cdransf/ai.robots.txt
1
1
Fork 0
mirror of https://github.com/ai-robots-txt/ai.robots.txt.git synced 2025-04-03 19:03:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

.htaccess: Allow robots access to /robots.txt

Browse source
This commit is contained in:
Dennis Camera 2025-02-17 21:00:57 +01:00
parent abfd6dfcd1
commit c0d418cd87
3 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.htaccess
View file

@ -1,3 +1,3 @@
RewriteEngine On
RewriteCond %{HTTP_USER_AGENT} ^.*(AI2Bot|Ai2Bot-Dolma|Amazonbot|anthropic-ai|Applebot|Applebot-Extended|Brightbot\ 1.0|Bytespider|CCBot|ChatGPT-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|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|PanguBot|PerplexityBot|PetalBot|Scrapy|SemrushBot-OCOB|SemrushBot-SWA|Sidetrade\ indexer\ bot|Timpibot|VelenPublicWebCrawler|Webzio-Extended|YouBot).*$ [NC]
RewriteRule .* - [F,L]
RewriteRule !^/?robots\.txt$ - [F,L]

2
code/robots.py
View file

@ -142,7 +142,7 @@ def json_to_htaccess(robot_json):
robots = map(lambda el: el.replace(" ", "\\ "), robot_json.keys())
htaccess += "|".join(robots)
htaccess += ").*$ [NC]\n"
htaccess += "RewriteRule .* - [F,L]"
htaccess += "RewriteRule !^/?robots\\.txt$ - [F,L]\n"
return htaccess

2
code/test_files/.htaccess
View file

@ -1,3 +1,3 @@
RewriteEngine On
RewriteCond %{HTTP_USER_AGENT} ^.*(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|PerplexityBot|PetalBot|Scrapy|Sidetrade\ indexer\ bot|Timpibot|VelenPublicWebCrawler|Webzio-Extended|YouBot).*$ [NC]
RewriteRule .* - [F,L]
RewriteRule !^/?robots\.txt$ - [F,L]