Google News Scraper
Extract real-time Google News search results, headlines, and article content as structured JSON without requiring a headless browser.
Google News Scraper delivers structured news search results, publisher links, and article metadata directly from Google News feeds in a single lightweight request. By bypassing heavy headless browsers by default, it operates with minimal latency and runs reliably in serverless environments like AWS Lambda and Vercel. With built-in capabilities to resolve original publisher URLs, fetch full article text, filter by locale or timeframe, and expose tools via an integrated Model Context Protocol (MCP) server, it provides an efficient pipeline for monitoring headlines and feeding live context to AI agents.
주요 기능
01Fetches news directly from RSS feeds without headless browsers for fast, serverless-friendly execution
02Resolves Google News redirect URLs automatically to surface original publisher links
03Supports localized editions with custom language, region, and timeframe filters
04Extracts optional full-text article content and favicons via on-demand Puppeteer integration
05Includes built-in Model Context Protocol (MCP) server support for AI agents like Claude and Cursor
06385 GitHub stars
사용 사례
01Automating brand, competitor, and industry monitoring pipelines
02Gathering market sentiment and real-time signals for research and forecasting
03Supplying fresh news context and source citations directly into LLM agent workflows