{
  "id": "ccbot",
  "token": "ccbot",
  "ua": "CCBot/2.0 (https://commoncrawl.org/faq/)",
  "label": "CCBot",
  "operator": "Common Crawl Foundation",
  "purpose": "archive",
  "respectsRobots": true,
  "docs": "https://commoncrawl.org/ccbot",
  "note": "Builds the open Common Crawl web archive, a common source of LLM pretraining corpora.",
  "sites_blocking": 3338,
  "sites_allowing": 26814,
  "block_rate": 11.1
}