Here is a minimum for a robots.txt file in a WordPress web site.
user-agent: *
Disallow: /wp-admin
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /mobile-registration
Disallow: /desktop-registrationHere is a more advanced list
# Daum search Korea robot
User-agent: daumoa
Disallow: /
# Infoseek robot
User-agent: Ultraseek
Disallow: /
# Infoseek robot search
User-agent: Ultraseek-www
Disallow: /
# Alexa / The Internet Archive (this has been disabled for a while)
User-agent: ia_archiver
Disallow: /
#Cuil bot
User-agent: twiceler
Disallow: /
#SEOkicks-Robot
User-agent: SEOkicks-Robot
Disallow: /
User-agent: YandexBot # will be used only by the main indexing robot
Disallow: /*id=
User-agent: Yandex # will be used by all Yandex robots
Disallow: /*sid= # other than the main indexing
# Zoominfo
User-agent: Zoominfobot
Disallow: /
# Now for the list of outright bans
User-agent: BLP_bbot/0.1
Disallow: /
User-Agent: Buiduspider
Disallow: /
User-agent: ^Java
Disallow: /
User-agent: ^Jakarta
Disallow: /
User-agent: User-Agent
Disallow: /
User-agent: compatible ;
Disallow: /
User-agent: Mozilla
Disallow: /
User-agent: libwww
Disallow: /
User-agent: lwp-trivial
Disallow: /
User-agent: curl
Disallow: /
User-agent: PHP/
Disallow: /
User-agent: urllib
Disallow: /
User-agent: GT::WWW
Disallow: /
User-agent: Snoopy
Disallow: /
User-agent: MFC_Tear_Sample
Disallow: /
User-agent: HTTP::Lite
Disallow: /
User-agent: PHPCrawl
Disallow: /
User-agent: URI::Fetch
Disallow: /
User-agent: Zend_Http_Client
Disallow: /
User-agent: http client
Disallow: /
User-agent: PECL::HTTP
Disallow: /
User-agent: panscient.com
Disallow: /
User-agent: IBM EVV
Disallow: /
User-agent: Bork-edition
Disallow: /
User-agent: Fetch API Request
Disallow: /
User-agent: [A-Z][a-z]{3,} [a-z]{4,} [a-z]{4,}
Disallow: /
User-agent: WEP Search
Disallow: /
User-agent: Wells Search II
Disallow: /
User-agent: Missigua Locator
Disallow: /
User-agent: Indy Library
Disallow: /
User-agent: Java/1.4.1_04
Disallow: /
User-agent: ^Java
Disallow: /
User-agent: MJ12bot/v1.0.8 (http://majestic12.co.uk/bot.php?+)
Disallow: /
User-agent: YandexSomething/1.0
Disallow: /
User-agent: Java/1.6.0_04
Disallow: /
User-agent: Java/1.5.0_06
Disallow: /
User-agent: Java/1.6.0_11
Disallow: /
User-agent: Java/1.6.0_07
Disallow: /
User-agent: Java/1.6.0_13
Disallow: /
User-agent: ISC Systems iRc Search 2.1
Disallow: /
User-agent: 8484 Boston Project v 1.0
Disallow: /
User-agent: Mozilla/5.0 (compatible; discobot/1.1; +http://discoveryengine.com/discobot.html)
Disallow: /
User-agent: Yandex/1.01.001 (compatible; Win16; m)
Disallow: /
User-agent: Yandex/1.01.001 (compatible; Win16; H)
Disallow: /
User-agent: Yandex/1.01.001 (compatible; Win16; P)
Disallow: /
User-agent: Yandex/1.01.001 (compatible; Win16; I)
Disallow: /
User-agent: +BecomeBot/3.0
Disallow: /
User-agent: AISearchBot
Disallow: /
User-agent: Alexibot
Disallow: /
User-agent: AmazonCloudServices
Disallow: /
User-agent: Apexoo Spider 1.0
Disallow: /
User-agent: Aqua_Products
Disallow: /
User-agent: Arachnoidea
