# # 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/robotstxt.html # # For syntax checking, see: # http://www.frobee.com/robots-txt-check User-agent: Twitterbot Disallow: User-agent: * # CSS, JS, Images Allow: /misc/*.css$ Allow: /misc/*.css? Allow: /misc/*.js$ Allow: /misc/*.js? Allow: /misc/*.gif Allow: /misc/*.jpg Allow: /misc/*.jpeg Allow: /misc/*.png Allow: /modules/*.css$ Allow: /modules/*.css? Allow: /modules/*.js$ Allow: /modules/*.js? Allow: /modules/*.gif Allow: /modules/*.jpg Allow: /modules/*.jpeg Allow: /modules/*.png Allow: /profiles/*.css$ Allow: /profiles/*.css? Allow: /profiles/*.js$ Allow: /profiles/*.js? Allow: /profiles/*.gif Allow: /profiles/*.jpg Allow: /profiles/*.jpeg Allow: /profiles/*.png Allow: /themes/*.css$ Allow: /themes/*.css? Allow: /themes/*.js$ Allow: /themes/*.js? Allow: /themes/*.gif Allow: /themes/*.jpg Allow: /themes/*.jpeg Allow: /themes/*.png # Directories Disallow: /includes/ Disallow: /misc/ Disallow: /modules/ Disallow: /profiles/ Disallow: /scripts/ #Disallow: /themes/ # Do not crawl links with session IDs Disallow: /*SID= Disallow: /*sid= # Files Disallow: /CHANGELOG.txt Disallow: /cron.php Disallow: /INSTALL.mysql.txt Disallow: /INSTALL.pgsql.txt Disallow: /INSTALL.sqlite.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: /filter/tips/ Disallow: /node/add/ Disallow: /search/ Disallow: /user/register/ Disallow: /user/password/ Disallow: /user/login/ Disallow: /user/logout/ # Paths (no clean URLs) Disallow: /?q=admin/ Disallow: /?q=comment/reply/ Disallow: /?q=filter/tips/ Disallow: /?q=node/add/ Disallow: /?q=search/ Disallow: /?q=user/password/ Disallow: /?q=user/register/ Disallow: /?q=user/login/ Disallow: /?q=user/logout/ Disallow: /*?rate= # Ajax Views stuff Disallow: /*?did= Disallow: /*&did= Disallow: /*?tid= Disallow: /*&tid= Disallow: /mnsviews/getview/ # Doubleclick Stuff Disallow: /9172182/ Allow: /relatedlinks/build Disallow: /token.php ## STORE ## ## Do not crawl sub category pages that are sorted or filtered. Disallow: /store/*dir= Disallow: /store/*limit= Disallow: /store/*mode= Disallow: /store/*order= Disallow: /store/*promotion= Disallow: /store/*product_flavor= Disallow: /store/*product_size= Disallow: /store/*form_factor= Disallow: /store/*manufacturer= Disallow: /store/*review_rating_summary= Disallow: /store/*color= Disallow: /store/*price= Disallow: /store/*cat= ## Do not crawl checkout and user account pages Disallow: /store/checkout/ Disallow: /store/customer/ Disallow: /store/customer/account/ Disallow: /store/customer/account/login/ ## Do not crawl search pages and not-SEO optimized catalog links Disallow: /store/catalogsearch/ Disallow: /store/catalog/product_compare/ Disallow: /store/catalog/category/view/ Disallow: /store/catalog/product/view/ Disallow: /store/supersaver.html Disallow: /*?nutrition-info-selector Disallow: /*&nutrition-info-selector Disallow: /store/reviews/report/ Disallow: /store/review/product/ Disallow: /store/reviews/review-posted Disallow: /store/sales/order/ Disallow: /store/shipping/ Disallow: /store/reviews/brands/*p= ## END STORE ## User-agent: ia_archiver Disallow: /