# # robots.txt for www.palmclub.nl (based from http://en.wikipedia.org/robots.txt) # # Please note: There are a lot of pages on this site, and there are # some misbehaved spiders out there that go _way_ too fast. If you're # irresponsible, your access to the site may be blocked. # # Crawlers that are kind enough to obey, but which we'd rather not have # unless they're feeding search engines. User-agent: Baiduspider Disallow: / User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / # Some bots are known to be trouble, particularly those designed to copy # entire sites. Please obey robots.txt. User-agent: sitecheck.internetseer.com Disallow: / User-agent: Zealbot Disallow: / User-agent: MSIECrawler Disallow: / User-agent: SiteSnagger Disallow: / User-agent: WebStripper Disallow: / User-agent: WebCopier Disallow: / User-agent: Fetch Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: WebZIP Disallow: / User-agent: linko Disallow: / User-agent: HTTrack Disallow: / User-agent: Microsoft.URL.Control Disallow: / User-agent: Xenu Disallow: / User-agent: larbin Disallow: / User-agent: libwww Disallow: / User-agent: ZyBORG Disallow: / User-agent: Download Ninja 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: / # Plaatjes User-agent: Googlebot-Image Disallow: / User-agent: Yahoo-MMCrawler Disallow: / User-agent: Browsershots Disallow: # # Friendly, low-speed bots are welcome viewing article pages, but not # dynamically-generated pages please. # # Inktomi's "Slurp" can read a minimum delay between hits; if your # bot supports such a thing using the 'Crawl-delay' or another # instruction, please let us know. # User-agent: * Disallow: /admin/ Disallow: /archief/ Disallow: /beta/ Disallow: /bestuur/_gertjan/ Disallow: /bestuur/_roel/ Disallow: /bestuur/_fjodor/ Disallow: /bmailinglist/ Disallow: /cgi/ Disallow: /cms/ Disallow: /docs/ Disallow: /files/ Disallow: /front-end/ Disallow: /images/ Disallow: /phpads/ Disallow: /spinnenval/ Disallow: /test/ Disallow: /tmp/ Disallow: /usage/ Disallow: /tvgids/ Disallow: /faq_pics/ Disallow: /forums/ajax.php Disallow: /forums/attachment.php Disallow: /forums/attachments/ Disallow: /forums/avantgo.php Disallow: /forums/calendar.php Disallow: /forums/login.php Disallow: /forums/misc.php Disallow: /forums/newreply.php Disallow: /forums/newthread.php Disallow: /forums/palmthread.php Disallow: /forums/poll.php Disallow: /forums/printthread.php Disallow: /forums/private.php Disallow: /forums/register.php Disallow: /forums/report.php Disallow: /forums/reputation.php Disallow: /forums/sendmessage.php Disallow: /forums/subscription.php Disallow: /forums/threadrate.php Disallow: /forums/usercp.php Disallow: /forums/usernote.php Disallow: /forums/clientscript/ Disallow: /forums/admincp/ Disallow: /forums/modcp/ Disallow: /forums/images/ Disallow: /forums/images_nld_25/ Disallow: /forums/customavatars/ Disallow: /forums/customprofilepics/ Disallow: /forums/showpost/ Disallow: /nieuws_pics/ Disallow: /nieuws/user/ Disallow: /bestuur/gonny/trouwen/ Disallow: /bestuur/jeanpaul/trouwen/ Disallow: /garmin/garmin.php Crawl-delay: 1