Extracts clean, readable text from web articles and blog posts by removing ads, navigation, and clutter.
Article Extractor is a specialized Claude Code skill designed to convert cluttered web pages into clean, structured text files. It leverages industry-standard tools like Mozilla's Readability and Trafilatura to strip away distractions such as advertisements, navigation menus, and newsletter popups. This skill is ideal for researchers, developers, and content creators who need to archive web content, feed clean data into LLMs, or read long-form articles without distractions. It handles title extraction, filename sanitization, and provides multiple fallback methods to ensure high-quality results across various website architectures.
주요 기능
01Preservation of core article structure and hierarchical headings
02Automatic removal of ads, sidebars, scripts, and navigation menus
03Smart filename generation and sanitization based on article titles
04Automated dependency checking and installation guidance
050 GitHub stars
06Multi-tool support using Readability-cli, Trafilatura, and Python fallbacks
사용 사례
01Converting online documentation into readable local text files for analysis
02Extracting clean text data for RAG (Retrieval-Augmented Generation) pipelines
03Downloading blog posts and tutorials for offline reading or archival
