# $Id: robots.txt,v 1.7.2.1 2007/03/23 18:57:07 drumm 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

#
# Greg June 25, 2009
# temporarily prohibit crawling to investigate performance problems
#
# IMPORTANT. I'm moving this to the bottom of the file to prohibit anyone
# not listed in the user-agent line below
#User-agent: *
#Disallow: /




#User-agent: msnbot msnbot-media Googlebot Slurp mcgill-gsa-crawler

User-agent: *
Crawl-delay: 30
# Directories
Disallow: /database/
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /sites/
Disallow: /themes/
Disallow: /scripts/
Disallow: /updates/
Disallow: /profiles/
#
#
Disallow: /local/
DIsallow: /files/

# gdl March 6, 2008
Disallow: /event/
#
# Not sure if this will work
# trying to block: GET /user/login?destination=comment/reply/2175%2523comment-form
Disallow: /user/
#
# These are mysql intensive but not sure if they will match
# Added at 13:35 June 25 - see what the logs say...
# Sept 21, 2009, GDL the mcgill-gsa-crawler is killing the server with biblio searches. Explicitly prohibit ALL biblio indexing while
# figuring out what is going on
Disallow: /biblio
#Disallow: /biblio/filter/
#Disallow: /biblio/Author/
#Disallow: /biblio?sort=year&order=asc
#Disallow: /biblio?sort=title&order=asc
#Disallow: /biblio?sort=type&order=asc
#Disallow: /biblio?sort=author&order=asc

# 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: /aggregator/
Disallow: /comment/reply/
Disallow: /contact/
Disallow: /logout/
Disallow: /node/add/
Disallow: /search/
# mcgill-gsa-crawler is grabbing /user/login?... so block all of /user/
Disallow: /user/
#Disallow: /user/register/
#Disallow: /user/password/
#Disallow: /user/login/
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=aggregator/
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/
#
# database intensive searches
Disallow: /people/students/user/