# $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

User-agent: *
Crawl-delay: 10
Disallow: /*sort=
# Directories
Allow: /content/news/
Allow: content/events/
Allow: /content/news/blog/
Allow: /content/articles/
Allow: /content/page/
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /sites/
Disallow: /themes/
Disallow: /database/
Disallow: /updates/
# 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)
Allow: /content/news/
Allow: content/events/
Allow: /content/news/blog/
Allow: /content/articles/
Allow: /content/page/
Allow: /content/jobs/
Disallow: /admin
Disallow: /category
Disallow:  /taxonomy
Disallow: /content/news/2005/*
Disallow: /category/tags/blog
Disallow: /category/tags/media
disallow: /content/about-us
disallow: /content/content
Disallow: /event/*
Disallow: /events/*
Disallow: /feeds/*
Disallow: /files
Disallow: /forum
Disallow: /jobs/bc/*
Disallow: /category/tags/*
Disallow: /content/2009/08/*
Disallow: /content/2007/*
Disallow: /content/2006/*
Disallow: /1909/business_continuity_jobs/current
Disallow: /comment/reply
Disallow: /search/
Disallow: /contact
Disallow: /logout
Disallow: /node/add
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login
# Paths (no clean URLs)
Allow: /?q=content/news/
Allow: /?q=events/
Allow: /?q=content/news/blog/
Allow: /?q=content/articles/
Allow: /?q=content/page/
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=contact/
Disallow: /?q=content/pandemicportal
Disallow: /?q=logout/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
# Added tryouts for better robot control
Disallow: /tracker?
Disallow: /*/track$
Disallow: /*/feed$
Disallow: /user$
Disallow: /*.pdf$
Disallow: /*.jpg$
Disallow: /*.gif$
Disallow: /*.png$
Disallow: /files/images/
User-agent: Bad-Robot Disallow: *