# $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.mywebsite.com/sitemap.xml Sitemap: http://www.soundcorp.com.au/sitemap/sitemap.xml # Crawlers Setup User-agent: * Crawl-delay: 30 # Allowable Index Allow: /*?p= Allow: /index.php/blog/ Allow: /catalog/seo_sitemap/category/ #Allow: /catalogsearch/result/ Allow: /catalog/category/view/ Allow: /catalog/product/view/ Allow: /js/mirasvit/code/feedexport/performance.js Allow: /media/css_secure/07a7e507b83b9692c8e4b10ac114dc6e.css Allow: /media/css_secure/8802dfdc9c116a4161cb4ec003c68174.css Allow: /media/css_secure/d141f1d0122a63b8a357eca4a49d5011.css Allow: /media/css_secure/63dad2004b05783cc9c6a49a906644f9.css Allow: /media/css_secure/2d78156c2d8945639568b4f965ca9f54.css Allow: /js/prototype/windows/themes/default.css Allow: /js/calendar/calendar-win2k-1.css Allow: /media/js/c0038fd26a754fb4e8c6a2e09c0ec758.js Allow: /media/css_secure/744e5ac2d4c77717ae45f4b1ce61d85b.css Allow: /skin/frontend/soundcorp/default/images/logo.gif Allow: /media/css_secure/a4d38a784d74629dd413721e60a17bb2.css Allow: /media/js/a9f5c09cc157822a8d4e50b11cf43237.js Allow: /skin/frontend/soundcorp/default/js/tabs.js Allow: /skin/frontend/soundcorp/default/images/free-shipping-small.png Allow: /media/js/d6d3a96e1e897578a30ba3f81e612c8a.js Allow: /skin/frontend/soundcorp/default/images/i_asc_arrow.gif Allow: /skin/frontend/base/default/images/pager_arrow_right.gif Allow: /skin/frontend/base/default/images/pager_arrow_left.gif Allow: /skin/frontend/soundcorp/default/images/noimg.png Allow: /media/js/b8ec7b50bff0d95585df80671a1541fb.js Allow: /media/css_secure/926b13b1b00dd92251df87940fab81a0.css Allow: /skin/frontend/soundcorp/default/images/i_desc_arrow.gif Allow: /media/js/330e43ab54d23f27f1dfe0fd40b8140a.js Allow: /skin/frontend/soundcorp/default/images/ Allow: /contacts/ Allow: /skin/frontend/soundcorp/default/css/*.css$ Allow: /skin/frontend/base/default/css/*.css$ Allow: /skin/frontend/base/default/aw_blog/css/*.css$ Allow: /skin/frontend/soundcorp/default/pmatch/css/*.css$ Allow: /skin/frontend/base/default/css/amasty/amcart/*.css$ Allow: /skin/frontend/base/default/css/amasty/amlabel/*.css$ Allow: /skin/frontend/base/default/css/magestore/*.css$ Allow: /skin/frontend/base/default/css/mirasvit/seo/*.css$ Allow: /skin/frontend/base/default/css/mirasvit/seositemap/*.css$ Allow: /skin/frontend/base/default/css/*.css$ Allow: /skin/frontend/soundcorp/default/algoliasearch/*.css$ Allow: /media/js/*.js$ Allow: /skin/frontend/soundcorp/default/algoliasearch/*.svg$ Allow: /skin/frontend/soundcorp/default/fonts/*.woff$ Allow: /skin/frontend/soundcorp/default/fonts/icomoon.woff?hj9m13 # Directories # This next line added on 17/1/11 as requested by SU (removal of .htpasswd) Disallow: /404/ Disallow: /app/ Disallow: /cgi-bin/ Disallow: /downloader/ Disallow: /errors/ Disallow: /includes/ Disallow: /js/ Disallow: /lib/ Disallow: /magento/ Disallow: /pkginfo/ Disallow: /report/ Disallow: /scripts/ Disallow: /shell/ Disallow: /skin/ Disallow: /stats/ Disallow: /var/ # Paths (clean URLs) Disallow: /index.php/ Disallow: /catalog/product_compare/ #Disallow: /catalog/category/view/ #Disallow: /catalog/product/view/ Disallow: /catalog/product/ #Disallow: /catalogsearch/ Disallow: /checkout/ Disallow: /control/ Disallow: /customer/ Disallow: /customize/ Disallow: /newsletter/ Disallow: /poll/ Disallow: /review/ Disallow: /sendfriend/ Disallow: /tag/ Disallow: /wishlist/ # Files Disallow: /cron.php Disallow: /cron.sh Disallow: /error_log Disallow: /install.php Disallow: /LICENSE.html Disallow: /LICENSE.txt Disallow: /LICENSE_AFL.txt Disallow: /STATUS.txt # Paths (no clean URLs) Disallow: /*.js$ Disallow: /*.css$ Disallow: /*.php$ #Disallow: /*?p=*& #Disallow: /*?SID= #Disallow: /*?limit=all Disallow: /no-group-selected # Uncomment if you do not wish for Google to index your images #User-agent: Googlebot-Image #Disallow: / #Allow: /media/catalog/ # #135 robots to keep away - Yellowpipe.com # User-agent: Aqua_Products Disallow: / User-agent: asterias Disallow: / User-agent: b2w/0.1 Disallow: / User-agent: BackDoorBot/1.0 Disallow: / User-agent: Black Hole Disallow: / User-agent: BlowFish/1.0 Disallow: / User-agent: Bookmark search tool Disallow: / User-agent: BotALot Disallow: / User-agent: BuiltBotTough Disallow: / User-agent: Bullseye/1.0 Disallow: / User-agent: BunnySlippers Disallow: / User-agent: Cegbfeieh Disallow: / User-agent: CheeseBot Disallow: / User-agent: CherryPicker Disallow: / User-agent: CherryPicker /1.0 Disallow: / User-agent: CherryPickerElite/1.0 Disallow: / User-agent: CherryPickerSE/1.0 Disallow: / User-agent: