# /robots.txt for http://www.webhostingsizzle.com/ # Search engine: "norobots.html" # Admin - Elijah (mhidelivers.com/feedback) # disallow a bunch of ill-behaved user agents (doubt this will deter them...) User-agent: TurnitinBot Disallow: / User-agent: ExtractorPro Disallow: / User-agent: EmailSiphon Disallow: / User-agent: EmailWolf Disallow: / User-agent: CherryPickerSE/1.0 Disallow: / User-agent: CherryPickerElite/1.0 Disallow: / User-agent: EmailCollector/1.0 Disallow: / User-agent: EmailWolf 1.00 Disallow: / User-agent: Crescent Internet ToolPak HTTP OLE Control v.1.0 Disallow: / User-agent: EmailSiphon Disallow: / User-agent: Mozilla/2.0 (compatible; NEWT ActiveX; Win32) Disallow: / # let google's ad crawler do its thing User-agent: Mediapartners-Google* Disallow: Disallow: /rate # dynamic Disallow: /cgi-bin # dynamic Disallow: /search # dynamic # by default User-agent: * Disallow: /ccrd # not useful to spiders Disallow: /click # not useful to spiders Disallow: /hc # dynamic Disallow: /rate # dynamic Disallow: /subbatch # dynamic Disallow: /vadd # dynamic Disallow: /vsearch # dynamic Disallow: /search # dynamic Disallow: /vedit # dynamic Disallow: /vdelete # dynamic Disallow: /cgi-bin # dynamic Disallow: /images/ # useless images Disallow: /icons/ # useless images Disallow: /concerts/ # deprecated URL form Disallow: /conferences # defunct #Examples #The following example "/robots.txt" file specifies that no robots should visit any URL starting with "/cyberworld/map/" or "/tmp/", or /foo.html: #------------------------------------------------------------------------ # robots.txt for http://www.example.com/ #User-agent: * #Disallow: /cyberworld/map/ # This is an infinite virtual URL space #Disallow: /tmp/ # these will soon disappear #Disallow: /foo.html #------------------------------------------------------------------------ #This example "/robots.txt" file specifies that no robots should visit any URL starting with "/cyberworld/map/", except the robot called "cybermapper": #------------------------------------------------------------------------ # robots.txt for http://www.example.com/ #User-agent: * #Disallow: /cyberworld/map/ # This is an infinite virtual URL space ## Cybermapper knows where to go. #User-agent: cybermapper #Disallow: #------------------------------------------------------------------------ #This example indicates that no robots should visit this site further: #------------------------------------------------------------------------ ## go away #User-agent: * #Disallow: /