{
 "name": "Common Crawl",
 "slug": "common-crawl",
 "category": "scraping-browsing",
 "description": "Free, open repository of petabytes of web crawl data, useful for research and training datasets.",
 "url": "https://commoncrawl.org/",
 "docs_url": "https://commoncrawl.org/get-started",
 "auth": "none",
 "pricing": "free",
 "http_status": 200,
 "last_checked_at": "2026-10-14",
 "status": "active",
 "category_name": "Scraping & Browsing",
 "swarmnest_url": "https://swarmnest.ai/directory/scraping-browsing/common-crawl/"
}