skills.rest
kivilaid
kivilaidCOMMUNITY
Explore all skills by this author →
GitHub

article-extractor

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

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the distractions of web articles (ads, navigation, pop-ups) by extracting only the core content. It saves you time and improves focus by providing clean, readable text from any URL, perfect for offline reading or content repurposing.

Core Features & Use Cases

  • Clutter-Free Extraction: Removes ads, navigation, and other distractions, leaving only the main article text.
  • Multiple Extraction Methods: Utilizes reader, trafilatura, or a fallback curl method for robust extraction across various websites.
  • Automated Formatting & Saving: Cleans up content, extracts the article title, and saves it to a neatly named text file.
  • Use Case: Download a research article from a busy website to a clean text file, allowing you to read and annotate it without interruptions, or easily integrate its content into your notes.

Quick Start

Extract an article using the best available tool

ARTICLE_URL="https://example.com/article"

The skill will automatically detect and use 'reader', 'trafilatura', or a fallback.

Example output:

✓ Extracted article: Article Title from Website ✓ Saved to: Article-Title-from-Website.txt Preview (first 10 lines): [Article content...]

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 content from a URL without ads and clutter?▼

Article extraction removes ads, navigation, and pop-ups to isolate core content. This Skill downloads URLs and outputs clean, readable text saved to a file, using reader, trafilatura, or curl methods to adapt to different website structures.

Can I save web articles as text files for offline reading?▼

Yes. The Skill extracts article text from URLs, automatically names the file from the article title, and saves it locally. This lets you read and annotate content offline without web interruptions or formatting distractions.

What extraction methods does this tool use if one isn't available?▼

The Skill checks for reader or trafilatura availability first, then falls back to curl if neither is installed. This multi-method approach ensures robust extraction across different website layouts and reduces dependency on a single tool.

How do I use this for web scraping blog posts and articles?▼

Provide a URL; the Skill downloads it, extracts the main article body, cleans whitespace and formatting, and saves cleaned text to a named file. It's designed for single-article extraction and content repurposing without manual parsing.

Does this work with paywalled or JavaScript-heavy websites?▼

Extraction success depends on the underlying tool's capabilities. Reader and trafilatura handle many sites, but paywalled or heavily JavaScript-rendered content may not extract fully. Test with your target URLs to verify compatibility.

Related Skills

Explore More Content & Communication Skills→
sungaoxiang-backendsungaoxiang-backend

rss-article-retriever

Fetch, clean, and structure RSS articles into JSON via WeWe-RSS and Playwright.

Community
Advanced
XSpoonAiXSpoonAi
17

vector-notes-indexer

Index local notes with vector embeddings for offline semantic search.

Official
Advanced
adilkalamadilkalam
2

article-extractor

Extract clean article text from URLs and save it to a file.

Community
Intermediate
taishan1994taishan1994
30

pdf-processing

Extract text, structure, and tables from PDF documents using PyPDF2 and pdfplumber.

Community
Intermediate