From f7ac0bffa6ba4fcce24efa0c5a68183d11f7945d Mon Sep 17 00:00:00 2001 From: Renan Bernordi Date: Thu, 28 Nov 2024 17:25:11 -0300 Subject: [PATCH] novas regras de bloqueio no robots https://github.com/ai-robots-txt/ai.robots.txt --- app/robots.txt | 65 +++++++++++++++++++++++++++++++------------------- 1 file changed, 40 insertions(+), 25 deletions(-) diff --git a/app/robots.txt b/app/robots.txt index 454a50c..a8782dd 100644 --- a/app/robots.txt +++ b/app/robots.txt @@ -1,34 +1,49 @@ +User-agent: * +Allow: / + User-agent: * Disallow: /p/ Disallow: /api/ -# Block common AI crawlers -User-agent: GPTBot -Disallow: / - -User-agent: ChatGPT-User -Disallow: / - +User-agent: AI2Bot +User-agent: Ai2Bot-Dolma +User-agent: Amazonbot User-agent: anthropic-ai -Disallow: / - +User-agent: Applebot +User-agent: Applebot-Extended +User-agent: Bytespider User-agent: CCBot -Disallow: / - -User-agent: Google-Extended -Disallow: / - -User-agent: FacebookBot -Disallow: / - +User-agent: ChatGPT-User User-agent: Claude-Web -Disallow: / - -User-agent: Omgilibot -Disallow: / - -User-agent: Omgili -Disallow: / - +User-agent: ClaudeBot +User-agent: cohere-ai +User-agent: Diffbot +User-agent: DuckAssistBot User-agent: FacebookBot +User-agent: facebookexternalhit +User-agent: FriendlyCrawler +User-agent: Google-Extended +User-agent: GoogleOther +User-agent: GoogleOther-Image +User-agent: GoogleOther-Video +User-agent: GPTBot +User-agent: iaskspider/2.0 +User-agent: ICC-Crawler +User-agent: ImagesiftBot +User-agent: img2dataset +User-agent: ISSCyberRiskCrawler +User-agent: Kangaroo Bot +User-agent: Meta-ExternalAgent +User-agent: Meta-ExternalFetcher +User-agent: OAI-SearchBot +User-agent: omgili +User-agent: omgilibot +User-agent: PerplexityBot +User-agent: PetalBot +User-agent: Scrapy +User-agent: Sidetrade indexer bot +User-agent: Timpibot +User-agent: VelenPublicWebCrawler +User-agent: Webzio-Extended +User-agent: YouBot Disallow: / \ No newline at end of file