# robots.txt # (C)2007 ageulen.de # 05jun07 # updated 07.10.08 # 270809 ueberwachen User-agent: wwwster Disallow: / User-agent: spbot Disallow: / User-agent: ia_archiver Disallow: / User-agent: plukkie Disallow: / # 05.06.09 E-Mail-Robot Crawler User-agent: rdfbot Disallow: / #addes 25.02.2009 User-agent: ScoutJet Disallow: / User-agent: Exabot Disallow: / User-agent: dotbot Disallow: / User-agent: Nutch Disallow: / # Added 08.10.08 User-agent: psbot/0.1 Disallow: / # Googlebot-Image hat es wohl nicht nötig, nach der robots.txt zu fragen? # Der Vollständigkeit halber trotzdem eingetragen. # Eventuell wertet Googlebot aus??? User-agent: Googlebot-Image/1.0 Disallow: / # Ein paar Crawler drosseln User-agent: Googlebot Disallow: /bot_falle/ Disallow: /fileadmin/ Disallow: /uploads/ Disallow: /typo3/ Disallow: /typo3conf/ Disallow: /typo3temp/ Crawl-delay: 86400 # Yahoo! Slurp drosseln User-agent: Slurp # Crawl-delay: 86400 # 600 Sek = 10 min Disallow: / # wegen Missachtung der robots.txt / Sperrbereich ! # msnbot und livebot (gleiche IP) User-agent: msnbot #Crawl-delay: 86400 # 07.05.08 02.01:15 bot_falle # msnbot beachtet robots.txt nicht. Deshalb gesperrt ueber Bot-Falle Disallow: / User-agent: infometrics-bot Disallow: / User-agent: livebot Disallow: / # disallow stress test User-agent: stress-agent Disallow: / # new and unknown crawlers User-agent: CentiverseBot Disallow: / User-agent: WebAlta Disallow: / User-agent: gonzo* Disallow: / User-agent: DepSpid Disallow: / User-agent: DepSpid/5.25 Disallow: / User-agent: OpenISearch Disallow: / User-agent: eventax/1.3 Disallow: / # Educational Crawler , student, papers, homework # to be observed ! ! ! ! User-agent: TurnitinBot/2.1 Disallow: / User-agent: turnitinbot Disallow: / # crawlers without learning-effect (content) User-agent: Gigabot/3.0 Disallow: / User-agent: cityreview Disallow: / # Unknown robots User-agent: Jyxobot Disallow: / User-agent: Toplistbot Disallow: / User-agent: Exabot Disallow: / User-agent: VoilaBot Disallow: / User-agent: ccubee Disallow: / User-agent: ccubee/9.0 Disallow: / User-agent: ccubee/2008 Disallow: / User-agent: MJ12bot Disallow: / User-agent: WebsiteWiki Disallow: / User-agent: AboutUsBot Disallow: / # Despicable and evil robots to keep out User-agent: CazoodleBot Disallow: / User-agent: Twiceler-0.9 Disallow: / User-agent: EmailCollector Disallow: / User-agent: NaverBot 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: psbot Disallow: / User-agent: Python-urllib Disallow: / User-agent: NetMechanic Disallow: / User-agent: URL_Spider_Pro Disallow: / User-agent: CherryPicker 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: Teleport Disallow: / User-agent: TeleportPro 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: BunnySlippers Disallow: / User-agent: Microsoft URL Control - 6.00.8169 Disallow: / User-agent: URLy Warning Disallow: / User-agent: Wget/1.6 Disallow: / User-agent: Wget/1.5.3 Disallow: / User-agent: Wget 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: 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: Flaming AttackBot Disallow: / User-agent: Oracle Ultra Search Disallow: / User-agent: MSIECrawler Disallow: / User-agent: PerMan Disallow: / User-agent: searchpreview Disallow: / User-agent: Acoon-Robot Disallow: / User-agent: yacybot Disallow: / User-agent: Eurobot Disallow: / # Der Rest User-agent: * Disallow: /bot_falle/ Disallow: /bugs_falle/ Disallow: /fileadmin/ Disallow: /uploads/ Disallow: /typo3/ Disallow: /typo3conf/ Disallow: /typo3temp/