#
# www.postcrossing.com robots.txt file
#

User-Agent: *
Disallow: /displayAddress/
Disallow: /support/thankYou
Allow: /

#
# This is only for the user to see, so stop generating 404's
#
User-agent: Mediapartners-Google
Disallow: /user/*/gallery/popular
Allow: /

#
# Thank you Slurp for providing Crawl-delay parameter
#

User-agent: Slurp
Crawl-delay: 5

#
# Browser pipelining/pre-fetching is not always a good idea
#
User-agent: Fasterfox
Disallow: /

#
# Silly bot that takes screenshots and runs Javascript in it (including AdSense)
#
User-agent: Exabot
Disallow: /postcards
Disallow: /users
Disallow: /gallery



#
# bad behaving bots, according to wikipedia 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: /