# $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
#
# Customized per http://drupalzilla.com/robots-txt
# and http://blamcast.net/articles/drupal-seo
# and http://groups.drupal.org/node/5391
# and http://tips.webdesign10.com/robots-txt-and-drupal

# block the Internet Archiver if you want the privacy
User-agent: ia_archiver
Disallow: /

User-agent: *
Crawl-delay: 10
# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /sites/
Disallow: /themes/
Disallow: /print/
Disallow: /printmail/
Disallow: /printpdf/
# 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: /aggregator
Disallow: /comment/
Disallow: /comment/reply/
Disallow: /contact/
Disallow: /logout/
Disallow: /logout
Disallow: /node/add/
Disallow: /search/
Disallow: /search$
Disallow: /taxonomy/

# Users
# I block my user's pages on most sites because they don't have much content. Only leave it unblocked if your user pages have good content on them.
# If you DON'T want your user's pages crawled, use this, otherwise delete it:
Disallow: /user
Disallow: /user$
# If you do want your user pages indexed, then delete the line above and uncomment these
# NOTE: JCK4 doesn't want these logon, register, etc crawled either
Disallow: /user/login
Disallow: /user/login/
Disallow: /user/password
Disallow: /user/password/
Disallow: /user/register
Disallow: /user/register/
# This prevents Drupal's default non-clean URLs from being indexed
Disallow: /?q=
# block tracker pages
Disallow: /*/track$
Disallow: /tracker/
# block paginated tracker pages
Disallow: /tracker?
# 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
Disallow: /node$
# 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
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=
Disallow: /forum/2?
Disallow: /forum/3?
# Prevent duplicate content created by the Image module
Disallow: /*size=
# If you have the Front module this will keep a duplicate front page from being indexed
Disallow: /front_page
# If you use the Views module's frontpage this will keep the duplicate from being indexed
Disallow: /frontpage

# 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/