# $Id: robots.txt,v 1.9 2007/06/27 22:37:44 goba 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: psbot Disallow: / User-agent: twiceler Disallow:/ User-agent: sogou spider Disallow:/ User-agent: * Disallow: /cgi-bin/ Disallow: /web2/calendar/ Disallow: /web2/files/ # Directories Disallow: /web2/database/ Disallow: /web2/includes/ Disallow: /web2/misc/ Disallow: /web2/modules/ Disallow: /web2/sites/ Disallow: /web2/themes/ Disallow: /web2/scripts/ Disallow: /web2/updates/ Disallow: /web2/profiles/ # Files Disallow: /web2/xmlrpc.php Disallow: /web2/cron.php Disallow: /web2/update.php Disallow: /web2/install.php Disallow: /web2/INSTALL.txt Disallow: /web2/INSTALL.mysql.txt Disallow: /web2/INSTALL.pgsql.txt Disallow: /web2/CHANGELOG.txt Disallow: /web2/MAINTAINERS.txt Disallow: /web2/LICENSE.txt Disallow: /web2/UPGRADE.txt # Paths (clean URLs) Disallow: /web2/admin/ Disallow: /web2/comment/reply/ Disallow: /web2/contact/ Disallow: /web2/logout/ Disallow: /web2/node/add/ Disallow: /web2/search/ Disallow: /web2/user/register/ Disallow: /web2/user/password/ Disallow: /web2/user/login/ # web postnuke Disallow: /web/admin Disallow: /web/banners Disallow: /web/config Disallow: /web/config-old Disallow: /web/error Disallow: /web/header Disallow: /web/footer Disallow: /web/pntables Disallow: /web/images Disallow: /web/includes Disallow: /web/themes Disallow: /web/pnTemp Disallow: /web/docs Disallow: /web/javascript