# This file is read and obeyed by polite search engines
# Please refer to the W3C notes:
# http://www.w3.org/TR/html4/appendix/notes.html#h-B.4.1.1
# or http://info.webcrawler.com/mak/projects/robots/exclusion.html

# Slurp is Yahoo's crawler
User-agent: Slurp
Crawl-delay: 1

# Turn away unwanted search engines
# The following list of bad bots was taken from
# http://www.tareeinternet.com/forum/knowledgebase/235-blocking-bad-bots-robots-txt.html
User-agent: aipbot
User-agent: ia_archiver
User-agent: Alexibot
User-agent: Aqua_Products
User-agent: asterias
User-agent: b2w/0.1
User-agent: BackDoorBot/1.0
User-agent: becomebot
User-agent: BlowFish/1.0
User-agent: Bookmark search tool
User-agent: BotALot
User-agent: BotRightHere
User-agent: BuiltBotTough
User-agent: Bullseye/1.0
User-agent: BunnySlippers
User-agent: CheeseBot
User-agent: CherryPicker
User-agent: CherryPickerElite/1.0
User-agent: CherryPickerSE/1.0
User-agent: Copernic
User-agent: CopyRightCheck
User-agent: cosmos
User-agent: Crescent
User-agent: Crescent Internet ToolPak HTTP OLE Control v.1.0
User-agent: DittoSpyder
User-agent: EmailCollector
User-agent: EmailSiphon
User-agent: EmailWolf
User-agent: EroCrawler
User-agent: ExtractorPro
User-agent: FairAd Client
User-agent: Fasterfox
User-agent: Flaming AttackBot
User-agent: Foobot
User-agent: Gaisbot
User-agent: GetRight/4.2
User-agent: Harvest/1.5
User-agent: hloader
User-agent: httplib
User-agent: HTTrack 3.0
User-agent: humanlinks
User-agent: IconSurf
User-agent: InfoNaviRobot
User-agent: Iron33/1.0.2
User-agent: JennyBot
User-agent: Kenjin Spider
User-agent: Keyword Density/0.9
User-agent: larbin
User-agent: LexiBot
User-agent: libWeb/clsHTTP
User-agent: LinkextractorPro
User-agent: LinkScan/8.1a Unix
User-agent: LinkWalker
User-agent: LNSpiderguy
User-agent: lwp-trivial
User-agent: lwp-trivial/1.34
User-agent: Mata Hari
User-agent: Microsoft URL Control
User-agent: Microsoft URL Control - 5.01.4511
User-agent: Microsoft URL Control - 6.00.8169
User-agent: MIIxpc
User-agent: MIIxpc/4.2
User-agent: Mister PiX
User-agent: moget
User-agent: moget/2.1
User-agent: Mozilla/4.0 (compatible; BullsEye; Windows 95)
User-agent: MSIECrawler
User-agent: NetAnts
User-agent: NICErsPRO
User-agent: Offline Explorer
User-agent: Openbot
User-agent: Openfind
User-agent: Openfind data gatherer
User-agent: Oracle Ultra Search
User-agent: PerMan
User-agent: ProPowerBot/2.14
User-agent: ProWebWalker
User-agent: psbot
User-agent: Python-urllib
User-agent: QueryN Metasearch
User-agent: Radiation Retriever 1.1
User-agent: RepoMonkey
User-agent: RepoMonkey Bait & Tackle/v1.01
User-agent: RMA
User-agent: searchpreview
User-agent: SiteSnagger
User-agent: SpankBot
User-agent: spanner
User-agent: SurveyBot
User-agent: suzuran
User-agent: Szukacz/1.4
User-agent: Teleport
User-agent: TeleportPro
User-agent: Telesoft
User-agent: The Intraformant
User-agent: TheNomad
User-agent: TightTwatBot
User-agent: toCrawl/UrlDispatcher
User-agent: True_Robot
User-agent: True_Robot/1.0
User-agent: turingos
User-agent: TurnitinBot
User-agent: TurnitinBot/1.5
User-agent: URL Control
User-agent: URL_Spider_Pro
User-agent: URLy Warning
User-agent: VCI
User-agent: VCI WebViewer VCI WebViewer Win32
User-agent: Web Image Collector
User-agent: WebAuto
User-agent: WebBandit
User-agent: WebBandit/3.50
User-agent: WebCapture 2.0
User-agent: WebCopier
User-agent: WebCopier v.2.2
User-agent: WebCopier v3.2a
User-agent: Webdup/0.9
User-agent: WebEnhancer
User-agent: WebSauger
User-agent: Website Quester
User-agent: Webster Pro
User-agent: WebStripper
User-agent: WebZip
User-agent: WebZip/4.0
User-agent: WebZIP/4.21
User-agent: WebZIP/5.0
User-agent: Wget
User-agent: wget
User-agent: Wget/1.5.3
User-agent: Wget/1.6
User-agent: WWW-Collector-E
User-agent: Xenu's
User-agent: Xenu's Link Sleuth 1.1c
User-agent: Zeus
User-agent: Zeus 32297 Webster Pro V2.9 Win32
User-agent: Zeus Link Scout
Disallow: /

User-agent: *
#
# Added by Jim 2007-04-16 to (hopefully) decrease server loads in the morning
# time is in GMT, works out noon-4 AM MST
# This is from a proposed Extended Standard for Robot Exclusion, not widely adopted yet.
# Who knows though, maybe some crawlers will honor it.
# Visit-time: 1800-1000
#
# Added by support@evolutionhosting.com to slow down GoogleBot
# Crawl-delay: 10
# Request-rate: 1/6
#
Disallow: /forums/banner/
Disallow: /forums/bookmarks/
Disallow: /forums/forums/
Disallow: /forums/forums/readAll/
Disallow: /forums/jforum
Disallow: /forums/pm/sendTo/
Disallow: /forums/pm/inbox
Disallow: /forums/pm/read/
Disallow: /forums/pm/sentbox
Disallow: /forums/pm/send
Disallow: /forums/pm/reply/
Disallow: /forums/posts/quote/
Disallow: /forums/posts/reply/
Disallow: /forums/posts/watch/
Disallow: /forums/posts/unwatch/
Disallow: /forums/posts/preList/
Disallow: /forums/posts/prelist/
Disallow: /forums/posts/like/
Disallow: /forums/posts/unlike/
Disallow: /forums/posts/reqResolved/
Disallow: /forums/posts/listByUser/
Disallow: /forums/posts/listTopicsByUser/
Disallow: /forums/posts/downloadAttach/
Disallow: /forums/rss/
Disallow: /forums/search/
Disallow: /forums/user/profile/
Disallow: /forums/user/edit/
Disallow: /forums/user/lostPassword
Disallow: /forums/user/insert
Disallow: /forums/user/login
Disallow: /forums/user/activateManual
Disallow: /mobile/

# Site map
Sitemap: http://www.coderanch.com/sitemap/sitemapindex.xml