# $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 # # Prevent blocking URL parameters with robots.txt # Use Google Webmaster Tools > Crawl > Url parameters instead # Website Sitemap #Sitemap: http://www.example.com/sitemap.xml # needs changing to correct URL # Crawlers Setup User-Agent: bingbot Disallow: / User-agent: * Crawl-delay: 10 # delays spiders speed slightly as they crawl round website to help with server load when being crawled #slow down rogerbot (SEO MOz bot) User-agent: rogerbot Disallow: *.pdf # Block pdf files. Non-standard but works for major search engines. Crawl-delay: 6 # Allowable Index # Mind that Allow is not an official standard Allow: /blog/ #comment out if there isnt a blog page 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/ Disallow: /~jangrode/ # 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/ # apparently there are now benefits from letting bots crawl your checkout! Disallow: /control/ Disallow: /contacts/ Disallow: /customer/ Disallow: /customize/ Disallow: /newsletter/ Disallow: /poll/ Disallow: /review/ Disallow: /sendfriend/ Disallow: /tag/ Disallow: /wishlist/ Disallow: /downloads/ Disallow: /Downloads/ # 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 ##### Querystring (disallow all URLs with querystring) ##### Disallow: /*?* # this sorts out category page filters issue ####################################### ########### SCREAMING FROG ############ ####################################### User-agent: Screaming Frog SEO Spider Crawl-delay: 1 Allow: / Disallow: /*.gif$ Disallow: /*.jpg$ Disallow: /*.png$ Disallow: /*.bmp$ Disallow: /*.xml$ #Disallow: /*.css$ #Disallow: /*.js$ #### Helen's Parameter Exclusions #### Disallow: /*?cat= Disallow: /*?price= Disallow: /*?p= Disallow: /*?dir= Disallow: /wishlist/ Disallow: /catalog/product_compare/ ### SEM RUSH ### User-agent: SemrushBot Crawl-delay: 1
Счетчик ИКС для сайта co-an.co.uk -
ID сайта (co-an.co.uk) - 585b3888af09204f17732489
Url в sha1 - 0e5c62f9e52b699ef0fc4277132c90ac517cf987
Система анализа и продвижения сайтов
