#
# 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.
#

# advertising-related bots:
User-agent: Mediapartners-Google*
Disallow: /

# Wikipedia work bots:
User-agent: IsraBot
Disallow:

User-agent: Orthogaffe
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: 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: /

# some extras from: http://www.jaguarpowered.com/sexyhtaccess.txt

User-agent: Atomz 
Disallow: /
User-agent: BlackWidow 
Disallow: /
User-agent: Bot\ mailto:craftbot@yahoo.com 
Disallow: /
User-agent: CherryPicker 
Disallow: /
User-agent: ChinaClaw 
Disallow: /
User-agent: Crescent 
Disallow: /
User-agent: Custo 
Disallow: /
User-agent: DISCo 
Disallow: /
User-agent: Download\ Demon 
Disallow: /
User-agent: Download\ Master 
Disallow: /
User-agent: DA\ 2.x 
Disallow: /
User-agent: DA\ 4.0 
Disallow: /
User-agent: DA\ 7.0 
Disallow: /
User-agent: DTS\ Agent 
Disallow: /
User-agent: eCatch 
Disallow: /
User-agent: EirGrabber 
Disallow: /
User-agent: Express\ WebPictures 
Disallow: /
User-agent: ExtractorPro 
Disallow: /
User-agent: EyeNetIE 
Disallow: /
User-agent: FDM\ 2.x 
Disallow: /
User-agent: FDM\ 1.x 
Disallow: /
User-agent: FlashGet 
Disallow: /
User-agent: FlickBot 
Disallow: /
User-agent: FrontPage
Disallow: /
User-agent: GetRight 
Disallow: /
User-agent: GetWeb! 
Disallow: /
User-agent: DA\ 7.0
Disallow: /
User-agent: Go!Zilla 
Disallow: /
User-agent: Go-Ahead-Got-It 
Disallow: /
User-agent: GornKer 
Disallow: /
User-agent: grabber 
Disallow: /
User-agent: GrabNet 
Disallow: /
User-agent: Grafula 
Disallow: /
User-agent: HMView 
Disallow: /
User-agent: HTTrack
Disallow: /
User-agent: IDA 
Disallow: /
User-agent: imagefetch 
Disallow: /
User-agent: Image\ Stripper 
Disallow: /
User-agent: Image\ Sucker 
Disallow: /
User-agent: Indy\ Library 
Disallow: /
User-agent: InterGET 
Disallow: /
User-agent: Internet\ Ninja
Disallow: /
User-agent: Irvine
Disallow: /
User-agent: JetCar
Disallow: /
User-agent: JOC\ Web\ Spider
Disallow: /
User-agent: larbin
Disallow: /
User-agent: LeechFTP
Disallow: /
User-agent: LeechGet\ 2002
Disallow: /
User-agent: Mass\ Downloader
Disallow: /
User-agent: Microsoft.URL
Disallow: /
User-agent: MIDown\ tool
Disallow: /
User-agent: Mister\ PiX
Disallow: /
User-agent: Navroad
Disallow: /
User-agent: NearSite
Disallow: /
User-agent: net.?(ants|mechanic|spider|vampire|zip)
Disallow: /
User-agent: NetAnts/1.25
Disallow: /
User-agent: NetPumper\ Pro/1.0
Disallow: /
User-agent: NICErsPRO
Disallow: /
User-agent: ninja
Disallow: /
User-agent: NPBot
Disallow: /
User-agent: Octopus
Disallow: /
User-agent: Offline\ Explorer
Disallow: /
User-agent: Offline\ Navigator
Disallow: /
User-agent: omniexplorer_bot
Disallow: /
User-agent: PageGrabber
Disallow: /
User-agent: Papa\ Foto
Disallow: /
User-agent: pavuk
