diff --git a/public/robots_allow.txt b/public/robots_allow.txt index 18050662..1702133f 100644 --- a/public/robots_allow.txt +++ b/public/robots_allow.txt @@ -1,4 +1,95 @@ -Sitemap: https://digital.library.ucla.edu/sitemap.xml +User-agent: AdsBot-Google +Disallow: / -User-agent: * -Disallow: +User-agent: Amazonbot +Disallow: / + +User-agent: anthropic-ai +Disallow: / + +User-agent: Applebot +Disallow: / + +User-agent: AwarioRssBot +Disallow: / + +User-agent: AwarioSmartBot +Disallow: / + +User-agent: Bytespider +Disallow: / + +User-agent: CCBot +Disallow: / + +User-agent: ChatGPT-User +Disallow: / + +User-agent: ClaudeBot +Disallow: / + +User-agent: Claude-Web +Disallow: / + +User-agent: cohere-ai +Disallow: / + +User-agent: DataForSeoBot +Disallow: / + +User-agent: Diffbot +Disallow: / + +User-agent: FacebookBot +Disallow: / + +User-agent: FriendlyCrawler +Disallow: / + +User-agent: Google-Extended +Disallow: / + +User-agent: GoogleOther +Disallow: / + +User-agent: GPTBot +Disallow: / + +User-agent: img2dataset +Disallow: / + +User-agent: ImagesiftBot +Disallow: / + +User-agent: magpie-crawler +Disallow: / + +User-agent: Meltwater +Disallow: / + +User-agent: omgili +Disallow: / + +User-agent: omgilibot +Disallow: / + +User-agent: peer39_crawler +Disallow: / + +User-agent: peer39_crawler/1.0 +Disallow: / + +User-agent: PerplexityBot +Disallow: / + +User-agent: PiplBot +Disallow: / + +User-agent: scoop.it +Disallow: / + +User-agent: Seekr +Disallow: / + +User-agent: YouBot +Disallow: / \ No newline at end of file