# $Id: robots.txt,v 1.7.2.3 2008/12/10 20:24:38 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: * Disallow: / #Crawl-delay: 10 # Directories #Disallow: /database/ #Disallow: /includes/ #Disallow: /misc/ #Disallow: /modules/ #Disallow: /profiles/ #Disallow: /scripts/ #Disallow: /sites/ #Disallow: /themes/ #Disallow: /scripts/ #Disallow: /updates/ #Disallow: /profiles/ # Files #Disallow: /xmlrpc.php #Disallow: /CHANGELOG.txt #Disallow: /cron.php #Disallow: /update.php #Disallow: /INSTALL.mysql.txt #Disallow: /INSTALL.pgsql.txt #Disallow: /install.php #Disallow: /INSTALL.txt #Disallow: /INSTALL.mysql.txt #Disallow: /INSTALL.pgsql.txt #Disallow: /CHANGELOG.txt #Disallow: /LICENSE.txt #Disallow: /MAINTAINERS.txt #Disallow: /update.php #Disallow: /UPGRADE.txt #Disallow: /xmlrpc.php # 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/ # added for pulitzer #Disallow: /faceted_search/ # Paths (no clean URLs) #Disallow: /?q=admin/ #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/