# A list of misbehaving crawlers. # originally from http://aardling.com/robots.txt 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: / User-agent: MSIECrawler Disallow: / User-agent: Offline Explorer Disallow: / User-agent: sitecheck.internetseer.com Disallow: / User-agent: SiteSnagger Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: UbiCrawler Disallow: / User-agent: WebCopier Disallow: / User-agent: WebStripper Disallow: / User-agent: WebZIP Disallow: / User-agent: Xenu Disallow: / User-agent: Zealbot Disallow: / User-agent: ZyBORG Disallow: / # Wget in its recursive mode is a frequent problem. 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: / # A capture bot, downloads gazillions of pages with no public benefit. # http://www.webreaper.net/ User-agent: WebReaper Disallow: / # Obviously don't want _these_ User-agent: zombies Disallow: /brains # These rules apply to everyone else. User-agent: * Disallow: /bin/ Disallow: /content/files/ Disallow: /install Disallow: /compareproducts Disallow: /clearcomparelist Disallow: /login Disallow: /logout Disallow: /cart Disallow: /wishlist Disallow: /emailwishlist Disallow: /checkout Disallow: /onepagecheckout Disallow: /checkout/shippingaddress Disallow: /checkout/billingaddress Disallow: /checkout/shippingmethod Disallow: /checkout/paymentmethod Disallow: /checkout/paymentinfo Disallow: /checkout/confirm Disallow: /checkout/completed Disallow: /orderdetails Disallow: /returnrequest Disallow: /passwordrecovery/confirm Disallow: /newsletter/subscriptionactivation Disallow: /customer/activation Disallow: /customer/forumsubscriptions Disallow: /emailwishlist Disallow: /boards/postedit Disallow: /boards/postdelete Disallow: /boards/postcreate Disallow: /boards/topicedit Disallow: /boards/topicdelete Disallow: /boards/topiccreate Disallow: /boards/topicmove Disallow: /boards/topicwatch Disallow: /boards/forumwatch Disallow: /privatemessages Disallow: /inboxupdate Disallow: /sentupdate Disallow: /sendpm Disallow: /viewpm Disallow: /deletepm Disallow: /c/10/specials Disallow: /Themes/ Disallow: /themes/ Disallow: /Scripts/ Disallow: /Plugins/ Disallow: /Content/smoothness Disallow: /content/images/thumbs Disallow: /error/ Disallow: /passwordrecovery/ Disallow: /register/ Disallow: /search/ Disallow: /t/Footy-Tips/ Disallow: /login