Extracts clean, readable text from URLs by stripping away ads, navigation menus, and web clutter.
Article Extractor is a specialized Claude Code skill designed to streamline the process of gathering information from the web. It intelligently identifies the core content of blog posts, news articles, and tutorials, discarding distractions like newsletter popups, sidebars, and cookie notices. By leveraging industry-standard tools like Mozilla's Readability and Trafilatura, it ensures high-quality text extraction that is perfect for research, offline reading, or feeding clean data into AI workflows. Whether you need to archive a tutorial or summarize a long-form essay, this skill automates the cleanup and saving process.
주요 기능
01Formatted text output optimized for readability and AI analysis
02Multi-tool support including Mozilla Readability and Trafilatura
03Smart filename generation using extracted article titles
040 GitHub stars
05Automated removal of ads, scripts, and navigation clutter
06Fallback Python-based extraction for environments without dependencies
사용 사례
01Downloading distraction-free versions of long-form articles for offline use
02Converting online blog posts into local text files for documentation
03Extracting clean content for AI summarization and research tasks
