# $Id: robots.txt,v 1.7 2007/01/08 12:02:18 dries 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.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: /search/
#
# If you DON'T want your user's pages crawled, use this, otherwise delete it:
Disallow: /user
#
# IMPORTANT: THE FOLLOWING LINE BLOCKS ALL /node* URLs 
# only use it if you do not have content with URLs like http://example.com/node/10. Alternatively use the Global Redirect module.
Disallow: /node
#
# block tracker pages
Disallow: /tracker/
# block paginated tracker pages
Disallow: /tracker?
#
# Disallow robots from all but the main feed - requires Pathauto feed aliases turned on. Optionally only block Google from the following paths because it causes the most havoc with Google
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 some modules like the Forums and Views modules
Disallow: /*sort=
# Prevent duplicate content created by the Image module
Disallow: /*size=
#
# This prevents Drupal's default non-clean URLs from being indexed
Disallow: /?q=
#