cdransf/ai.robots.txt
1
1
Fork 0
mirror of https://github.com/ai-robots-txt/ai.robots.txt.git synced 2025-04-07 04:17:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions1

chore: add img2dataset to nginx.conf

Browse source
This commit is contained in:
Cory Dransfeldt 2024-04-22 09:28:21 -07:00 committed by GitHub
parent 2b77b0b0ad
commit 8ddd2a0bb3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions

2
servers/nginx.conf
View file

@ -1,6 +1,6 @@
# for nginx.conf; intended to block via user agent string
# note: we recommend following the approach outlined here https://underlap.org/nginx-robot-access
# and contributing if you're able: https://github.com/glyn/nginx_robot_access
if ($http_user_agent ~* (AdsBot-Google|Amazonbot|anthropic-ai|Applebot|AwarioRssBot|AwarioSmartBot|Bytespider|CCBot|ChatGPT-User|ClaudeBot|Claude-Web|cohere-ai|DataForSeoBot|FacebookBot|FriendlyCrawler|Google-Extended|GoogleOther|GPTBot|ImagesiftBot|magpie-crawler|Meltwater|omgili|omgilibot|peer39_crawler|peer39_crawler/1.0|PerplexityBot|PiplBot|Seekr|YouBot)) {
if ($http_user_agent ~* (AdsBot-Google|Amazonbot|anthropic-ai|Applebot|AwarioRssBot|AwarioSmartBot|Bytespider|CCBot|ChatGPT-User|ClaudeBot|Claude-Web|cohere-ai|DataForSeoBot|FacebookBot|FriendlyCrawler|Google-Extended|GoogleOther|GPTBot|img2dataset|ImagesiftBot|magpie-crawler|Meltwater|omgili|omgilibot|peer39_crawler|peer39_crawler/1.0|PerplexityBot|PiplBot|Seekr|YouBot)) {
return 403;
}