Disallow: /
User-agent: pcBrowser
Disallow: /
User-agent: PersonaPilot
Disallow: /
User-agent: dloader(NaverRobot)
Disallow: /
User-agent: ReGet
Disallow: /
User-agent: SearchExpress
Disallow: /
User-agent: SiteSnagger
Disallow: /
User-agent: SmartDownload
Disallow: /
User-agent: Sqworm
Disallow: /
User-agent: StarDownloader/1.45
Disallow: /
User-agent: SuperBot
Disallow: /
User-agent: SuperHTTP
Disallow: /
User-agent: Surfbot
Disallow: /
User-agent: SurveyBot
Disallow: /
User-agent: Siphon
Disallow: /
User-agent: tAkeOut
Disallow: /
User-agent: Teleport\ Pro
Disallow: /
User-agent: TurnitinBot
Disallow: /
User-agent: vayala
Disallow: /
User-agent: VoidEYE
Disallow: /
User-agent: Web\ Sucker
Disallow: /
User-agent: WebAuto
Disallow: /
User-agent: WebBandit
Disallow: /
User-agent: WebCopier
Disallow: /
User-agent: WebFetch
Disallow: /
User-agent: WebGo\ IS
Disallow: /
User-agent: WebLeacher
Disallow: /
User-agent: WebReaper
Disallow: /
User-agent: WebSauger
Disallow: /
User-agent: Website\ eXtractor
Disallow: /
User-agent: Website\ Quester
Disallow: /
User-agent: WebStripper
Disallow: /
User-agent: WebWhacker
Disallow: /
User-agent: WebZIP
Disallow: /
User-agent: Widow
Disallow: /
User-agent: WWWOFFLE
Disallow: /
User-agent: Xaldon\ WebSpider
Disallow: /
User-agent: Zeus
Disallow: /
User-agent: ZyBorg
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.
#
User-agent: *
Disallow: /w/
Disallow: /trap/
Disallow: /wiki/Especial:Search
Disallow: /wiki/Especial%3ASearch
Disallow: /wiki/Special:Randompage
Disallow: /wiki/Special%3ARandompage
Disallow: /wiki/Special:Search
Disallow: /wiki/Special%3ASearch
Disallow: /wiki/Spesial:Search
Disallow: /wiki/Spesial%3ASearch
Disallow: /wiki/Spezial:Search
Disallow: /wiki/Spezial%3ASearch
Disallow: /wiki/Specjalna:Search
Disallow: /wiki/Specjalna%3ASearch
Disallow: /wiki/Speciaal:Search
Disallow: /wiki/Speciaal%3ASearch
Disallow: /wiki/Speciaal:Randompage
Disallow: /wiki/Speciaal%3ARandompage
Disallow: /wiki/Speciel:Search
Disallow: /wiki/Speciel%3ASearch
Disallow: /wiki/Speciale:Search
Disallow: /wiki/Speciale%3ASearch
Disallow: /wiki/Istimewa:Search
Disallow: /wiki/Istimewa%3ASearch
Disallow: /wiki/Toiminnot:Search
Disallow: /wiki/Toiminnot%3ASearch
#ar
Disallow: /wiki/%D8%AE%D8%A7%D8%B5:Search
Disallow: /wiki/%D8%AE%D8%A7%D8%B5%3ASearch
#he
Disallow: /wiki/%D7%9E%D7%99%D7%95%D7%97%D7%93:Search
Disallow: /wiki/%D7%9E%D7%99%D7%95%D7%97%D7%93%3ASearch
#hu
Disallow: /wiki/Speci%C3%A1lis:Search
Disallow: /wiki/Speci%C3%A1lis%3ASearch
#ja
Disallow: /wiki/%E7%89%B9%E5%88%A5:Search
Disallow: /wiki/%E7%89%B9%E5%88%A5%3ASearch
#ru
Disallow: /wiki/%D0%A1%D0%BF%D0%B5%D1%86%D0%B8%D0%B0%D0%BB%D1%8C%D0%BD%D1%8B%D0%B5:Search
Disallow: /wiki/%D0%A1%D0%BF%D0%B5%D1%86%D0%B8%D0%B0%D0%BB%D1%8C%D0%BD%D1%8B%D0%B5%3ASearch
Crawl-delay: 1