# # robots.txt generated for www.isoc.lu # on 1/12/2004 # # Updated 26/7/2005 # Updated 5/9/2005 # Updated 29/5/2007 included reference to sitemap.xml SITEMAP: http://www.isoc.lu/sitemap.xml User-agent: * # All spiders should avoid # disallow all files in these directories Disallow: /cgi-bin/ Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /tag/ Disallow: /wp-content/b Disallow: /wp-content/p Disallow: /trackback/ Disallow: /*?* Disallow: */trackback/ Disallow: /wp-images/ Disallow: /wp-admin/ Disallow: /wp-config.php/ Disallow: /wp-includes/ Allow: /wp-content/uploads/ User-agent: Googlebot # disallow all files ending with these extensions Disallow: /*.php$ Disallow: /*.js$ Disallow: /*.inc$ Disallow: /*.css$ Disallow: /*.gz$ Disallow: /*.cgi$ Disallow: /*.wmv$ Disallow: /*.cgi$ Disallow: /*.xhtml$ Disallow: /*.php* Disallow: */trackback* Disallow: /*?* Disallow: /wp-* Allow: /wp-content/uploads/ # allow google image bot to search all images User-agent: Googlebot-Image Allow: /* User-agent: Googlebot-Image Allow: / User-agent: Googlebot-Mobile Allow: / User-agent: ia_archiver-web.archive.org Allow: / User-agent: duggmirror Disallow: / User-agent: Spock* Disallow: * User-agent: * Disallow: /Templates/ User-agent: * Disallow: /js/ User-agent: * Disallow: /styles/ User-agent: * Disallow: /rss/ # end file # BEGIN XML-SITEMAP-PLUGIN Sitemap: http://www.isoc.lu/sitemap.xml.gz # END XML-SITEMAP-PLUGIN