# $Id: robots.txt,v 1.7.2.3 2008/12/10 20:24:38 drumm Exp $
# @logorev: $Revision: 66223 $, $LastChangedBy: widholmk $ #
#
# 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: 60

# Directories
Disallow: /database/ # no longer used, but let's keep for now
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /sites/
Disallow: /themes/
# Files
Disallow: /ajax.php
Disallow: /callbacks.php
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: /aggregator/	# has links to other sites
Disallow: /book/print/
Disallow: /comment/reply/
Disallow: /forum/	# removes forums from GSA. Keep?
Disallow: /contact/
Disallow: /files/
Disallow: /logout/
Disallow: /node/add/
Disallow: /pics/
Disallow: /search/
# some tracker pages are followed via query string
Disallow: /tracker/	# processing expensive.
Disallow: /tracker	# also have /tracker/, do we need both?
Disallow: /user/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=aggregator/
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/

# Disable the gsa-crawler
# User-agent: gsa-crawler
# Disallow: *
# @jira LOGOT-3284: Crawl kill mechanism: 
# This is already implemented by default in GSA's
# here we just kill other crawlers as well.
Disallow: /no_crawl/

User-agent: gsa-crawler
Disallow: /archive/