article-extractor

Extract clean text content from web URLs using Mozilla Readability or Trafilatura.

Updated Feb 1, 2026

Search Tags:#automation #readability #web scraping #article extraction #text processing #content cleaning

Ready to run

npx skills add https://github.com/nferrer-dev/claude-dotfiles --skill article-extractor-nferrer-dev

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @mozilla/readability-cli, trafilatura, curl, python3.

What problem does it solve?

This skill removes the friction of reading online content by stripping away ads, navigation menus, and layout clutter to provide a clean, readable text version of any URL.

Core Features & Use Cases

Intelligent Extraction: Uses Mozilla Readability or Trafilatura to identify the main content of a page.
Fallback Parsing: Employs a custom HTML parser to ensure content is captured even when specialized tools fail.
Use Case: When you need to summarize a long-form blog post or tutorial for research, use this skill to extract the core text into a clean file for your analysis.

Quick Start

Use the article-extractor skill to download and clean the content from the provided URL.

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 URL without ads and navigation menus?▼

To extract clean text from a web URL, this skill uses Mozilla Readability and Trafilatura engines to strip away advertisements, navigation elements, and layout clutter, leaving only the core readable content. A custom HTML parser acts as a fallback for difficult pages.

What is the best way to scrape article content from news sites or technical tutorials?▼

The best way to scrape article content from news sites or tutorials is using automated extraction engines that identify main page content. This skill supports diverse web sources, intelligently isolating text for research or analysis.

Do I need Python and curl installed to extract readable web content?▼

Yes, you need Python and curl installed to extract readable web content, as this skill requires curl for downloading web pages and Python for executing the text processing and file management tasks.

How does Trafilatura compare to Mozilla Readability for web scraping?▼

Trafilatura and Mozilla Readability are both used for web scraping and content cleaning within this skill, offering dual intelligent extraction engines to ensure reliable text capture. They work together with a fallback HTML parser for maximum coverage.

What should I do if web scraping fails to extract the main article text?▼

If web scraping fails to extract the main article text using specialized tools, this skill employs a custom HTML parser as a fallback mechanism to ensure core content is still captured from the web page.