User-agent: * Allow: / # # Crawlers that are kind enough to obey, but which we'd rather not have. # User-Agent: YahooSeeker Disallow: / User-Agent: BecomeBot Disallow: / # # A growing list of pest bots # User-Agent: BaiDuSpider Disallow: / User-Agent: CherryPicker Disallow: / User-Agent: Crescent Internet ToolPak Disallow: / User-Agent: DISCo Pump Disallow: / User-Agent: EmailSiphon Disallow: / User-Agent: htdig Disallow: / User-Agent: HTTrack Disallow: / User-Agent: LNSpiderGuy Disallow: / User-Agent: Netprospector Disallow: / User-Agent: PerMan Surfer Disallow: / User-Agent: psbot Disallow: / User-Agent: szukacz Disallow: / User-Agent: RPT-HTTPClient Disallow: / User-Agent: Teleport Disallow: / User-Agent: Telesoft Disallow: / User-Agent: Ultraseek Disallow: / User-Agent: vspider Disallow: / User-Agent: WebCopier Disallow: / User-Agent: WebEMailExtractor Disallow: / User-Agent: WebReaper Disallow: / User-Agent: Webster Pro Disallow: / User-Agent: WebStripper Disallow: / User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / User-agent: InternetSeer.com 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 refer to the manual and use it properly; there is a # wait = x number of seconds 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: / User-Agent: grub Disallow: / # # Doesn't follow robots.txt # 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. # http://www.webreaper.net/ User-agent: WebReaper Disallow: /