# $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

# campaigncc modifications 

# Yahoo Slurp uses far too much bandwidth so try to throttle it 
# http://help.yahoo.com/l/us/yahoo/search/webcrawler/slurp-03.html
# lots of people complain about it. 
#
# JA Jul 23rd 2009 

User-agent: Slurp
Crawl-delay: 200	

# Anton October 21st 2009 - added Yandex bot to disallow list because it's using too much bandwidth. This might or might not work.

User-agent: Yandex bot
Disallow: / 

# JA Oct 27th 2009 added Yandex again

User-agent: Yandex    
Disallow: / 


# # JA Nov 18th 2009 added 

User-agent: FAST Enterprise Crawler
Disallow: / 

# campaigncc, cutout all files because they are so large

Disallow: /files/
Disallow: *.jpg
Disallow: *.gif
Disallow: *.pdf
Disallow: *.doc
Disallow: *.xls


# Directories    (standard list from drupal)
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /sites/
Disallow: /themes/
# 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
# 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/




# google and everybody else

User-agent: *
Crawl-delay: 10

# Block ShopWiki

User-agent: ShopWiki
Disallow: /


# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /sites/
Disallow: /themes/
# 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
# 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/

# Anton added June 2010 to stop aggregated RSS feeds from being crawled

User-agent: *
Disallow: /aggregator/

# Anton added July 2010

User-agent: Googlebot-Mobile
Disallow: /

User-agent: Mediapartners-Google
Disallow: /

User-agent: Adsbot-Google
Disallow: /