# # robots.txt # # This file is to prevent the crawling and indexing of certain parts # of your site by web crawlers and spiders run by sites like Yahoo! # and Google. By telling these "robots" where not to go on your site, # you save bandwidth and server resources. # # This file will be ignored unless it is at the root of your host: # Used: https://example.com/robots.txt # Ignored: https://example.com/site/robots.txt # # --------------------------------------------------------------------------- # AI ANSWER ENGINE & LLM CRAWLERS — Explicitly allowed # --------------------------------------------------------------------------- User-agent: GPTBot Allow: / User-agent: ChatGPT-User Allow: / User-agent: ClaudeBot Allow: / User-agent: anthropic-ai Allow: / User-agent: PerplexityBot Allow: / User-agent: Google-Extended Allow: / User-agent: Amazonbot Allow: / User-agent: Applebot-Extended Allow: / User-agent: CCBot Allow: / User-agent: Bytespider Disallow: / # --------------------------------------------------------------------------- # GENERAL CRAWLERS # --------------------------------------------------------------------------- User-agent: * Allow: / User-agent: Googlebot User-agent: Googlebot-image Disallow: /new-in/* Disallow: /pre-launch Disallow: /*/pre-launch Disallow: /*/talents Disallow: /*/success-story Disallow: /*/office-furniture-bulk-orders Disallow: /*/business-offer Disallow: /*/reseller-program Disallow: /*/influencer-review Disallow: /*/press-feature Disallow: /*/track-your-order Disallow: /*/share-and-earn-money Disallow: /*/QC-* Disallow: /QC-* Disallow: /anon/ Allow: /p/office-furniture-bulk-orders # --------------------------------------------------------------------------- # SPAM / SEO TOOL CRAWLERS — Blocked # --------------------------------------------------------------------------- User-agent: Yandex Disallow: / User-agent: ichiro Disallow: / User-agent: moget Disallow: / User-agent: NaverBot Disallow: / User-agent: Baiduspider Disallow: / User-agent: Sogou Disallow: / User-agent: YoudaoBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: SeznamBot Disallow: / User-agent: AhrefsBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: ltx71 Disallow: / User-agent: Gigabot Disallow: / User-agent: Spiderbot Disallow: / User-agent: majestic12 Disallow: / User-agent: scoutjet Disallow: / User-agent: changedetection Disallow: / User-agent: linkfluence Disallow: / User-agent: mj12bot Disallow: / User-agent: mojeek Disallow: / User-agent: aihitdata Disallow: / User-agent: wotbox Disallow: / User-agent: mediatoolkit Disallow: / User-agent: safedns Disallow: / User-agent: aboundex Disallow: / User-agent: webmeup-crawler Disallow: / User-agent: orangebot Disallow: / # --------------------------------------------------------------------------- # INTERNAL / DEV PATHS — Blocked for all # --------------------------------------------------------------------------- User-agent: * Disallow: /api Disallow: /dev. # --------------------------------------------------------------------------- # SITEMAP # --------------------------------------------------------------------------- Sitemap: https://www.autonomous.ai/sitemap.xml