# $Id: robots.txt,v 1.9 2007/06/27 22:37:44 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: *
# COMMENTED OUT: 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: /comment/reply/
Disallow: /contact
Disallow: /logout
Disallow: /node/add
Disallow: /search
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login


# GPST Society Specific

Disallow: /resources/search
Disallow: /news/all
Disallow: /groups
Disallow: /groups/
Disallow: /profile/
Disallow: /link
Disallow: /forum/
Disallow: /contact/
Disallow: /help/
Disallow: /flag_content/
Disallow: /search/
Disallow: /accessibility
Disallow: /directory/
Disallow: /news/frontpage/
Disallow: /print/
Disallow: /printpdf/
Disallow: /printmail/
Disallow: /feed-item/
Disallow: /flag/
Disallow: /taxonomy/term/
Disallow: /rdf

# For Boost module
Disallow: /boost_stats.php

# 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/

# Additional (as per http://tips.webdesign10.com/robots-txt-and-drupal)
Disallow: /node$
Disallow: /node/*
Disallow: /*sort=
Disallow: /search$
Disallow: /*/feed$
Disallow: /*/track$
Disallow: /tracker?
Disallow: /activities$
Disallow: /activities/*
Disallow: /news/archive
Disallow: /news/20*
Disallow: /news/all
Disallow: /image/*pictures$
Disallow: /*?*
Disallow: /user