# # 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: / # Don't allow the wayback-maschine to index user-pages #User-agent: ia_archiver #Disallow: /wiki/User #Disallow: /wiki/Benutzer # # 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: /birdoftheweek.htm Disallow: /preview_picks/ # Changes frequently Disallow: /bird_of_the_week/ # Changes frequently Disallow: /australianbirds.htm Disallow: /old_world_birds.htm Disallow: /new_world_birds.htm Disallow: /printpurchases.htm Disallow: /accipitridae_sa/ # Old Directory Disallow: /anseriformes/ # Old Directory Disallow: /anthochaera/ # Old Directory Disallow: /manorina/ # Old Directory Disallow: /sterniniOld/ # Old Directory Disallow: /epthianura/ # Old Directory Disallow: /philemon/ # Old Directory Disallow: /psittacidae_sa/ # Old Directory Disallow: /alcinae/ # Old Directory Disallow: /caprimulgi/ # Old Directory Disallow: /strigiformesSA/ # Old Directory Disallow: /emberizini/ # Old Directory Disallow: /dendrocygnidae/ # Old Directory Disallow: /centropidae/ # Old Directory Disallow: /source/ # Old Directory Disallow: /scolopacinae/ # Old Directory Disallow: /tringinae/ # Old Directory Disallow: /charadriidae_sa/ # Old Directory Disallow: /strigidae_eua/ # Old Directory Disallow: /strigiformes/ # Old Directory Disallow: /anserantidae/ # Old Directory Disallow: /cerylidae/ # Old Directory Disallow: /coraciiformes_as/ # Old Directory Disallow: /nyctiibidae/ # Old Directory Disallow: /thraupini/ # Old Directory Disallow: /stercorariini/ # Old Directory Disallow: /anthochaera/ # Old Directory Disallow: /jacanoidea/ # Old Directory Disallow: /sturnidae_sam/ # Old Directory Disallow: /podicepidae/ # Old Directory Disallow: /fringillinae/ # Old Directory Disallow: /estrildinae/ # Old Directory Disallow: /falconidae_sa/ # Old Directory Disallow: /cathartinae/ # Old Directory Disallow: /motacillinae/ # Old Directory Disallow: /rupicola/ # Old Directory Disallow: /apodiformes/ # Old Directory Disallow: /TrogonOld/ # Old Directory Disallow: /uploads/ # Old Directory Disallow: /bucerotidae_eua/ # Old Directory Disallow: /diomedeinae/ # Old Directory Disallow: /cuculiformes/ # Old Directory Disallow: /cuculiformes_sa/ # Old Directory Disallow: /funariidae/ # Old Directory Disallow: /pachycephalinae/ # Old Directory Disallow: /oriolini/ # Old Directory Disallow: /dicrurinae/ # Old Directory Disallow: /garrulacinae/ # Old Directory Disallow: /passerinae/ # Old Directory Disallow: /procellariinae/ # Old Directory Disallow: /muscicapidae_aus/ # Old Directory Disallow: /laridae/ # Old Directory