# robots.txt or http://www.sciencebuster.com/ - nur für deployment in ROOT context !!!

# -----------------------------------------------------------------------------
# SECTION "unfriendly" bots [copied from wikipedia]
# advertising-related bots:
User-agent: Mediapartners-Google*
Disallow: /

# Crawlers that are kind enough to obey, but which we'd rather not have
# unless they're feeding search engines.
User-agent: UbiCrawler
Disallow: /

User-agent: DOC
Disallow: /

User-agent: Zao
Disallow: /

# Some bots are known to be trouble, particularly those designed to copy
# entire sites. Please obey robots.txt.
User-agent: sitecheck.internetseer.com
Disallow: /

User-agent: Zealbot
Disallow: /

User-agent: MSIECrawler
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: Fetch
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Teleport
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: linko
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: Microsoft.URL.Control
Disallow: /

User-agent: Xenu
Disallow: /

User-agent: larbin
Disallow: /

User-agent: libwww
Disallow: /

User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

#
# Sorry, wget in its recursive mode is a frequent problem.
# Please read the man page and use it properly; there is a
# --wait option you can use to set the delay between hits,
# for instance.
#
User-agent: wget
Disallow: /

#
# The 'grub' distributed client has been *very* poorly behaved.
#
User-agent: grub-client
Disallow: /

#
# Doesn't follow robots.txt anyway, but...
#
User-agent: k2spider
Disallow: /

#
# Hits many times per second, not acceptable
# http://www.nameprotect.com/botinfo.html
User-agent: NPBot
Disallow: /

# A capture bot, downloads gazillions of pages with no public benefit
# http://www.webreaper.net/
User-agent: WebReaper
Disallow: /


# -----------------------------------------------------------------------------
# SECTION for all "friendly" bots

User-agent: *

# disallow form based pages
Disallow: /portal/admin
Disallow: /portal/activate
Disallow: /portal/login
Disallow: /portal/search
Disallow: /portal/contactmember
Disallow: /portal/sendtofriend

# allow some images
Allow: /images/*logo.gif               # our own logo
Allow: /images/*logo.jpg               # our own logo
Allow: /portal/image/                             # registered entertainers
Allow: /portal/participator/image                 # partner entertainers
Allow: /portal/faq/image
Allow: /portal/events/image
Allow: /portal/memberships/image

# disallow partner company logos
Disallow: /portal/agency/image
Disallow: /portal/partner/image
                                                                                 
# disallow internal files/images e.g. borders, backgrounds, stylesheets, ...
Disallow: /images
Disallow: /resources
Disallow: /styles
Disallow: /newsletter*/image
Disallow: /*.gif$
Disallow: /*.png$
Disallow: /*.swf$
Disallow: /*.jpg$
Disallow: /*.jpeg$
Disallow: /*.bmp$

# advise "nice" crawlers to pause 10 seconds after a successful request
Crawl-delay: 5

# advise "nice" crawlers to visit in early morning 2-6 MET (below is GMTlocal)
Visit-time: 0100-0500