# # robots.txt for allmusic.biz # User-agent: * Disallow: /bbs/admin/ Disallow: /bbs/attachment/ Disallow: /bbs/data/ Disallow: /bbs/hack/ Disallow: /bbs/images/ Disallow: /bbs/ipdata/ Disallow: /bbs/js/ Disallow: /bbs/lang/ Disallow: /bbs/require/ Disallow: /bbs/template/ Disallow: /bbs/wap/ Disallow: /bbs/simple/ Disallow: /blog/ Disallow: /ad05/ Disallow: /cert/ Disallow: /download/ Disallow: /freemind/ Disallow: /img/ Disallow: /listen/ Disallow: /myriad/ Disallow: /player/ Disallow: /pum/ Disallow: /podcast/wp-admin/ Disallow: /podcast/mediafile/ Disallow: /wiki/Special:Random Disallow: /wiki/Special%3ARandom Disallow: /wiki/Special:Search Disallow: /wiki/Special%3ASearch Disallow: /wiki/*action=edit Disallow: /wiki/*action%3Dedit Disallow: /wiki/*action=history Disallow: /wiki/*oldid= Disallow: /wiki/*oldid%3D Disallow: /wiki/*diff= Disallow: /wiki/*diff%3D Disallow: /wiki/config/ Disallow: /wiki/skins/ Disallow: /wiki/images/ Disallow: /wiki/mw_tools/ # # User-agent: Baiduspider Disallow: /wiki/*action=edit Disallow: /wiki/*action%3Dedit Disallow: /wiki/*action=history Disallow: /wiki/*action%3Dhistory Disallow: /wiki/*oldid= Disallow: /wiki/*oldid%3D Disallow: /wiki/*diff= Disallow: /wiki/*diff%3D Disallow: /wiki/*variant= User-agent: Slurp Disallow: /wiki/*action=edit Disallow: /wiki/*action%3Dedit Disallow: /wiki/*action=history Disallow: /wiki/*action%3Dhistory Disallow: /wiki/*oldid= Disallow: /wiki/*oldid%3D Disallow: /wiki/*diff= Disallow: /wiki/*diff%3D User-agent: Googlebot Disallow: /wiki/*action=edit Disallow: /wiki/*action%3Dedit Disallow: /wiki/*action=history Disallow: /wiki/*action%3Dhistory Disallow: /wiki/*oldid= Disallow: /wiki/*oldid%3D Disallow: /wiki/*diff= Disallow: /wiki/*diff%3D #no use for wiki. User-agent: twiceler Disallow: / User-agent: WebAlta Crawler 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: / # Don't allow the wayback-maschine to index user-pages #User-agent: ia_archiver #Disallow: /wiki/User