# CJP: robots.txt,v 1.0 2009/08/04
#
# 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 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

User-agent: *
Crawl-delay: 10

# Directories
Disallow: /basket/
Disallow: /stylesheets/
Disallow: /blocks/
Disallow: /db/
Disallow: /docs/
Disallow: /editor/
Disallow: /images/
Disallow: /includes/
Disallow: /js/
Disallow: /messages/
Disallow: /payments/
Disallow: /shipping/
Disallow: /sms/
Disallow: /styles/
Disallow: /swf/
Disallow: /templates/
Disallow: /1/

# Files
# You can specify files not to crawl here with the command Disallow: /filename.extension
Disallow: /manuals*
Disallow: /user*
Disallow: /cart*
Disallow: /checkout*

# Paths (clean URLs)
# You can specify URLS not to crawl here with the command Disallow: /path without domain/

# Paths (no clean URLs)
# I like to keep clean and complex URL separate 
# You can specify URLS not to crawl here with the command Disallow: /?q=path without domain/