# robots.txt file for http://www.sequart.com/ # # Please note that ours is a large site, and some spiders are indexing the site far too fast. # If you wish to spider a large number of pages, please slow down using the 'Crawl-delay' or another instruction. # # Some bots are known to be trouble, particularly those designed to copy # entire sites. Please obey robots.txt. # general instructions # 1 second delay if honored User-agent: * Crawl-delay: 1 Disallow: /cgi-bin/ Disallow: /members/login.php Disallow: /members/new.php Disallow: /members/forgotten_password.php # Yahoo's crawler has given us trouble with its speed User-agent: Slurp Crawl-delay: 1 Disallow: /cgi-bin/ Disallow: /members/login.php Disallow: /members/new.php Disallow: /members/forgotten_password.php Disallow: /*? Disallow: /*.gif$ Disallow: /*.jpg$ Disallow: /*.png$ 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: / # This bot hits many times per second # http://www.nameprotect.com/botinfo.html User-agent: NPBot Disallow: / # A capture bot that downloads lots of pages with no public benefit # http://www.webreaper.net/ User-agent: WebReaper Disallow: /