cdransf/ai.robots.txt
1
1
Fork 0
mirror of https://github.com/ai-robots-txt/ai.robots.txt.git synced 2025-04-05 19:37:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'main' into feature/add-table-of-crawler-detail

Browse source
This commit is contained in:
Cory Dransfeldt 2024-04-10 09:07:45 -07:00 committed by GitHub
commit db06035714
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 9 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
apache.conf.txt Normal file
View file

@ -0,0 +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|ImagesiftBot|magpie-crawler|Meltwater|omgili|omgilibot|peer39_crawler|peer39_crawler/1.0|PerplexityBot|PiplBot|Seekr|YouBot) [NC]
RewriteRule .* - [F,L]

4
nginx.conf.txt Normal file
View file

@ -0,0 +1,4 @@
# for nginx.conf; intended to block via user agent string
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)) {
return 403;
}

1
robots.txt
View file

@ -12,6 +12,7 @@ User-agent: Claude-Web
User-agent: cohere-ai User-agent: cohere-ai
User-agent: DataForSeoBot User-agent: DataForSeoBot
User-agent: FacebookBot User-agent: FacebookBot
User-agent: FriendlyCrawler
User-agent: Google-Extended User-agent: Google-Extended
User-agent: GoogleOther User-agent: GoogleOther
User-agent: GPTBot User-agent: GPTBot