Disallow: /
User-agent: ArchitextSpider
Disallow: /
User-agent: ASPSimply
Disallow: /
User-agent: asterias
Disallow: /
User-agent: AttributorCorporationDMCABot
Disallow: /
User-agent: Avant+Browser+
Disallow: /
User-agent: Axonize-bot
Disallow: /
User-agent: b2w/0.1
Disallow: /
User-agent: BackDoorBot/1.0
Disallow: /
User-agent: becomebot
Disallow: /
User-agent: BecomeBot/3.0
Disallow: /
User-agent: Bitacle
Disallow: /
User-agent: Bitacle bot
Disallow: /
User-agent: Bitacle bot/1.1
Disallow: /
User-agent: Bitacle*
Disallow: /
User-agent: Black Hole
Disallow: /
User-agent: BlowFish/1.0
Disallow: /
User-agent: BobCrawl
Disallow: /
User-agent: boitho
Disallow: /
User-agent: boitho.com
Disallow: /
User-agent: Bookmark search tool
Disallow: /
User-agent: bot/1.0
Disallow: /
User-agent: bot/1.0+(bot;+http://;+bot@bot.bot)
Disallow: /
User-agent: BotALot
Disallow: /
User-agent: botmobi
Disallow: /
User-agent: bsalsa
Disallow: /
User-agent: BuiltBotTough
Disallow: /
User-agent: Bullseye/1.0
Disallow: /
User-agent: BunnySlippers
Disallow: /
User-agent: Butterfly
Disallow: /
User-agent: Cazoodle-Bot
Disallow: /
User-agent: CazoodleBot
Disallow: /
User-agent: Cegbfeieh
Disallow: /
User-agent: Charlotte
Disallow: /
User-agent: CheeseBot
Disallow: /
User-agent: CherryPicker
Disallow: /
User-agent: CherryPickerElite/1.0
Disallow: /
User-agent: CherryPickerSE/1.0
Disallow: /
User-agent: classroombot
Disallow: /
User-agent: ConveraCrawler/0.9d
Disallow: /
User-agent: ConveraCrawler/0.9e
Disallow: /
User-agent: Copernic
Disallow: /
User-agent: CopyRightCheck
Disallow: /
User-agent: cosmos
Disallow: /
User-agent: crawl13.exabot.com
Disallow: /
User-agent: crawl6.exabot.com
Disallow: /
User-agent: Crescent
Disallow: /
User-agent: Crescent Internet ToolPak HTTP OLE Control v.1.0
Disallow: /
User-agent: cyberpatrol
Disallow: /
User-agent: cyberpatrolcrawler
Disallow: /
User-agent: datacha0s/2.0
Disallow: /
User-agent: DBLBot
Disallow: /
User-agent: dcbot
Disallow: /
User-agent: del.icio.us
Disallow: /
User-agent: del.icio.us-thumbnails/1.0
Disallow: /
User-agent: DepSpid
Disallow: /
User-agent: discobot
Disallow: /
User-agent: DittoSpyder
Disallow: /
User-agent: DoCoMo
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: dotbot
Disallow: /
User-agent: DTAAgent
Disallow: /
User-agent: eagle
Disallow: /
User-agent: ee:
Disallow: /
User-agent: EmailCollector
Disallow: /
User-agent: EmailSiphon
Disallow: /
User-agent: EmailWolf
Disallow: /
User-agent: envolk
Disallow: /
User-agent: EroCrawler
Disallow: /
User-agent: EUDORA
Disallow: /
User-agent: Everest-Vulcan
Disallow: /
User-agent: exabot
Disallow: /
User-agent: Exabot
Disallow: /
User-agent: Exabot-Images/1.0
Disallow: /
User-agent: Exabot-Images/3.0
Disallow: /
User-agent: Exabot/2.0
Disallow: /
User-agent: Exabot/3.0
Disallow: /
User-agent: exooba
Disallow: /
User-agent: ExtractorPro
Disallow: /
User-agent: FairAd Client
Disallow: /
User-agent: FairShare
Disallow: /
User-agent: fast
Disallow: /
User-agent: fast Enterprise crawler
Disallow: /
User-agent: fast metaweb crawler
