# # Sitemap link for Google, Yahoo etc. # Sitemap: http://www.mudanzasmadrid.es/sitemap.xml # # Poorly behaved Crawlers, some of these ignore # robots.txt but... # User-agent: grub-client Disallow: / User-agent: k2spider Disallow: / User-agent: NPBot Disallow: / # # Well behaved Crawlers, but are unnecessary since # they don't seem to feed search engines # User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / User-agent: Twiceler Disallow: / # # Crawlers that are designed to copy entire sites # or download them for offline viewing. # User-agent: Jyxobot Disallow: / User-agent: mAgent Disallow: / User-agent: MJ12bot Disallow: / User-agent: Speedy Spider Disallow: / User-agent: ShopWiki Disallow: / User-agent: Huasai Disallow: / User-agent: DataCha0s Disallow: / User-agent: Baiduspider Disallow: / User-agent: Atomic_Email_Hunter Disallow: / User-agent: Mp3Bot Disallow: / User-agent: WinHttp Disallow: / User-agent: betaBot Disallow: / User-agent: core-project Disallow: / User-agent: panscient.com Disallow: / User-agent: Java Disallow: / User-agent: libwww-perl Disallow: / 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: / User-agent: WebReaper Disallow: / User-agent: wget Disallow: / # # Don't allow specific Crawlers that # are only here to hunt for images. # Thanks for listening. # # Google Image Bot User-agent: Googlebot-Image Disallow: /images/ Disallow: /js/ # Yahoo! Image Search User-agent: Yahoo-MMCrawler Disallow: /images/ Disallow: /js/ # MSN PicSearch User-agent: psbot Disallow: /images/ Disallow: /js/ # SingFish User-agent: asterias Disallow: /images/ Disallow: /js/ # MSNBOT User-agent: msnbot Disallow: /images/ Disallow: /js/ # # Don't allow any Crawlers to access # website images. # User-agent: * Disallow: /cgi-bin/ Disallow: /images/ Disallow: /stats/ Disallow: /mandamail.php Disallow: /mandamail_empresa.php Disallow: /mandamail_inclusion_portal.php Disallow: /lssi.html Disallow: /*.js$ Disallow: /*.css$ Disallow: /*.swf$