# $Id: robots.txt $ # # 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. # # This file will be ignored unless it is at the root of your host: # Used: http://example.com/robots.txt # Ignored: http://example.com/site/robots.txt # # 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: /analyse/ Disallow: /cgi-bin/ Disallow: /css/ Disallow: /FCKeditor/ Disallow: /flashMap/ Disallow: /framesets/ Disallow: /htmleditor/ Disallow: /images/ Disallow: /img/ Disallow: /inhalt/ Disallow: /js/ Disallow: /META-INF/ Disallow: /WEB-INF/ # Files Disallow: /crossdomain.xml Disallow: /.dirdoc.xml Disallow: /foo.jsp Disallow: /index.gsp Disallow: /index_jn3.jsp Disallow: /testPlattform.gsp Disallow: /testQuickUploader.jsp Disallow: /toto-aef.jsp # Paths (clean URLs) Disallow: /admin/ Disallow: /admin/login/ Disallow: /admin/login.do Disallow: /cgi-bin/ Disallow: /htmlEditor/ Disallow: /internat/ Disallow: /international/ Disallow: /public/ Disallow: /public/search? Disallow: /public/xml/ Disallow: /public/xmlxslt/ Disallow: /search/ Disallow: /wiki/ Disallow: /xstatisch/ # Paths (no clean URLs) Disallow: /search.do? Disallow: /statlog?