# For all robots User-agent: * # Allow search crawlers to discover the sitemap Sitemap: /sitemap.xml Allow: /medias/Homepage-en-* Allow: /medias/Product-en-* Allow: /medias/Category-en-* Allow: /medias/Content-en-* Allow: /medias/Custom-en-* # Block access to specific groups of pages Disallow: /cart Disallow: /checkout Disallow: /my-account Disallow: /medias/ # Block CazoodleBot as it does not present correct accept content headers User-agent: CazoodleBot Disallow: / # Block MJ12bot as it is just noise User-agent: MJ12bot Disallow: / # Block dotbot as it cannot parse base urls properly User-agent: dotbot/1.0 Disallow: / # Block Gigabot User-agent: Gigabot Disallow: / #Block Ajax User-agent: * Disallow: /*?ajax=1