# # robots.txt # # First, this is the # robots.txt from http://www.wikipedia.org/ for "other" robots # Thanks Wikipedians! # # 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. # # Google Image User-agent: Googlebot-Image Disallow: Allow: /* # Google AdSense User-agent: Mediapartners-Google* Disallow: Allow: /* # digg mirror User-agent: duggmirror Disallow: / User-agent: Orthogaffe 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: / User-agent: * Disallow: /cgi-bin Disallow: /wp-content/plugins Disallow: /wp-content/backup* Disallow: /wp-content/cache Disallow: /wp-content/themes Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /*/*/*/feed.xml Disallow: /*/*/attachment Disallow: */trackback Disallow: /search/ Disallow: */comment-page-*/ Disallow: */*/?x=0&y=0 Disallow: */*/*&x=0&y=0 Disallow: /*/*/?newwindow=* Disallow: /*/*/?dur=* Disallow: /*/?newwindow=* Disallow: /*/?dur=* Disallow: /*/*/?utm_source=* Disallow: /*/*/?a=* Disallow: /*/?utm_source=* Disallow: /*/?a=* Disallow: /*?utm_source Disallow: /*?utm_medium Disallow: /*?utm_campaign Disallow: /*?utm_term Disallow: /*?utm_content Disallow: /*?utm_nooverride Disallow: /*&utm_source Disallow: /*&utm_medium Disallow: /*&utm_campaign Disallow: /*&utm_term Disallow: /*&utm_content Disallow: /*&utm_nooverride Sitemap: http://www.decoracion-deinteriores.com/sitemap.xml.gz