www.woolwarehouse.co.uk

# $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.woolwarehouse.co.uk/sitemap.xml

# Try to fix Google Merchant Center errors relating to uncrawlable content [Rees]
User-agent: Googlebot
Disallow:
User-agent: Googlebot-image
Disallow:
# Crawlers Setup
User-agent: *
# Crawl-delay: 30
# Directories
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: /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
# Paths (no clean URLs)
Disallow: /*.js$
Disallow: /*.css$
Disallow: /*.php$
Disallow: /*?p=*&
Disallow: /*?SID= 
Disallow: /*?limit=all