diff options
Diffstat (limited to 'data')
| -rw-r--r-- | data/botPolicies.json | 398 | ||||
| -rw-r--r-- | data/embed.go | 8 |
2 files changed, 406 insertions, 0 deletions
diff --git a/data/botPolicies.json b/data/botPolicies.json new file mode 100644 index 0000000..0e33706 --- /dev/null +++ b/data/botPolicies.json @@ -0,0 +1,398 @@ +{ + "bots": [ + { + "name": "amazonbot", + "user_agent_regex": "Amazonbot", + "action": "DENY" + }, + { + "name": "googlebot", + "user_agent_regex": "\\+http\\://www\\.google\\.com/bot\\.html", + "action": "ALLOW", + "remote_addresses": [ + "2001:4860:4801:10::/64", + "2001:4860:4801:11::/64", + "2001:4860:4801:12::/64", + "2001:4860:4801:13::/64", + "2001:4860:4801:14::/64", + "2001:4860:4801:15::/64", + "2001:4860:4801:16::/64", + "2001:4860:4801:17::/64", + "2001:4860:4801:18::/64", + "2001:4860:4801:19::/64", + "2001:4860:4801:1a::/64", + "2001:4860:4801:1b::/64", + "2001:4860:4801:1c::/64", + "2001:4860:4801:1d::/64", + "2001:4860:4801:1e::/64", + "2001:4860:4801:1f::/64", + "2001:4860:4801:20::/64", + "2001:4860:4801:21::/64", + "2001:4860:4801:22::/64", + "2001:4860:4801:23::/64", + "2001:4860:4801:24::/64", + "2001:4860:4801:25::/64", + "2001:4860:4801:26::/64", + "2001:4860:4801:27::/64", + "2001:4860:4801:28::/64", + "2001:4860:4801:29::/64", + "2001:4860:4801:2::/64", + "2001:4860:4801:2a::/64", + "2001:4860:4801:2b::/64", + "2001:4860:4801:2c::/64", + "2001:4860:4801:2d::/64", + "2001:4860:4801:2e::/64", + "2001:4860:4801:2f::/64", + "2001:4860:4801:31::/64", + "2001:4860:4801:32::/64", + "2001:4860:4801:33::/64", + "2001:4860:4801:34::/64", + "2001:4860:4801:35::/64", + "2001:4860:4801:36::/64", + "2001:4860:4801:37::/64", + "2001:4860:4801:38::/64", + "2001:4860:4801:39::/64", + "2001:4860:4801:3a::/64", + "2001:4860:4801:3b::/64", + "2001:4860:4801:3c::/64", + "2001:4860:4801:3d::/64", + "2001:4860:4801:3e::/64", + "2001:4860:4801:40::/64", + "2001:4860:4801:41::/64", + "2001:4860:4801:42::/64", + "2001:4860:4801:43::/64", + "2001:4860:4801:44::/64", + "2001:4860:4801:45::/64", + "2001:4860:4801:46::/64", + "2001:4860:4801:47::/64", + "2001:4860:4801:48::/64", + "2001:4860:4801:49::/64", + "2001:4860:4801:4a::/64", + "2001:4860:4801:4b::/64", + "2001:4860:4801:4c::/64", + "2001:4860:4801:50::/64", + "2001:4860:4801:51::/64", + "2001:4860:4801:52::/64", + "2001:4860:4801:53::/64", + "2001:4860:4801:54::/64", + "2001:4860:4801:55::/64", + "2001:4860:4801:56::/64", + "2001:4860:4801:60::/64", + "2001:4860:4801:61::/64", + "2001:4860:4801:62::/64", + "2001:4860:4801:63::/64", + "2001:4860:4801:64::/64", + "2001:4860:4801:65::/64", + "2001:4860:4801:66::/64", + "2001:4860:4801:67::/64", + "2001:4860:4801:68::/64", + "2001:4860:4801:69::/64", + "2001:4860:4801:6a::/64", + "2001:4860:4801:6b::/64", + "2001:4860:4801:6c::/64", + "2001:4860:4801:6d::/64", + "2001:4860:4801:6e::/64", + "2001:4860:4801:6f::/64", + "2001:4860:4801:70::/64", + "2001:4860:4801:71::/64", + "2001:4860:4801:72::/64", + "2001:4860:4801:73::/64", + "2001:4860:4801:74::/64", + "2001:4860:4801:75::/64", + "2001:4860:4801:76::/64", + "2001:4860:4801:77::/64", + "2001:4860:4801:78::/64", + "2001:4860:4801:79::/64", + "2001:4860:4801:80::/64", + "2001:4860:4801:81::/64", + "2001:4860:4801:82::/64", + "2001:4860:4801:83::/64", + "2001:4860:4801:84::/64", + "2001:4860:4801:85::/64", + "2001:4860:4801:86::/64", + "2001:4860:4801:87::/64", + "2001:4860:4801:88::/64", + "2001:4860:4801:90::/64", + "2001:4860:4801:91::/64", + "2001:4860:4801:92::/64", + "2001:4860:4801:93::/64", + "2001:4860:4801:94::/64", + "2001:4860:4801:95::/64", + "2001:4860:4801:96::/64", + "2001:4860:4801:a0::/64", + "2001:4860:4801:a1::/64", + "2001:4860:4801:a2::/64", + "2001:4860:4801:a3::/64", + "2001:4860:4801:a4::/64", + "2001:4860:4801:a5::/64", + "2001:4860:4801:c::/64", + "2001:4860:4801:f::/64", + "192.178.5.0/27", + "192.178.6.0/27", + "192.178.6.128/27", + "192.178.6.160/27", + "192.178.6.192/27", + "192.178.6.32/27", + "192.178.6.64/27", + "192.178.6.96/27", + "34.100.182.96/28", + "34.101.50.144/28", + "34.118.254.0/28", + "34.118.66.0/28", + "34.126.178.96/28", + "34.146.150.144/28", + "34.147.110.144/28", + "34.151.74.144/28", + "34.152.50.64/28", + "34.154.114.144/28", + "34.155.98.32/28", + "34.165.18.176/28", + "34.175.160.64/28", + "34.176.130.16/28", + "34.22.85.0/27", + "34.64.82.64/28", + "34.65.242.112/28", + "34.80.50.80/28", + "34.88.194.0/28", + "34.89.10.80/28", + "34.89.198.80/28", + "34.96.162.48/28", + "35.247.243.240/28", + "66.249.64.0/27", + "66.249.64.128/27", + "66.249.64.160/27", + "66.249.64.224/27", + "66.249.64.32/27", + "66.249.64.64/27", + "66.249.64.96/27", + "66.249.65.0/27", + "66.249.65.128/27", + "66.249.65.160/27", + "66.249.65.192/27", + "66.249.65.224/27", + "66.249.65.32/27", + "66.249.65.64/27", + "66.249.65.96/27", + "66.249.66.0/27", + "66.249.66.128/27", + "66.249.66.160/27", + "66.249.66.192/27", + "66.249.66.224/27", + "66.249.66.32/27", + "66.249.66.64/27", + "66.249.66.96/27", + "66.249.68.0/27", + "66.249.68.128/27", + "66.249.68.32/27", + "66.249.68.64/27", + "66.249.68.96/27", + "66.249.69.0/27", + "66.249.69.128/27", + "66.249.69.160/27", + "66.249.69.192/27", + "66.249.69.224/27", + "66.249.69.32/27", + "66.249.69.64/27", + "66.249.69.96/27", + "66.249.70.0/27", + "66.249.70.128/27", + "66.249.70.160/27", + "66.249.70.192/27", + "66.249.70.224/27", + "66.249.70.32/27", + "66.249.70.64/27", + "66.249.70.96/27", + "66.249.71.0/27", + "66.249.71.128/27", + "66.249.71.160/27", + "66.249.71.192/27", + "66.249.71.224/27", + "66.249.71.32/27", + "66.249.71.64/27", + "66.249.71.96/27", + "66.249.72.0/27", + "66.249.72.128/27", + "66.249.72.160/27", + "66.249.72.192/27", + "66.249.72.224/27", + "66.249.72.32/27", + "66.249.72.64/27", + "66.249.72.96/27", + "66.249.73.0/27", + "66.249.73.128/27", + "66.249.73.160/27", + "66.249.73.192/27", + "66.249.73.224/27", + "66.249.73.32/27", + "66.249.73.64/27", + "66.249.73.96/27", + "66.249.74.0/27", + "66.249.74.128/27", + "66.249.74.160/27", + "66.249.74.192/27", + "66.249.74.32/27", + "66.249.74.64/27", + "66.249.74.96/27", + "66.249.75.0/27", + "66.249.75.128/27", + "66.249.75.160/27", + "66.249.75.192/27", + "66.249.75.224/27", + "66.249.75.32/27", + "66.249.75.64/27", + "66.249.75.96/27", + "66.249.76.0/27", + "66.249.76.128/27", + "66.249.76.160/27", + "66.249.76.192/27", + "66.249.76.224/27", + "66.249.76.32/27", + "66.249.76.64/27", + "66.249.76.96/27", + "66.249.77.0/27", + "66.249.77.128/27", + "66.249.77.160/27", + "66.249.77.192/27", + "66.249.77.224/27", + "66.249.77.32/27", + "66.249.77.64/27", + "66.249.77.96/27", + "66.249.78.0/27", + "66.249.78.32/27", + "66.249.79.0/27", + "66.249.79.128/27", + "66.249.79.160/27", + "66.249.79.192/27", + "66.249.79.224/27", + "66.249.79.32/27", + "66.249.79.64/27", + "66.249.79.96/27" + ] + }, + { + "name": "bingbot", + "user_agent_regex": "\\+http\\://www\\.bing\\.com/bingbot\\.htm", + "action": "ALLOW", + "remote_addresses": [ + "157.55.39.0/24", + "207.46.13.0/24", + "40.77.167.0/24", + "13.66.139.0/24", + "13.66.144.0/24", + "52.167.144.0/24", + "13.67.10.16/28", + "13.69.66.240/28", + "13.71.172.224/28", + "139.217.52.0/28", + "191.233.204.224/28", + "20.36.108.32/28", + "20.43.120.16/28", + "40.79.131.208/28", + "40.79.186.176/28", + "52.231.148.0/28", + "20.79.107.240/28", + "51.105.67.0/28", + "20.125.163.80/28", + "40.77.188.0/22", + "65.55.210.0/24", + "199.30.24.0/23", + "40.77.202.0/24", + "40.77.139.0/25", + "20.74.197.0/28", + "20.15.133.160/27", + "40.77.177.0/24", + "40.77.178.0/23" + ] + }, + { + "name": "qwantbot", + "user_agent_regex": "\\+https\\://help\\.qwant\\.com/bot/", + "action": "ALLOW", + "remote_addresses": [ + "91.242.162.0/24" + ] + }, + { + "name": "kagibot", + "user_agent_regex": "\\+https\\://kagi\\.com/bot", + "action": "ALLOW", + "remote_addresses": [ + "216.18.205.234/32", + "35.212.27.76/32", + "104.254.65.50/32", + "209.151.156.194/32" + ] + }, + { + "name": "marginalia", + "user_agent_regex": "search\\.marginalia\\.nu", + "action": "ALLOW", + "remote_addresses": [ + "193.183.0.162/31", + "193.183.0.164/30", + "193.183.0.168/30", + "193.183.0.172/31", + "193.183.0.174/32" + ] + }, + { + "name": "mojeekbot", + "user_agent_regex": "http\\://www\\.mojeek\\.com/bot\\.html", + "action": "ALLOW", + "remote_addresses": [ + "5.102.173.71/32" + ] + }, + { + "name": "us-artificial-intelligence-scraper", + "user_agent_regex": "\\+https\\://github\\.com/US-Artificial-Intelligence/scraper", + "action": "DENY" + }, + { + "name": "well-known", + "path_regex": "^/.well-known/.*$", + "action": "ALLOW" + }, + { + "name": "favicon", + "path_regex": "^/favicon.ico$", + "action": "ALLOW" + }, + { + "name": "robots-txt", + "path_regex": "^/robots.txt$", + "action": "ALLOW" + }, + { + "name": "lightpanda", + "user_agent_regex": "^Lightpanda/.*$", + "action": "DENY" + }, + { + "name": "headless-chrome", + "user_agent_regex": "HeadlessChrome", + "action": "DENY" + }, + { + "name": "headless-chromium", + "user_agent_regex": "HeadlessChromium", + "action": "DENY" + }, + { + "name": "generic-bot-catchall", + "user_agent_regex": "(?i:bot|crawler)", + "action": "CHALLENGE", + "challenge": { + "difficulty": 16, + "report_as": 4, + "algorithm": "slow" + } + }, + { + "name": "generic-browser", + "user_agent_regex": "Mozilla", + "action": "CHALLENGE" + } + ], + "dnsbl": true +} diff --git a/data/embed.go b/data/embed.go new file mode 100644 index 0000000..5a5f4d2 --- /dev/null +++ b/data/embed.go @@ -0,0 +1,8 @@ +package data + +import "embed" + +var ( + //go:embed botPolicies.json + BotPolicies embed.FS +) |