# /robots.txt file for http://www.utrecht.nl/ # # user-agent op blok! User-agent: webcrawler Disallow:/ User-agent: lycra Disallow: / User-agent: Googlebot-Image Disallow: / User-agent: Slurp Disallow: / # advert-gerelateerde bots: User-agent: Mediapartners-Google* Disallow: / # extra toegevoegde bloklijst met bekende 'probleemjeugd' bots User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / 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: 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: / # Elke user-agent mag nu door, maar mag geen path's (/tmp;/logs;) User-agent: * Disallow: /tmp Disallow: /logs Disallow: /images Disallow: /css Disallow: /print Disallow: /cgi-bin Disallow: /test Disallow: /cora