# $Id: robots.txt,v 1.7.2.1 2007/03/23 18:57:07 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 (clean URLs)
Disallow: /admin/
Disallow: /aggregator
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=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/

# block tracker pages
Disallow: /tracker/
# block paginated tracker pages
Disallow: /tracker?

# IMPORTANT: THE FOLLOWING LINE BLOCKS ALL /node* URLs – 
Disallow: /node

# Disallow robots from all but the main feed - 
Disallow: /*/feed

# Prevent print-friendly duplicate pages from being crawled
Disallow: /book/export/

# This is important for the Forward module
Disallow: /forward/

# This prevents duplicate content caused by the Forums and Views modules
Disallow: /*sort=

# Prevent duplicate content created by the Image module
Disallow: /*size=

# This will keep a duplicate front page from being indexed
Disallow: /front_page

# This will keep the duplicate from being indexed
Disallow: /frontpage