# $Id: robots.txt,v 1.7.2.2 2008/02/25 02:18:25 drumm 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: /database/
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /sites/
Disallow: /themes/
Disallow: /scripts/
Disallow: /updates/
Disallow: /profiles/

# Files
Disallow: /xmlrpc.php
Disallow: /cron.php
Disallow: /update.php
Disallow: /install.php
Disallow: /INSTALL.txt
Disallow: /INSTALL.mysql.txt
Disallow: /INSTALL.pgsql.txt
Disallow: /CHANGELOG.txt
Disallow: /MAINTAINERS.txt
Disallow: /LICENSE.txt
Disallow: /UPGRADE.txt

# Paths
Disallow: /admin/
#Disallow: /comment/reply/
Disallow: /contact/
Disallow: /logout/
Disallow: /node/add/
Disallow: /search/
#Disallow: /user/register/
#Disallow: /user/password/
#Disallow: /user/login/

# Added by DHG
Disallow: /comment/
Disallow: /user/
Disallow: /files/
Disallow: /taxonomy/
Disallow: /*?
Disallow: /*/feed$
Allow: /tag/original?page=*
Allow: /node*?page=*