RAG Text Scraper is a Chrome extension designed to simplify the process of extracting clean article text from multiple URLs. This free tool is particularly useful for developers, researchers, and AI enthusiasts who require high-quality datasets for Retrieval-Augmented Generation systems. It features both bulk and single-page scraping capabilities, allowing users to process large lists of URLs or scrape directly from the current tab with ease.

The extension utilizes Mozilla's Readability.js library to intelligently extract core article content, eliminating ads and other distractions. Additionally, it offers optional AI-powered cleaning, enabling users to enhance their datasets further by connecting to language models like Google Gemini or OpenAI GPT. Each scraped article is saved as a tidy .txt file, complete with relevant metadata, making it easy to gather and organize text data for various applications.