# $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
# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /sites/
Disallow: /themes/
# 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/
#CEAV specific entries. The site uses clean URLs so hopefully I don't need to repeat
#these in the next section.
Disallow: /faq_ask/
Disallow: /faq/
Disallow: /conference-register-2009/
Disallow: /bookroom-order/
Disallow: /photos/
Disallow: /calendar/submit-new-event/
Disallow: /ncdw/dream-career/entryform/
Disallow: /publications/journal-article-submission/
Disallow: /resource_index/submit/
Disallow: /resource_index/broken-link/
Disallow: /resource_index/
Disallow: /forms/
Disallow: /career-resources/members/
Disallow: /career-resources/careernav/
Disallow: /echo_issues_list/
Disallow: /journal_archive/
Disallow: /podcasts/
Disallow: /blog/
Disallow: /taxonomy_vtn/
Disallow: /advanced_blog/
Disallow: /staff-blogs/
#Allow the career vacancies page but disallow individual vacancy nodes.
Disallow: /vacancy/
#Some FAQ nodes.
Disallow: /node/156/
Disallow: /node/158/
Disallow: /node/159/
Disallow: /node/155/
Disallow: /node/233/
# 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/
Disallow: /?q=faq/
Disallow: /?q=echo_issues_list/
Disallow: /?q=journal_archive/
Disallow: /?q=career-resources/members/
Disallow: /?q=career-resources/careernav/
Disallow: /?q=podcasts/
Disallow: /?q=resource_index/
Disallow: /?q=photos/
Disallow: /?q=blog/
Disallow: /?q=taxonomy_vtn/