User-agent: * Disallow: /dev Disallow: /sandbox Disallow: millercenter.org/index.php Disallow: millercenter.org/expressionengine.php # The grub distributed search engine behaves very badly. User-agent: grub-client Disallow: / # They totally overwhelm servers with traffic. # http://www.nameprotect.com/botinfo.html User-agent: NPBot Disallow: / # Proprietary German backlinks service. User-agent: SEOkicks-Robot Disallow: / # wget run recusively just *wrecks* server capacity. User-agent: wget Disallow: / # This spider's output isn't public. User-agent: 008 Disallow: / # Entireweb User-agent: Speedy Disallow: / # Foreign-language bot User-agent: Sogou web spider Disallow: / # Poorly behaved bot User-agent: Ezooms Disallow: / # Brandwatch User-agent: magpie-crawler Disallow: / # Russian image search engine User-agent: YandexImages Disallow: / # Magestic-12 User-agent: MJ12bot Disallow: / # Yoydao User-agent: YodaoBot Disallow: / # NerdByNature.Net User-agent: NerdByNature.Bot Disallow: / # Discovery Engine User-agent: discobot Disallow: / # No idea. User-agent: knowaboutBot Disallow:/ # Gnip User-agent: UnwindFetchor Disallow: / # These bots are designed to duplicate entire sites. User-agent: sitecheck.internetseer.com Disallow: / User-agent: Zealbot Disallow: / User-agent: MSIECrawler Disallow: / User-agent: WebReaper 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: / # My Testing Crawler is allowed User-agent: MattBot Disallow: