#
# robots.txt for http://www.oobdoo.com/ and friends
#
# Please note: There are a lot of pages on this site, and there are
# some misbehaved spiders out there that go _way_ too fast. If you're
# irresponsible, your access to the site may be blocked.
#


# Wikipedia work bots:
User-agent: IsraBot
Disallow: /index.htm

User-agent: Orthogaffe
Disallow: /index.htm

# 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: /

User-agent: Mediapartners-Google*
Disallow: /abcestates/
Disallow: /aboutus/
Disallow: /adart/
Disallow: /admin_images/
Disallow: /ads/
Disallow: /advert/
Disallow: /advertise/
Disallow: /cgibin/
Disallow: /directory/
Disallow: /dwodp/
Disallow: /error1/
Disallow: /error2/
Disallow: /mikezeta/
Disallow: /news_data/
Disallow: /news_images/
Disallow: /odp/
Disallow: /oobdoosearch1/
Disallow: /phpodp/
Disallow: /phpodp2/
Disallow: /radio/
Disallow: /reciprocals/
Disallow: /royton/
Disallow: /RSS/
Disallow: /search/
Disallow: /secure/
Disallow: /submiturl/
Disallow: /test/
Disallow: /online/advertise/
Disallow: /online/index.htm/
Disallow: /online/inter-change.subportal.com/
Disallow: /online/legal.htm/
Disallow: /online/logos.htm/
Disallow: /online/lotto.htm/
Disallow: /online/manind.htm/
Disallow: /online/suggest.htm/
Disallow: /online/online/
Disallow: /bussop.htm/
Disallow: /index2.htm/
Disallow: /searchome/
Disallow: /shop/
Disallow: /shoping/
Disallow: /w/

#
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: /

#
# Friendly, low-speed bots are welcome viewing article pages, but not
# dynamically-generated pages please.
#
# Inktomi's "Slurp" can read a minimum delay between hits; if your
# bot supports such a thing using the 'Crawl-delay' or another
# instruction, please let us know.
#
User-agent: *
Disallow: /*.html
Disallow: /abcestates/
Disallow: /aboutus/
Disallow: /adart/
Disallow: /admin_images/
Disallow: /ads/
Disallow: /advert/
Disallow: /advertise/
Disallow: /cgibin/
Disallow: /directory/
Disallow: /dwodp/
Disallow: /error1/
Disallow: /error2/
Disallow: /mikezeta/
Disallow: /news_data/
Disallow: /news_images/
Disallow: /odp/
Disallow: /oobdoosearch1/
Disallow: /phpodp/
Disallow: /phpodp2/
Disallow: /radio/
Disallow: /reciprocals/
Disallow: /royton/
Disallow: /RSS/
Disallow: /search/
Disallow: /secure/
Disallow: /submiturl/
Disallow: /test/
Disallow: /online/advertise/
Disallow: /online/index.htm/
Disallow: /online/inter-change.subportal.com/
Disallow: /online/legal.htm/
Disallow: /online/logos.htm/
Disallow: /online/lotto.htm/
Disallow: /online/manind.htm/
Disallow: /online/suggest.htm/
Disallow: /online/online/
Disallow: /bussop.htm/
Disallow: /index2.htm/
Disallow: /searchome/
Disallow: /shop/
Disallow: /shoping/
Disallow: /w/