#/** # * robots.txt # * # * refer to 'Robots Exclusion Standard RFC4' # * the use of crawlers or other automated tests on this host is forbidden for # * any path defined by 'Disallow' directives. # */ # concerns any client application User-agent: * # do not index assets as-is Disallow: /skinny/ # disallow weird piracy checks, worms & spiders Disallow: /MSADC/ Disallow: /MSOffice/ Disallow: /_vti_bin/ Disallow: /_mem_bin/ Disallow: /c/ Disallow: /d/ Disallow: /scripts/ Disallow: /%7e Disallow: %7e Disallow: /images/ # special interest rules User-agent: WebZIP User-agent: WebReaper User-agent: genieBot User-agent: aipbot User-agent: audioCrawlerBot.* User-agent: Exabot User-agent: Twiceler Disallow: / # 'protect' possibly contained e-mail addresses User-agent: EmailCollector User-agent: EmailSiphon User-agent: EmailWolf User-agent: WebEMailExtrac.* User-agent: autoemailspider Disallow: / User-agent: msnbot Crawl-Delay: 40 User-agent: Slurp Crawl-Delay: 300