# # 09145 # robots.txt for http://www.josephs-hair.com # # 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 search engines. 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: / User-agent: Outfox Disallow: / # # Sorry, wget in its recursive mode is a frequent problem. # Please read the main 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 # support directories please. # User-agent: * Disallow: /tdi_jlmadm.asp # User-agent: * Disallow: /tdi_404.asp # User-agent: * Disallow: /tdi_hers.asp # User-agent: * Disallow: /*.txt$ # User-agent: * Disallow: /_fpclass/ # User-agent: * Disallow: /_private/ # User-agent: * Disallow: /aspnet_client/ # User-agent: * Disallow: /ASPEditor/ # User-agent: * Disallow: /ASPSpellCheck/ # # CSI User-agent: * Disallow: /csi/ # User-agent: * Disallow: /css/ # User-agent: * Disallow: /hair_salon/inc/ # # SUP User-agent: * Disallow: /sup/ans/inc/ # User-agent: * Disallow: /sup/fts/inc/ # User-agent: * Disallow: /sup/osl/inc/ # # SYS User-agent: * Disallow: /sys/air/ # User-agent: * Disallow: /sys/cbp/inc/ # User-agent: * Disallow: /sys/gen/inc/ # User-agent: * Disallow: /sys/ssl/ # # TDI User-agent: * Disallow: /tdd/ # User-agent: * Disallow: /tdg/ # User-agent: * Disallow: /tdn/ # User-agent: * Disallow: /tds/ # # SUB-DOMS User-agent: * Disallow: /tdi1_adm/ # User-agent: * Disallow: /tdi1_sup/ # User-agent: * Disallow: /tdi1_sys/ # User-agent: * Disallow: /tdi1_tdi/ # ## *at least* 1 second please. preferably more delay Crawl-delay: 1