# # robots.txt # # This file is to prevent the crawling and indexing of certain parts # of your site by web crawlers and spiders run by sites like Yahoo! # and Google. By telling these "robots" where not to go on your site, # you save bandwidth and server resources. # # This file will be ignored unless it is at the root of your host: # Used: http://example.com/robots.txt # Ignored: http://example.com/site/robots.txt # # For more information about the robots.txt standard, see: # http://www.robotstxt.org/robotstxt.html User-agent: * Crawl-delay: 10 # CSS, JS, Images Allow: /core/*.css$ Allow: /core/*.css? Allow: /core/*.js$ Allow: /core/*.js? Allow: /core/*.gif Allow: /core/*.jpg Allow: /core/*.jpeg Allow: /core/*.png Allow: /core/*.svg Allow: /profiles/*.css$ Allow: /profiles/*.css? Allow: /profiles/*.js$ Allow: /profiles/*.js? Allow: /profiles/*.gif Allow: /profiles/*.jpg Allow: /profiles/*.jpeg Allow: /profiles/*.png Allow: /profiles/*.svg # Directories Disallow: /core/ Disallow: /profiles/ Disallow: /includes/ Disallow: /log/ Disallow: /misc/ Disallow: /modules/ Disallow: /profiles/ Disallow: /scripts/ Disallow: /themes/ # Files Disallow: /README.txt Disallow: /web.config Disallow: /CHANGELOG.txt Disallow: /cron.php Disallow: /INSTALL.mysql.txt Disallow: /INSTALL.pgsql.txt Disallow: /INSTALL.sqlite.txt Disallow: /install.php Disallow: /INSTALL.txt Disallow: /LICENSE.txt Disallow: /MAINTAINERS.txt Disallow: /update.php Disallow: /UPGRADE.txt Disallow: /xmlrpc.php # Paths (clean URLs) Disallow: /admin/ Disallow: /comment/reply/ Disallow: /filter/tips Disallow: /node/add/ Disallow: /search/ Disallow: /user/register Disallow: /user/password Disallow: /user/login Disallow: /user/logout # Paths (no clean URLs) Disallow: /index.php/admin/ Disallow: /index.php/comment/reply/ Disallow: /index.php/filter/tips Disallow: /index.php/node/add/ Disallow: /index.php/search/ Disallow: /index.php/user/password Disallow: /index.php/user/register Disallow: /index.php/user/login Disallow: /index.php/user/logout Disallow: /?q=admin/ Disallow: /?q=comment/reply/ Disallow: /?q=filter/tips/ Disallow: /?q=node/add/ Disallow: /?q=search/ Disallow: /?q=user/password/ Disallow: /?q=user/register/ Disallow: /?q=user/login/ Disallow: /?q=user/logout/ Disallow: /node/* User-agent: Mediapartners-Google* Disallow: User-agent: Googlebot Disallow: User-agent: Mozilla/3.0 (compatible;miner;mailto:miner@miner.com.br) Disallow: User-agent: WebFerret Disallow: User-agent: Due to a deficiency in Java it's not currently possible to set the User-agent. Disallow: User-agent: no Disallow: User-agent: 'Ahoy! The Homepage Finder' Disallow: User-agent: Arachnophilia Disallow: User-agent: ArchitextSpider Disallow: User-agent: ASpider/0.09 Disallow: User-agent: AURESYS/1.0 Disallow: User-agent: BackRub/*.