# $Id: robots.txt,v 1.7.2.2 2008/02/25 02:18:25 drumm Exp $ # # robots.txt # # This file is to prevent the crawling and indexing of certain parts # of your site by web crawlers and spiders run by sites like Yahoo! # and Google. By telling these "robots" where not to go on your site, # you save bandwidth and server resources. # # This file will be ignored unless it is at the root of your host: # Used: http://example.com/robots.txt # Ignored: http://example.com/site/robots.txt # # For more information about the robots.txt standard, see: # http://www.robotstxt.org/wc/robots.html # # For syntax checking, see: # http://www.sxw.org.uk/computing/robots/check.html User-agent: IsraBot Disallow: User-agent: Orthogaffe Disallow: User-agent: DBLBot Disallow: / 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: 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: wget Disallow: / User-agent: grub-client Disallow: / User-agent: k2spider Disallow: / User-agent: NPBot Disallow: / User-agent: WebReaper Disallow: / User-agent: LinkWalker Disallow: / User-agent: BPImageWalker Disallow: / # Don't allow the wayback-maschine to index user-pages User-agent: ia_archiver Disallow: / User-agent: * Crawl-delay: 10 # Directories Disallow: /cms/database/ Disallow: /cms/includes/ Disallow: /cms/logs/ Disallow: /cms/misc/ Disallow: /cms/modules/ Disallow: /cms/sites/ Disallow: /cms/themes/ Disallow: /cms/scripts/ Disallow: /cms/updates/ Disallow: /cms/profiles/ Disallow: /c/add/ Disallow: /c/view/ # Files Disallow: /cms/xmlrpc.php Disallow: /cms/cron.php Disallow: /cms/update.php Disallow: /cms/install.php Disallow: /cms/INSTALL.txt Disallow: /cms/INSTALL.mysql.txt Disallow: /cms/INSTALL.pgsql.txt Disallow: /cms/CHANGELOG.txt Disallow: /cms/MAINTAINERS.txt Disallow: /cms/LICENSE.txt Disallow: /cms/UPGRADE.txt # Paths (clean URLs) Disallow: /cms/about/ Disallow: /cms/admin/ Disallow: /cms/comment/reply/ Disallow: /cms/contact/ Disallow: /cms/de/contact Disallow: /cms/de/impressum Disallow: /cms/disclaimer Disallow: /cms/en/contact Disallow: /cms/logout/ Disallow: /cms/node/add/ Disallow: /cms/search/ Disallow: /cms/user/register/ Disallow: /cms/user/password/ Disallow: /cms/user/login/ # Paths (no clean URLs) Disallow: /cms/?q=about Disallow: /cms/?q=about/ Disallow: /cms/?q=admin/ Disallow: /cms/?q=comment/reply/ Disallow: /cms/?q=contact/ Disallow: /cms/?q=de/contact Disallow: /cms/?q=de/impressum Disallow: /cms/?q=disclaimer Disallow: /cms/?q=en/contact Disallow: /cms/?q=logout/ Disallow: /cms/?q=node/add/ Disallow: /cms/?q=search/ Disallow: /cms/?q=user/password/ Disallow: /cms/?q=user/register/ Disallow: /cms/?q=user/login/