remote/ai.robots.txt
1
0
Fork 0
mirror of https://github.com/ai-robots-txt/ai.robots.txt.git synced 2026-09-28 21:04:16 +02:00
Code Issues Projects Releases Packages Wiki Activity

Regenerate lighttpd test fixture for case-insensitive match

Browse source
This commit is contained in:
Sam Hartley 2026-09-07 20:08:06 -07:00
commit 3adc0cb1db
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
code/test_files/lighttpd-block-ai-bots.conf
View file

@ -1 +1 @@
$HTTP["url"] != "/robots.txt" { $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" { url.access-deny = ( "" ) } }
$HTTP["url"] != "/robots.txt" { $HTTP["user-agent"] =~ "(?i)\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" { url.access-deny = ( "" ) } }