# $Id: robots.txt,v 1.7.2.1 2007/03/23 18:57:07 drumm Exp $ # # 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 # Disallow BAD BOTS User-agent: http://www.almaden.ibm.com/cs/crawler Disallow: / User-agent: NPBot Disallow: / User-agent: Linguee Bot Disallow: / User-agent: TurnitinBot Disallow: / User-agent: twiceler Disallow: / User-agent: EmailCollector Disallow: / User-agent: EmailWolf Disallow: / User-agent: CopyRightCheck Disallow: / User-agent: Black Hole Disallow: / User-agent: Titan Disallow: / User-agent: NetMechanic Disallow: / User-agent: CherryPicker Disallow: / User-agent: EmailSiphon Disallow: / User-agent: WebBandit Disallow: / User-agent: Crescent Disallow: / User-agent: NICErsPRO Disallow: / User-agent: SiteSnagger Disallow: / User-agent: ProWebWalker Disallow: / User-agent: CheeseBot Disallow: / User-agent: ia_archiver Disallow: / User-agent: ia_archiver/1.6 Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: Wget Disallow: / User-agent: MIIxpc Disallow: / User-agent: Telesoft Disallow: / User-agent: Website Quester Disallow: / User-agent: WebZip Disallow: / User-agent: moget/2.1 Disallow: / User-agent: WebZip/4.0 Disallow: / User-agent: Mister PiX Disallow: / User-agent: WebStripper Disallow: / User-agent: WebSauger Disallow: / User-agent: WebCopier Disallow: / User-agent: NetAnts 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: DittoSpyder Disallow: / User-agent: SpankBot Disallow: / User-agent: BotALot Disallow: / User-agent: lwp-trivial/1.34 Disallow: / User-agent: lwp-trivial Disallow: / User-agent: Wget/1.6 Disallow: / User-agent: BunnySlippers Disallow: / User-agent: URLy Warning Disallow: / User-agent: Wget/1.5.3 Disallow: / User-agent: LinkWalker 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: 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: TightTwatBot 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: 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: Kenjin Spider Disallow: / User-agent: Keyword Density/0.9 Disallow: / User-agent: Cegbfeieh Disallow: / User-agent: SurveyBot Disallow: / User-agent: duggmirror Disallow: / User-agent: Yandex Disallow: / User-agent: * # Crawl-delay: 10 # Directories Disallow: /database/ Disallow: /includes/ Disallow: /misc/ Disallow: /modules/ Disallow: /sites/ Disallow: /themes/ Disallow: /scripts/ Disallow: /updates/ Disallow: /profiles/ # Files Disallow: /xmlrpc.php Disallow: /cron.php Disallow: /update.php Disallow: /install.php Disallow: /INSTALL.txt Disallow: /INSTALL.mysql.txt Disallow: /INSTALL.pgsql.txt Disallow: /CHANGELOG.txt Disallow: /MAINTAINERS.txt Disallow: /LICENSE.txt Disallow: /UPGRADE.txt # Paths (clean URLs) Disallow: /admin/ Disallow: /aggregator Disallow: /aggregator/ Disallow: /comment/reply/ Disallow: /contact Disallow: /logout Disallow: /node/add Disallow: /search/ Disallow: /users/ Disallow: /user/register Disallow: /user/password Disallow: /user/login # Site specific Disallow: /files/thebailouteconomy.com/ # Other special Disallows per site advise at "tips.webdesign10.com/robots-txt-and-drupal" Disallow: /user$ Disallow: /search$ Disallow: /*/feed$ # Paths (no clean URLs) Disallow: /?q=admin/ Disallow: /?q=aggregator/ Disallow: /?q=comment/reply/ Disallow: /?q=contact/ Disallow: /?q=logout/ Disallow: /?q=node/add/ Disallow: /?q=search/ Disallow: /?q=user/password/ Disallow: /?q=user/register/ Disallow: /?q=user/login/ # Extras on drupal.org # no access for table sorting paths or any paths that have parameters. Disallow: /*sort=