# # 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. # # 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: cityreview Disallow: / User-agent: GurujiBot Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / User-agent: dotbot Disallow: / User-agent: ia_archiver Disallow: / User-Agent: Charlotte Disallow: / User-Agent: msnbot Disallow: / User-Agent: Speedy Disallow: / User-Agent: ScoutJet Disallow: / User-Agent: discobot Disallow: / User-Agent: accelobot Disallow: / User-Agent: YoudaoBot Disallow: / User-Agent: YodaoBot Disallow: / User-agent: kalooga Disallow: / User-agent: SBIder Disallow: / User-agent: Dolphin Disallow: / User-agent: SindiceBot Disallow: / User-agent: OOZBOT Disallow: / User-agent: NAVER Disallow: / User-agent: Yeti Disallow: / # Some bots are known to be trouble, particularly those designed to copy # entire sites. Please obey robots.txt. User-agent: MJ12bot 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: / # # Don't follow robots.txt anyway, but... # User-agent: robot Disallow: / User-agent: bot- Disallow: / User-agent: bot/ Disallow: / User-agent: \wbot Disallow: / User-agent: crawl Disallow: / User-agent: Crawl Disallow: / User-agent: Exabot Disallow: / User-agent: k2spider Disallow: / User-agent: attributor.com Disallow: / User-agent: AISearchBot Disallow: / User-Agent: spider 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: / # # Sorry "Slurp" but you are crawling our website much too often # User-agent: Slurp Disallow: / #User-agent: Slurp #Crawl-delay: 10 # Friendly, low-speed bots are welcome viewing article pages, but not # dynamically-generated pages please. # # Msnbot interprets the delay as seconds # User-agent: msnbot Crawl-delay: 120 Disallow: /trap/ User-agent: * Disallow: /trap/ # no sure of the behavior of the "?" character so the following disallows have been put in comments # Disallow: /syw/index.php?title=Special:Randompage # Disallow: /syw/index.php?title=Special%3ARandompage # Disallow: /syw/index.php?title=Special:Search # Disallow: /syw/index.php?title=Special%3ASearch # Disallow: /syw/index.php?title=Special:Recentchanges # Disallow: /syw/index.php?title=Special%3ARecentchanges # *at least* 2 second please. preferably more :D Crawl-delay: 2