# $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 Allow: /thedmp/ Disallow: /*/ # Directories Disallow: /book/ Disallow: /college/ Disallow: /img/ Disallow: /collaborations/ Disallow: /preview/ Disallow: /notyet/ Disallow: /tmp/ Disallow: /thedmp/database/ Disallow: /thedmp/includes/ Disallow: /thedmp/misc/ Disallow: /thedmp/modules/ Disallow: /thedmp/sites/ Disallow: /thedmp/themes/ Disallow: /thedmp/scripts/ Disallow: /thedmp/updates/ Disallow: /thedmp/profiles/ Disallow: /thedmp/files/ # Files Disallow: /thedmp/xmlrpc.php Disallow: /thedmp/cron.php Disallow: /thedmp/update.php Disallow: /thedmp/install.php Disallow: /thedmp/INSTALL.mysql.txt Disallow: /thedmp/INSTALL.pgsql.txt Disallow: /thedmp/CHANGELOG.txt Disallow: /thedmp/MAINTAINERS.txt Disallow: /thedmp/LICENSE.txt Disallow: /thedmp/UPGRADE.txt # Paths (clean URLs) Disallow: /thedmp/admin/ Disallow: /thedmp/aggregator/ Disallow: /thedmp/comment/reply/ Disallow: /thedmp/contact/ Disallow: /thedmp/logout/ Disallow: /thedmp/node/add/ Disallow: /thedmp/search/ Disallow: /thedmp/user/register/ Disallow: /thedmp/user/password/ Disallow: /thedmp/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/