# # robots.txt for severein.nl # # advertising-related bots: User-agent: Mediapartners-Google* Disallow: / # Crawlers that are kind enough to obey, but which we'd rather not have # unless they're feeding (non-image!) search engines. User-agent: asterias Disallow: / User-agent: DOC Disallow: / User-agent: Googlebot-Image Disallow: / User-agent: psbot Disallow: / User-agent: UbiCrawler Disallow: / User-agent: yahoo-blogs/v3.9 Disallow: / User-agent: yahoo-mmcrawler Disallow: / User-agent: User-agent: Zao Disallow: / # Site owners can block their web pages from being displayed as # thumbnail images in MSN Search Preview. We do. User-agent: searchpreview Disallow:/ # Some bots are known to be trouble for severein.nl, particularly those # designed to copy entire sites. This is listed alphabetically for maintenance. # Please obey robots.txt # Bots starting with A ############################################# User-agent: Accoona-AI-Agent/1.1.1 Disallow: / User-agent: Accoona-AI-Agent/1.1.2 Disallow: / User-agent: ALPHA libwww-perl/0.20 Disallow: / # Bots starting with B ############################################# User-agent: BizBot04 Disallow: / User-agent: Bizbot003 Disallow: / # Bots starting with C ############################################# User-agent: CyberSpyder Disallow: / User-agent: CaliforniaBrownSpider Disallow: / # Bots starting with D ############################################# User-agent: Download Ninja Disallow: / # Bots starting with E ############################################# User-agent: EI*Net/0.1 Disallow: / User-agent: EnigmaBot Disallow: / # Bots starting with F ############################################# User-agent: Fetch Disallow: / # Bots starting with G ############################################# User-agent: Gigabot Disallow: / User-agent: gserver.kw.net Disallow: / # Bots starting with H ############################################# User-agent: HappyBot Disallow: / User-agent: heraSpider Disallow: / User-agent: HTTrack Disallow: / # Bots starting with I ############################################# User-agent: ITI Spider Disallow: / User-agent: Ibot/1.0 Disallow: / User-agent: ibwww-perl/0.40 Disallow: / # Bots starting with J ############################################# # Bots starting with K ############################################# User-agent: kirk.overleaf.com Disallow: / # Bots starting with L ############################################# User-agent: larbin Disallow: / User-agent: libwww Disallow: / User-agent: libwww/0.1 Disallow: / User-agent: libwww/2.17 Disallow: / User-agent: Libertech-Rover Disallow: / User-agent: linklooker Disallow: / User-agent: linko Disallow: / # Bots starting with M ############################################# User-agent: Merritt/1.0 Disallow: / User-agent: Microsoft.URL.Control Disallow: / User-agent: MSIECrawler Disallow: / User-agent: MyCNNSpider Disallow: / # Bots starting with N ############################################# User-agent: Nutch Disallow: / # Bots starting with O ############################################# User-agent: Offline Explorer Disallow: / User-agent: OGspider Disallow: / # Bots starting with P ############################################# User-agent: processor/0.0 Disallow: / User-agent: psbot Disallow: / # Bots starting with Q ############################################# # Bots starting with R ############################################# User-agent: Robozilla Disallow: / # Bots starting with S ############################################# User-agent: SandBot Disallow: / User-agent: Scrubby Disallow: / User-agent: sitecheck.internetseer.com Disallow: / User-agent: SiteSnagger Disallow: / User-agent: SlowBot Disallow: / User-agent: spyder3.microsys.com Disallow: / User-agent: StatFetcher/1.0 Disallow: / User-agent: SummyCrawler Disallow: / User-agent: Surfbot Disallow: / # Bots starting with T ############################################# User-agent: TeacherSoft/1.0 Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / # Bots starting with U ############################################# # Bots starting with V ############################################# # Bots starting with W ############################################# User-agent: WebCopier Disallow: / User-agent: WebStripper Disallow: / User-agent: WebWalker Disallow: / User-agent: WebZIP Disallow: / User-agent: WhoWhere Robot Disallow: / User-agent: wobot/1.0 Disallow: / User-agent: www.freeloader.com Disallow: / User-agent: WWW Collector Disallow: / User-agent: w3index Disallow: / # Bots starting with X ############################################# User-agent: Xenu Disallow: / # Bots starting with Y ############################################# # Bots starting with Z ############################################# User-agent: Zealbot Disallow: / User-agent: ZyBORG Disallow: / # # Sorry, wget in its recursive mode is a frequent problem. # Please read the man page and use it properly; there is a # --wait option you can use to set the delay between hits, # for instance. # User-agent: wget Disallow: / # # The 'grub' distributed client has been *very* poorly behaved. # User-agent: grub-client Disallow: / # # Doesn't follow robots.txt anyway, but... # User-agent: k2spider Disallow: / # # Hits many times per second, not acceptable # http://www.nameprotect.com/botinfo.html User-agent: NPBot Disallow: / # A capture bot, downloads gazillions of pages with no public benefit # http://www.webreaper.net/ User-agent: WebReaper Disallow: / # # Friendly, low-speed bots are welcome, but not all dirs: # User-agent: * Disallow: /cgi-bin/ Disallow: /hordijk/ Disallow: /julia/ Disallow: /lem/ Disallow: /luchtfoto/ Disallow: /marktplaats/ Disallow: /snelwegenforum/ Disallow: /wegenkaarten/ Disallow: /zandstadjansen/ Disallow: /familie/ ## *at least* 2 seconds please Crawl-delay: 2