# $Id: robots.txt,v magento-specific 2010/28/01 18:24:19 goba Exp $ # Edited: 2012/06/11 by Byte Internet # # 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: https://www.costumesmascot.com/sitemap.xml # Crawlers Setup User-agent: * Crawl-delay: 10 # Allowable Index # Mind that Allow is not an official standard Allow: /*?p= Allow: /index.php/blog/ Allow: /catalog/seo_sitemap/category/ # Allow: /catalogsearch/result/ Allow: /media/catalog/ # Directories Disallow: /404/ Disallow: /app/ Disallow: /cgi-bin/ Disallow: /downloader/ Disallow: /errors/ Disallow: /includes/ Disallow: /js/ Disallow: /lib/ Disallow: /magento/ # Disallow: /media/ Disallow: /media/captcha/ # Disallow: /media/catalog/ Disallow: /media/css/ Disallow: /media/css_secure/ Disallow: /media/customer/ Disallow: /media/dhl/ Disallow: /media/downloadable/ Disallow: /media/import/ Disallow: /media/js/ Disallow: /media/pdf/ Disallow: /media/sales/ Disallow: /media/tmp/ Disallow: /media/wysiwyg/ Disallow: /media/xmlconnect/ 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/gallery/ #Disallow: /catalogsearch/ Disallow: /checkout/ Disallow: /control/ Disallow: /contacts/ 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 Disallow: /get.php # Magento 1.5+ # Paths (no clean URLs) Disallow: /*.js$ Disallow: /*.css$ Disallow: /*.php$ Disallow: /*?SID= Disallow: /rss* Disallow: /*PHPSESSID User-Agent: almaden Disallow: / User-Agent: ASPSeek Disallow: / User-Agent: Axmo Disallow: / User-Agent: BaiduSpider Disallow: / User-Agent: booch Disallow: / User-Agent: DTS Agent Disallow: / User-Agent: Downloader Disallow: / User-Agent: EmailCollector Disallow: / User-Agent: EmailSiphon Disallow: / User-Agent: EmailWolf Disallow: / User-Agent: Expired Domain Sleuth Disallow: / User-Agent: Franklin Locator Disallow: / User-Agent: Gaisbot Disallow: / User-Agent: grub Disallow: / User-Agent: HughCrawler Disallow: / User-Agent: iaea.org Disallow: / User-Agent: lcabotAccept Disallow: / User-Agent: IconSurf Disallow: / User-Agent: Iltrovatore-Setaccio Disallow: / User-Agent: Indy Library Disallow: / User-Agent: IUPUI Disallow: / User-Agent: Kittiecentral Disallow: / User-Agent: iaea.org Disallow: / User-Agent: larbin Disallow: / User-Agent: lwp-trivial Disallow: / User-Agent: MetaTagRobot Disallow: / User-Agent: Missigua Locator Disallow: / User-Agent: NetResearchServer Disallow: / User-Agent: NextGenSearch Disallow: / User-Agent: NPbot Disallow: / User-Agent: Nutch Disallow: / User-Agent: ObjectsSearch Disallow: / User-Agent: Oracle Ultra Search Disallow: / User-Agent: PEERbot Disallow: / User-Agent: PictureOfInternet Disallow: / User-Agent: PlantyNet Disallow: / User-Agent: QuepasaCreep Disallow: / User-Agent: ScSpider Disallow: / User-Agent: SOFT411 Disallow: / User-Agent: spider.acont.de Disallow: / User-Agent: Sqworm Disallow: / User-Agent: SSM Agent Disallow: / User-Agent: TAMU Disallow: / User-Agent: TheUsefulbot Disallow: / User-Agent: TurnitinBot Disallow: / User-Agent: Tutorial Crawler Disallow: / User-Agent: TutorGig Disallow: / User-Agent: WebCopier Disallow: / User-Agent: WebZIP Disallow: / User-Agent: ZipppBot Disallow: / User-Agent: Xenu Disallow: / User-Agent: Wotbox Disallow: / User-Agent: Wget Disallow: / User-Agent: NaverBot Disallow: / User-Agent: mozDex Disallow: / User-Agent: Sosospider Disallow: / User-agent: Sogou web spider Disallow: / User-agent: sogou spider Disallow: / User-agent: Googlebot Disallow: User-agent: AdsBot-Google Disallow: User-agent: Googlebot-Image Disallow: