# $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

#sitemaps
Sitemap: http://www.semel.ucla.edu/sitemap.xml
Sitemap: http://www.semel.ucla.edu/?q=sitemap.xml

User-agent: *
Crawl-delay: 10

# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /sites/
Disallow: /themes/
Disallow: /pdf/
Disallow: /cgi/
# 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
Disallow: /default.aspx
# Paths (clean URLs)
Disallow: /admin/
Disallow: /aggregator/
Disallow: /biblio/
Disallow: /cache/
Disallow: /comment/reply/
Disallow: /logout/
Disallow: /node/
Disallow: /noderelationships/
Disallow: /not_used/
Disallow: /print/
Disallow: /printmail/
Disallow: /search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /directory.csv/
Disallow: /directory.xml/
Disallow: /feed-item/
Disallow: /personnel/
Disallow: /frc4/
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=logout/
Disallow: /?q=node/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
Disallow: /boost_stats.php
# Paths (clean URLs) - no slash (needed by Google)
Disallow: /admin
Disallow: /aggregator
Disallow: /biblio
Disallow: /cache
Disallow: /comment/reply
Disallow: /logout
Disallow: /node
Disallow: /noderelationships
Disallow: /not_used
Disallow: /print
Disallow: /printmail
Disallow: /search
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login
Disallow: /directory.csv
Disallow: /directory.xml
Disallow: /feed-item
Disallow: /personnel
Disallow: /frc4
# Paths (no clean URLs)
Disallow: /?q=admin
Disallow: /?q=aggregator
Disallow: /?q=biblio
Disallow: /?q=cache
Disallow: /?q=comment/reply
Disallow: /?q=logout
Disallow: /?q=node
Disallow: /?q=noderelationships
Disallow: /?q=not_used
Disallow: /?q=print
Disallow: /?q=printmail
Disallow: /?q=search
Disallow: /?q=user/register
Disallow: /?q=user/password
Disallow: /?q=user/login
Disallow: /?q=directory.csv
Disallow: /?q=directory.xml
Disallow: /?q=feed-item
Disallow: /?q=personnel
Disallow: /?q=frc4
# Stop HTML being regarded as keyword
Disallow: /taxonomy/
Disallow: /taxonomy
Disallow: /?q=taxonomy
# Shib login links
Disallow: /Shibboleth.sso
# Stop indexing Faculty names on course listings
Disallow: /education/courses?order
Disallow: /education/courses?field_course
Disallow: /education/courses?sort
Disallow: /education/courses?term
Disallow: /?q=education/courses
# Allow images to be crawled
Allow: /sites/*.jpg
Allow: /sites/*.png