# robots.txt rules mainly like they are used at http://www.wikipedia.org
#
# 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.

# 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: 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: Sproose
Disallow: /

User-agent: Speedy
Disallow: /

# urltrends.com
User-agent: Snappy
Disallow: /

User-agent: Yandex
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: /

# WayBackMachine archiver
User-agent: ia_archiver
Disallow: /

# Bots we dont need to have..
User-Agent: YodaoBot
Disallow: /

User-Agent: baiduspider
Disallow: /

User-agent: Shim-Crawler
Disallow: /

User-agent: MJ12bot
Disallow: /

# added 18-03-07
User-agent: IRLbot 
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/
Disallow: /trap/
Disallow: /javadoc/
Disallow: /wiki/index.php/Special:Random
Disallow: /wiki/index.php/Special%3ARandom
Disallow: /wiki/index.php/Special:Search
Disallow: /wiki/index.php/Special%3ASearch
Disallow: /wiki/index.php/Special:Recentchanges
Disallow: /wiki/index.php/Special%3ARecentchanges
Disallow: /wiki/index.php?title=Special:Recentchanges
Disallow: /wiki/index.php?title=Special%3ARecentchanges
Disallow: /wiki/index.php/Special:Newpages
Disallow: /wiki/index.php/Special%3ANewpages
Disallow: /wiki/index.php?title=Special:Newpages
Disallow: /wiki/index.php?title=Special%3ANewpages
Disallow: /wiki/index.php?title=Special:Ipblocklist
Disallow: /wiki/index.php?title=Special%3AIpblocklist
Disallow: /wiki/index.php?title=Special:Contributions
Disallow: /wiki/index.php?title=Special%3AContributions
Disallow: /*&oldid
Disallow: /*Special:
Disallow: /*MediaWiki:

## *at least* 60 second please. preferably more :D
## 60 second is not enough again yahoo slurp... 10 minutes!!!
Crawl-delay: 600