remote/ai.robots.txt
1
0
Fork 0
mirror of https://github.com/ai-robots-txt/ai.robots.txt.git synced 2026-09-27 20:34:16 +02:00
Code Issues Projects Releases Packages Wiki Activity

Regenerate nginx test fixture for case-insensitive match

Browse source
This commit is contained in:
Sam Hartley 2026-09-07 20:08:06 -07:00
commit aa623355c1
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
code/test_files/nginx-block-ai-bots.conf
View file

@ -1,6 +1,6 @@
set $block 0;
if ($http_user_agent ~ '\\b(AI2Bot|Ai2Bot-Dolma|Amazonbot|anthropic-ai|Applebot|Applebot-Extended|Bytespider|CCBot|ChatGPT-User|Claude-Web|ClaudeBot|cohere-ai|Diffbot|FacebookBot|facebookexternalhit|FriendlyCrawler|Google-Extended|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2\\.0|ICC-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\\ Bot|Meta-ExternalAgent|Meta-ExternalFetcher|OAI-SearchBot|omgili|omgilibot|Perplexity-User|PerplexityBot|PetalBot|Scrapy|Sidetrade\\ indexer\\ bot|Timpibot|VelenPublicWebCrawler|Webzio-Extended|YouBot|crawler\\.with\\.dots|star\\*\\*\\*crawler|Is\\ this\\ a\\ crawler\\?|a\\[mazing\\]\\{42\\}\\(robot\\)|2\\^32\\$|curl\\|sudo\\ bash)\\b') {
if ($http_user_agent ~* '\\b(AI2Bot|Ai2Bot-Dolma|Amazonbot|anthropic-ai|Applebot|Applebot-Extended|Bytespider|CCBot|ChatGPT-User|Claude-Web|ClaudeBot|cohere-ai|Diffbot|FacebookBot|facebookexternalhit|FriendlyCrawler|Google-Extended|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2\\.0|ICC-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\\ Bot|Meta-ExternalAgent|Meta-ExternalFetcher|OAI-SearchBot|omgili|omgilibot|Perplexity-User|PerplexityBot|PetalBot|Scrapy|Sidetrade\\ indexer\\ bot|Timpibot|VelenPublicWebCrawler|Webzio-Extended|YouBot|crawler\\.with\\.dots|star\\*\\*\\*crawler|Is\\ this\\ a\\ crawler\\?|a\\[mazing\\]\\{42\\}\\(robot\\)|2\\^32\\$|curl\\|sudo\\ bash)\\b') {
set $block 1;
}
@ -10,4 +10,4 @@ if ($request_uri = '/robots.txt') {
if ($block) {
return 403;
}
}