* Disallow: User-agent: Big Brother Disallow: User-agent: BlackWidow Disallow: User-agent: BSpider/1.0 libwww-perl/0.40 Disallow: User-agent: CACTVS Chemistry Spider Disallow: User-agent: Digimarc CGIReader/1.0 Disallow: User-agent: Checkbot/x.xx LWP/5.x Disallow: User-agent: CMC/0.01 Disallow: User-agent: combine/0.0 Disallow: User-agent: conceptbot/0.3 Disallow: User-agent: root/0.1 Disallow: User-agent: CS-HKUST-IndexServer/1.0 Disallow: User-agent: CyberSpyder/2.1 Disallow: User-agent: Deweb/1.01 Disallow: User-agent: DragonBot/1.0 libwww/5.0 Disallow: User-agent: EIT-Link-Verifier-Robot/0.2 Disallow: User-agent: Emacs-w3/v[0-9\.]+ Disallow: User-agent: EMC Spider Disallow: User-agent: explorersearch Disallow: User-agent: Explorer Disallow: User-agent: FelixIDE/1.0 Disallow: User-agent: Hazel's Ferret Web hopper, Disallow: User-agent: ESIRover v1.0 Disallow: User-agent: fido/0.9 Harvest/1.4.pl2 Disallow: User-agent: Hämähäkki/0.2 Disallow: User-agent: KIT-Fireball/2.0 libwww/5.0a Disallow: User-agent: Fish-Search-Robot Disallow: User-agent: Mozilla/2.0 (compatible fouineur v2.0; fouineur.9bit.qc.ca) Disallow: User-agent: Robot du CRIM 1.0a Disallow: User-agent: Freecrawl Disallow: User-agent: FunnelWeb-1.0 Disallow: User-agent: gcreep/1.0 Disallow: User-agent: ??? Disallow: User-agent: GetURL.rexx v1.05 Disallow: User-agent: Golem/1.1 Disallow: User-agent: Gromit/1.0 Disallow: User-agent: Gulliver/1.1 Disallow: User-agent: yes Disallow: User-agent: AITCSRobot/1.1 Disallow: User-agent: wired-digital-newsbot/1.5 Disallow: User-agent: htdig/3.0b3 Disallow: User-agent: HTMLgobble v2.2 Disallow: User-agent: IBM_Planetwide, Disallow: User-agent: gestaltIconoclast/1.0 libwww-FM/2.17 Disallow: User-agent: INGRID/0.1 Disallow: User-agent: IncyWincy/1.0b1 Disallow: User-agent: Informant Disallow: User-agent: InfoSeek Robot 1.0 Disallow: User-agent: Infoseek Sidewinder Disallow: User-agent: InfoSpiders/0.1 Disallow: User-agent: inspectorwww/1.0 http://www.greenpac.com/inspectorwww.html Disallow: User-agent: 'IAGENT/1.0' Disallow: User-agent: IsraeliSearch/1.0 Disallow: User-agent: JCrawler/0.2 Disallow: User-agent: Jeeves v0.05alpha (PERL, LWP, lglb@doc.ic.ac.uk) Disallow: User-agent: Jobot/0.1alpha libwww-perl/4.0 Disallow: User-agent: JoeBot, Disallow: User-agent: JubiiRobot Disallow: User-agent: jumpstation Disallow: User-agent: Katipo/1.0 Disallow: User-agent: KDD-Explorer/0.1 Disallow: User-agent: KO_Yappo_Robot/1.0.4(http://yappo.com/info/robot.html) Disallow: User-agent: LabelGrab/1.1 Disallow: User-agent: LinkWalker Disallow: User-agent: logo.gif crawler Disallow: User-agent: Lycos/x.x Disallow: User-agent: Lycos_Spider_(T-Rex) Disallow: User-agent: Magpie/1.0 Disallow: User-agent: MediaFox/x.y Disallow: User-agent: MerzScope Disallow: User-agent: NEC-MeshExplorer Disallow: User-agent: MOMspider/1.00 libwww-perl/0.40 Disallow: User-agent: Monster/vX.X.X -$TYPE ($OSTYPE) Disallow: User-agent: Motor/0.2 Disallow: User-agent: MuscatFerret Disallow: User-agent: MwdSearch/0.1 Disallow: User-agent: NetCarta CyberPilot Pro Disallow: User-agent: NetMechanic Disallow: User-agent: NetScoop/1.0 libwww/5.0a Disallow: User-agent: NHSEWalker/3.0 Disallow: User-agent: Nomad-V2.x Disallow: User-agent: NorthStar Disallow: User-agent: Occam/1.0 Disallow: User-agent: HKU WWW Robot, Disallow: User-agent: Orbsearch/1.0 Disallow: