# # 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/wc/robots.html # # For syntax checking, see: # http://www.sxw.org.uk/computing/robots/check.html User-agent: dotbot User-agent: DotBot User-agent: DotBot/1.1 User-agent: Aboundex User-agent: 80legs User-agent: 360Spider User-agent: Java User-agent: Cogentbot User-agent: Alexibot User-agent: asterias User-agent: attach User-agent: BackDoorBot User-agent: BackWeb User-agent: Bandit User-agent: BatchFTP User-agent: Bigfoot User-agent: Black.Hole User-agent: BlackWidow User-agent: BlowFish User-agent: BotALot User-agent: Buddy User-agent: BuiltBotTough User-agent: Bullseye User-agent: BunnySlippers User-agent: Cegbfeieh User-agent: CheeseBot User-agent: CherryPicker User-agent: ChinaClaw User-agent: Collector User-agent: Copier User-agent: CopyRightCheck User-agent: cosmos User-agent: Crescent User-agent: Custo User-agent: AIBOT User-agent: DISCo User-agent: DIIbot User-agent: DittoSpyder User-agent: Download Demon User-agent: Download Devil User-agent: Download Wonder User-agent: dragonfly User-agent: Drip User-agent: eCatch User-agent: EasyDL User-agent: ebingbong User-agent: EirGrabber User-agent: EmailCollector User-agent: EmailSiphon User-agent: EmailWolf User-agent: EroCrawler User-agent: Exabot User-agent: Express WebPictures User-agent: Extractor User-agent: EyeNetIE User-agent: Foobot User-agent: flunky User-agent: FrontPage User-agent: Go-Ahead-Got-It User-agent: gotit User-agent: GrabNet User-agent: Grafula User-agent: Harvest User-agent: hloader User-agent: HMView User-agent: HTTrack User-agent: humanlinks User-agent: IlseBot User-agent: Image Stripper User-agent: Image Sucker User-agent: Indy Library User-agent: InfoNaviRobot User-agent: InfoTekies User-agent: Intelliseek User-agent: InterGET User-agent: Internet Ninja User-agent: Iria User-agent: Jakarta User-agent: JennyBot User-agent: JetCar User-agent: JOC User-agent: JustView User-agent: Jyxobot User-agent: Kenjin.Spider User-agent: Keyword.Density User-agent: larbin User-agent: LexiBot User-agent: lftp User-agent: libWeb/clsHTTP User-agent: likse User-agent: LinkextractorPro User-agent: LinkScan/8.1a.Unix User-agent: LNSpiderguy User-agent: LinkWalker User-agent: lwp-trivial User-agent: LWP::Simple User-agent: Magnet User-agent: Mag-Net User-agent: MarkWatch User-agent: Mass Downloader User-agent: Mata.Hari User-agent: Memo User-agent: MIDown tool User-agent: MIIxpc User-agent: Mirror User-agent: Missigua Locator User-agent: Mister PiX User-agent: moget User-agent: Mozilla/3.Mozilla/2.01 User-agent: Mozilla.*NEWT User-agent: NAMEPROTECT User-agent: Navroad User-agent: NearSite User-agent: NetAnts User-agent: Netcraft User-agent: NetMechanic User-agent: NetSpider User-agent: Net Vampire User-agent: NetZIP User-agent: NextGenSearchBot User-agent: NG User-agent: NICErsPRO User-agent: niki-bot User-agent: NimbleCrawler User-agent: Ninja User-agent: NPbot User-agent: Octopus User-agent: Offline Explorer User-agent: Offline Navigator User-agent: Openfind User-agent: OutfoxBot User-agent: PageGrabber User-agent: Papa Foto User-agent: pavuk User-agent: pcBrowser User-agent: PHP version tracker User-agent: Pockey User-agent: ProPowerBot/2.14 User-agent: ProWebWalker User-agent: psbot User-agent: Pump User-agent: QueryN.Metasearch User-agent: RealDownload User-agent: Reaper User-agent: Recorder User-agent: ReGet User-agent: RepoMonkey User-agent: RMA User-agent: Siphon User-agent: SiteSnagger User-agent: SlySearch User-agent: SmartDownload User-agent: Snake User-agent: Snapbot User-agent: Snoopy User-agent: sogou User-agent: SpaceBison User-agent: SpankBot User-agent: spanner User-agent: Sqworm User-agent: Stripper User-agent: Sucker User-agent: SuperBot User-agent: SuperHTTP User-agent: Surfbot User-agent: suzuran User-agent: Szukacz/1.4 User-agent: tAkeOut User-agent: Teleport User-agent: Telesoft User-agent: TurnitinBot/1.5 User-agent: The.Intraformant User-agent: TheNomad User-agent: TightTwatBot User-agent: Titan User-agent: True_Robot User-agent: turingos User-agent: TurnitinBot User-agent: URLy.Warning User-agent: Vacuum User-agent: VCI User-agent: VoidEYE User-agent: Web Image Collector User-agent: Web Sucker User-agent: WebAuto User-agent: WebBandit User-agent: Webclipping.com User-agent: WebCopier User-agent: WebEMailExtrac.