User-agent: * Disallow: # 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. # 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: 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: / # 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: / # # Hotelopia site robots.txt # User-agent: * Disallow:/xsl/* Disallow:/xml*/* Disallow:/user/* Disallow:/plantilla_freya/* Disallow:/js/* Allow:/info/* Disallow:/img/* Disallow:/html/* Disallow:/Generator/*/* Disallow:/errors/* Disallow:/dtd/* Disallow:/css/* Disallow:/CallCenter/* Disallow:/Bin/* Disallow:/App_*/* Disallow:/*? # # Hotelopia Sitemap by market # Sitemap: http://www.hotelopia.dk/sitemaps/sitemap_dk_01.xml.gz Sitemap: http://hoteller.hotelopia.dk/sitemaps/sitemap_dk_hoteller_index.xml.gz Sitemap: http://www.hotelopia.it/sitemaps/sitemap_it_01.xml.gz Sitemap: http://hotels.hotelopia.it/sitemaps/sitemap_it_hotels_index.xml.gz Sitemap: http://www.hotelopia.pt/sitemaps/sitemap_pt_01.xml.gz Sitemap: http://hoteis.hotelopia.pt/sitemaps/sitemap_pt_hoteis_index.xml.gz Sitemap: http://www.hotelopia.se/sitemaps/sitemap_se_01.xml.gz Sitemap: http://hotell.hotelopia.se/sitemaps/sitemap_se_hotell_index.xml.gz Sitemap: http://www.hotelopia.nl/sitemaps/sitemap_nl_01.xml.gz Sitemap: http://hotels.hotelopia.nl/sitemaps/sitemap_nl_hotels_index.xml.gz Sitemap: http://www.hotelopia.de/sitemaps/sitemap_de_01.xml.gz Sitemap: http://hotels.hotelopia.de/sitemaps/sitemap_de_hotels_index.xml.gz Sitemap: http://www.hotelopia.fr/sitemaps/sitemap_fr_01.xml.gz Sitemap: http://hotels.hotelopia.fr/sitemaps/sitemap_fr_hotels_index.xml.gz