diff --git a/internal/web/robots.go b/internal/web/robots.go index 3309de97c..be0126109 100644 --- a/internal/web/robots.go +++ b/internal/web/robots.go @@ -31,6 +31,8 @@ # AI scrapers and the like. # https://github.com/ai-robots-txt/ai.robots.txt/ +User-agent: AI2Bot +User-agent: Ai2Bot-Dolma User-agent: AdsBot-Google User-agent: Amazonbot User-agent: anthropic-ai @@ -50,9 +52,11 @@ User-agent: GoogleOther-Image User-agent: GoogleOther-Video User-agent: GPTBot +User-agent: ICC-Crawler User-agent: ImagesiftBot User-agent: img2dataset User-agent: Meta-ExternalAgent +User-agent: Meta-ExternalFetcher User-agent: OAI-SearchBot User-agent: omgili User-agent: omgilibot @@ -61,6 +65,7 @@ User-agent: Scrapy User-agent: Timpibot User-agent: VelenPublicWebCrawler +User-agent: Webzio-Extended User-agent: YouBot Disallow: /