# $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
#Specific

User-agent: dotbot
Disallow: /
#Specific

User-agent: ScoutJet
Disallow: /
#Specific

User-agent: Speedy
Disallow: /
#Specific

User-agent: Accelobot
Disallow: /
#Specific

User-agent: ShopWiki
Disallow: /
#Specific

User-agent: MS Search 4.0 Robot
Disallow: /
#Specific

User-agent: MS Search 5.0 Robot
Disallow: /
#Specific
#Below all

User-agent: *
Crawl-delay: 10
# Directories
# Disallow: /
Disallow: /legacy/
Disallow: /advocacy/
Disallow: /utils/
Disallow: /iff_films/
Disallow: /patches/
Disallow: /database/
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /sites/
Disallow: /themes/
Disallow: /scripts/
Disallow: /updates/
Disallow: /profiles/
Disallow: /french/
Disallow: /images/
Disallow: /english/
Disallow: /style/
Disallow: /cgi-bin/
Disallow: /doc/
Disallow: /tmp/
Disallow: /reports_old/
Disallow: /reports/
Disallow: /podcast/
Disallow: /patches/
Disallow: /backgrounder/
Disallow: /backgrounder_old/
Disallow: /archive/
# 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: /ar/search
Disallow: /en/search
Disallow: /fr/search
Disallow: /de/search
Disallow: /ru/search
Disallow: /es/search
Disallow: /ja/search
Disallow: /he/search
Disallow: /search
Disallow: /en/cities/calendar/*
Disallow: /*/cities/calendar/*
# 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?
# Other
Disallow: /en/filter
Disallow: /fr/filter
Disallow: /filter
Disallow: /print/
Disallow: /forward?
Disallow: /*filter*
#New
Disallow: /ar/by-issue/
Disallow: /en/by-issue/
Disallow: /fr/by-issue/
Disallow: /de/by-issue/
Disallow: /ru/by-issue/
Disallow: /es/by-issue/
Disallow: /ja/by-issue/
Disallow: /he/by-issue/
Disallow: /ar/news-filter/
Disallow: /en/news-filter/
Disallow: /fr/news-filter/
Disallow: /de/news-filter/
Disallow: /ru/news-filter/
Disallow: /es/news-filter/
Disallow: /ja/news-filter/
Disallow: /he/news-filter/
Disallow: /ar/publications/reports/
Disallow: /en/publications/reports/
Disallow: /fr/publications/reports/
Disallow: /de/publications/reports/
Disallow: /ru/publications/reports/
Disallow: /es/publications/reports/
Disallow: /ja/publications/reports/
Disallow: /he/publications/reports/
Disallow: /publications/reports/