# $Id: robots.txt,v magento-specific 2010/28/01 18:24:19 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 # Website Sitemap Sitemap: http://www.unitedstatesofvitamins.com/cart/usvsitemap.xml # Crawlers Setup User-agent: * Crawl-delay: 10 # Allowable Index Allow: /*?p= Allow: /cart/index.php/blog/ Allow: /cart/catalog/seo_sitemap/category/ Allow: /cart/catalogsearch/result/ Allow: /cart/review/ Allow: /cart/media/ # Directories Disallow: /cart/404/ Disallow: /cart/app/ Disallow: /cart/cgi-bin/ Disallow: /cart/downloader/ Disallow: /cart/includes/ Disallow: /cart/js/ Disallow: /cart/lib/ Disallow: /cart/magento/ Disallow: /cart/pkginfo/ Disallow: /cart/report/ Disallow: /cart/skin/ Disallow: /cart/stats/ Disallow: /cart/var/ # Paths (clean URLs) Disallow: /cart/index.php/ Disallow: /cart/catalog/product_compare/ Disallow: /cart/catalog/category/view/ Disallow: /cart/catalog/product/view/ Disallow: /cart/catalogsearch/ Disallow: /cart/checkout/ Disallow: /cart/control/ Disallow: /cart/contacts/ Disallow: /cart/customer/ Disallow: /cart/customize/ Disallow: /cart/newsletter/ Disallow: /cart/poll/ Disallow: /cart/sendfriend/ Disallow: /cart/tag/ Disallow: /cart/wishlist/ # Files Disallow: /cart/cron.php Disallow: /cart/cron.sh Disallow: /cart/error_log Disallow: /cart/install.php Disallow: /cart/LICENSE.html Disallow: /cart/LICENSE.txt Disallow: /cart/LICENSE_AFL.txt Disallow: /cart/STATUS.txt # Paths (no clean URLs) Disallow: /*? Disallow: /*.js$ Disallow: /*.css$ Disallow: /*.php$ Disallow: /*?p=*& Disallow: /*?SID= Disallow: /*.pdf$ Disallow: /*.js$ Disallow: /*.cgi$ Disallow: /*.xhtml$ Disallow: /*.php* Disallow: /*.inc$ Disallow: /*.txt$ Disallow: /*?* Disallow: */feed/ Disallow: */trackback/ Disallow: /cgi-bin/ Disallow: /k/ # Stop Yandex from hogging bandwidth User-agent: yandex bot Disallow: /