# # robots.txt thanks to wikipedia.org and friends # # Please note: There are # some misbehaved spiders out there that go _way_ too fast. If you're # irresponsible, your access to the site may be blocked. # # advertising-related bots: User-agent: Mediapartners-Google* 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: / # # self added additional lines # # fast russian crawler User-agent: Mail.Ru Disallow: / # Crawler for hire User-agent: 008 Disallow: / User-agent: abot Disallow: / User-agent: aibot Disallow: / User-agent: aipbot Disallow: / User-agent: anbo-ubot Disallow: / User-agent: ccubee Disallow: / User-agent: ConveraCrawler Disallow: / User-agent: ConveraMultiMediaCrawler Disallow: / User-agent: http://www.almaden.ibm.com/cs/crawler Disallow: / User-agent: iCCrawler Disallow: / User-agent: Jakarta Commons-HttpClient Disallow: / User-agent: libwww-perl Disallow: / User-agent: linkwalker Disallow: / User-agent: MS FrontPage Disallow: / User-agent: obot Disallow: / User-agent: oBot Disallow: / User-agent: OmniExplorer_Bot Disallow: / User-agent: PhpDig Disallow: / User-agent: QualidatorWebSiteAnalyzer Disallow: / User-agent: QualidatorBot Disallow: / User-agent: SBIder Disallow: / User-agent: Scumbot Disallow: / User-agent: siteBot Disallow: / User-agent: Sosospider Disallow: / User-agent: Sogou web spider Disallow: / User-agent: spbot Disallow: / User-agent: VEDENSBOT Disallow: / # # This is a production host # list only disallowed paths # User-agent: * Disallow: /viewvc/ Disallow: /jenkins/ Disallow: /hudson/ Disallow: /artifactory/ Disallow: /forrest/ Disallow: /documentation/archiv/ Disallow: /mir/ Sitemap: https://www.mycore.de/sitemap.xml