User-agent: PackRat/1.0 Disallow: User-agent: Patric/0.01a Disallow: User-agent: Peregrinator-Mathematics/0.7 Disallow: User-agent: Duppies Disallow: User-agent: Pioneer Disallow: User-agent: PGP-KA/1.2 Disallow: User-agent: Resume Robot Disallow: User-agent: Road Runner: ImageScape Robot (lim@cs.leidenuniv.nl) Disallow: User-agent: Robbie/0.1 Disallow: User-agent: ComputingSite Robi/1.0 (robi@computingsite.com) Disallow: User-agent: Roverbot Disallow: User-agent: SafetyNet Robot 0.1, Disallow: User-agent: Scooter/1.0 Disallow: User-agent: not available Disallow: User-agent: Senrigan/xxxxxx Disallow: User-agent: SG-Scout Disallow: User-agent: Shai'Hulud Disallow: User-agent: SimBot/1.0 Disallow: User-agent: Open Text Site Crawler V1.0 Disallow: User-agent: SiteTech-Rover Disallow: User-agent: Slurp/2.0 Disallow: User-agent: ESISmartSpider/2.0 Disallow: User-agent: Snooper/b97_01 Disallow: User-agent: Solbot/1.0 LWP/5.07 Disallow: User-agent: Spanner/1.0 (Linux 2.0.27 i586) Disallow: User-agent: Mozilla/3.0 (Black Widow v1.1.0; Linux 2.0.27; Dec 31 1997 12:25:00 Disallow: User-agent: Tarantula/1.0 Disallow: User-agent: tarspider Disallow: User-agent: dlw3robot/x.y (in TclX by http://hplyot.obspm.fr/~dl/) Disallow: User-agent: Templeton/ Disallow: User-agent: TitIn/0.2 Disallow: User-agent: TITAN/0.1 Disallow: User-agent: UCSD-Crawler Disallow: User-agent: urlck/1.2.3 Disallow: User-agent: Valkyrie/1.0 libwww-perl/0.40 Disallow: User-agent: Victoria/1.0 Disallow: User-agent: vision-search/3.0' Disallow: User-agent: VWbot_K/4.2 Disallow: User-agent: w3index Disallow: User-agent: W3M2/x.xxx Disallow: User-agent: WWWWanderer v3.0 Disallow: User-agent: WebCopy/ Disallow: User-agent: WebCrawler/3.0 Robot libwww/5.0a Disallow: User-agent: WebFetcher/0.8, Disallow: User-agent: weblayers/0.0 Disallow: User-agent: WebLinker/0.0 libwww-perl/0.1 Disallow: User-agent: WebMoose/0.0.0000 Disallow: User-agent: Digimarc WebReader/1.2 Disallow: User-agent: webs@recruit.co.jp Disallow: User-agent: webvac/1.0 Disallow: User-agent: webwalk Disallow: User-agent: WebWalker/1.10 Disallow: User-agent: WebWatch Disallow: User-agent: w3mir Disallow: User-agent: WWWC/0.25 (Win95) Disallow: User-agent: none Disallow: User-agent: XGET/0.7 Disallow: User-agent: Nederland.zoek Disallow: User-agent: BizBot04 kirk.overleaf.com Disallow: User-agent: HappyBot (gserver.kw.net) Disallow: User-agent: CaliforniaBrownSpider Disallow: User-agent: EI*Net/0.1 libwww/0.1 Disallow: User-agent: Ibot/1.0 libwww-perl/0.40 Disallow: User-agent: Merritt/1.0 Disallow: User-agent: StatFetcher/1.0 Disallow: User-agent: TeacherSoft/1.0 libwww/2.17 Disallow: User-agent: WWW Collector Disallow: User-agent: processor/0.0ALPHA libwww-perl/0.20 Disallow: User-agent: wobot/1.0 from 206.214.202.45 Disallow: User-agent: Libertech-Rover www.libertech.com? Disallow: User-agent: WhoWhere Robot Disallow: User-agent: ITI Spider Disallow: User-agent: MyCNNSpider Disallow: User-agent: SummyCrawler Disallow: User-agent: OGspider Disallow: User-agent: linklooker Disallow: User-agent: CyberSpyder (amant@www.cyberspyder.com) Disallow: User-agent: SlowBot Disallow: User-agent: heraSpider Disallow: User-agent: Surfbot Disallow: User-agent: Bizbot003 Disallow: User-agent: WebWalker Disallow: User-agent: SandBot Disallow: User-agent: EnigmaBot Disallow: User-agent: spyder3.microsys.com Disallow: User-agent: www.freeloader.com. Disallow: User-agent: METAGOPHER Disallow: # disallow section User-agent: BecomeBot Disallow: / User-agent: Nutch Disallow: / User-agent: Jetbot/1.0 Disallow: / User-agent: Jetbot Disallow: / User-agent: AskJeeves Disallow: / User-agent: Teoma Disallow: / User-agent: Jeeves Disallow: / User-agent: WebVac Disallow: / User-agent: Stanford Disallow: / User-agent: Stanford CompSciClub Disallow: / User-agent: Stanford CompClub Disallow: / User-agent: Stanford Spiderboys Disallow: / User-agent: scooter Disallow: / User-agent: naver Disallow: / User-agent: dumbot Disallow: / User-agent: Hatena Antenna Disallow: / User-agent: grub-client Disallow: / User-agent: grub Disallow: / User-agent: looksmart Disallow: / User-agent: WebZip Disallow: / User-agent: larbin Disallow: / User-agent: b2w/0.1 Disallow: / User-agent: Copernic Disallow: / User-agent: psbot Disallow: / User-agent: Python-urllib Disallow: / User-agent: URL_Spider_Pro Disallow: / User-agent: CherryPicker Disallow: / User-agent: EmailCollector Disallow: / User-agent: EmailSiphon Disallow: / User-agent: WebBandit Disallow: / User-agent: EmailWolf Disallow: / User-agent: ExtractorPro Disallow: / User-agent: CopyRightCheck Disallow: / User-agent: Crescent Disallow: / User-agent: SiteSnagger Disallow: / User-agent: ProWebWalker Disallow: / User-agent: CheeseBot Disallow: / User-agent: LNSpiderguy Disallow: / User-agent: Mozilla Disallow: / User-agent: mozilla Disallow: / User-agent: mozilla/3 Disallow: / User-agent: mozilla/4 Disallow: / User-agent: mozilla/5 Disallow: / User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows NT) 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 XP) Disallow: / User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows 2000) Disallow: / User-agent: ia_archiver Disallow: / User-agent: ia_archiver/1.6 Disallow: / User-agent: Alexibot Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: Stanford Comp Sci Disallow: / User-agent: MIIxpc Disallow: / User-agent: Telesoft Disallow: / User-agent: Website Quester Disallow: / User-agent: moget/2.1 Disallow: / User-agent: WebZip/4.0 Disallow: / User-agent: WebStripper Disallow: / User-agent: WebSauger Disallow: / User-agent: WebCopier Disallow: / User-agent: NetAnts Disallow: / User-agent: Mister PiX Disallow: / User-agent: WebAuto Disallow: / User-agent: TheNomad Disallow: / User-agent: WWW-Collector-E Disallow: / User-agent: RMA Disallow: / User-agent: libWeb/clsHTTP Disallow: / User-agent: asterias Disallow: / User-agent: httplib Disallow: / User-agent: turingos Disallow: / User-agent: spanner Disallow: / User-agent: InfoNaviRobot Disallow: / User-agent: Harvest/1.5 Disallow: / User-agent: Bullseye/1.0 Disallow: / User-agent: Mozilla/4.0 (compatible; BullsEye; Windows 95) Disallow: / User-agent: