robots.txt 1.8 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101
  1. User-agent: webproxy-mozz
  2. Disallow: /
  3. User-agent: serpstatbot
  4. Disallow: /
  5. User-agent: ltx71
  6. Disallow: /
  7. User-agent: oBot
  8. Disallow: /
  9. User-agent: DuckDuckBot
  10. Disallow:
  11. User-agent: ia_archiver
  12. Disallow: /
  13. User-agent: ltx71 - (http://ltx71.com/)
  14. Disallow: /
  15. User-agent: BLEXBot
  16. Disallow: /
  17. User-agent: Twingly Recon
  18. Disallow: /
  19. User-agent: Googlebot
  20. Disallow: /identity/
  21. Disallow: /webring.html
  22. Disallow: /blog/
  23. User-agent: Googlebot-Image
  24. Disallow: /
  25. User-agent: PageThing
  26. Disallow: /
  27. User-agent: adsbot
  28. Disallow: /
  29. User-agent: SurdotlyBot
  30. Disallow: /
  31. User-agent: DataForSeoBot
  32. Disallow: /
  33. User-agent: SpiderLing
  34. Disallow: /
  35. # Fuck your AI and fuck your scraping
  36. User-agent: AI2Bot
  37. User-agent: Ai2Bot-Dolma
  38. User-agent: Amazonbot
  39. User-agent: anthropic-ai
  40. User-agent: Applebot
  41. User-agent: Applebot-Extended
  42. User-agent: Bytespider
  43. User-agent: CCBot
  44. User-agent: ChatGPT-User
  45. User-agent: Claude-Web
  46. User-agent: ClaudeBot
  47. User-agent: cohere-ai
  48. User-agent: cohere-training-data-crawler
  49. User-agent: Diffbot
  50. User-agent: DuckAssistBot
  51. User-agent: FacebookBot
  52. User-agent: FriendlyCrawler
  53. User-agent: Google-Extended
  54. User-agent: GoogleOther
  55. User-agent: GoogleOther-Image
  56. User-agent: GoogleOther-Video
  57. User-agent: GPTBot
  58. User-agent: iaskspider/2.0
  59. User-agent: ICC-Crawler
  60. User-agent: ImagesiftBot
  61. User-agent: img2dataset
  62. User-agent: ISSCyberRiskCrawler
  63. User-agent: Kangaroo Bot
  64. User-agent: Meta-ExternalAgent
  65. User-agent: Meta-ExternalFetcher
  66. User-agent: OAI-SearchBot
  67. User-agent: omgili
  68. User-agent: omgilibot
  69. User-agent: PanguBot
  70. User-agent: PerplexityBot
  71. User-agent: PetalBot
  72. User-agent: Scrapy
  73. User-agent: SemrushBot
  74. User-agent: Sidetrade indexer bot
  75. User-agent: Timpibot
  76. User-agent: VelenPublicWebCrawler
  77. User-agent: Webzio-Extended
  78. User-agent: YouBot
  79. Disallow: /
  80. User-agent: *
  81. Disallow: /