# For tips see http://www.askapache.com/seo/seo-with-robotstxt.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: set_language
Disallow: force_web
Disallow: login_form
Disallow: sendto_form
Disallow: /images
Disallow: /etusivu
Disallow: /sisalto/etusivu
Disallow: footer-text
Disallow: /ohjeet
Disallow: /sisalto/ohjeet
Disallow: carousel
Disallow: kuvapankki
# Do not show the site front page twice in search results
Disallow: http://www.siida.fi/sisalto/siida-nayttelykeskus-ja-kohtaamispaikka

Disallow: /search_form
Disallow: /sendto_form
Disallow: /accessibility-info
Disallow: /contact-info
Disallow: /login_form
Disallow: /mail_password_form?userid=
Disallow: /news_item
Disallow: /enabling_cookies
Disallow: /front-page
Disallow: /test-folder
Disallow: /portal_javascripts
Disallow: /portal_kss
Disallow: /author
Disallow: /*talkback
Disallow: /*RSS
Disallow: /events_listing
Disallow: /vcs_view
Disallow: /ics_view
Disallow: /events/events-by-date/


# 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: /*?* 
Disallow: /*folder_factories$
Allow: /@@mobile_sitemap?         

# Allow Adsense bot on entire site
User-agent: Mediapartners-Google*
Disallow:
Allow: /*