{
 "operator": "Linguee",
 "slug": "linguee",
 "docs": "https://www.linguee.com",
 "crawler_count": 1,
 "crawlers": [
  {
   "slug": "linguee-bot",
   "name": "Linguee Bot",
   "operator": "Linguee",
   "operator_slug": "linguee",
   "category": "ai-training",
   "category_label": "AI training crawlers",
   "robots_token": "Linguee Bot",
   "user_agent_substring": "Linguee Bot",
   "user_agent_example": "Linguee Bot",
   "respects_robots_txt": "disputed",
   "respects_robots_txt_label": "compliance disputed",
   "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": "Gathers bilingual text for Linguee's translation corpus and the machine translation trained on it. Recorded in the ai.robots.txt dataset as not respecting robots.txt.",
   "cost_of_blocking": "Multilingual pages stop feeding a translation corpus. If your site is translated, being in it is usually a benefit.",
   "operator_docs": "https://www.linguee.com",
   "html_url": "https://www.pathwren.workers.dev/crawler/linguee-bot.html",
   "json_url": "https://www.pathwren.workers.dev/crawler/linguee-bot.json",
   "last_reviewed": "2026-09-01"
  }
 ],
 "ip_range_endpoints": []
}