876352800cfcb9d40ed5f7abd8b7816bb8c8b9af
lrnassar
  Fri Oct 31 14:38:33 2025 -0700
Tweaking the bots we are blocking based on a new attempt to be more AI/crawl friendly (hoping china bots still stay out), refs #36635

diff --git src/hg/htdocs/robots.rr.txt src/hg/htdocs/robots.rr.txt
index c95bc3c0293..6eeaf3c8ee3 100644
--- src/hg/htdocs/robots.rr.txt
+++ src/hg/htdocs/robots.rr.txt
@@ -1,43 +1,37 @@
 User-agent: AhrefsBot
-User-agent: Amazonbot
-User-agent: anthropic-ai
-User-agent: Applebot
 User-agent: AwarioRssBot
 User-agent: AwarioSmartBot
 User-agent: Bytedance
 User-agent: Bytespider
 User-agent: CCBot
-User-agent: ChatGPT-User
-User-agent: ClaudeBot
-User-agent: Claude-Web
 User-agent: cohere-ai
 User-agent: DataForSeoBot
 User-agent: Diffbot
 User-agent: FacebookBot
 User-agent: SemrushBot
 User-agent: FriendlyCrawler
 User-agent: GPTBot
 User-agent: img2dataset
 User-agent: ImagesiftBot
 User-agent: magpie-crawler
 User-agent: Meltwater
 User-agent: omgili
 User-agent: omgilibot
 User-agent: peer39_crawler
 User-agent: peer39_crawler/1.0
 User-agent: PerplexityBot
 User-agent: PiplBot
 User-agent: scoop.it
 User-agent: Seekr
 User-agent: YandexBot
 User-agent: YouBot
 Disallow: /
 
 User-agent: *
 Crawl-delay: 5
 Disallow: /admin/stats/
 Disallow: /goldenPath/certificate.html
 Disallow: /goldenPath/certificates/
 Disallow: /cgi-bin/hgTracks*.customText*.
 Disallow: /cgi-bin/hgBlat*output=json*
 Disallow: /cgi-bin/hgGeneGraph*