# $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 # robots.txt generated at http://www.mcanerin.com # shd 6/23/09 User-agent: Googlebot Allow: User-agent: googlebot-image Allow: User-agent: googlebot-mobile Allow: User-agent: Google Sitemaps Allow: User-agent: Ask Allow: User-agent: MSNBot-media Allow: User-agent: MSNBot Disallow: User-agent: Slurp Disallow: User-agent: Teoma Disallow: User-agent: twiceler Disallow: User-agent: Gigabot Disallow: User-agent: Scrubby Disallow: User-agent: Robozilla Disallow: User-agent: Nutch Disallow: User-agent: ia_archiver Disallow: User-agent: baiduspider Disallow: User-agent: naverbot Disallow: User-agent: yeti Allow: User-agent: yahoo-mmcrawler Disallow: User-agent: psbot Disallow: User-agent: asterias Allow: User-agent: yahoo-blogs/v3.9 Disallow: User-agent: * Disallow: / Crawl-delay: 1 Disallow: /cgi-bin/ # Directories Disallow: /includes/ Disallow: /misc/ Disallow: /modules/ Disallow: /profiles/ Disallow: /scripts/ Disallow: /sites/ Disallow: /themes/ Disallow: /jay/ Disallow: /terrance/ # Files 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 # Paths (clean URLs) Disallow: /admin/ Disallow: /comment/reply/ Disallow: /contact/ Disallow: /logout/ Disallow: /node/add/ Disallow: /search/ Disallow: /user/register/ Disallow: /user/password/ Disallow: /user/login/ # Paths (no clean URLs) Disallow: /?q=admin/ Disallow: /?q=comment/reply/ Disallow: /?q=contact/ Disallow: /?q=logout/ Disallow: /?q=node/add/ Disallow: /?q=search/ Disallow: /?q=user/password/ Disallow: /?q=user/register/ Disallow: /?q=user/login/ Sitemap: http://www.copycraft.com/sitemap.xml.gz Disallow: /BookmarksOrderNow Disallow: /BusinessCardsOrderNow Disallow: /BrochuresOrderNow Disallow: /LabelsOrderNow Disallow: /NotepadsOrderNow Disallow: /LetterheadOrderNow Disallow: /PocketFoldersOrderNow Disallow: /PostersOrderNow Disallow: /DoorhangersOrderNow Disallow: /PostcardsOrderNow Disallow: /StatementStuffersOrderNow Disallow: /TableTentsOrderNow Disallow: /RackcardsOrderNow Disallow: /StatementStuffersOrderNow