default-config.yaml 2.6 KB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788
  1. - # Pathological bots to deny
  2. # This correlates to data/bots/_deny-pathological.yaml in the source tree
  3. # https://github.com/TecharoHQ/anubis/blob/main/data/bots/_deny-pathological.yaml
  4. import: (data)/bots/_deny-pathological.yaml
  5. - import: (data)/bots/aggressive-brazilian-scrapers.yaml
  6. # Aggressively block AI/LLM related bots/agents by default
  7. - import: (data)/meta/ai-block-aggressive.yaml
  8. # Consider replacing the aggressive AI policy with more selective policies:
  9. # - import: (data)/meta/ai-block-moderate.yaml
  10. # - import: (data)/meta/ai-block-permissive.yaml
  11. # Search engine crawlers to allow, defaults to:
  12. # - Google (so they don't try to bypass Anubis)
  13. # - Apple
  14. # - Bing
  15. # - DuckDuckGo
  16. # - Qwant
  17. # - The Internet Archive
  18. # - Kagi
  19. # - Marginalia
  20. # - Mojeek
  21. - import: (data)/crawlers/_allow-good.yaml
  22. # Challenge Firefox AI previews
  23. - import: (data)/clients/x-firefox-ai.yaml
  24. # Allow common "keeping the internet working" routes (well-known, favicon, robots.txt)
  25. - import: (data)/common/keep-internet-working.yaml
  26. # # Punish any bot with "bot" in the user-agent string
  27. # # This is known to have a high false-positive rate, use at your own risk
  28. # - name: generic-bot-catchall
  29. # user_agent_regex: (?i:bot|crawler)
  30. # action: CHALLENGE
  31. # challenge:
  32. # difficulty: 16 # impossible
  33. # algorithm: slow # intentionally waste CPU cycles and time
  34. # Requires a subscription to Thoth to use, see
  35. # https://anubis.techaro.lol/docs/admin/thoth#geoip-based-filtering
  36. - name: countries-with-aggressive-scrapers
  37. action: WEIGH
  38. geoip:
  39. countries:
  40. - BR
  41. - CN
  42. weight:
  43. adjust: 10
  44. # Requires a subscription to Thoth to use, see
  45. # https://anubis.techaro.lol/docs/admin/thoth#asn-based-filtering
  46. - name: aggressive-asns-without-functional-abuse-contact
  47. action: WEIGH
  48. asns:
  49. match:
  50. - 13335 # Cloudflare
  51. - 136907 # Huawei Cloud
  52. - 45102 # Alibaba Cloud
  53. weight:
  54. adjust: 10
  55. # ## System load based checks.
  56. # # If the system is under high load, add weight.
  57. # - name: high-load-average
  58. # action: WEIGH
  59. # expression: load_1m >= 10.0 # make sure to end the load comparison in a .0
  60. # weight:
  61. # adjust: 20
  62. ## If your backend service is running on the same operating system as Anubis,
  63. ## you can uncomment this rule to make the challenge easier when the system is
  64. ## under low load.
  65. ##
  66. ## If it is not, remove weight.
  67. # - name: low-load-average
  68. # action: WEIGH
  69. # expression: load_15m <= 4.0 # make sure to end the load comparison in a .0
  70. # weight:
  71. # adjust: -10
  72. # Generic catchall rule
  73. - name: generic-browser
  74. user_agent_regex: >-
  75. Mozilla|Opera
  76. action: WEIGH
  77. weight:
  78. adjust: 10