# $Id: robots.txt,v 1.4.4.3 2008/11/04 09:14:25 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: /sites/all/ Disallow: /css Disallow: /includes/ Disallow: /misc/ Disallow: /modules/ Disallow: /profiles/ Disallow: /scripts/ Disallow: /sites/ Disallow: /themes/ # Files Disallow: /CHANGELOG.txt Disallow: /cron.php Disallow: /INSTALL.mysql.txt Disallow: /INSTALL.pgsql.txt Disallow: /install.php Disallow: /INSTALL.txt Disallow: /LICENSE.txt Disallow: /MAINTAINERS.txt Disallow: /update.php Disallow: /UPGRADE.txt Disallow: /xmlrpc.php # Paths (clean URLs) Disallow: /about_show/ Disallow: /ad_fed/* Disallow: /ad_fwd/* Disallow: /ad_fwd/ Disallow: /admin/ Disallow: /aggregator/ Disallow: /allusers/ Disallow: /calendar/ Disallow: /catalog/ Disallow: /category/tags/ Disallow: /choose_gc/ Disallow: /comment/reply/ Disallow: /contact/ Disallow: /content/code-conduct/ Disallow: /content/terms-use-agreement/ Disallow: /control_panel/ Disallow: /im_galleries/ Disallow: /logout/ Disallow: /misc/ Disallow: /node/ Disallow:/node/*/ Disallow: /node/add/ Disallow: /page-clicktrack/* Disallow: /page-clicktrack/ Disallow: /portalink/ Disallow: /privacy-policy/ Disallow: /refer_friend/ Disallow: /rss.xml/ Disallow: /search/ Disallow: /search_advanced/ Disallow: /site-manager-special/ Disallow: /sites/ Disallow: /sites/* Disallow: /tagadelic/ Disallow: /taxonomy/ Disallow: /user/ Disallow: /user/* Disallow: /users/ Disallow: /user/login/ Disallow: /user/password/ Disallow: /user/register/ Disallow: /visitor/ # 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/ # Paths (clean URLs) FIXED Disallow: /sites/all Disallow: /about_show Disallow: /ad_fed/* Disallow: /ad_fwd Disallow: /admin Disallow: /allusers Disallow: /aggregator Disallow: /allusers Disallow: /calendar Disallow: /catalog Disallow: /category/tags Disallow: /choose_gc Disallow: /comment/reply Disallow: /contact Disallow: /content/code-conduct Disallow: /content/terms-use-agreement Disallow: /control_panel Disallow: /css Disallow: /im_galleries Disallow: /includes Disallow: /logout Disallow: /misc Disallow: /modules Disallow: /node Disallow:/node/* Disallow: /node/add Disallow: /page-clicktrack Disallow: /portalink Disallow: /profiles Disallow: /privacy-policy Disallow: /refer_friend Disallow: /rss.xml Disallow: /scripts Disallow: /search Disallow: /search_advanced Disallow: /site-manager-special Disallow: /sites Disallow: /tagdelic Disallow: /taxonomy Disallow: /themes Disallow: /user Disallow: /user/login Disallow: /user/password Disallow: /user/register Disallow: /visitor # Paths (no clean URLs) FIXED 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 # fixes Disallow: /*sort= Disallow: /abuse/ Disallow: /*size= Disallow: /*/track$ Sitemap: http://www.theportalusa.org/sitemap.xml