cdransf/ai.robots.txt
1
1
Fork 0
mirror of https://github.com/ai-robots-txt/ai.robots.txt.git synced 2025-04-19 00:26:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

chore: add Diffbot and scoopit

Browse source
This commit is contained in:
Cory Dransfeldt 2024-05-05 14:50:04 -07:00
parent 29e0799332
commit dea035365f
No known key found for this signature in database
5 changed files with 8 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
servers/apache.conf
View file

@ -1,4 +1,4 @@
# for apache2.conf or .htaccess; intended to block via user agent string
RewriteEngine On
RewriteCond %{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) [NC]
RewriteCond %{HTTP_USER_AGENT} (AdsBot-Google|Amazonbot|anthropic-ai|Applebot|AwarioRssBot|AwarioSmartBot|Bytespider|CCBot|ChatGPT-User|ClaudeBot|Claude-Web|cohere-ai|DataForSeoBot|Diffbot|FacebookBot|FriendlyCrawler|Google-Extended|GoogleOther|GPTBot|img2dataset|ImagesiftBot|magpie-crawler|Meltwater|omgili|omgilibot|peer39_crawler|peer39_crawler/1.0|PerplexityBot|PiplBot|scoop.it|Seekr|YouBot) [NC]
RewriteRule .* - [F,L]

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 ($http_user_agent ~* (AdsBot-Google|Amazonbot|anthropic-ai|Applebot|AwarioRssBot|AwarioSmartBot|Bytespider|CCBot|ChatGPT-User|ClaudeBot|Claude-Web|cohere-ai|DataForSeoBot|FacebookBot|FriendlyCrawler|Google-Extended|GoogleOther|GPTBot|img2dataset|ImagesiftBot|magpie-crawler|Meltwater|omgili|omgilibot|peer39_crawler|peer39_crawler/1.0|PerplexityBot|PiplBot|Seekr|YouBot)) {
if ($http_user_agent ~* (AdsBot-Google|Amazonbot|anthropic-ai|Applebot|AwarioRssBot|AwarioSmartBot|Bytespider|CCBot|ChatGPT-User|ClaudeBot|Claude-Web|cohere-ai|DataForSeoBot|Diffbot|FacebookBot|FriendlyCrawler|Google-Extended|GoogleOther|GPTBot|img2dataset|ImagesiftBot|magpie-crawler|Meltwater|omgili|omgilibot|peer39_crawler|peer39_crawler/1.0|PerplexityBot|PiplBot|scoop.it|Seekr|YouBot)) {
return 403;
}