From 26f946d43081cfd63b4909dd2342c3daa2b18d26 Mon Sep 17 00:00:00 2001 From: Helen Chong <119173961+helenclx@users.noreply.github.com> Date: Sun, 5 Jan 2025 15:53:45 +0800 Subject: [PATCH] Block cohere-training-data-crawler --- .htaccess | 2 +- robots.txt | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/.htaccess b/.htaccess index f3c0953..20a9235 100644 --- a/.htaccess +++ b/.htaccess @@ -20,5 +20,5 @@ RewriteRule ^.+$ index.php [L] # Block bad bots -RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot-Dolma|Amazonbot|anthropic-ai|Applebot-Extended|Bytespider|ChatGPT-User|Claude-Web|ClaudeBot|cohere-ai|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|Sidetrade.*indexer.*bot|Timpibot|VelenPublicWebCrawler|Webzio-Extended|YouBot) [NC] +RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot-Dolma|Amazonbot|anthropic-ai|Applebot-Extended|Bytespider|ChatGPT-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|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|Sidetrade.*indexer.*bot|Timpibot|VelenPublicWebCrawler|Webzio-Extended|YouBot) [NC] RewriteRule .* https://nocommercialuse.org/ [L] \ No newline at end of file diff --git a/robots.txt b/robots.txt index 24c58bf..4c4ac3a 100644 --- a/robots.txt +++ b/robots.txt @@ -11,6 +11,7 @@ User-agent: ChatGPT-User User-agent: Claude-Web User-agent: ClaudeBot User-agent: cohere-ai +User-agent: cohere-training-data-crawler User-agent: Diffbot User-agent: DuckAssistBot User-agent: FacebookBot