Extract clean article text from URLs into plain text files.
npx skills add https://github.com/ShunmeiCho/dotclaude --skill article-extractor-shunmeicho
Please help me install this Agent Skill. Skill: article-extractor Source: https://github.com/ShunmeiCho/dotclaude/tree/main/skills/article-extractor Command: npx skills add https://github.com/ShunmeiCho/dotclaude --skill article-extractor-shunmeicho
This Skill makes it easy to fetch a web article or blog post from a URL and produce clean, readable text by stripping ads, navigation, and clutter.
Run: reader "URL" > article.txt If reader is not installed, run: trafilatura --URL "URL" --output-format txt > article.txt
High-intent search queries and answers about installing and using this skill.
To extract clean article text from a URL, you can pass the link to reader or trafilatura, which strips away ads and navigation to output readable plain text. This allows you to easily save blog posts or tutorials for offline study.
The best way to strip webpage clutter is using extraction tools like Mozilla Readability or trafilatura. They fetch the web article from your URL and remove navigation and ads, producing a clean plain text file named after the article title.
If reader or trafilatura is not installed, you can extract article content using a lightweight curl-based fallback method. This ensures the text extraction process remains functional even in minimal environments where standard tools are unavailable.
Yes, URL text extraction works in minimal environments without complex dependencies by utilizing a lightweight curl-based fallback. This ensures you can still retrieve main article content from web pages even when lacking specialized parsing libraries.
You can use trafilatura and Mozilla Readability as multiple tool options for web scraping article text. The system attempts reader first and falls back to trafilatura, ensuring robust extraction of main content from various blog post URLs.
adilkalamExtract clean article text from URLs and save it to a file.
ElliotDrelConvert PDF files to Markdown or plain text using the RunPulse API.
XJTLUmediaExtract structured content and metadata from public web URLs.
0xBigBossFetches web pages and converts main content into clean markdown using CSS selectors.
