{
 "operator": "Hunter (Velen)",
 "slug": "hunter",
 "docs": "https://velen.io/",
 "crawler_count": 1,
 "crawlers": [
  {
   "slug": "velenpublicwebcrawler",
   "name": "VelenPublicWebCrawler",
   "operator": "Hunter (Velen)",
   "operator_slug": "hunter",
   "category": "dataset",
   "category_label": "Corpus and dataset builders",
   "robots_token": "VelenPublicWebCrawler",
   "user_agent_substring": "VelenPublicWebCrawler",
   "user_agent_example": "VelenPublicWebCrawler",
   "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": "Hunter's crawler, written in Go, building business datasets and machine-learning models from public pages. Its page states it follows robots.txt and meta directives and never fetches more than one page every two seconds.",
   "cost_of_blocking": "Your company pages stop feeding a B2B contact and company dataset. The crawl rate it documents makes this one of the cheapest visitors to simply allow.",
   "operator_docs": "https://velen.io/",
   "html_url": "https://www.pathwren.workers.dev/crawler/velenpublicwebcrawler.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/velenpublicwebcrawler.json",
   "last_reviewed": "2026-09-01"
  }
 ],
 "ip_range_endpoints": []
}