User-agent: * Allow: / Sitemap: https://www.marshallwhite.com.au/sitemap-index.xml Host: https://www.marshallwhite.com.au User-agent: Googlebot # Allow files critical for rendering Allow: *.js Allow: *.css # Allow AJAX - Do Not Remove - #Prevent private admin areas from being crawled Disallow: *admin.datocms.com* # Prevent duplicate /feed/ pages from being crawled Disallow: /*/feed/ # Prevent Trackback Neg SEO Disallow: /trackback/ #These rules apply to everyone else. User-agent:* # A list of misbehaving crawlers. User-agent: OAI-SearchBot Disallow: / User-agent: GPTBot Disallow: / User-agent: ChatGPT-User Disallow: / User-agent: DOC Disallow: / User-agent: Download Ninja Disallow: / User-agent: Zao Disallow: / # Some bots are known to be trouble, particularly those designed to copy entire sites. User-agent: Fetch Disallow: / User-agent: HTTrack Disallow: / User-agent: larbin Disallow: / User-agent: libwww. Disallow: / User-agent: linko Disallow: / User-agent: Microsoft.URL.Control Disallow: /