# CRELoaded Generated Robots.txt # Robot Exclusion File -- robots.txt # Author: CRELoaded Team # Last Updated : May 11th 2005 #enhancements by Ted C User-Agent: * Disallow: /admin/ Disallow: /download/ Disallow: /includes/ Disallow: /temp/ Disallow: /debug/ Disallow: /tmp/ Disallow: /pub/ Disallow: /templates/ Disallow: /urchin/ #User-agent: * #*Disallow: crawlers.looksmart.com #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: /admin/ Disallow: /download/ Disallow: /font/ Disallow: /includes/ Disallow: /install/ Disallow: /tmp/ Disallow: /templates/ # #Block out things that are secure or login oriented Disallow: /address_book_process.php Disallow: /account.php Disallow: /account_edit.php Disallow: /account_edit_process.php Disallow: /account_history.php Disallow: /account_history_info.php Disallow: /address_book.php Disallow: /checkout_process.php Disallow: /advanced_search.php Disallow: /advanced_search_result.php Disallow: /checkout_address.php Disallow: /checkout_confirmation.php Disallow: /checkout_payment.php Disallow: /checkout_success.php Disallow: /conditions.php Disallow: /contact_us.php Disallow: /create_account.php Disallow: /create_account_process.php Disallow: /create_account_success.php Disallow: /info_shopping_cart.php Disallow: /login.php Disallow: /logoff.php Disallow: /password_forgotten.php Disallow: /popup_image.php Disallow: /popup_search_help.php Disallow: /privacy.php Disallow: /product_notifications.php Disallow: /product_reviews.php Disallow: /product_reviews_info.php Disallow: /product_reviews_write.php Disallow: /redirect.php Disallow: /reviews.php Disallow: /shipping.php Disallow: /shopping_cart.php Disallow: /tell_a_friend.php Disallow: /cookie_usage.php # 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: Googlebot-Image #Disallow: / # # Crawlers that are kind enough to obey, but which we'd rather not have. # User-Agent: YahooSeeker Disallow: / User-Agent: BecomeBot Disallow: / # # A growing list of pest bots # User-Agent: BaiDuSpider Disallow: / User-Agent: Cherry Picker Disallow: / User-Agent: Crescent Internet ToolPak Disallow: / User-Agent: DISCo Pump Disallow: / User-Agent: EmailSiphon Disallow: / User-Agent: htdig Disallow: / User-Agent: HTTrack Disallow: / User-Agent: LNSpiderGuy Disallow: / User-Agent: Netprospector Disallow: / User-Agent: PerMan Surfer Disallow: / User-Agent: psbot Disallow: / User-Agent: szukacz Disallow: / User-Agent: RPT-HTTPClient Disallow: / User-Agent: Teleport Disallow: / User-Agent: Telesoft Disallow: / User-Agent: Ultraseek Disallow: / User-Agent: vspider Disallow: / User-Agent: WebCopier Disallow: / User-Agent: WebEMailExtractor Disallow: / User-Agent: WebReaper Disallow: / User-Agent: Webster Pro Disallow: / User-Agent: WebStripper Disallow: / User-agent: IsraBot Disallow: User-agent: Orthogaffe Disallow: User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / User-agent: InternetSeer.com Disallow: / # Some bots are known to be trouble, particularly those designed to copy # entire sites. Please obey robots.txt. User-agent: sitecheck.internetseer.com Disallow: / User-agent: Zealbot Disallow: / User-agent: MSIECrawler Disallow: / User-agent: SiteSnagger Disallow: / User-agent: WebStripper Disallow: / User-agent: WebCopier Disallow: / User-agent: Fetch Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: WebZIP Disallow: / User-agent: linko Disallow: / User-agent: HTTrack Disallow: / User-agent: Microsoft.URL.Control Disallow: / User-agent: Xenu Disallow: / User-agent: larbin Disallow: / User-agent: libwww Disallow: / User-agent: ZyBORG Disallow: / User-agent: Download Ninja Disallow: / # # Sorry, wget in its recursive mode is a frequent problem. # Please refer to the manual and use it properly; there is a # wait = x number of seconds option you can use to set the delay between hits, # for instance. # User-agent: wget Disallow: / # # The 'grub' distributed client has been *very* poorly behaved. # User-agent: grub-client Disallow: / User-Agent: grub Disallow: / # # Doesn't follow robots.txt # User-agent: k2spider Disallow: / # # Hits many times per second, not acceptable # http://www.nameprotect.com/botinfo.html User-agent: NPBot Disallow: / # A capture bot, downloads gazillions of pages. # http://www.webreaper.net/ User-agent: WebReaper Disallow: / Sitemap: http://www.championjuicer.com/mature/sitemap.xml