test(config): add Xesite's old policy file to known good test cases (#382)

Signed-off-by: Xe Iaso <me@xeiaso.net>
This commit is contained in:
Xe Iaso 2025-04-27 09:32:50 -04:00 committed by GitHub
parent b08580ca33
commit 0fa9906e3a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -0,0 +1,79 @@
{
"bots": [
{
"name": "amazonbot",
"user_agent_regex": "Amazonbot",
"action": "DENY"
},
{
"name": "googlebot",
"user_agent_regex": "\\+http\\:\\/\\/www\\.google\\.com/bot\\.html",
"action": "ALLOW"
},
{
"name": "bingbot",
"user_agent_regex": "\\+http\\:\\/\\/www\\.bing\\.com/bingbot\\.htm",
"action": "ALLOW"
},
{
"name": "qwantbot",
"user_agent_regex": "\\+https\\:\\/\\/help\\.qwant\\.com/bot/",
"action": "ALLOW"
},
{
"name": "discordbot",
"user_agent_regex": "Discordbot/2\\.0; \\+https\\:\\/\\/discordapp\\.com",
"action": "ALLOW"
},
{
"name": "blueskybot",
"user_agent_regex": "Bluesky Cardyb",
"action": "ALLOW"
},
{
"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$",
"action": "ALLOW"
},
{
"name": "rss-readers",
"path_regex": ".*\\.(rss|xml|atom|json)$",
"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-browser",
"user_agent_regex": "Mozilla",
"action": "CHALLENGE"
}
]
}