Disallow: /
User-agent: FAST-WebCrawler
Disallow: /
User-agent: fast-Webcrawler
Disallow: /
User-agent: findlinks/1.1.1-a5
Disallow: /
User-agent: findlinks/1.1.3-beta9
Disallow: /
User-agent: Flaming AttackBot
Disallow: /
User-agent: flatlandbot
Disallow: /
User-agent: FollowSiteBot
Disallow: /
User-agent: Foobot
Disallow: /
User-agent: FunWebProducts
Disallow: /
User-agent: FunWebProducts f39-2350
Disallow: /
User-agent: FyberSpider
Disallow: /
User-agent: Gaisbot
Disallow: /
User-agent: genieBot
Disallow: /
User-agent: genieBot (wgao@genieknows.com)
Disallow: /
User-agent: genieBot+(wgao@genieknows.com)
Disallow: /
User-agent: genieBot+wgao@genieknows.com
Disallow: /
User-agent: GetRight/4.2
Disallow: /
User-agent: Gigabot
Disallow: /
User-agent: Gigabot*
Disallow: /
User-agent: Gigabot/2.0
Disallow: /
User-agent: GingerCrawler
Disallow: /
User-agent: Googlebot-Image
Disallow: /
User-agent: grub
Disallow: /
User-agent: grub-client
Disallow: /
# Note: gsa-crawler is not Google
User-agent: gsa-crawler
Disallow: /
User-agent: Gulliver
Disallow: /
User-agent: Harvest/1.5
Disallow: /
User-agent: HenryTheMiragoRobot
Disallow: /
User-agent: heritrix
Disallow: /
User-agent: heritrix/1.12.1 +http://www.page-store.com)
Disallow: /
User-agent: hloader
Disallow: /
User-agent: HMSE_Robot
Disallow: /
User-agent: HornySexSearch
Disallow: /
User-agent: http://www.almaden.ibm.com/cs/crawler
Disallow: /
User-agent: http://www.cuill.com/twiceler/robot.html
Disallow: /
User-agent: HTTP/1.1 zibber-v0.1(www.zibb.com/crawler/)
Disallow: /
User-agent: httplib
Disallow: /
User-agent: humanlinks
Disallow: /
User-agent: ia_archive
Disallow: /
User-agent: ia_archiver-web.archive.org
Disallow: /
User-agent: ia_archiver/1.6
Disallow: /
User-agent: IBM
Disallow: /
User-agent: IBM_Planetwide
Disallow: /
User-agent: ichiro/2.0
Disallow: /
User-agent: ichiro/2.0 (ichiro@nttr.co.jp)
Disallow: /
User-agent: ichiro/2.0+(http://help.goo.ne.jp/door/crawler.html)
Disallow: /
User-agent: IconSurf
Disallow: /
User-agent: InfoNaviRobot
Disallow: /
User-agent: InfoPath
Disallow: /
User-agent: InfoPath.1
Disallow: /
User-agent: InfoPath.2
Disallow: /
User-agent: IntegraTelecom
Disallow: /
User-agent: internetseer
Disallow: /
User-agent: InternetSeer.com
Disallow: /
User-agent: ips-agent
Disallow: /
User-agent: IRLbot
Disallow: /
User-agent: IRLbot/3.0
Disallow: /
User-agent: IRLbot/3.0 (compatible; MSIE 6.0; http://irl.cs.tamu.edu/crawler)
Disallow: /
User-agent: Iron33/1.0.2
Disallow: /
User-agent: Isidorus
Disallow: /
User-agent: Jakarta Commons-HttpClient
Disallow: /
User-agent: Java
Disallow: /
User-agent: Java Bot 2.0
Disallow: /
User-agent: Java/1.5.0_05
Disallow: /
User-agent: Java/1.5.0_10
Disallow: /
User-agent: JavaBot
Disallow: /
User-agent: JavaBot 2.0
Disallow: /
User-agent: JennyBot
Disallow: /
User-agent: Jyxobot
Disallow: /
User-agent: kalooga
Disallow: /
User-agent: KaloogaBot
Disallow: /
User-agent: Kenjin Spider
Disallow: /
User-agent: Keyword Density/0.9
Disallow: /
User-agent: kyluka
Disallow: /
