# The servers: hercules.kgs.ku.edu, deuteron.kgs.ku.edu, drysdale.kgs.ku.edu, neutrino.kgs.ku.edu 
# follow the robots.txt file that wikipedia.org uses.  We got burned by HTTrack on November 24, 2003.
# 

# 
# robots.txt for http://www.wikipedia.org/ 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.
#
User-agent: *
Disallow: /

# Wikipedia work bots:
User-Agent: IsraBot
Allow: /


# 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: askjeeves
Disallow: /

User-Agent: AskJeeves
Disallow: /

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: /

User-Agent: HTTrack
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: /w/
#Crawl-delay: 15