# 10-09-2007 02:38

Sitemap: http://www.rslinks.org/sitemap.xml

User-agent: Mediapartners-Google*
Disallow: /

User-agent: Googlebot-Image
Disallow: /

# block the Internet Archiver if you want the privacy
User-agent: ia_archiver
Disallow: /
#
# All other robots
User-agent: *
# Directories
Disallow: /database/
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /sites/
Disallow: /themes/
Disallow: /scripts/
Disallow: /updates/
Disallow: /profiles/
Disallow: /myscripts/
Disallow: /go/
#
# 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
Disallow: /boost_stats.php

#
# Paths (clean URLs) -- modified from default!
Disallow: /admin/
Disallow: /aggregator/
Disallow: /comment/
Disallow: /node/add
Disallow: /node/add/
Disallow: /logout
Disallow: /user/register
Disallow: /user/register/
Disallow: /user/password
Disallow: /user/password/
Disallow: /user/login
Disallow: /login
Disallow: /flag_content
Disallow: /i/
Disallow: /i/r/
Disallow: /i/o/
Disallow: /i/rw/
Disallow: /i/up/
#
# Additional Rules
#
Disallow: /node
#Disallow: /search
Disallow: /taxonomy/
Disallow: /dlc

# 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/
#
# This prevents Drupal's default non-clean URLs from being indexed
Disallow: /?q=
#Disallow: /*?
Disallow: /?page
#
# block tracker pages
Disallow: /tracker?
# block paginated tracker pages
Disallow: /tracker?
Disallow: /*/track$
#
#
#
#
# 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 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=
# 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