User-agent: LaBot
Disallow: /
User-agent: larbin
Disallow: /
User-agent: larbin_2.6.1
Disallow: /
User-agent: larbin_2.6.1+(larbin2.6.1@unspecified.mail)
Disallow: /
User-agent: laycat
Disallow: /
User-agent: LexiBot
Disallow: /
User-agent: LexiBotWeb Image Collector
Disallow: /
User-agent: libcurl-agent
Disallow: /
User-agent: libWeb/clsHTTP
Disallow: /
User-agent: libwww-perl
Disallow: /
User-agent: libwww-perl/5.65
Disallow: /
User-agent: LinkAider
Disallow: /
User-agent: LinkextractorPro
Disallow: /
User-agent: LinkScan/8.1a Unix
Disallow: /
User-agent: LinkWalker
Disallow: /
User-agent: LinkWalker/2.0
Disallow: /
User-agent: LinkWalker/2.0 - www.seventwentyfour.com
Disallow: /
User-agent: LMQueueBot/0.2
Disallow: /
User-agent: LNSpiderguy
Disallow: /
User-agent: LocalBot
Disallow: /
User-agent: LocalcomBot
Disallow: /
User-agent: looksmart
Disallow: /
User-agent: lwp-trivial/1.34
Disallow: /
User-agent: Mail.Ru
Disallow: /
User-agent: MantraAgent
Disallow: /
User-agent: Mata Hari
Disallow: /
User-agent: Mediapartners-Google*
Disallow: /
User-agent: Microsoft URL Control
Disallow: /
User-agent: Microsoft URL Control - 5.01.4511
Disallow: /
User-agent: Microsoft URL Control - 6.00.8169
Disallow: /
User-agent: MIIxpc
Disallow: /
User-agent: MIIxpc/4.2
Disallow: /
User-agent: Mister PiX
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: MJ12bot/v1.2.0
Disallow: /
User-agent: MJ12bot/v1.2.0 (http://majestic12.co.uk/bot.php? )
Disallow: /
User-agent: MLBot
Disallow: /
User-agent: Modified GMMBotRightHere
Disallow: /
User-agent: moget
Disallow: /
User-agent: moget/2.1
Disallow: /
User-agent: moget/2.1 (moget@goo.ne.jp)
Disallow: /
User-agent: Moozilla
Disallow: /
User-agent: Mozilla/2.0 (compatible; Ask Jeeves/Teoma)
Disallow: /
User-agent: mozilla/3
Disallow: /
User-agent: mozilla/4
Disallow: /
User-agent: Mozilla/4.0
Disallow: /
User-agent: Mozilla/4.0 (compatible; BullsEye; Windows 95)
Disallow: /
User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows 2000)
Disallow: /
User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows 9
Disallow: /
User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows 95)
Disallow: /
User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows 98)
Disallow: /
User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows NT)
Disallow: /
User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows XP)
Disallow: /
User-agent: Mozilla/4.0 (compatible; MSIE 5.0; Windows 95) VoilaBot BETA 1.2
Disallow: /
User-agent: Mozilla/4.0 (compatible; MSIE 5.05; Windows NT 3.51)
Disallow: /
User-agent: Mozilla/4.0 (compatible; MSIE 5.05; Windows NT 4.0)
Disallow: /
User-agent: Mozilla/4.0 (compatible; MSIE 5.05; Windows NT 5.0)
Disallow: /
User-agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0)
Disallow: /
User-agent: Mozilla/4.0+compatible+ZyBorg/1.0+
Disallow: /
User-agent: mozilla/5
Disallow: /
User-agent: Mozilla/5.0 (compatible; Yahoo! Slurp China; http://misc.yahoo.com.cn/help.html)
Disallow: /
User-agent: Mozilla/5.0+(compatible;+BecomeBot/3.0;++http://www.become.com/site_owners.html)
