# $Id: robots.txt,v 1.7 2007/01/08 12:02:18 dries Exp $ # # 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 Disallow: /*.js$ Disallow: /*.inc$ Disallow: /*.css$ Disallow: /*.gz$ Disallow: /*.sql$ Disallow: /*.doc$ #varie Disallow: /*?* Disallow: /*? User-agent: Mediapartners-Google Allow: / User-agent: Adsbot-Google Allow: / User-agent: Googlebot-Image Allow: / User-agent: Googlebot-Mobile Allow: / User-agent: TwengaBot Allow: / User-agent: ia_archiver-web.archive.org Disallow: / # indirizzo della sitemap Sitemap: http://www.suqui.it/sitemap.xml