# robots.txt # # http://www.4cheaters.de/ # Sitemap: /sitemap.xml User-agent: * Disallow: /cgi-bin Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /wp- Disallow: /trackback/ Disallow: /linkex Disallow: /admin Disallow: /amazon Disallow: /banner Disallow: /i Disallow: /sys Disallow: /modules Disallow: /cdn Disallow: /js Disallow: /libs User-agent: Googlebot Disallow: /*.js$ Disallow: /*.inc$ Disallow: /*.css$ Disallow: /*.gz$ Disallow: /*.wmv$ Disallow: /*.cgi$ Disallow: /*.xhtml$ # Prefetching User-agent: Fasterfox 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: / # We are just a few Seattle based guys trying to figure out how to make internet data as open as possible. # http://www.dotnetdotcom.org/ User-agent: dotbot Disallow: / User-agent: discobot Disallow: / User-agent: ccbot Disallow: / User-agent: VoilaBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: Yanga Disallow: / User-agent: Speedy Disallow: / User-agent: duggmirror Disallow: / User-agent: Similarpages Disallow: / User-agent: Nutch 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: / User-agent: psbot Disallow: / User-agent: Python-urllib Disallow: / User-agent: lwp-trivial/1.34 Disallow: / User-agent: lwp-trivial Disallow: / User-agent: lwp-request Disallow: / User-agent: Cazoodle 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: / User-agent: SBIder Disallow: / # Don't know these, but don't want them... User-agent: asterias Disallow: / User-agent: TECOMAC-Crawler Disallow: / User-agent: Custo Disallow: / User-agent: ichiro Disallow: / User-agent: Sensis Web Crawler Disallow: / User-agent: IRLbot Disallow: / # http://www.exabot.com/go/robot User-agent: Exabot Disallow: / User-agent: CFNetwork Disallow: / User-agent: TencentTraveler Disallow: / # 2009-06-03 # http://gais.cs.ccu.edu.tw/robot.php User-agent: Gaisbot Disallow: / # http://help.soso.com/webspider.htm User-agent: Sosospider Disallow: / # http://lucene.apache.org/nutch/bot.html User-agent: Nutch Disallow: / # http://CaretByte.com User-agent: CaretByte Disallow: / # http://www.dontbuylists.com/ # http://www.dontbuylists.com/DBLBot_Explained.pdf User-agent: DBLBot Disallow: / # # Kalooga is an internet search engine for photo albums and image galleries # # http://www.kalooga.com/info.html?page=crawler # Mozilla/5.0 (compatible; KaloogaBot; http://www.kalooga.com/info.html?page=crawler) # User-agent: kalooga # Allow: / # Charlotte is a spider that is indexing the web for sites to include in its search engine index. # http://www.searchme.com/support/spider/ User-agent: Charlotte Disallow: / # This is one of several experimental search engines produced by Thunderstone's R&D group whose mission is to advance our overall technology leadership. # http://search.thunderstone.com/texis/websearch/about.html User-agent: thunderstone Disallow: / # # http://help.live.com/help.aspx?project=wl_webmasters # User-agent: MSNbot # Allow: / # CatchBot investigates websites for publicly available information about companies, such as a company’s name, address, telephone number and keyword data about a company’s products and services. # http://www.catchbot.com User-agent: CatchBot Disallow: / # # Startup based out of San Francisco called Topsy Labs. Building something cool. # # http://labs.topsy.com/butterfly.html # User-agent: butterfly # Allow: / # http://www.sogou.com/docs/help/webmasters.htm#07 User-agent: sogou Disallow: / # Allow only specific directories # http://www.scoutjet.com/ User-agent: ScoutJet Disallow: / # http://www.youdao.com/help/webmaster/robot/003/ User-Agent: YodaoBot Disallow: / # http://help.naver.com/robots/ User-agent: NaverBot Disallow: / User-agent: Yeti Disallow: / # http://www.feedsky.com User-agent: Feedsky Disallow: / # 2009-08-03 # http://www.bots-on-para.de/bot.html User-agent: BotOnParade Disallow: / # Tagoobot/3.0; +http://www.tagoo.ru User-agent: Tagoobot Disallow: / # 2009-12-02 # aiHitBot-DS/1.0; +http://www.aihit.com/ User-agent: aiHitBot Disallow: / # 2009-12-17 # Mozilla/5.0 (compatible; 008/0.83; http://www.80legs.com/spider.html;) Gecko/2008032620 User-agent: 008 Disallow: / # 2010-01-04 # TurnitinBot - http://www.turnitin.com/robot/crawlerinfo.html # TurnitinBot/2.1 (http://www.turnitin.com/robot/crawlerinfo.html) User-agent: TurnitinBot Disallow: / # MLBot (www.metadatalabs.com/mlbot) User-agent: MLBot Disallow: / # 2010-02-02 # Linguee Bot (http://www.linguee.com/bot; bot@linguee.com) User-agent: Linguee Disallow: / # 2010-04-23 # BiWeC: Big Web Corpus http://nlp.fi.muni.cz/projekty/biwec/ User-agent: BiWeC Disallow: / # 2013-07-07 # BLEXBot/1.0; +http://webmeup.com/crawler.html User-agent: BLEXBot Disallow: /