# Define access-restrictions for robots/spiders
# http://www.robotstxt.org/wc/norobots.html
# Normal robots.txt body is purely substring match only
# We exclude lots of general purpose forms which are available in various mount points of the site
# and internal image bank which is hidden in the navigation tree in any case

User-agent: *
Disallow: /author
Disallow: /search_form
Disallow: /sendto_form
Disallow: /accessibility-info
Disallow: /login_form
Disallow: /mail_password_form?userid=
Disallow: /front-page
Disallow: /portal_javascripts
Disallow: /portal_kss
Disallow: /events_listing
Disallow: /vcs_view
Disallow: /ics_view

# By default we allow robots to access all areas of our site 
# already accessible to anonymous users

User-agent: *
Disallow:

# Add Googlebot-specific syntax extension to exclude forms 
# that are repeated for each piece of content in the site 
# the wildcard is only supported by Googlebot
# http://www.google.com/support/webmasters/bin/answer.py?answer=40367&ctx=sibling
# Googlebot allows regex in its syntax
# Block all URLs including query strings (? pattern) - contentish objects expose query string only for actions or status reports which
# might confuse search results.
# This will also block ?set_language

User-Agent: Googlebot
Disallow: /*talkback
Disallow: /*RSS
Disallow: /*sendto_form$
Disallow: /*folder_factories$
Disallow: /*?*