skills.rest
XSIJIE975
XSIJIE975COMMUNITY
Explore all skills by this author →
GitHub

article-extractor

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

Updated Aug 23, 2026
Search Tags:#readability#text-extraction#web-content#article-extraction#offline-reading
One-click install
npx skills add https://github.com/XSIJIE975/agents-skills --skill article-extractor-xsijie975
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: article-extractor
Source: https://github.com/XSIJIE975/agents-skills/tree/main/skills/article-extractor
Command: npx skills add https://github.com/XSIJIE975/agents-skills --skill article-extractor-xsijie975

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill extracts the main content from web articles and blog posts, removing navigation, ads, newsletter signups, and other clutter to produce clean, readable text for offline use.

Core Features & Use Cases

  • Automated extraction: Retrieve article text from URLs and strip away clutter.
  • Title-aware saving: Save content to a text file named after the article title with a sanitized filename.
  • Use Case: Save research articles or blog posts for offline reading, summarization, or archiving.

Quick Start

To extract an article:

  • If reader is installed: reader "https://example.com/article" > article.txt TITLE=$(head -n 1 article.txt | sed 's/^# //') FILENAME="$TITLE.txt" mv article.txt "$FILENAME"
  • If trafilatura is installed: trafilatura --URL "https://example.com/article" --output-format txt > article.txt TITLE=$(trafilatura --URL "https://example.com/article" --json | python3 -c "import json, sys; print(json.load(sys.stdin).get('title','Article'))") FILENAME="$TITLE.txt" mv article.txt "$FILENAME"
  • Fallback (curl-based): curl -s "https://example.com/article" | python3 -c "import sys, html.parser; print('Article extraction via simple parser placeholder')" > article.txt

    Then rename as above

Frequently Asked Questions about article-extractor

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

FAQPage Schema
How do I extract readable article text from a URL for offline reading?▼

Article extraction removes navigation, ads, and clutter from web pages to produce clean text. This Skill uses CLI tools like reader or trafilatura to parse URLs and save the main content for offline reading.

How do I save extracted web content to a file named after the article title?▼

Title-aware saving extracts the article title from the output, sanitizes it into a valid filename, and renames the text file. This ensures your downloaded web content files are named automatically after the article itself.

Can I extract web content if reader or trafilatura are not installed?▼

Yes, you can extract web content using a curl-based fallback. This method fetches the HTML via curl and processes it through a simple Python parser to retrieve the article text when reader or trafilatura are unavailable.

What is the best way to download news articles and blog posts for archiving?▼

The best way to download news articles for archiving is using automated extraction. This Skill retrieves URLs, removes website clutter like ads and navigation, and outputs clean readable text files for your archive.

What types of web clutter does article extraction remove from blog posts?▼

Article extraction removes website navigation menus, advertisements, newsletter signups, and other non-content clutter from blog posts. This ensures the final text file contains only the core readable article content.

Related Skills

Explore More Content & Communication Skills→
Ocean326Ocean326

article-extractor

Extract clean article content from URLs and save as .txt files.

Community
Intermediate
nadicodeainadicodeai

ocr-and-documents

Extract and convert PDF, scanned document, and image text to plain text or Markdown using OCR and pymupdf/marker-pdf.

Official
Intermediate
nicepkgnicepkg
276

article-extractor

Extract clean article text from web URLs and save as a text file.

Official
Intermediate
tedtv1007-ctrltedtv1007-ctrl

cloudflare-crawl

Fetch rendered HTML from dynamic websites via the Cloudflare Browser Rendering API.

Community
Intermediate