Disallow: /
User-agent: MSIECrawler
Disallow: /
User-agent: msnbot-media
Disallow: /
User-agent: MSR-ISRCCrawler
Disallow: /
User-agent: nambu
Disallow: /
User-agent: NationalDirectory-SuperSpider
Disallow: /
User-agent: NaverBot
Disallow: /
User-agent: naverbot
Disallow: /
User-agent: NetAnts
Disallow: /
User-agent: NetMechanic
Disallow: /
User-agent: nexen
Disallow: /
User-agent: NextGenSearchBot
Disallow: /
User-agent: NG/2.0
Disallow: /
User-agent: nicebot
Disallow: /
User-agent: NICErsPRO
Disallow: /
User-agent: noxtrumbot/1.0
Disallow: /
User-agent: Nutch
Disallow: /
User-agent: obot
Disallow: /
User-agent: Ocelli
Disallow: /
User-agent: Offline Explorer
Disallow: /
User-agent: Offline Explorer/1.5
Disallow: /
User-agent: Offline Explorer/1.9
Disallow: /
User-agent: Offline Explorer/2.5
Disallow: /
User-agent: OmniExplorer
Disallow: /
User-agent: OmniExplorer_Bot
Disallow: /
User-agent: OmniExplorer_Bot/1.07
Disallow: /
User-agent: OmniExplorer_Bot/1.09
Disallow: /
User-agent: OmniExplorer_Bot/1.10
Disallow: /
User-agent: OnTownsBot
Disallow: /
User-agent: OOZBOT
Disallow: /
User-agent: Openbot
Disallow: /
User-agent: Openfind
Disallow: /
User-agent: Openfind data gathere
Disallow: /
User-agent: OpenX
Disallow: /
User-agent: Oracle Ultra Search
Disallow: /
User-agent: page_prefetcher
Disallow: /
User-agent: perl
Disallow: /
User-agent: PerMan
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: phpversion
Disallow: /
User-agent: Piffany_Web_Cacher_v0.91
Disallow: /
User-agent: ProPowerBot/2.14
Disallow: /
User-agent: ProWebWalker
Disallow: /
User-agent: psbot
Disallow: /
User-agent: psbot/0.1
Disallow: /
User-agent: psbot/0.1+(+http://www.picsearch.com/bot.html)
Disallow: /
User-agent: PSIBots
Disallow: /
User-agent: Python-urllib
Disallow: /
User-agent: QEAVis
Disallow: /
User-agent: QueryN Metasearch
Disallow: /
User-agent: Radiation Retriever 1.1
Disallow: /
User-agent: Rankivabot
Disallow: /
User-agent: REAP-Crawler
Disallow: /
User-agent: RepoMonkey
Disallow: /
User-agent: RepoMonkey Bait & Tackle/v1.01
Disallow: /
User-agent: RiceComputerArchitecture
Disallow: /
User-agent: RMA
Disallow: /
User-agent: robotgenius
Disallow: /
User-agent: Robozilla
Disallow: /
User-agent: ru_com_viewer
Disallow: /
User-agent: RufusBot
Disallow: /
User-agent: SapphireWebCrawler
Disallow: /
User-agent: sbider
Disallow: /
User-agent: SBIder
Disallow: /
User-agent: SBIder/SBIder-0.8.2-dev
Disallow: /
User-agent: scooter
Disallow: /
User-agent: Scooter/2.0
Disallow: /
User-agent: scoutjet
Disallow: /
User-agent: Scrubby
Disallow: /
User-agent: searchme
Disallow: /
User-agent: searchpreview
Disallow: /
User-agent: Sensis Web Crawler
Disallow: /
User-agent: Sensis Web Crawler (search_comments\\at\\sensis\\dot\\com\\dot\\au)
Disallow: /
User-agent: Sensis+Web+Crawler+
Disallow: /
User-agent: Servage
Disallow: /
User-agent: ServageRobot
Disallow: /
User-agent: setooz
Disallow: /
User-agent: ShopWiki
Disallow: /
User-agent: Sidewinder
Disallow: /
User-agent: Sika
Disallow: /
