# robots.txt for Sports Courts .au, .nz, .co.uk and .com sites # # Derived from http://en.wikipedia.org/robots.txt # # Disallow Honey trap for all search engines # whoever doesn't read robots will be trapped User-agent: * Disallow: /facebook/no_follow # disallow crawling browse page using different dates # as most requests may generate a similar result. Disallow: /browse/*b1* Disallow: /browse/*b3* Disallow: /browse/*b4* Disallow: /browse/*b5* Disallow: /browse/*b6* Disallow: /browse/*b7* Disallow: /browse/*b8* Disallow: /browse/*b9* # advertising-related bots: # User-agent: Mediapartners-Google* # Disallow: / # Crawlers for search engines outside target geographic area User-agent: Baiduspider Disallow: / # Crawlers that are kind enough to obey, but which we'd rather not have # unless they're feeding search engines. User-agent: ahrefs Disallow: / User-agent: UbiCrawler Disallow: / User-agent: Xenu Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / User-agent: SearchmetricsBot Disallow: / User-agent: grapeshot Disallow: / User-agent: 360Spider Disallow: / User-agent: MJ12bot Disallow: / # Some bots are known to be trouble, particularly those designed to copy # entire sites. Please obey robots.txt. User-agent: AhrefsBot Disallow: / User-agent: Ezooms Disallow: / User-agent: WBSearchBot Disallow: / 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: / # 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: / # 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: /