# $Id: robots.txt,v 1.7.2.2 2008/02/25 02:18:25 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
#
#
User-agent: *
Crawl-delay: 10
# Directories
Disallow: /meeting-rooms/
Disallow: /database/
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /sites/
Disallow: /themes/
Disallow: /scripts/
Disallow: /updates/
Disallow: /profiles/
Disallow: /categories/
# 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/
# 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/
Disallow: /groups/archive
#
# LDEO - Lamont-Doherty Earth Observatory of Columbia University
#
Allow: /
#
Disallow: /publications/
Disallow: /LCSN/WebSeis
Disallow: /activityreports/
Disallow: /activityreports.keep
Disallow: /activityreports.keep2
Disallow: /css/
Allow: /directory/
Disallow: /dlc-0.4.0/
Disallow: /dp_ldeo/
Disallow: /drupal/
Disallow: /static/
Disallow: /events/
Disallow: /extlink/
Disallow: /files/
Disallow: /flash/
Disallow: /images/
Disallow: /includes/
Disallow: /karner/
Disallow: /ldeo/
Disallow: /ldeo/it/
Disallow: /ldeo/it.old/
Disallow: /ldeo-video
Disallow: /misc/
Disallow: /modules/
Disallow: /node_pages/
Disallow: /resources/
Disallow: /scripts/
Disallow: /meeting-rooms
Disallow: /old-directory
Disallow: /server-info/
Disallow: /server-status/
Disallow: /sites/
Disallow: /taxonomy/
Disallow: /themes/
Disallow: /txt/
Disallow: /warehouse/
Disallow: /webmail/
#
Allow: /LCSN/
Allow: /chrr/
Allow: /cicar/
Allow: /colloquium/
Allow: /core_rotation/
Allow: /edu/
Allow: /estuary/
Allow: /globalcmt/
Allow: /news/
Allow: /outr/
Allow: /res/
Allow: /seismology/
Allow: /users/
Allow: /vetlesen/
Allow: /ldeo/cal/sundial
#
# Block the agent from Searchme robot.
User-Agent: Charlotte/1.0t
Disallow: /