# directed to all robots User-agent: * Disallow: /common/ Disallow: /banned/ Disallow: /anything/ # # Friendly, low-speed bots are welcome viewing article pages, but not # dynamically-generated pages please. Disallow: /*/Special:Random Disallow: /*/Special:Randompage Disallow: /*/Special%3ARandompage Disallow: /*/Special:Search Disallow: /*/Special%3ASearch Disallow: /*/Special:PdfPrint Disallow: /*/Template Disallow: /*/MediaWiki Disallow: /*/MediaWiki: Disallow: /*/MediaWiki%3A Disallow: /*/Special:Recentchangeslinked Disallow: /*/Special%3ARecentchangeslinked Disallow: /*/Special:Export Disallow: /*/index.php?diff= Disallow: /*/index.php?oldid= Disallow: /*/index.php?title=Help Disallow: /*/index.php?title=Image Disallow: /*/index.php?title=MediaWiki Disallow: /*/index.php?title=Special: Disallow: /*/index.php?title=Template Disallow: /*/index.php?*&printable=yes Disallow: /feed/magpie/ # # 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: ZyBORG Disallow: / User-agent: Download Ninja 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: /