# Welcome All Search Engine Friendly Robots # # robots.txt for http://www.tophotels-beijing.com # # 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. # # All automated robots "Don't Crawl Espire's Web Site Otherwise You will be Blocked ". # Robots Controlled by ProfitBySearch User-agent: * Allow: / # advertising-related bots: User-agent: Mediapartners-Google* Disallow: /site_mgxt # Wikipedia work bots: User-agent: IsraBot Disallow: /site_mgt User-agent: Orthogaffe Disallow: /site_mgt # Crawlers feeding search engines Like . User-agent: UbiCrawler Disallow: /site_mgt User-agent: DOC Disallow: /site_mgt User-agent: Zao Disallow: /site_mgt # Some bots are known to be trouble, particularly those designed to copy # entire sites. Please obey robots.txt. User-agent: sitecheck.internetseer.com Disallow: /site_mgt User-agent: Zealbot Disallow: /site_mgt User-agent: MSIECrawler Disallow: /site_mgt User-agent: SiteSnagger Disallow: /site_mgt User-agent: WebStripper Disallow: /site_mgt User-agent: WebCopier Disallow: /site_mgt User-agent: Fetch Disallow: /site_mgt User-agent: Offline Explorer Disallow: /site_mgt User-agent: Teleport Disallow: /site_mgt User-agent: TeleportPro Disallow: /site_mgt User-agent: WebZIP Disallow: /site_mgt User-agent: linko Disallow: /site_mgt User-agent: Microsoft.URL.Control Disallow: /site_mgt User-agent: Xenu Disallow: /site_mgt User-agent: larbin Disallow: /site_mgt User-agent: libwww Disallow: /site_mgt User-agent: ZyBORG Disallow: /site_mgt User-agent: Download Ninja Disallow: /site_mgt # The 'grub' distributed client has been *very* poorly behaved. User-agent: grub-client Disallow: /site_mgt # Doesn't follow robots.txt anyway, but... User-agent: k2spider Disallow: /site_mgt # Hits many times per second, not acceptable # http://www.nameprotect.com/botinfo.html User-agent: NPBot Disallow: /site_mgt # A capture bot, downloads gazillions of pages with no public benefit # http://www.webreaper.net/ User-agent: WebReaper Disallow: /site_mgt # Allow the wayback-maschine to index user-pages #User-agent: ia_archiver #Disallow: / sitemap:http://www.tophotels-beijing.com/sitemap.xml