User-agent: * # disallow files in /cgi-bin Disallow: /cgi-bin/ # disallow all files ending in .php Disallow: /*.php$ Disallow: /*.js$ Disallow: /*.inc$ Disallow: /*.css$ Disallow: /*.txt$ #disallow all files in /wp- directorys Disallow: /wp-*/ # disallow all files with ? in url Disallow: /*? # disallow any files that are stats related Disallow: /stats* Disallow: /about/legal-notice/ Disallow: /about/copyright-policy/ Disallow: /about/terms-and-conditions/ Disallow: /about/feed/ Disallow: /about/trackback/ # disallow Duplicates -fatto da manolo Disallow: */trackback/ Disallow: */feed/ Disallow: */category/ Disallow: */tag/ Disallow: */grappling-italia.com_Backup_* Disallow: */fantamma/ # Google Image User-agent: Googlebot-Image Disallow: Allow: /* # Google AdSense User-agent: Mediapartners-Google* Disallow: Allow: /* # Does anyone care I love Google Apache htaccess, not to mention robots.txt, wordpress and hacking code # Internet Archiver Wayback Machine User-agent: ia_archiver Disallow: # http://www.sitemaps.org/faq.php # Add Nonstandard extensions Sitemap: http://www.grappling-italia.com/sitemap.xml