pmrpc.com

#
# 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: /sites/default/files/
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /themes/
# Files
Disallow: /CHANGELOG.txt
Disallow: /cron.php
Disallow: /INSTALL.mysql.txt
Disallow: /INSTALL.pgsql.txt
Disallow: /INSTALL.sqlite.txt
Disallow: /install.php
Disallow: /INSTALL.txt
Disallow: /LICENSE.txt
Disallow: /MAINTAINERS.txt
Disallow: /update.php
Disallow: /UPGRADE.txt
Disallow: /xmlrpc.php
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips/
Disallow: /node
Disallow: /content
Disallow: /newsletters
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/
DIsallow: /classified
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=filter/tips/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
Disallow: /?q=user/logout/
# no access for table sorting paths or any paths that have parameters.
Disallow: /*?sort*
Disallow: /*&sort*

Disallow: /*?solrsort*
Disallow: /*&solrsort*

# no access to profile listings, they are costly to generate and don't provide
# useful information.
Disallow: /profile
Disallow: /profile/*
Disallow: /?q=profile
Disallow: /?q=profile/*

# Disallow bogus aggregator pages
Disallow: /aggregator/*

# Disallow project search
Disallow: /project/issues/search
Disallow: /project/issues/search/*
Disallow: /project/issues/*/search

# Disallow book export
Disallow: /book/export/*

# Disallow pift tests
Disallow: /pift/retest/*

# Disallow project subscription
Disallow: /project/issues/subscribe-mail/*

# Disallow URLs with destination parameter
Disallow: /user/login?destination=*
Disallow: /user/register?destination=*
Disallow: /user?destination=*

# Googlebot picked up strange homepage URLs somewhere
Disallow: /home/*