# 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: magpie-crawler 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: JikeSpider Disallow: / # User-agent: Xenu Disallow: / # User-agent: larbin Disallow: / # User-agent: libwww Disallow: / # User-agent: ZyBORG Disallow: / # User-agent: Download Ninja Disallow: / # User-agent: BLEXBot 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: / # # # Friendly, low-speed bots are welcome viewing article pages, but not # dynamically-generated pages please. # User-agent: * # trying to slow down all search spiders Crawl-delay: 2 # wiki disallows Disallow: /w/ Disallow: /wiki/Special:Collection Disallow: /wiki/Special:Random Disallow: /wiki/Special%3ARandom Disallow: /wiki/Special:Search Disallow: /wiki/Special%3ASearch Disallow: /wiki/Special:Ask/ Disallow: /wiki/Special:Browse/ Disallow: /wiki/Special:SearchByProperty/ Disallow: /wiki/Special:ExportRDF/ Disallow: /wiki/Special:PageProperty/ Disallow: /wiki/Special:Properties/ Disallow: /wiki/Special:UnusedProperties/ Disallow: /wiki/Special:WantedProperties/ Disallow: /wiki/Special:SMWAdmin/ Disallow: /wiki/Special:Types/ Disallow: /wiki/Special:URIResolver/ Disallow: /wiki/Special:QueryCreator/ # general pages Disallow: /uploads/image.php Disallow: /images/ Disallow: /css/ Disallow: /inc/ Disallow: /search/ # forum pages Disallow: /forums/posting.php Disallow: /forums/admin/ Disallow: /forums/db/ Disallow: /forums/images/ Disallow: /forums/includes/ Disallow: /forums/language/ Disallow: /forums/templates/ Disallow: /forums/common.php Disallow: /forums/config.php Disallow: /forums/faq.php Disallow: /forums/groupcp.php Disallow: /forums/login.php Disallow: /forums/memberlist.php Disallow: /forums/modcp.php Disallow: /forums/posting.php Disallow: /forums/privmsg.php Disallow: /forums/profile.php Disallow: /forums/search.php Disallow: /forums/viewonline.php Disallow: /forums/ucp.php # test and old files Disallow: /nforums/ Disallow: /old_forums/ Disallow: /tblog/