{
 "slug": "ccbot",
 "name": "CCBot",
 "operator": "Common Crawl",
 "operator_slug": "commoncrawl",
 "category": "dataset",
 "category_label": "Corpus and dataset builders",
 "robots_token": "CCBot",
 "user_agent_substring": "CCBot",
 "user_agent_example": "CCBot/2.0 (https://commoncrawl.org/faq/)",
 "respects_robots_txt": "documented",
 "respects_robots_txt_label": "obeys robots.txt (documented)",
 "verification_method": "none",
 "verification_label": "no published verification method",
 "published_ip_ranges_url": null,
 "ip_ranges_endpoint": null,
 "ipv4_prefix_count": 0,
 "ipv6_prefix_count": 0,
 "what_it_is": "Common Crawl's corpus builder. It trains nothing itself, but its archive is an input to most open and many closed LLM training sets, which makes it the highest-leverage single entry on this list.",
 "cost_of_blocking": "Future Common Crawl snapshots exclude you, so downstream training sets lose you too — but only going forward. Existing snapshots are permanent and blocking today does not retract them.",
 "operator_docs": "https://commoncrawl.org/faq",
 "html_url": "https://www.pathwren.workers.dev/crawler/ccbot.html",
 "json_url": "https://www.pathwren.workers.dev/crawler/ccbot.json",
 "last_reviewed": "2026-09-01"
}