User-Agent: * Disallow: /wp-content/plugins/ Disallow: /wp-content/themes/ Disallow: /wp-includes/ Disallow: /wp-admin/ Disallow: /cgi-bin Disallow: /wp-admin Disallow: /wp-content/cache Disallow: /trackback Disallow: /comments Disallow: /category/*/* Disallow: */trackback Disallow: */comments Disallow: /*?* Disallow: /*? Allow: /wp-content/uploads Disallow: /wp- Disallow: http://www.martinrevert.com.ar/index.php/putobox/ Disallow: http://www.martinrevert.com.ar/index.php/open-source-haciendo-y-optimizando-negocios/ Disallow: http://www.martinrevert.com.ar/index.php/category/uncategorized/ Disallow: http://www.martinrevert.com.ar/index.php/2009/10/13/hello-world/ Disallow: http://www.martinrevert.com.ar/index.php/2007/12/09/blogs-versus-medios-el-personal-fest/ # # Sitemap permitido, búsquedas no. # Sitemap: http://www.martinrevert.com.ar/sitemap.xml.gz Disallow: /?s= Disallow: /search Allow: /feed/$ Disallow: /feed Disallow: /comments/feed Disallow: /*/feed/$ Disallow: /*/feed/rss/$ Disallow: /*/trackback/$ Disallow: /*/*/feed/$ Disallow: /*/*/feed/rss/$ Disallow: /*/*/trackback/$ Disallow: /*/*/*/feed/$ Disallow: /*/*/*/feed/rss/$ Disallow: /*/*/*/trackback/$ User-agent: WebCopier Disallow: / User-agent: HTTrack Disallow: / User-agent: Microsoft.URL.Control Disallow: / User-agent: libwww Disallow: / User-agent: noxtrumbot Crawl-delay: 50 User-agent: msnbot Crawl-delay: 30 User-agent: Slurp Crawl-delay: 10 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: / # 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 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: / # Google Image User-agent: Googlebot-Image Disallow: Allow: /* # Google AdSense User-agent: Mediapartners-Google* Disallow: Allow: /* # digg mirror User-agent: duggmirror Disallow: /