# $Id: robots.txt,v 1.2.2.3 2007/08/05 09:56:41 hass 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: * Crawl-delay: 10 # Directories Disallow: /database/ Disallow: /includes/ Disallow: /misc/ Disallow: /modules/ Disallow: /sites/ Disallow: /themes/ Disallow: /scripts/ Disallow: /updates/ Disallow: /profiles/ # Files Disallow: /xmlrpc.php Disallow: /cron.php Disallow: /update.php Disallow: /install.php Disallow: /INSTALL.txt Disallow: /INSTALL.mysql.txt Disallow: /INSTALL.pgsql.txt Disallow: /CHANGELOG.txt Disallow: /MAINTAINERS.txt Disallow: /LICENSE.txt Disallow: /UPGRADE.txt # Paths (clean URLs) Disallow: /admin/ Disallow: /aggregator/ Disallow: /comment/reply/ Disallow: /contact/ Disallow: /logout/ Disallow: /node/add/ Disallow: /search/ Disallow: /user/register/ Disallow: /user/password/ Disallow: /user/login/ # Paths (no clean URLs) Disallow: /?q=admin/ Disallow: /?q=aggregator/ Disallow: /?q=comment/reply/ Disallow: /?q=contact/ Disallow: /?q=logout/ Disallow: /?q=node/add/ Disallow: /?q=search/ Disallow: /?q=user/password/ Disallow: /?q=user/register/ Disallow: /?q=user/login/ # Paths (clean URLs) Disallow: /admin/ Disallow: /aggregator/ Disallow: /comment/reply/ Disallow: /contact/ Disallow: /logout/ Disallow: /node/add/ Disallow: /search/ Disallow: /user/password/ Disallow: /user/register/ Disallow: /user/login/ # eigene Eintraege: User-agent: EmailCollector Disallow: / User-agent: A-Online Search Disallow: / User-agent: LinkWalker Disallow: / User-agent: fido/1.0 Harvest/1.4.pl2 Disallow: / User-agent: MegaSheep Disallow: / User-agent: msnbot Disallow: / User-agent: NaverBot-1.0 Disallow: / User-agent: Openfind data gatherer Disallow: / User-agent: B-l-i-t-z-Bot Disallow: / User-agent: WSB Disallow: / User-agent: http://www.almaden.ibm.com/cs/crawler Disallow: / User-agent: Yahoo-MMCrawler* Disallow: / User-agent: psbot Disallow: / User-agent: seekbot Disallow: / User-agent: B+l+i+t+z+B+O+T+@+t+r+i+c+u+s+.+c+o+m Disallow: / User-agent: mirago Disallow: / User-agent: turnitinbot Disallow: / User-agent: BruinBot Disallow: / User-agent: * Disallow: /*.css Disallow: /*.gif Disallow: /*.jpg Disallow: /*.pdf Disallow: /*.ps Disallow: /*.wmv Disallow: /*.png Disallow: /bildergalerie/ Disallow: /galerie/ Disallow: /webstats/ Disallow: /wiki/