skills.rest
michalparkola
michalparkolaCOMMUNITY
Explore all skills by this author →
Website𝕏@michalparkolaGitHub

article-extractor

Extract article content from URLs and save it as a text file.

515|67|Updated Oct 17, 2025
Search Tags:#automation#readability#web scraping#article#text extraction#content cleanup#extractor
One-click install
npx skills add https://github.com/michalparkola/tapestry-skills-for-claude-code --skill article-extractor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: article-extractor
Source: https://github.com/michalparkola/tapestry-skills-for-claude-code/tree/main/article-extractor
Command: npx skills add https://github.com/michalparkola/tapestry-skills-for-claude-code --skill article-extractor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires reader-cli, trafilatura, and includes scripts (resource) components.

What problem does it solve?

Web articles are often cluttered with ads, navigation, and sign-up forms, making focused reading difficult and content extraction messy. This skill removes the noise.

Core Features & Use Cases

  • Clutter-Free Extraction: Automatically removes ads, navigation, and newsletter pop-ups for a clean reading experience.
  • Multiple Methods: Employs Mozilla Readability, Trafilatura, or a fallback method for robust content extraction from diverse websites.
  • Use Case: Save a tutorial blog post as a clean text file, free from distractions, for focused learning, offline reference, or as input for other AI tasks.

Quick Start

Extract an article from a URL

Claude will automatically use this skill when you ask:

"Extract the article from https://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 article text from a website without ads and clutter?▼

Article extraction removes ads, navigation, and pop-ups from web pages automatically. This Skill uses Mozilla Readability, Trafilatura, or a fallback method to download and clean article content, saving it as a text file with a preview of the extracted text.

Can I save blog posts and news articles as clean text files for offline reading?▼

Yes. This Skill extracts article content from URLs and saves the cleaned text to a file named after the article title, removing distractions so you can read or reference the content offline without ads or navigation elements.

What methods does article extraction use to handle different website layouts?▼

Article extraction uses a prioritized pipeline: Mozilla Readability, then Trafilatura for robust content handling, with a curl-based fallback. This multi-method approach works across diverse websites and blog formats to ensure reliable extraction.

Can I use article extraction as input for other automation tasks?▼

Yes. After extracting and cleaning article text, the saved file output serves as input for downstream tasks like summarization, analysis, or feeding content into AI workflows without manual cleanup.

Does article extraction work with paywalled or JavaScript-heavy sites?▼

Article extraction works best with standard HTML articles, blogs, and news posts. JavaScript-rendered content and paywalled sites may have limitations; the fallback method provides coverage for sites the primary methods cannot parse.

Related Skills

Explore More Content & Communication Skills→
isiouisiou

web-scraper

Extracts structured metadata and HTML content from a web page URL via the WebPageSnap API.

Community
Basic
sungaoxiang-backendsungaoxiang-backend

read-wechat-article

Extract clean text from WeChat public account articles via Playwright.

Community
Intermediate
winsorllcwinsorllc

web-fetch

Fetch and parse web content from specified URLs.

Community
Basic
eesha000009-deveesha000009-dev
1

web-reader

Extract article content, metadata, and cleaned HTML from web pages.

Community
Intermediate