|
11 | 11 | ## /usr/share/docs/anubis/data or in the tarball you extracted Anubis from. |
12 | 12 |
|
13 | 13 | bots: |
14 | | -# Pathological bots to deny |
15 | | -- # This correlates to data/bots/ai-robots-txt.yaml in the source tree |
16 | | - import: (data)/bots/ai-robots-txt.yaml |
17 | | -- import: (data)/bots/cloudflare-workers.yaml |
18 | | -- import: (data)/bots/headless-browsers.yaml |
19 | | -- import: (data)/bots/us-ai-scraper.yaml |
20 | | - |
21 | | -# Search engines to allow |
22 | | -- import: (data)/crawlers/googlebot.yaml |
23 | | -- import: (data)/crawlers/bingbot.yaml |
24 | | -- import: (data)/crawlers/duckduckbot.yaml |
25 | | -- import: (data)/crawlers/qwantbot.yaml |
26 | | -- import: (data)/crawlers/internet-archive.yaml |
27 | | -- import: (data)/crawlers/kagibot.yaml |
28 | | -- import: (data)/crawlers/marginalia.yaml |
29 | | -- import: (data)/crawlers/mojeekbot.yaml |
30 | | - |
31 | | -# Allow common "keeping the internet working" routes (well-known, favicon, robots.txt) |
32 | | -- import: (data)/common/keep-internet-working.yaml |
33 | | -- import: /xe/cfg/anubis/xesite-rss-feeds.yaml |
34 | | - |
35 | | -# # Punish any bot with "bot" in the user-agent string |
36 | | -# # This is known to have a high false-positive rate, use at your own risk |
37 | | -# - name: generic-bot-catchall |
38 | | -# user_agent_regex: (?i:bot|crawler) |
39 | | -# action: CHALLENGE |
40 | | -# challenge: |
41 | | -# difficulty: 16 # impossible |
42 | | -# report_as: 4 # lie to the operator |
43 | | -# algorithm: slow # intentionally waste CPU cycles and time |
44 | | - |
45 | | -# Generic catchall rule |
46 | | -- name: generic-browser |
47 | | - user_agent_regex: >- |
48 | | - Mozilla|Opera |
49 | | - action: CHALLENGE |
| 14 | + # Pathological bots to deny |
| 15 | + - # This correlates to data/bots/ai-robots-txt.yaml in the source tree |
| 16 | + import: (data)/bots/ai-robots-txt.yaml |
| 17 | + - import: (data)/bots/cloudflare-workers.yaml |
| 18 | + - import: (data)/bots/headless-browsers.yaml |
| 19 | + - import: (data)/bots/us-ai-scraper.yaml |
| 20 | + |
| 21 | + # Search engines to allow |
| 22 | + - import: (data)/crawlers/googlebot.yaml |
| 23 | + - import: (data)/crawlers/bingbot.yaml |
| 24 | + - import: (data)/crawlers/duckduckbot.yaml |
| 25 | + - import: (data)/crawlers/qwantbot.yaml |
| 26 | + - import: (data)/crawlers/internet-archive.yaml |
| 27 | + - import: (data)/crawlers/kagibot.yaml |
| 28 | + - import: (data)/crawlers/marginalia.yaml |
| 29 | + - import: (data)/crawlers/mojeekbot.yaml |
| 30 | + |
| 31 | + # Allow common "keeping the internet working" routes (well-known, favicon, robots.txt) |
| 32 | + - import: (data)/common/keep-internet-working.yaml |
| 33 | + - import: /xe/cfg/anubis/xesite-rss-feeds.yaml |
| 34 | + |
| 35 | + # Requires a subscription to Thoth to use, see |
| 36 | + # TODO(Xe): docs link |
| 37 | + # |
| 38 | + # Throw blanket challenges for specific countries known to host abusive scrapers |
| 39 | + # that do not respond to abuse complaints |
| 40 | + - name: challenge-aggressive-scrapers |
| 41 | + geoip: |
| 42 | + counties: |
| 43 | + - BR |
| 44 | + - CN |
| 45 | + action: WEIGH |
| 46 | + weight: |
| 47 | + adjust: 30 |
| 48 | + |
| 49 | + # Requires a subscription to Thoth to use, see |
| 50 | + # TODO(Xe): docs link |
| 51 | + # |
| 52 | + # Deny traffic from the worst offenders hosting AI scrapers. |
| 53 | + - name: deny-aggressive-asns-without-functional-abuse-contact |
| 54 | + asns: |
| 55 | + match: |
| 56 | + - 13335 # Cloudflare |
| 57 | + - 136907 # Huawei Cloud |
| 58 | + - 45102 # Alibaba Cloud |
| 59 | + action: WEIGH |
| 60 | + weight: |
| 61 | + adjust: 30 |
| 62 | + |
| 63 | + - name: residential-proxy |
| 64 | + asns: |
| 65 | + match: |
| 66 | + - 7018 |
| 67 | + action: WEIGH |
| 68 | + weight: |
| 69 | + adjust: 10 |
| 70 | + |
| 71 | + # # Punish any bot with "bot" in the user-agent string |
| 72 | + # # This is known to have a high false-positive rate, use at your own risk |
| 73 | + # - name: generic-bot-catchall |
| 74 | + # user_agent_regex: (?i:bot|crawler) |
| 75 | + # action: CHALLENGE |
| 76 | + # challenge: |
| 77 | + # difficulty: 16 # impossible |
| 78 | + # report_as: 4 # lie to the operator |
| 79 | + # algorithm: slow # intentionally waste CPU cycles and time |
| 80 | + |
| 81 | + # Generic catchall rule |
| 82 | + - name: generic-browser |
| 83 | + user_agent_regex: >- |
| 84 | + Mozilla|Opera |
| 85 | + action: WEIGH |
| 86 | + weight: |
| 87 | + adjust: 5 |
50 | 88 |
|
51 | 89 | dnsbl: false |
0 commit comments