CopyRightCheck Disallow: / User-agent: cosmos Disallow: / User-agent: Crescent Disallow: / User-agent: Crescent Internet ToolPak HTTP OLE Control v.1.0 Disallow: / User-agent: DittoSpyder Disallow: / User-agent: EmailCollector Disallow: / User-agent: EmailSiphon Disallow: / User-agent: EmailWolf Disallow: / User-agent: EroCrawler Disallow: / User-agent: ExtractorPro Disallow: / User-agent: FairAd Client Disallow: / User-agent: Flaming AttackBot Disallow: / User-agent: Foobot Disallow: / User-agent: Gaisbot Disallow: / User-agent: GetRight/4.2 Disallow: / User-agent: grub Disallow: / User-agent: grub-client Disallow: / User-agent: Harvest/1.5 Disallow: / User-agent: hloader Disallow: / User-agent: httplib Disallow: / User-agent: humanlinks Disallow: / User-agent: ia_archiver Disallow: / User-agent: ia_archiver/1.6 Disallow: / User-agent: InfoNaviRobot Disallow: / User-agent: Iron33/1.0.2 Disallow: / User-agent: JennyBot Disallow: / User-agent: Kenjin Spider Disallow: / User-agent: Keyword Density/0.9 Disallow: / User-agent: larbin Disallow: / User-agent: LexiBot Disallow: / User-agent: libWeb/clsHTTP Disallow: / User-agent: LinkextractorPro Disallow: / User-agent: LinkScan/8.1a Unix Disallow: / User-agent: LinkWalker Disallow: / User-agent: LNSpiderguy Disallow: / User-agent: lwp-trivial Disallow: / User-agent: lwp-trivial/1.34 Disallow: / User-agent: Mata Hari Disallow: / User-agent: Microsoft URL Control Disallow: / User-agent: Microsoft URL Control - 5.01.4511 Disallow: / User-agent: Microsoft URL Control - 6.00.8169 Disallow: / User-agent: MIIxpc Disallow: / User-agent: MIIxpc/4.2 Disallow: / User-agent: Mister PiX Disallow: / User-agent: moget Disallow: / User-agent: moget/2.1 Disallow: / User-agent: mozilla/4 Disallow: / User-agent: Mozilla/4.0 (compatible; BullsEye; Windows 95) Disallow: / User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows 2000) Disallow: / User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows 95) Disallow: / User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows 98) Disallow: / User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows ME) Disallow: / User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows NT) Disallow: / User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows XP) Disallow: / User-agent: mozilla/5 Disallow: / User-agent: MSIECrawler Disallow: / User-agent: NetAnts Disallow: / User-agent: NetMechanic Disallow: / User-agent: NICErsPRO Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Openbot Disallow: / User-agent: Openfind Disallow: / User-agent: Openfind data gathere Disallow: / User-agent: Oracle Ultra Search Disallow: / User-agent: PerMan Disallow: / User-agent: ProPowerBot/2.14 Disallow: / User-agent: ProWebWalker Disallow: / User-agent: psbot Disallow: / User-agent: Python-urllib Disallow: / User-agent: QueryN Metasearch Disallow: / User-agent: Radiation Retriever 1.1 Disallow: / User-agent: RepoMonkey Disallow: / User-agent: RepoMonkey Bait & Tackle/v1.01 Disallow: / User-agent: RMA Disallow: / User-agent: searchpreview Disallow: / User-agent: SiteSnagger Disallow: / User-agent: SpankBot Disallow: / User-agent: spanner Disallow: / User-agent: suzuran Disallow: / User-agent: Szukacz/1.4 Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: Telesoft Disallow: / User-agent: The Intraformant Disallow: / User-agent: TheNomad Disallow: / User-agent: TightTwatBot Disallow: / User-agent: Titan Disallow: / User-agent: toCrawl/UrlDispatcher Disallow: / User-agent: True_Robot Disallow: / User-agent: True_Robot/1.0 Disallow: / User-agent: turingos Disallow: / User-agent: URL Control Disallow: / User-agent: URL_Spider_Pro Disallow: / User-agent: URLy Warning Disallow: / User-agent: VCI Disallow: / User-agent: VCI WebViewer VCI WebViewer Win32 Disallow: / User-agent: Web Image Collector Disallow: / User-agent: WebAuto Disallow: / User-agent: WebBandit Disallow: / User-agent: WebBandit/3.50 Disallow: / User-agent: WebCopier Disallow: / User-agent: WebEnhancer Disallow: / User-agent: WebmasterWorldForumBot Disallow: / User-agent: WebSauger Disallow: / User-agent: Website Quester Disallow: / User-agent: Webster Pro Disallow: / User-agent: WebStripper Disallow: / User-agent: WebZip Disallow: / User-agent: WebZip/4.0 Disallow: / User-agent: Wget Disallow: / User-agent: Wget/1.5.3 Disallow: / User-agent: Wget/1.6 Disallow: / User-agent: WWW-Collector-E Disallow: / User-agent: Xenu's Disallow: / User-agent: Xenu's Link Sleuth 1.1c Disallow: / User-agent: Zeus Disallow: / User-agent: Zeus 32297 Webster Pro V2.9 Win32 Disallow: / User-agent: Zeus Link Scout Disallow: /