# $Id: robots.txt,v 1.7 2007/01/08 12:02:18 dries 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: /_corp/database/ Disallow: /_corp/includes/ Disallow: /_corp/misc/ Disallow: /_corp/modules/ Disallow: /_corp/sites/ Disallow: /_corp/themes/ Disallow: /_corp/scripts/ Disallow: /_corp/updates/ Disallow: /_corp/profiles/ # Files Disallow: /_corp/xmlrpc.php Disallow: /_corp/cron.php Disallow: /_corp/update.php Disallow: /_corp/install.php Disallow: /_corp/INSTALL.mysql.txt Disallow: /_corp/INSTALL.pgsql.txt Disallow: /_corp/CHANGELOG.txt Disallow: /_corp/MAINTAINERS.txt Disallow: /_corp/LICENSE.txt Disallow: /_corp/UPGRADE.txt # Paths (clean URLs) Disallow: /_corp/admin/ Disallow: /_corp/aggregator/ Disallow: /_corp/comment/reply/ Disallow: /_corp/contact/ Disallow: /_corp/logout/ Disallow: /_corp/node/add/ Disallow: /_corp/search/ Disallow: /_corp/user/register/ Disallow: /_corp/user/password/ Disallow: /_corp/user/login/ # Paths (no clean URLs) Disallow: /_corp/?q=admin/ Disallow: /_corp/?q=aggregator/ Disallow: /_corp/?q=comment/reply/ Disallow: /_corp/?q=contact/ Disallow: /_corp/?q=logout/ Disallow: /_corp/?q=node/add/ Disallow: /_corp/?q=search/ Disallow: /_corp/?q=user/password/ Disallow: /_corp/?q=user/register/ Disallow: /_corp/?q=user/login/