* User-agent: WebEnhancer User-agent: WebFetch User-agent: WebGo IS User-agent: Web.Image.Collector User-agent: WebLeacher User-agent: WebmasterWorldForumBot User-agent: WebReaper User-agent: WebSauger User-agent: Website eXtractor User-agent: Website Quester User-agent: Webster User-agent: WebStripper User-agent: WebWhacker User-agent: WebZIP User-agent: Whacker User-agent: Widow User-agent: WISENutbot User-agent: WWWOFFLE User-agent: WWW-Collector-E User-agent: Xaldon User-agent: Xenu User-agent: Zeus User-agent: ZmEu User-agent: Zyborg User-agent: Baiduspider Disallow: / User-agent: * Crawl-delay: 10 # CSS, JS, Images Allow: /misc/*.css$ Allow: /misc/*.css? Allow: /misc/*.js$ Allow: /misc/*.js? Allow: /misc/*.gif Allow: /misc/*.jpg Allow: /misc/*.jpeg Allow: /misc/*.png Allow: /modules/*.css$ Allow: /modules/*.css? Allow: /modules/*.js$ Allow: /modules/*.js? Allow: /modules/*.gif Allow: /modules/*.jpg Allow: /modules/*.jpeg Allow: /modules/*.png 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: /themes/*.css$ Allow: /themes/*.css? Allow: /themes/*.js$ Allow: /themes/*.js? Allow: /themes/*.gif Allow: /themes/*.jpg Allow: /themes/*.jpeg Allow: /themes/*.png Allow: /themes/*.svg Allow: /themes/*.ttf Allow: /themes/*.woff Allow: /themes/dcine/images/*.png Allow: /themes/dcine/images/*.jpg Allow: /themes/dcine/images/*.svg # Directories Disallow: /includes/ Disallow: /misc/ Disallow: /profiles/ Disallow: /scripts/ Disallow: /themes/ # Files Disallow: /CHANGELOG.txt Disallow: /cron.php Disallow: /INSTALL.mysql.txt Disallow: /INSTALL.pgsql.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: /logout Disallow: /node/add Disallow: /?q=node/ Disallow: /node/ Disallow: /node$ Disallow: /user/register Disallow: /user/password Disallow: /user/login Disallow: /category/ Disallow: /dcine2/ Disallow: /dcine3/ Disallow: /dcine-nuevo/ Disallow: /ronda-de-votaciones Disallow: /usuarios Disallow: /wordpress2/ Disallow: /debates/ Disallow: /donostiablog/ Disallow: /casasdemadera/ Disallow: /casasdemadera Disallow: /asele/ Disallow: /asur/ Disallow: /aref2/ Disallow: /tuctucmusic/ Disallow: /grados3/ Disallow: /masters/ Disallow: /masters2/ Disallow: /blog/ Disallow: /petit-comite/ Disallow: /catedra/ Disallow: /aref/ Disallow: /cache/ Disallow: /category/* Disallow: /taxonomy/* Disallow: /valparaiso1/ Disallow: /content/* Disallow: /outbound # Paths (no clean URLs) Disallow: /?q=admin Disallow: /?q=comment/reply Disallow: /?q=logout Disallow: /?q=node/add Disallow: /?q=search Disallow: /?q=user/password Disallow: /?q=user/register Disallow: /?q=user/login Disallow: /*sort= Disallow: /*order= Disallow: /*/feed$ Disallow: /*/track$ # Extras on drupal.org # no access for table sorting paths or any paths that have parameters Disallow: /*?sort Disallow: /*&sort Disallow: /*?solrsort Disallow: /*&solrsort Disallow: /?quicktabs # no access to profiles that are often targeted by spammers. Disallow: /profile/interest/ Disallow: /profile/industries/ Disallow: /profile/companies/ # Disallow bogus aggregator pages Disallow: /aggregator # Disallow project search Disallow: /project/issues/search/ Disallow: /project/issues/ # No access for quicktabs in the URL Disallow: /*?quicktabs_* Disallow: /*&quicktabs_* Disallow: /*& # Sitemap Sitemap: https://www.dcine.org/sitemap.xml Disallow: /boost_stats.php User-agent: SemrushBot Disallow: User-agent: SemrushBot-SA Disallow: