# $Id: robots.txt,v 1.9.2.1 2008/12/10 20:12:19 goba 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 # disallow all User-agent: * Disallow: / Crawl-delay: 600 User-agent: PetalBot Disallow: / User-agent MegaIndex Disallow: / User-agent: MegaIndex.ru Disallow: / # but allow only important bots User-agent: Googlebot User-agent: Googlebot-Image User-agent: Mediapartners-Google User-agent: msnbot User-agent: msnbot-media User-agent: Slurp User-agent: Yahoo-Blogs User-agent: Yahoo-MMCrawler User-agent: Twitterbot User-agent: facebookexternalhit User-agent: SiteimproveBot-Crawler # Directories Disallow: /vk/admin/ Disallow: /vk/provider/ # Files Disallow: /vk/volunteers/my_opportunities_info_preprint.aspx Disallow: /vk/volunteers/my_opportunities_info_print.asp Disallow: /vk/volunteers/my_opportunities_info_print.htm Disallow: /vk/volunteers/search.htm Disallow: /vk/volunteers/search.asp Disallow: /CHANGELOG.txt Disallow: /cron.php Disallow: /INSTALL.mysql.txt Disallow: /INSTALL.pgsql.txt Disallow: /install.php Disallow: /INSTALL.txt Disallow: /LICENSE.txt Disallow: /MAINTAINERS.txt Disallow: /update.php Disallow: /UPGRADE.txt Disallow: /xmlrpc.php Crawl-delay: 600