# $Id: robots.txt,v 1.0 2008/12/10 20:24:38 dyrathror $ # # robots.txt # # This file is to prevent the crawling and indexing of certain parts # of your site by web crawlers and spiders run by sites like Yahoo! # and Google. By telling these "robots" where not to go on your site, # you save bandwidth and server resources. # # For more information about the robots.txt standard, see: # http://www.robotstxt.org/wc/robots.html # # For syntax checking, see: # http://www.sxw.org.uk/computing/robots/check.html User-agent: * Crawl-delay: 10 # Directories Disallow: /java/ Disallow: /rsschache/ Disallow: /WEB-INF/ # Files Disallow: /WEB-INF/web.xml # Paths (clean URLs) # Paths (no clean URLs) Disallow: /?r=site/news/ # Paths to disabled Pages Disallow: /?r=site/china/ Disallow: /?r=site/hosting/ Disallow: /?r=site/translation/ Disallow: /?r=site/services/