# robots.txt for http://www.wasteconsulting.com/ User-agent: googlebot disallow: /exchange.htm disallow: /form.asp User-agent: Slurp disallow: /exchange.htm disallow: /form.asp User-agent: msnbot/1.1 disallow: /exchange.htm disallow: /form.asp # Bad Bots User-agent: NPBot Disallow: / User-agent: TurnitinBot Disallow: / User-agent: EmailSiphon Disallow: / User-agent: EmailWolf Disallow: / User-agent: ExtractorPro Disallow: / User-agent: CherryPicker Disallow: / User-agent: NICErsPRO Disallow: / User-agent: Teleport Disallow: / User-agent: EmailCollector 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: 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: larbin Disallow: / User-agent: libwww Disallow: / User-agent: ZyBORG Disallow: / User-agent: Download Ninja Disallow: / User-agent: grub-client Disallow: / # # Doesn't follow robots.txt anyway, but... # User-agent: k2spider Disallow: / User-agent: NPBot Disallow: / # A capture bot, downloads gazillions of pages with no public benefit # http://www.webreaper.net/ User-agent: WebReaper Disallow: /