# File managed by Ansible User-agent: * Crawl-delay: 10 Sitemap: http://digital.osl.state.or.us/sitemap.xml # Directories Disallow: /includes/ Disallow: /misc/ Disallow: /modules/ Disallow: /profiles/ Disallow: /scripts/ Disallow: /themes/ # Files 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/ # Islandora disallows Disallow: /islandora/search/ Disallow: /islandora/object/*/datastream/*/download Disallow: /islandora/object/*/datastream/OCR/view Disallow: /islandora/object/*/datastream/HOCR/view Disallow: /islandora/object/*/datastream/FULL_TEXT/view # This should allow /islandora/object/namespace:pid but disallow # a crawler to get caught up in the arguments for collection view # so it doesn't crawl all the possible facets of a collection Disallow: /islandora/object/*?* Disallow: /iiif/ Disallow: /oai2 Disallow: /oai2/ Disallow: /islandora/object/*/datastream/* # Paths (no clean URLs) 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/ # Bad robots block User-agent: AhrefsBot Disallow: / User-agent: Anonymizer Disallow: / User-agent: asterias Disallow: / User-agent: Attributor Disallow: / User-agent: BackDoorBot/1.0 Disallow: / User-agent: Black Hole Disallow: / User-agent: BLEXBot Disallow: / User-agent: BlowFish/1.0 Disallow: / User-agent: Bork-edition Disallow: / User-agent: BotALot Disallow: / User-agent: BuiltBotTough Disallow: / User-agent: Bullseye/1.0 Disallow: / User-agent: BunnySlippers Disallow: / User-agent: Cegbfeieh Disallow: / User-agent: CheeseBot Disallow: / User-agent: CherryPicker Disallow: / User-agent: CherryPickerElite/1.0 Disallow: / User-agent: CherryPickerSE/1.0 Disallow: / User-agent: CopyRightCheck Disallow: / User-agent: cosmos Disallow: / User-agent: Crescent Disallow: / User-agent: Crescent Internet ToolPak HTTP OLE Control v.1.0 Disallow: / User-agent: DataCha0s Disallow: / User-agent: Deepnet Explorer Disallow: / User-agent: desktopsmiley Disallow: / User-agent: DigExt Disallow: / User-agent: DittoSpyder Disallow: / User-agent: dotbot Disallow: / User-agent: EmailCollector Disallow: / User-agent: EmailSiphon Disallow: / User-agent: EmailWolf Disallow: / User-agent: EroCrawler Disallow: / User-agent: ExtractorPro Disallow: / User-agent: feedfinder Disallow: / User-agent: Foobot Disallow: / User-agent: gamingharbor Disallow: / User-agent: Harvest/1.5 Disallow: / User-agent: heritrix Disallow: / User-agent: hloader Disallow: / User-agent: httplib Disallow: / User-agent: humanlinks Disallow: / User-agent: Indy Library Disallow: / User-agent: InfoNaviRobot Disallow: / User-agent: Jakarta Disallow: / User-agent: Java Disallow: / User-agent: JennyBot Disallow: / User-agent: juicyaccess Disallow: / User-agent: Kenjin Spider Disallow: / User-agent: Keyword Density/0.9 Disallow: / User-agent: larbin Disallow: / User-agent: LexiBot Disallow: / User-agent: libWeb/clsHTTP Disallow: / User-agent: linkdex Disallow: / User-agent: LinkextractorPro Disallow: / User-agent: LinkScan/8.1a Unix Disallow: / User-agent: LinkWalker Disallow: / User-agent: LNSpiderguy Disallow: / User-agent: lwp-trivial Disallow: / User-agent: lwp-trivial/1.34 Disallow: / User-agent: Mata Hari Disallow: / User-agent: MegaIndex Disallow: / User-agent: MegaIndex.ru Disallow: / User-agent: MegaIndex.ru/2.0 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: Missigua Disallow: / User-agent: Mister PiX Disallow: / User-agent: MJ12bot Disallow: / User-agent: mj12bot Disallow: / User-agent: moget Disallow: / User-agent: moget/2.1 Disallow: / User-agent: mozilla/4 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 95) Disallow: / User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows 98) Disallow: / User-agent: Mozilla/4.0 (compatible; MSIE 4.0; Windows ME) 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/5 Disallow: / User-agent: MRSPUTNIK Disallow: / User-agent: NetAnts Disallow: / User-agent: NICErsPRO Disallow: / User-agent: Nutch Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Openfind Disallow: / User-agent: Openfind data gathere Disallow: / User-agent: panscient Disallow: / User-agent: plaNETWORK Disallow: / User-agent: ProPowerBot/2.14 Disallow: / User-agent: ProWebWalker Disallow: / User-agent: QueryN Metasearch Disallow: / User-agent: RepoMonkey Disallow: / User-agent: RepoMonkey Bait & Tackle/v1.01 Disallow: / User-agent: RMA Disallow: / User-agent: rogerbot Disallow: / User-agent: SemrushBot Disallow: / User-agent: SiteSnagger Disallow: / User-agent: Snapbot Disallow: / User-agent: Sogou Disallow: / User-agent: SpankBot Disallow: / User-agent: spanner Disallow: / User-agent: suzuran Disallow: / User-agent: Szukacz/1.4 Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: Telesoft Disallow: / User-agent: TestiTest1 Disallow: / User-agent: The Intraformant Disallow: / User-agent: TheNomad Disallow: / User-agent: TightTwatBot Disallow: / User-agent: TinEye Disallow: / User-agent: Titan Disallow: / User-agent: toCrawl/UrlDispatcher Disallow: / User-agent: True_Robot Disallow: / User-agent: True_Robot/1.0 Disallow: / User-agent: turingos Disallow: / User-agent: TwengaBot Disallow: / User-agent: Twitturly Disallow: / User-agent: URLy Warning Disallow: / User-agent: User-Agent Disallow: / User-agent: VCI Disallow: / User-agent: VCI WebViewer VCI WebViewer Win32 Disallow: / User-agent: Viewzi Disallow: / User-agent: Web Image Collector Disallow: / User-agent: WebAuto Disallow: / User-agent: WebBandit Disallow: / User-agent: WebBandit/3.50 Disallow: / User-agent: WebCapture Disallow: / User-agent: WebCopier Disallow: / User-agent: WebEnhancer Disallow: / User-agent: WebmasterWorldForumBot Disallow: / User-agent: WebSauger Disallow: / User-agent: Website Quester Disallow: / User-agent: Webster Pro Disallow: / User-agent: WebStripper Disallow: / User-agent: WebZip Disallow: / User-agent: WebZip/4.0 Disallow: / User-agent: Wget Disallow: / User-agent: Wget/1.5.3 Disallow: / User-agent: Wget/1.6 Disallow: / User-agent: WWW-Collector-E Disallow: / User-agent: Xenu's Disallow: / User-agent: Xenu's Link Sleuth 1.1c Disallow: / User-agent: XX Disallow: / User-agent: Yandex Disallow: / User-agent: YebolBot Disallow: / User-agent: Zeus Disallow: / User-agent: Zeus 32297 Webster Pro V2.9 Win32 Disallow: /