{
 "operator": "NICT",
 "slug": "nict",
 "docs": "https://www.nict.go.jp/en/",
 "crawler_count": 1,
 "crawlers": [
  {
   "slug": "icc-crawler",
   "name": "ICC-Crawler",
   "operator": "NICT",
   "operator_slug": "nict",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "ICC-Crawler",
   "user_agent_substring": "ICC-Crawler",
   "user_agent_example": "ICC-Crawler",
   "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": "Operated by NICT, Japan's national information and communications research institute. The collected data supports AI research and, per the operator, is also provided to third parties including commercial companies.",
   "cost_of_blocking": "You are excluded from a national research corpus and from the commercial redistributions of it. This is a dataset-shaped block: one refusal, many downstream effects.",
   "operator_docs": "https://www.nict.go.jp/en/",
   "html_url": "https://www.pathwren.workers.dev/crawler/icc-crawler.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/icc-crawler.json",
   "last_reviewed": "2026-09-01"
  }
 ],
 "ip_range_endpoints": []
}