User-agent: Orthogaffe Disallow: / User-agent: sqlmap Disallow: / # 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: / User-agent: Twiceler Disallow: / # Some bots are known to be trouble, particularly those designed to copy # entire sites or download them for offline viewing. 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: Nutch Disallow: / User-agent: spock Disallow: / User-agent: OmniExplorer_Bot Disallow: / User-agent: TurnitinBot Disallow: / User-agent: BecomeBot Disallow: / User-agent: genieBot Disallow: / User-agent: dotbot Disallow: / User-agent: MLBot Disallow: / User-agent: 80bot Disallow: / User-agent: Linguee Bot Disallow: / User-agent: aiHitBot Disallow: / User-agent: Exabot Disallow: / User-agent: SBIder/Nutch Disallow: / User-agent: Jyxobot Disallow: / User-agent: mAgent Disallow: / User-agent: MJ12bot Disallow: / User-agent: Speedy Spider Disallow: / User-agent: ShopWiki Disallow: / User-agent: Huasai Disallow: / User-agent: DataCha0s Disallow: / User-agent: Baiduspider Disallow: / User-agent: Atomic_Email_Hunter Disallow: / User-agent: Mp3Bot Disallow: / User-agent: WinHttp Disallow: / User-agent: betaBot Disallow: / User-agent: core-project Disallow: / User-agent: panscient.com Disallow: / User-agent: Java Disallow: / User-agent: libwww-perl Disallow: / # Sorry, 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: / User-agent: curl Disallow: / # # A capture bot, downloads gazillions of pages with no public benefit # http://www.webreaper.net/ User-agent: WebReaper Disallow: / # Poorly behaved Crawlers, some of these ignore # robots.txt but... # # The 'grub' distributed client has been *very* poorly behaved. User-agent: grub-client Disallow: / User-agent: k2spider Disallow: / User-agent: bingbot Disallow: / User-agent: msnbot Disallow: / # Hits many times per second, not acceptable # http://www.nameprotect.com/botinfo.html User-agent: NPBot Disallow: / User-agent: * Disallow: /tool/