Sitemap: https://wageindicator.fi/sitemap.xml.gz

# Define access-restrictions for robots/spiders
# http://www.robotstxt.org/wc/norobots.html


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

User-agent: *
Disallow:
crawl-delay: 4

User-agent: www.deadlinkchecker.com
Crawl-delay: 1

# 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

User-Agent: Googlebot
# we want pages like our landing pages to be indexed (?job-id=7412100000000)
# Disallow: /*?
Disallow: /*atct_album_view$
Disallow: /*folder_factories$
Disallow: /*folder_summary_view$
Disallow: /*login_form$
Disallow: /*mail_password_form$
Disallow: /@@search
Disallow: /*search_rss$
Disallow: /*sendto_form$
Disallow: /*summary_view$
Disallow: /*thumbnail_view$
Disallow: /*?job-id=*    
Disallow: /google-search-result?q=*
# waarschijnlijk kan het geen kwaad om deze "view" aan het einde van de URL te indexeren?
# Disallow: /*view$

# Do not index archive folders with this ID
Disallow: /*archive-no-index$