User-agent: sitecat
Disallow: /
User-agent: sitecheck.internetseer.com
Disallow: /
User-agent: Sitemap: http://www.jaxcarpentry.com/sitemap.xml
Disallow: /
User-agent: SiteSnagger
Disallow: /
User-agent: Slicehost
Disallow: /
User-agent: Slurp.so/1.0
Disallow: /
User-agent: slurp@inktomi
Disallow: /
User-agent: slurp@inktomi.com
Disallow: /
User-agent: Slurp/2.0-KiteHourly
Disallow: /
User-agent: Slurp/2.0-OwlWeekly
Disallow: /
User-agent: Slurp/2.0j
Disallow: /
User-agent: Slurp/3.0-AU
Disallow: /
User-agent: SlySearch
Disallow: /
User-agent: SlySearch/1.0
Disallow: /
User-agent: SlySearch/1.x
Disallow: /
User-agent: Snapbot
Disallow: /
User-agent: Snapbot/1.0
Disallow: /
User-agent: SnapPreviewBot
Disallow: /
User-agent: Snappy
Disallow: /
User-agent: Snappybot
Disallow: /
User-agent: sogou spider
Disallow: /
User-agent: sogou+spider
Disallow: /
User-agent: SpankBot
Disallow: /
User-agent: spanner
Disallow: /
User-agent: Speedy
Disallow: /
User-agent: speedyspider
Disallow: /
User-agent: sphsearch
Disallow: /
User-agent: sproose
Disallow: /
User-agent: StackRambler/2.0
Disallow: /
User-agent: StackRambler/2.0+(MSIE+incompatible)
Disallow: /
User-agent: SuperBot/4.4.0.60 (Windows XP)
Disallow: /
User-agent: SuperPages
Disallow: /
User-agent: SurveyBot
Disallow: /
User-agent: SurveyBot/2.3
Disallow: /
User-agent: SurveyBot/2.3 (Whois Source)
Disallow: /
User-agent: suzuran
Disallow: /
User-agent: Szukacz/1.4
Disallow: /
User-agent: T-Online Browser
Disallow: /
User-agent: T-Rex
Disallow: /
User-agent: Teleport
Disallow: /
User-agent: TeleportPro
Disallow: /
User-agent: TeleportProMIIxpc
Disallow: /
User-agent: Telesoft
Disallow: /
User-agent: Teoma
Disallow: /
User-agent: The Intraformant
Disallow: /
User-agent: TheNomad
Disallow: /
User-agent: therarestparser
Disallow: /
User-agent: TightTwatBot
Disallow: /
User-agent: Titan
Disallow: /
User-agent: toCrawl/UrlDispatcher
Disallow: /
User-agent: Trident
Disallow: /
User-agent: True_Robot
Disallow: /
User-agent: True_Robot /1.0turingos
Disallow: /
User-agent: True_Robot/1.0
Disallow: /
User-agent: turingos
Disallow: /
User-agent: turnitinbot
Disallow: /
User-agent: TurnitinBot
Disallow: /
User-agent: TurnitinBot/1.5
Disallow: /
User-agent: TurnitinBot/2.0 http://www.turnitin.com/robot/crawlerinfo.html
Disallow: /
User-agent: Tutorial Crawler
Disallow: /
User-agent: twiceler
Disallow: /
User-agent: Twiceler
Disallow: /
User-agent: Twiceler-0.9
Disallow: /
User-agent: Twiceler-0.9+http://www.cuill.com/twiceler/robot.html
Disallow: /
User-agent: uberbot
Disallow: /
User-agent: UltraSeek
Disallow: /
User-agent: URL Control
Disallow: /
User-agent: URL_Spider_Pro
Disallow: /
User-agent: URLy Warning
Disallow: /
User-agent: User-agetn: Mozilla/4.0 (compatible; B-l-i-t-z-B-O-T)
Disallow: /
User-agent: uw_cse_xwc
Disallow: /
User-agent: VCI
Disallow: /
User-agent: VCI WebViewer VCI WebViewer Win32
Disallow: /
User-agent: VCIVCI
Disallow: /
User-agent: ViolaBot
Disallow: /
User-agent: voilabot
Disallow: /
User-agent: voyager
Disallow: /
User-agent: voyager/1.0
