# Sample robots.txt file (make sure the filename is ALL LOWERCASE on Linux/Unix systems) # This file should go in your web site's ROOT directory # The root directory is where your site's main /index.html file would be found # It is usually found in /yourhomedir/public_html/ or /yourhomedir/httpdocs # Where "yourhomedir" is your user account's name # # We invite you to also check out our popular contribution: Simple Template System (STS) # It lets you layout or change your OSC look-and-feel by modifying a single HTML file # http://www.oscommerce.com/community/contributions,1524 or SimpleTemplateSystem.com # Enjoy! - Brian Gallagher @ DiamondSea.com User-agent: crawlers.looksmart.com Disallow: / # This says to apply these settings to ALL search engine spiders/crawlers # User-agent: * # These settings will keep spiders from indexing your unwanted pages # This assumes that your OSC install is in your web site's ROOT directory # ie: http://www.yoursite.com/index.php <- Use if this brings up your OSC main page # Disallow: /admin # Disallow: /account.php # Disallow: /advanced_search.php # Disallow: /checkout_shipping.php # Disallow: /create_account.php # Disallow: /login.php # Disallow: /login.php # Disallow: /password_forgotten.php # Disallow: /popup_image.php # Disallow: /shopping_cart.php # Disallow: /allprods.php # These settings will keep spiders from indexing your unwanted pages # This assumes that your OSC install is in your web site's ROOT directory # ie: http://www.yoursite.com/catalog/index.php <- Use if this brings up your OSC main page Disallow: /catalog/admin/ Disallow: /catalog/account.php Disallow: /catalog/advanced_search.php Disallow: /catalog/checkout_shipping.php Disallow: /catalog/create_account.php Disallow: /catalog/login.php Disallow: /catalog/login.php Disallow: /catalog/password_forgotten.php Disallow: /catalog/popup_image.php Disallow: /catalog/shopping_cart.php Disallow: /catalog/pricematch.php Disallow: /catalog/allprods.php # CRELoaded Generated Robots.txt # Robot Exclusion File -- robots.txt # Author: CRELoaded Team # Last Updated : May 11th 2005 #Block All Images Disallow: *.gif Disallow: *.jpg Disallow: /*.gif$ Disallow: /*.jpg$ # #To block main page due to size from bots # Disallow: /index.php # #To shut down site completely from bots use either # Disallow: / # #If you had search engine friendly URLs on and want to clean them out of the bots #Disallow: /default.php/cPath/ # # #Block out directories bots don't need to go to Disallow: /catalog/download/ Disallow: /catalog/font/ Disallow: /catalog/images/ Disallow: /catalog/includes/ Disallow: /catalog/install/ Disallow: /catalog/tmp/ Disallow: /catalog/templates/ # #Block out things that are secure or login oriented Disallow: /catalog/address_book_process.php Disallow: /catalog/account.php Disallow: /catalog/account_edit.php Disallow: /catalog/account_edit_process.php Disallow: /catalog/account_history.php Disallow: /catalog/account_history_info.php Disallow: /catalog/address_book.php Disallow: /catalog/checkout_process.php Disallow: /catalog/advanced_search.php Disallow: /catalog/advanced_search_result.php Disallow: /catalog/checkout_address.php Disallow: /catalog/checkout_confirmation.php Disallow: /catalog/checkout_payment.php Disallow: /catalog/checkout_success.php Disallow: /catalog/conditions.php Disallow: /catalog/contact_us.php Disallow: /catalog/create_account.php Disallow: /catalog/create_account_process.php Disallow: /catalog/create_account_success.php Disallow: /catalog/info_shopping_cart.php Disallow: /catalog/login.php Disallow: /catalog/logoff.php Disallow: /catalog/password_forgotten.php Disallow: /catalog/popup_image.php Disallow: /catalog/popup_search_help.php Disallow: /catalog/privacy.php Disallow: /catalog/product_notifications.php Disallow: /catalog/product_reviews.php Disallow: /catalog/product_reviews_info.php Disallow: /catalog/product_reviews_write.php Disallow: /catalog/redirect.php Disallow: /catalog/reviews.php Disallow: /catalog/shipping.php Disallow: /catalog/shopping_cart.php Disallow: /catalog/tell_a_friend.php Disallow: /catalog/cookie_usage.php Disallow: /catalog/pricematch.php Disallow: /cgi-bin/ Disallow: /_borders/ Disallow: /_derived/ Disallow: /_fpclass/ Disallow: /_overlay/ Disallow: /_private/ Disallow: /_themes/ Disallow: /_vti_bin/ Disallow: /_vti_cnf/ Disallow: /_vti_log/ Disallow: /_vti_map/ Disallow: /_vti_pvt/ Disallow: /_vti_txt/ # Feel free to add any other pages on your site that you don't want to be indexed by # the search engines. # PLEASE NOTE: Any pages that you list here should be secured by other means if you # don't want people to be able to view them, as some malicious users will look at a # robots.txt file to try to find "hidden" or "secret" areas of web sites to find # confidential information. # Just Uncomment a line or add new ones as you see fit. # Disallow: /private # Disallow: /hidden # IF YOU DO NOT WISH TO HAVE THE GOOGLE IMAGE BOT SCAN YOUR DOMAIN FOR IMAGES # THEN YOU CAN INCLUDE THE FOLLOWING IN YOUR ROBOTS FILE. # I FOUND THAT MY BANDWIDTH USAGE DROPPED BY A MASSIVE AMOUNT AFTER I GOT RID # OF THE GOOGLE IMAGE BOT. ALL I HAD WAS IMAGE HUNTERS STEALING PRODUCT SHOTS # AND NOT EVEN BROWSING THE SITE. User-agent: ShopWiki Crawl-Delay: 87 User-agent: Googlebot-Image Disallow: /