User-agent: * Disallow: /teststore/ 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/ # CRELoaded Generated Robots.txt # Robot Exclusion File -- robots.txt # Author: CRELoaded Team # Last Updated : September 11th, 2007 User-Agent: * Disallow: /admin/ Disallow: /cache/ Disallow: /cert/ Disallow: /debug/ Disallow: /download/ Disallow: /ext/ Disallow: /includes/ Disallow: /pear/ Disallow: /pub/ Disallow: /temp/ Disallow: /templates/ Disallow: /tmp/ #To prevent only a select bots from any scans #User-agent: crawlers.looksmart.com #Disallow: / #To prenet any images from being scanned #Disallow: *.gif #Disallow: *.jpg #Disallow: *.png #To block main page due to size from bots #Disallow: /index.php #To shut down site completely from bots use # Disallow: / #Block out things that are secure or login oriented #These are based on not using any rewrite rules Disallow: /account.php Disallow: /account_edit.php Disallow: /account_history.php Disallow: /account_history_info.php Disallow: /account_password.php Disallow: /address_book.php Disallow: /address_book_process.php Disallow: /checkout_confirmation.php Disallow: /checkout_payment.php Disallow: /checkout_payment_address.php Disallow: /checkout_process.php Disallow: /checkout_shipping.php Disallow: /checkout_shipping_address.php Disallow: /checkout_success.php Disallow: /cookie_usage.php Disallow: /create_account.php Disallow: /create_account_success.php Disallow: /ipn.php Disallow: /login.php Disallow: /logoff.php Disallow: /password_forgotten.php Disallow: /paypal_notify.php Disallow: /redirect.php Disallow: /shipping_estimator_popup.php Disallow: /ssl_check.php Disallow: /vvc_display.php Disallow: /wpcallback.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: / # END OF CRE-LOADED Robots.txt # advertising-related bots: User-agent: Mediapartners-Google* Disallow: / User-agent: Orthogaffe Disallow: # Crawlers that are kind enough to obey, but which we'd rather not have # unless they're feeding search engines. User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao 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 read the man page and use it properly; there is a # --wait 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: / # # Doesn't follow robots.txt anyway, but... # 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 with no public benefit # http://www.webreaper.net/ User-agent: WebReaper Disallow: / # Don't allow the wayback-maschine to index user-pages #User-agent: ia_archiver #Disallow: /wiki/User #Disallow: /wiki/Benutzer # # Friendly, low-speed bots are welcome viewing article pages, but not # dynamically-generated pages please. # # Inktomi's "Slurp" can read a minimum delay between hits; if your # bot supports such a thing using the 'Crawl-delay' or another # instruction, please let us know. #