# $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
User-agent: Mediapartners-Google
Disallow:
User-agent: *
# Crawl-delay: 10
# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /sites/
Disallow: /themes/
# 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: /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=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/

## custom additions - not found in google webmaster reports
Disallow: /poormanscron

# Additions based on http://tips.webdesign10.com/robots-txt-and-drupal
# This will disallow the user form at http://example.com/user.
# If you would like to block all user pages, remove the trailing ampersand from this rule and all user pages will be blocked.
Disallow: /user$

Disallow: /*sort=
# This takes care of problems with the Forum Module, the Views Module and other modules that sort tables by column headers.

Disallow: /search$
# This will block your search form at http://example.com/search. 
# That URL does a 302 redirect to http://example.com/search/node which is already blocked by the default robots.txt file.

Disallow: /*/feed$
# This rule with block all the RSS feeds on the site except for the main RSS feed which is located at http://example.com/rss.xml by default.

Disallow: /*/track$
# This will block all of the URLs created by the Tracker Module which are in the format http://example.com/user/5/track.

Disallow: /tracker?
# My recommendation is to leave http://example.com/tracker exposed to search engines, 
# while blocking the paginated tracker pages like http://example.com/tracker?page=50.

# As per: http://www.sitemaps.org/protocol.php#submit_robots
# You can specify more than one Sitemap file per robots.txt file.
Sitemap: http://www.quit-smoking-stop.com/sitemap.xml