# $Id: robots.txt,v 1.2.2.3 2007/08/05 09:56:41 hass 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

#taken from http://drupalzilla.com/robots-txt
User-agent: *

# 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: /aggregator
Disallow: /comment/reply/
Disallow: /contact
Disallow: /logout
Disallow: /node/add
Disallow: /search/
Disallow: /search$
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: taxonomy/>Disallow: /?q=logout
Disallow: /?q=node/add
Disallow: /?q=search/
Disallow: /?q=user/password
Disallow: /?q=user/register
Disallow: /?q=user/login
# Additional Rules
Disallow: /node$
Disallow: /user$
Disallow: /*sort=
Disallow: /search$
Disallow: /*/feed$
Disallow: /*/track$
# If you don't want the bulk of your "recent posts" pages indexed, add this:
Disallow: /tracker?

Sitemap: http://www.clydeunion.com/sitemap.xml