#Robots.txt for Pulsus.com - by Deval Parikh # Allowed Robot to crawl pulsus.com User-agent: Googlebot Disallow: User-agent: Googlebot-Image Disallow: User-agent: MSNBot Disallow: User-agent: Teoma Disallow: User-agent: yahoo-mmcrawler Disallow: User-agent: yahoo-blogs/v3.9 Disallow: User-agent: crawl.yahoo.net Disallow: User-agent: twiceler Disallow: User-agent: htdig/3.1.6 Disallow: # Disallow directories to all robots - By default all Robots are Disallowed User-agent: * Disallow: /cgi-bin Disallow: /Article_ Disallow: /pdf Disallow: /cf Disallow: /CF Disallow: /err Disallow: /ema Disallow: /htd Disallow: /intr Disallow: /WEB-INF Disallow: /banner Crawl-delay: 5 Sitemap: http://www.pulsus.com/journals/sitemap.xml