# robots.txt for http://debianguiden.dk/ # Don't crawl dynamically generated pages User-agent: * Disallow: /w/ # Cuill/Twiceler is behaving badly, repeatedly reading this file User-agent: cuill Disallow: / User-agent: Twiceler-0.9 Disallow: / User-agent: Twiceler Disallow: / # A bit too eager User-agent: Jyxobot/1 Disallow: / # Robots behaving badly (lifted from Wikimedia Foundation) 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: / User-agent: grub-client Disallow: / User-agent: k2spider Disallow: / User-agent: NPBot Disallow: / User-agent: WebReaper Disallow: /