# $Id: robots.txt,v 1.9.2.1 2008/12/10 20:12:19 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: * Crawl-delay: 10 # Disallow: /index.php?q=form_files/ Disallow: /index.php?q=form_files Disallow: /form_files/ Disallow: /form_files Disallow: /calendar/*mini= Disallow: /calendar/*destination= Disallow: /calendar/*page= Disallow: /search$ Disallow: /*/feed$ Disallow: /node$ Disallow: /node/*/details/ Disallow: /node/*/details Disallow: /index.php?q=category/ Disallow: /index.php?q=category Disallow: /content/*size= # tell google to stop looking for stuff that isn't there Disallow: /SportsRecreation Disallow: /SportsRecreation/ Disallow: /index.php?q=SportsRecreation Disallow: /index.php?q=SportsRecreation/ Disallow: /index.php?q=Nightlife Disallow: /index.php?q=Nightlife/ Disallow: /Nightlife Disallow: /Nightlife/ Disallow: /index.php?q=Diversity Disallow: /index.php?q=Diversity/ Disallow: /Diversity Disallow: /Diversity/ Disallow: /index.php?q=ShoppingServices Disallow: /index.php?q=ShoppingServices/ Disallow: /ShoppingServices Disallow: /ShoppingServices/ Disallow: /index.php?q=Visitors Disallow: /index.php?q=Visitors/ Disallow: /Visitors Disallow: /Visitors/ Disallow: /index.php?q=Meetings Disallow: /index.php?q=Meetings/ Disallow: /Meetings/ Disallow: /Meetings Disallow: /EmploymentTraining Disallow: /EmploymentTraining/ Disallow: /index.php?q=EmploymentTraining Disallow: /index.php?q=EmploymentTraining/ Disallow: /site/Home.aspx Disallow: /11DaysofGlobalUnity91121/ Disallow: /11DaysofGlobalUnity91121 Disallow: /index.php?q=11DaysofGlobalUnity91121/ Disallow: /index.php?q=11DaysofGlobalUnity91121 Disallow: /Arts/ Disallow: /Arts Disallow: /index.php?q=Arts Disallow: /index.php?q=Arts/ Disallow: /AmesSchools/ Disallow: /AmesSchools Disallow: /index.php?q=AmesSchools Disallow: /index.php?q=AmesSchools/ Disallow: /ContactUs/ Disallow: /ContactUs Disallow: /index.php?q=ContactUs Disallow: /index.php?q=ContactUs/ Disallow: /Faith/ Disallow: /Faith Disallow: /index.php?q=Faith Disallow: /index.php?q=Faith/ Disallow: /Home/ Disallow: /Home Disallow: /index.php?q=Home Disallow: /index.php?q=Home/ Disallow: /ISU/ Disallow: /ISU Disallow: /index.php?q=ISU Disallow: /index.php?q=ISU/ Disallow: /Kids/ Disallow: /Kids Disallow: /index.php?q=Kids Disallow: /index.php?q=Kids/ Disallow: /DesktopModules/ Disallow: /DesktopModules Disallow: /index.php?q=DesktopModules/ Disallow: /index.php?q=DesktopModules Disallow: /Politics/ Disallow: /Politics Disallow: /index.php?q=Politics/ Disallow: /index.php?q=Politics Disallow: /View Disallow: /View/ Disallow: /index.php?q=View Disallow: /index.php?q=View/ Disallow: /ViewEvent Disallow: /ViewEvent/ Disallow: /index.php?q=ViewEvent Disallow: /index.php?q=ViewEvent/ Disallow: /Site/ Disallow: /Site Disallow: /index.php?q=Site Disallow: /index.php?q=Site/ Disallow: /site/Feature.aspx Disallow: /ScienceTechnology/ Disallow: /ScienceTechnology Disallow: /index.php?q=ScienceTechnology Disallow: /index.php?q=ScienceTechnology/ Disallow: /Seniors/ Disallow: /Seniors Disallow: /index.php?q=Seniors Disallow: /index.php?q=Seniors/ Disallow: /Portals Disallow: /Portals/ Disallow: /index.php?q=Portals Disallow: /index.php?q=Portals/ Disallow: /Entertainment Disallow: /Entertainment/ # Directories 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: /admin/ Disallow: /comment/reply/ Disallow: /contact/ Disallow: /logout/ Disallow: /node/add/ Disallow: /search/ Disallow: /user/register/ Disallow: /user/password/ Disallow: /user/login/ # Paths (no clean URLs) Disallow: /?q=admin/ Disallow: /?q=ad/ 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: /admin Disallow: /comment/reply Disallow: /contact Disallow: /logout Disallow: /node/add Disallow: /search Disallow: /user/register Disallow: /user/password Disallow: /user/login # Paths (no clean URLs) Disallow: /?q=admin Disallow: /?q=ad 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 # #Disallow: /calendar #Disallow: /calendar/ Disallow: /print Disallow: /print/ Disallow: /ad Disallow: /ad/ # Disallow: /boost_stats.php # Bad blocked robots User-agent: twiceler Disallow: / User-agent: Baiduspider Disallow: / User-agent: ia_archiver Disallow: / User-agent: sogou spider Disallow: / User-agent: Exabot Disallow: / User-agent: fyberspider Disallow: / User-agent: Sosospider Disallow: / User-agent: Yandex Disallow: / User-agent: ParchBot Disallow: / User-agent: heritrix Disallow: / User-agent: ia_archiver Disallow: / User-agent: CamontSpider Disallow: / User-agent: Gigabot Disallow: / User-agent: 008 Disallow: / User-agent: OneRiot Disallow: / User-agent: abby Disallow: / User-agent: R6_CommentReader Disallow: / User-agent: ccbot Disallow: / User-agent: Teoma Disallow: / User-agent: dotbot Disallow: / User-agent: spbot Disallow: / User-agent: Yahoo!+Slurp+China Disallow: / User-agent: Speedy Disallow: / User-agent: panscient.com Disallow: / # Sitemap: http://amesnewsonline.com/sitemap.xml