Disallow: /
User-agent: voyager/2.0
Disallow: /
User-agent: vscooter
Disallow: /
User-agent: VWBot
Disallow: /
User-agent: Web Downloader/4.5
Disallow: /
User-agent: Web Downloader/5.7
Disallow: /
User-agent: Web Downloader/6.9
Disallow: /
User-agent: Web Image Collector
Disallow: /
User-agent: webalta
Disallow: /
User-agent: WebarooBot
Disallow: /
User-agent: WebAuto
Disallow: /
User-agent: WebBandit
Disallow: /
User-agent: WebBandit/3.50
Disallow: /
User-agent: Webcollage
Disallow: /
User-agent: WebCopier
Disallow: /
User-agent: WebCopier v3.2a
Disallow: /
User-agent: WebCopier v3.3
Disallow: /
User-agent: WebCopier v3.3.0
Disallow: /
User-agent: WebCopier v3.3.2
Disallow: /
User-agent: WebCrawler
Disallow: /
User-agent: WebDataCentreBot
Disallow: /
User-agent: WebEnhancer
Disallow: /
User-agent: WebmasterWorld Extractor
Disallow: /
User-agent: WebmasterWorldForumBot
Disallow: /
User-agent: WebSauger
Disallow: /
User-agent: Websense
Disallow: /
User-agent: Website Quester
Disallow: /
User-agent: Webspider
Disallow: /
User-agent: Webster Pro
Disallow: /
User-agent: WebStripper
Disallow: /
User-agent: WebViewer
Disallow: /
User-agent: WebZip
Disallow: /
User-agent: WebZIP/3.5 (http://www.spidersoft.com)
Disallow: /
User-agent: WebZip/4.0
Disallow: /
User-agent: WGet
Disallow: /
User-agent: Wget
Disallow: /
User-agent: Wget/1.10.2
Disallow: /
User-agent: Wget/1.5.3
Disallow: /
User-agent: Wget/1.6
Disallow: /
User-agent: Wget/1.9.1
Disallow: /
User-agent: Wget/1.9+cvs-stable (Red Hat modified)
Disallow: /
User-agent: whois.de
Disallow: /
User-agent: whoisde.de
Disallow: /
User-agent: WillyBot
Disallow: /
User-agent: Win32
Disallow: /
User-agent: worio
Disallow: /
User-agent: WWW-Collector-E
Disallow: /
User-agent: Xenu Link Sleuth
Disallow: /
User-agent: Xenu Link Sleuth 1.2i
Disallow: /
User-agent: Xenu's
Disallow: /
User-agent: Xenu's Link Sleuth 1.1c
Disallow: /
User-agent: Y!J
Disallow: /
User-agent: y!j-bsc
Disallow: /
User-agent: Y!J-BSC
Disallow: /
User-agent: Y!J-BSC/1.0
Disallow: /
User-agent: y!j-bsc/1.0 (http://help.yahoo.co.jp/help/jp/search/indexing/indexing-15.html)
Disallow: /
User-agent: y!j/1.0
Disallow: /
User-agent: Yahoo-Blogs
Disallow: /
User-agent: Yahoo-Blogs/v3.9
Disallow: /
User-agent: Yahoo-MMCrawler/3.x
Disallow: /
User-agent: YahooSeeker
Disallow: /
User-agent: YahooSeeker-Testing/v3.9 (compatible; Mozilla 4.0; MSIE 5.5; http://search.yahoo.com/)
Disallow: /
User-agent: YahooYSMcm
Disallow: /
User-agent: YahooYSMcm/2.0.0
Disallow: /
User-agent: yandex
Disallow: /
User-agent: YandexSomething
Disallow: /
User-agent: Yanga
Disallow: /
User-agent: Yeti
Disallow: /
User-agent: yoogliFetchAgent/0.1
Disallow: /
User-agent: Zao
Disallow: /
User-agent: zermelo
Disallow: /
User-agent: Zeus
Disallow: /
User-agent: Zeus 32297 Webster Pro V2.9 Win32
Disallow: /
User-agent: Zeus Link Scout
Disallow: /
User-agent: zibber
Disallow: /
User-agent: zibber v0.1
Disallow: /
User-agent: zibber-v0.1(www.zibb.com/crawler/)
Disallow: /
User-agent: ZupeeCrawler
Disallow: /
