{
 "slug": "diffbot",
 "name": "Diffbot",
 "operator": "Diffbot",
 "operator_slug": "diffbot",
 "category": "dataset",
 "category_label": "Corpus and dataset builders",
 "robots_token": "Diffbot",
 "user_agent_substring": "Diffbot",
 "user_agent_example": "Mozilla/5.0 (compatible; Diffbot/0.1; +http://www.diffbot.com)",
 "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": "Extracts structured records from pages to build a commercial knowledge graph that is resold and used for retrieval and training.",
 "cost_of_blocking": "Your facts stop entering a widely-licensed knowledge graph. Whether that is a loss depends on whether you want to be a machine-readable entity.",
 "operator_docs": "https://docs.diffbot.com/",
 "html_url": "https://www.pathwren.workers.dev/crawler/diffbot.html",
 "json_url": "https://www.pathwren.workers.dev/crawler/diffbot.json",
 "last_reviewed": "2026-09-01"
}