#
# 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.
#

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

User-agent: Orthogaffe
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: 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: /

#
# 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.
#
# above is from wikipedia's robots.txt, below is mine.
#
User-agent: *
Disallow: /cgi-bin/
Crawl-Delay: 5 

# Specific Bot Blocking / Allowing Stuff
# Slow down yahoo!
User-agent: Slurp
Crawl-delay: 10 

User-agent: googlebot
Allow: /

# MSN, yicky but whatever.
User-agent: msnbot
Crawl-Delay: 10

# Allow the internet archive.
User-agent: ia_archiver
Allow: /
Disallow: /cgi-bin/
Crawl-Delay: 5 

# Become.com - shopping robot, we don't like that kind of thing here, bye bye
User-agent: BecomeBot 
Disallow: /

# Pingdom -  I don't need you monitoring my website kthxbye
User-Agent: Pingdom GIGRIB
Disallow: /

# holy crap, stop spidering EVERYTHING.
User-Agent: sogou music spider
Disallow: /

# We don't need you.  Plz die.
User-Agent: Twiceler
Disallow: /

# oh fuck off.
User-Agent: voyager
Disallow: /

# eat my asshole
User-Agent: IWAgent
Disallow: /

# ugh ugh ugh
User-agent: SBIder
Disallow: /