aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorXe Iaso <me@xeiaso.net>2025-04-27 09:32:50 -0400
committerGitHub <noreply@github.com>2025-04-27 13:32:50 +0000
commit0fa9906e3ac0ba02547daa44f07a4020f81b90f0 (patch)
treef3198fb70128a77caa36fd79352e017c909b9c3c
parentb08580ca336d25240c850889bcf2cc17ddf6bf58 (diff)
downloadanubis-0fa9906e3ac0ba02547daa44f07a4020f81b90f0.tar.xz
anubis-0fa9906e3ac0ba02547daa44f07a4020f81b90f0.zip
test(config): add Xesite's old policy file to known good test cases (#382)
Signed-off-by: Xe Iaso <me@xeiaso.net>
-rw-r--r--lib/policy/config/testdata/good/old_xesite.json79
1 files changed, 79 insertions, 0 deletions
diff --git a/lib/policy/config/testdata/good/old_xesite.json b/lib/policy/config/testdata/good/old_xesite.json
new file mode 100644
index 0000000..21816bd
--- /dev/null
+++ b/lib/policy/config/testdata/good/old_xesite.json
@@ -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"
+ }
+ ]
+} \ No newline at end of file