# Internet Archive Way Back Machine User-agent: ia_archiver Disallow: / # advertising-related bots: User-agent: Mediapartners-Google* Disallow: / # Wikipedia work bots: User-agent: IsraBot 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: / # Don't allow the wayback-maschine to index user-pages #User-agent: ia_archiver #Disallow: /wiki/User User-agent: * Disallow: /BP/ Disallow: /add/ Disallow: /dbOLD/ Disallow: /dbTest/ Disallow: ExampleID.mp3 Disallow: MixesDB_Search.php Disallow: MixesDB_Search.xml Disallow: favicon.ico Disallow: googlec49dd5f70754b9b1.html Disallow: info.php Disallow: ref.php Disallow: /db/Especial:Search Disallow: /db/Especial%3ASearch Disallow: /db/Special:Collection Disallow: /db/Spezial:Sammlung Disallow: /db/Special:Random Disallow: /db/Special%3ARandom Disallow: /db/Special:Search Disallow: /db/Special%3ASearch Disallow: /db/Spesial:Search Disallow: /db/Spesial%3ASearch Disallow: /db/Spezial:Search Disallow: /db/Spezial%3ASearch Disallow: /db/Specjalna:Search Disallow: /db/Specjalna%3ASearch Disallow: /db/Speciaal:Search Disallow: /db/Speciaal%3ASearch Disallow: /db/Speciaal:Random Disallow: /db/Speciaal%3ARandom Disallow: /db/Speciel:Search Disallow: /db/Speciel%3ASearch Disallow: /db/Speciale:Search Disallow: /db/Speciale%3ASearch Disallow: /db/Istimewa:Search Disallow: /db/Istimewa%3ASearch Disallow: /db/Toiminnot:Search Disallow: /db/Toiminnot%3ASearch Disallow: sitemap.txt Disallow: robots.txt