Crescent Internet ToolPak HTTP OLE Control v.1.0 Disallow: / User-agent: CherryPickerSE/1.0 Disallow: / User-agent: CherryPickerElite/1.0 Disallow: / User-agent: WebBandit/3.50 Disallow: / User-agent: NICErsPRO Disallow: / User-agent: Microsoft URL Control - 5.01.4511 Disallow: / User-agent: DittoSpyder Disallow: / User-agent: Foobot Disallow: / User-agent: WebmasterWorldForumBot Disallow: / User-agent: SpankBot Disallow: / User-agent: BotALot Disallow: / User-agent: lwp-trivial/1.34 Disallow: / User-agent: lwp-trivial Disallow: / User-agent: http://www.WebmasterWorld.com bot Disallow: / User-agent: BunnySlippers Disallow: / User-agent: Microsoft URL Control - 6.00.8169 Disallow: / User-agent: URLy Warning Disallow: / User-agent: cosmos Disallow: / User-agent: moget Disallow: / User-agent: hloader Disallow: / User-agent: humanlinks Disallow: / User-agent: LinkextractorPro Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Mata Hari Disallow: / User-agent: LexiBot Disallow: / User-agent: Web Image Collector Disallow: / User-agent: The Intraformant Disallow: / User-agent: True_Robot/1.0 Disallow: / User-agent: True_Robot Disallow: / User-agent: BlowFish/1.0 Disallow: / User-agent: http://www.SearchEngineWorld.com bot Disallow: / User-agent: JennyBot Disallow: / User-agent: MIIxpc/4.2 Disallow: / User-agent: BuiltBotTough Disallow: / User-agent: ProPowerBot/2.14 Disallow: / User-agent: BackDoorBot/1.0 Disallow: / User-agent: toCrawl/UrlDispatcher Disallow: / User-agent: WebEnhancer Disallow: / User-agent: suzuran Disallow: / User-agent: VCI WebViewer VCI WebViewer Win32 Disallow: / User-agent: VCI Disallow: / User-agent: Szukacz/1.4 Disallow: / User-agent: QueryN Metasearch Disallow: / User-agent: Openfind data gathere Disallow: / User-agent: Openfind Disallow: / User-agent: Xenu's Link Sleuth 1.1c Disallow: / User-agent: Xenu's Disallow: / User-agent: Zeus Disallow: / User-agent: RepoMonkey Bait & Tackle/v1.01 Disallow: / User-agent: RepoMonkey Disallow: / User-agent: Microsoft URL Control Disallow: / User-agent: Openbot Disallow: / User-agent: URL Control Disallow: / User-agent: Zeus Link Scout Disallow: / User-agent: Zeus 32297 Webster Pro V2.9 Win32 Disallow: / User-agent: Webster Pro Disallow: / User-agent: EroCrawler Disallow: / User-agent: LinkScan/8.1a Unix Disallow: / User-agent: Keyword Density/0.9 Disallow: / User-agent: Kenjin Spider Disallow: / User-agent: Iron33/1.0.2 Disallow: / User-agent: Bookmark search tool Disallow: / User-agent: GetRight/4.2 Disallow: / User-agent: FairAd Client Disallow: / User-agent: Gaisbot Disallow: / User-agent: Aqua_Products Disallow: / User-agent: Radiation Retriever 1.1 Disallow: / User-agent: WebmasterWorld Extractor Disallow: / User-agent: Flaming AttackBot Disallow: / User-agent: Oracle Ultra Search Disallow: / User-agent: MSIECrawler Disallow: / User-agent: PerMan Disallow: / User-agent: searchpreview Disallow: / User-agent: sootle Disallow: / User-agent: es Disallow: / User-agent: Enterprise_Search/1.0 Disallow: / User-agent: Enterprise_Search Disallow: / User-agent: MSRBOT Disallow: /