User-agent: zyborg
Disallow: /
User-agent: ZyBorg/1.0
Disallow: /
User-agent: Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36
Disallow: /
User-agent: msnbot
Disallow: /sample-page/
Disallow: /activate/ # har har
Disallow: /cgi-bin/ # MT refugees
Disallow: /uploads/wpo-plugins-tables-list.json
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /robots.txt
Disallow: /?s={search_term_string}
User-agent: Bingbot
Disallow: /sample-page/
Disallow: /activate/ # har har
Disallow: /cgi-bin/ # MT refugees
Disallow: /uploads/wpo-plugins-tables-list.json
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /robots.txt
Disallow: /?s={search_term_string}
User-agent: Googlebot
Disallow: /sample-page/
Disallow: /activate/ # har har
Disallow: /cgi-bin/ # MT refugees
Disallow: /uploads/wpo-plugins-tables-list.json
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /robots.txt
Disallow: /?s={search_term_string}
# We do not target China market
#-------------Sogou---------------
User-Agent: sogou spider
User-Agent: Sogou web spider
User-agent: Sogou blog
User-agent: Sogou News Spider
User-agent: Sogou Orion spider
User-agent: Sogou web spider/4.0(+http://www.sogou.com/docs/help/webmasters.htm#07)
User-agent: Sogou Pic Spider/3.0( http://www.sogou.com/docs/help/webmasters.htm#07)
User-agent: Sogou head spider/3.0( http://www.sogou.com/docs/help/webmasters.htm#07)
User-agent: Sogou Orion spider/3.0( http://www.sogou.com/docs/help/webmasters.htm#07)
Disallow: /
#SoGou (CN)
#Info: http://www.sogou.com/docs/help/webmasters.htm#07
#Required robots.txt code:
User-agent: sogou spider
Disallow: /
#-------------Sogou---------------
# ------------Block Baidu-----------------
User-agent: Baiduspider
User-agent: Baiduspider-video
User-agent: Baiduspider-image
User-agent: Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)
User-agent: Mozilla/5.0 (compatible; Baiduspider/3.0; +http://www.baidu.com/search/spider.html)
User-agent: Mozilla/5.0 (compatible; Baiduspider/4.0; +http://www.baidu.com/search/spider.html)
User-agent: Mozilla/5.0 (compatible; Baiduspider/5.0; +http://www.baidu.com/search/spider.html)
User-agent: Baiduspider/2.0
User-agent: Baiduspider/3.0
User-agent: Baiduspider/4.0
User-agent: Baiduspider/5.0
User-agent: Baiduspider+(+http://www.baidu.com/search/spider_jp.html)
User-agent: Mozilla/5.0 (iPhone; CPU iPhone OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1 (compatible; Baiduspider-render/2.0; +http://www.baidu.com/search/spider.html)
Disallow: /
#Baidu (CN)
#Info: http://www.baidu.com/search/spider.htm
#Required robots.txt code:
User-agent: Baiduspider
User-agent: Baiduspider-video
User-agent: Baiduspider-image
Disallow: /
#MJ12Bot
User-Agent: MJ12bot
Crawl-Delay: 5
User-agent: IRLbot
Crawl-delay: 3600
Disallow: /activate/ # har har
Disallow: /cgi-bin/ # MT refugees
Disallow: /uploads/wpo-plugins-tables-list.json
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /robots.txt
User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /uploads/wpo-plugins-tables-list.json
Be the first to comment