sitemap: http://www.puntofape.com/sitemap.xml # # robots.txt from http://www.wikipedia.org/ for "other" robots # Thanks Wikipedians! # User-agent: Mediapartners-Google* Disallow: User-agent: Googlebot-Image Allow: /wp-content/uploads/*.gif Allow: /wp-content/uploads/*.png Allow: /wp-content/uploads/*.jpg 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: duggmirror Disallow: / User-agent: * Disallow: /trackback/ Disallow: */trackback/ Disallow: */trackback* Disallow: /*/trackback/$ Disallow: /*/*/trackback/$ Disallow: /*/*/*/trackback/$ Disallow: /feed Disallow: /feed/ Disallow: */feed/ Disallow: /feed/$ Disallow: /*/feed/$ Disallow: /*/*/feed Disallow: /*/*/feed/ Disallow: /*/*/feed/$ Disallow: /*/*/*/feed Disallow: /*/*/*/feed/$ Disallow: /*/feed/rss/$ Disallow: /*/*/*/feed/ Disallow: /*/*/*/*/feed Disallow: /*/*/*/*/feed/ Disallow: /*/*/feed/rss/$ Disallow: /*/*/*/feed/rss/$ Disallow: /respond/ Disallow: /respond/feed Disallow: /comment Disallow: /comment-* Disallow: /wp-* Disallow: /wp-content/ Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /*? Disallow: /*?* Disallow: /*.php$ Disallow: /*.js$ Disallow: /*.inc$ Disallow: /*.css$ Disallow: /*.cgi$ Disallow: /*.wmv$ Disallow: /*.xhtml$ Disallow: /*.php* Disallow: /*.gz$ Disallow: /search Disallow: /css/ Disallow: /images/ Disallow: /img/ Disallow: /linkman/ Disallow: /test/ Disallow: /ver/ Disallow: /picture_library/ Disallow: /cgi-bin/ Disallow: /author/ Disallow: /page/ Disallow: /page/* Disallow: /date/