##############################################
# These Bots must not index at all
User-agent: Googlebot-Image
User-agent: msnbot-media
User-agent: Twiceler
User-agent: Accoona
User-agent: Seekbot
User-agent: Firefox
User-agent: turnitinbot
User-agent: Exabot-Images
Disallow: /

##############################################
# Exabot see: http://www.exalead.com/about/document/53
User-agent: Exabot
Crawl-delay: 30
Disallow: *?

##############################################
# Selected User Agents
# Bots that parse the Allow directive, may overwrite the Disallowed urls
User-agent: Googlebot
User-agent: Teoma
User-agent: Yahoo
User-agent: search.ch
User-agent: msnbot
User-agent: spidersearch
User-agent: VoilaBot
Disallow: /musik
Disallow: /musik/
Disallow: /rsc
Disallow: /rsc/
Disallow: /download.htm
Disallow: /bdeonline/museum
Disallow: /BDE_DB_export.html
Disallow: /KJVTenachBDE.html
Disallow: /LuTeLXXBDE.html
Disallow: /mail.html
Disallow: /cgi/mail
Disallow: *.jpg$
Disallow: *.jpeg$
Disallow: *.gif$
Disallow: *.png$
Disallow: *.doc$
Disallow: *.odt$
Disallow: *.zip$
Disallow: /ehome-factory/__
Disallow: /ehome-factory/__*
Disallow: /ehome-factory/admin
Allow: /ehome-factory/
Allow: /kaffeesatz	
Allow: /kaffeesatz/
Allow: /cgi/tok.pl?extern=*
Allow: /cgi/tok.pl?lang=0$
Allow: /cgi/tok.pl?lang=1$
Allow: /cgi/tok.pl$

##############################################
# All Other User Agents 
# I suppose they don't understand an Allow directive.
User-agent: *
Disallow: /musik
Disallow: /musik/
Disallow: /rsc
Disallow: /rsc/
Disallow: /cgi/mail
Disallow: /cgi/mail/
Disallow: *.jpg$
Disallow: *.jpeg$
Disallow: *.gif$
Disallow: *.png$
Disallow: *.doc$
Disallow: *.odt$
Disallow: *.zip$
Disallow: /download.htm
Disallow: /bdeonline/museum
Disallow: /BDE_DB_export.html
Disallow: /KJVTenachBDE.html
Disallow: /LuTeLXXBDE.html
Disallow: /mail.html
Disallow: /ehome-factory/admin
Disallow: /ehome-factory/__

###############################
# Notes
# Google
#    siehe http://www.google.com/support/webmasters/bin/answer.py?answer=40367&topic=8846
#
# Turnitin: A bot for a non public database (plagiarism prevention service)
#    siehe http://www.turnitin.com/robot/crawlerinfo.html
#    I suspect, it reads but disrespect the directive.
#    status: blocked by htaccess
#
# END #