# # robots.txt taken from http://www.wikipedia.org/ and others # ############# # good bots # ############# # # 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. # Disallow: /wp-includes/ Disallow: /wp-content/ Disallow: /wp-admin/ Disallow: /feed/ Disallow: /art/wp-includes/ Disallow: /art/wp-content/ Disallow: /art/wp-admin/ Disallow: /art/guestbook-comments/ Disallow: /art/contacts/ Disallow: /art/*/*/*/*/feed/ Disallow: /art/*/*/*/feed/ Disallow: /art/*/*/feed/ Disallow: /art/*/feed/ Disallow: /art/feed/ Disallow: /viagens/comments/feed/ Disallow: /viagens/wp-includes/ Disallow: /viagens/wp-content/ Disallow: /viagens/wp-admin/ Disallow: /viagens/feed/ Disallow: /viagens/wp-content/plugins/ Disallow: /viagens/acerca-deste-site/useronline/ /art/contacts/ User-agent: * # disallow all files in these directories Disallow: /cgi-bin/ Disallow: /z/j/ Disallow: /z/c/ Disallow: /stats/ Disallow: /dh_ Disallow: /about/ Disallow: /contact/ Disallow: /tag/ Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /contact Disallow: /manual Disallow: /manual/* Disallow: /phpmanual/ Disallow: /category/ User-agent: Googlebot # disallow all files ending with these extensions # Disallow: /*.php$ <-- not sure Disallow: /*.js$ Disallow: /*.inc$ Disallow: /*.css$ Disallow: /*.gz$ Disallow: /*.wmv$ Disallow: /*.cgi$ Disallow: /*.xhtml$ # disallow all files with ? in url Disallow: /*?* # disable duggmirror # allow google image bot to search all images User-agent: Googlebot-Image Disallow: Allow: /* # allow adsense bot on entire site User-agent: Mediapartners-Google* Disallow: Allow: /* ############ # bad bots # ############ #Adsbot-Google # crawls pages to measure AdWords landing page quality. # We only use this bot if you use Google AdWords to advertise your site. # Find out more about this bot and how to block it from portions of your site. # Meaning, "allow adsense bot on entire site" # 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: duggmirror 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