# # robots.txt for http://www.wikipedia.org/ and friends # # Please note: There are a lot of pages on this site, and there are # some misbehaved spiders out there that go _way_ too fast. If you're # irresponsible, your access to the site may be blocked. # # advertising-related bots: User-agent: Mediapartners-Google* Disallow: / # Wikipedia work bots: User-agent: IsraBot Disallow: User-agent: Orthogaffe 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: / # 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: 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: / # # Friendly, low-speed bots are welcome viewing article pages, but not # dynamically-generated pages please. # # Inktomi's "Slurp" can read a minimum delay between hits; if your # bot supports such a thing using the 'Crawl-delay' or another # instruction, please let us know. # User-agent: * Disallow: /w/ Disallow: /trap/ Disallow: /Especial:Search Disallow: /Especial%3ASearch Disallow: /Special:Randompage Disallow: /Special%3ARandompage Disallow: /Special:Search Disallow: /Special%3ASearch Disallow: /Spesial:Search Disallow: /Spesial%3ASearch Disallow: /Spezial:Search Disallow: /Spezial%3ASearch Disallow: /Specjalna:Search Disallow: /Specjalna%3ASearch Disallow: /Speciaal:Search Disallow: /Speciaal%3ASearch Disallow: /Speciaal:Randompage Disallow: /Speciaal%3ARandompage Disallow: /Speciel:Search Disallow: /Speciel%3ASearch Disallow: /Speciale:Search Disallow: /Speciale%3ASearch Disallow: /Istimewa:Search Disallow: /Istimewa%3ASearch Disallow: /Toiminnot:Search Disallow: /Toiminnot%3ASearch #hu Disallow: /index.php/Seg%C3%ADts%C3%A9g: Disallow: /index.php/Speci%C3%A1lis: Disallow: /index.php/Speci%C3%A1lis:Search Disallow: /index.php/Speci%C3%A1lis%3ASearch Disallow: /index.php/Speci%C3%A1lis:Specialpages Disallow: /index.php/Speci%C3%A1lis:Userlogin Disallow: /index.php/Speci%C3%A1lis:Preferences Disallow: /index.php/Speci%C3%A1lis:Watchlist Disallow: /index.php/Speci%C3%A1lis:Recentchanges Disallow: /index.php/Speci%C3%A1lis:Upload Disallow: /index.php/Speci%C3%A1lis:Imagelist Disallow: /index.php/Speci%C3%A1lis:Newimages Disallow: /index.php/Speci%C3%A1lis:Listusers Disallow: /index.php/Speci%C3%A1lis:Listadmins Disallow: /index.php/Speci%C3%A1lis:Statistics Disallow: /index.php/Speci%C3%A1lis:Lonelypages Disallow: /index.php/Speci%C3%A1lis:Uncategorizedpages Disallow: /index.php/Speci%C3%A1lis:Uncategorizedcategories Disallow: /index.php/Speci%C3%A1lis:Unusedimages Disallow: /index.php/Speci%C3%A1lis:Popularpages Disallow: /index.php/Speci%C3%A1lis:Wantedpages Disallow: /index.php/Speci%C3%A1lis:Shortpages Disallow: /index.php/Speci%C3%A1lis:Longpages Disallow: /index.php/Speci%C3%A1lis:Newpages Disallow: /index.php/Speci%C3%A1lis:Ancientpages Disallow: /index.php/Speci%C3%A1lis:Deadendpages Disallow: /index.php/Speci%C3%A1lis:Allpages Disallow: /index.php/Speci%C3%A1lis:Ipblocklist Disallow: /index.php/Speci%C3%A1lis:Maintenance Disallow: /index.php/Speci%C3%A1lis:Booksources Disallow: /index.php/Speci%C3%A1lis:Categories Disallow: /index.php/Speci%C3%A1lis:Export Disallow: /index.php/Speci%C3%A1lis:Version Disallow: /index.php/Speci%C3%A1lis:Allmessages Disallow: /index.php/Speci%C3%A1lis:Log Disallow: /index.php/Speci%C3%A1lis:Undelete Disallow: /index.php/Speci%C3%A1lis:Blockip Disallow: /index.php/Speci%C3%A1lis:Makesysop Disallow: /index.php/Seg%C3%ADts%C3%A9g:Tartalom Crawl-delay: 10