide the URL to the skill. It uses tools like Readability and Trafilatura to remove ads and navigation, returning readable text content.

Does the text extraction remove ads and website clutter?▼

Yes, the text extraction specifically removes ads, navigation, and newsletter signups. It parses the URL to isolate the main article content into a clean, readable format.

Can I use curl and Python to extract article content from a blog post?▼

Yes, you can use curl and Python parsing to extract article content. The skill integrates curl and Python3 alongside Trafilatura to fetch and clean content from URLs.

What is the best way to save extracted web content as a text file?▼

The best way to save extracted web content is using this skill's built-in save function. It processes the URL and outputs a text file containing the clean article content and a preview.

How does Trafilatura compare to Readability for article analysis?▼

Trafilatura and Readability are both used for article analysis within this skill. They work together to ensure robust text extraction and clutter removal from various web sources.