# See http://www.robotstxt.org/wc/norobots.html for documentation on how to use the robots.txt file
# and http://tool.motoricerca.info/robots-checker.phtml for a handly robots.txt checker
# and http://phpweby.com/services/robots to ensure that the big boys (eg. Google, Yahoo) are still allowed in
# CW: disallowed 23/05/2011 as it has created a whole load of malformed urls - each of which was causing our app
# to generate an email exception report (and the bot gives us no benefit as it is an anti-plagiarism site)
User-agent: TurnitinBot
Disallow: /
# CW: disallowed 01/09/2011 : see trac #3
User-agent: plukkie
Disallow: /
# #584 : stop the good crawlers from getting the you_eye pages
# #769 : overruled, so now good crawlers can get the you_eye pages
# User-agent: *
# Disallow: /offices/*/you_eye*
# Disallow: /offices/*/historical_sales*
# #740 : Rob asked to have this removed.
# # #717 : and stop them from getting to the default-redirected page when coming from wellsteadandwellstead.co.uk
# User-agent: *
# Disallow: /offices/bournemouth?wellstead=ferndown$
# CW: add in our site map, #82
Sitemap: http://www.youhome.co.uk/sitemap.xml
# TB: popup information urls, presumably extracted from our js. #731
User-agent: *
Disallow: */popup_information?ids=*
User-agent: *
Disallow: */popup_information
# CW: prevent Google from hitting some JS-only urls
User-agent: *
Disallow: */extra_info?*