# Default rules for all user agents User-agent: * # Magento directories Disallow: /app/ Disallow: /downloader/ Disallow: /errors/ Disallow: /includes/ Disallow: /lib/ Disallow: /pkginfo/ Disallow: /shell/ Disallow: /var/ Disallow: /maintenance/ Disallow: /ajax/ # Paths (clean URLs) Disallow: /admin/ Disallow: /catalog/category/view/ Disallow: /catalog/product/view/ Disallow: /catalog/product_compare/ Disallow: /contacts/ Disallow: /control/ Disallow: /customer/ Disallow: /newsletter/ Disallow: /poll/ Disallow: /tag/ Disallow: /wishlist/ Disallow: /*/admin/ Disallow: /*/catalog/category/view/ Disallow: /*/catalog/product/view/ Disallow: /*/catalog/product_compare/ Disallow: /*/catalog_category/infiniteview/ Disallow: /*/contacts/ Disallow: /*/control/ Disallow: /*/customer/ Disallow: /*/newsletter/ Disallow: /*/quickbuy/ Disallow: /*/review/ Disallow: /*/tag/ Disallow: /*/wishlist/ Disallow: /guest/* Disallow: /*/stores/store/ Disallow: /*/catalogsearch/result/ # Magento files Disallow: /CHANGELOG.md Disallow: /LICENSE.html Disallow: /LICENSE.txt Disallow: /LICENSE_AFL.txt # Paths (no clean URLs) Disallow: /*.php$ # Allow acces for Googlebot agents User-agent: Googlebot Allow: / Disallow: /*/catalog/product_compare/ Disallow: /*/wishlist/ Disallow: /*/catalog_category/infiniteview/ Disallow: /*/quickbuy/ Disallow: /*/stores/store/ Disallow: /*/catalogsearch/result/ User-agent: Googlebot-image Allow: / Disallow: /*/catalog/product_compare/ Disallow: /*/wishlist/ # Crawlers that are kind enough to obey, but which we'd rather not have # unless they're feeding search engines. User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / # Some bots are known to be trouble, particularly those designed to copy # entire sites. Please obey robots.txt. User-agent: sitecheck.internetseer.com Disallow: / User-agent: Zealbot Disallow: / User-agent: MSIECrawler Disallow: / User-agent: SiteSnagger Disallow: / User-agent: WebStripper Disallow: / User-agent: WebCopier Disallow: / User-agent: Fetch Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: WebZIP Disallow: / User-agent: linko Disallow: / User-agent: HTTrack Disallow: / User-agent: Microsoft.URL.Control Disallow: / User-agent: Xenu Disallow: / User-agent: larbin Disallow: / User-agent: libwww Disallow: / User-agent: ZyBORG Disallow: / User-agent: Download Ninja Disallow: / User-agent: DataForSeoBot Disallow: / User-agent: Bytespider Disallow: / # wget in its recursive mode is a frequent problem. # Please read the man page and use it properly; there is a # --wait option you can use to set the delay between hits, # for instance. User-agent: wget Disallow: / # The 'grub' distributed client has been *very* poorly behaved. User-agent: grub-client Disallow: / # Doesn't follow robots.txt anyway, but... User-agent: k2spider Disallow: / # Hits many times per second, not acceptable # http://www.nameprotect.com/botinfo.html User-agent: NPBot Disallow: / User-agent: PetalBot Disallow: / User-agent: GeedoBot Disallow: / User-agent: serpstatbot Disallow: / User-agent: proximic Disallow: / # A capture bot, downloads gazillions of pages with no public benefit # http://www.webreaper.net/ User-agent: WebReaper Disallow: / Sitemap: http://www.freshfarm.it/media/sitemap/sitemap_it_it.xml Sitemap: http://www.freshfarm.it/media/sitemap/sitemap.xml Sitemap: http://www.freshfarm.it/media/sitemap/sitemap_fr_fr.xml Sitemap: http://www.freshfarm.it/media/sitemap/sitemap_de_de.xml Sitemap: http://www.freshfarm.it/media/sitemap/sitemap_es_es.xml