# $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
#
# http://www.privacydigest.com/gsitemap
# <searchengine_URL>/ping?sitemap=http%3A%2F%2Fwww.privacydigest.com%2Fgsitemap
# 
# http://search.yahooapis.com/SiteExplorerService/V1/ping?sitemap=http%3A%2F%2Fwww.privacydigest.com%2Fgsitemap
# http://search.live.com/ping?sitemap=http%3A%2F%2Fwww.privacydigest.com%2Fgsitemap     MSN NG - Error msg
# http://search.yahooapis.com/SiteExplorerService/V1/ping?sitemap=http%3A%2F%2Fwww.privacydigest.com%2Fsitemap.xml
# http://search.live.com/ping?sitemap=http%3A%2F%2Fwww.privacydigest.com%2Fsitemap.xml    MSN NG - Error msg
#
# Old - Sitemap: http://www.privacydigest.com/gsitemap  PPH 2007-0523
Sitemap: http://www.privacydigest.com/sitemap.xml

User-agent: *
Crawl-delay: 10
# Directories
# added my local files directory PPH 2007-0523
Disallow: /PDfilesPD30/
# added my local upgrade directory PPH 2009-0706
Disallow: /Drupal519upgrade/
Disallow: /d610/
Disallow: /old-Drupal55/
Disallow: /Drupal613/
Disallow: /drupal-5.1/
Disallow: /drupal-5.5/
Disallow: /database/
# Original below 2009-0714 PPH
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/
# Since I have PathAuto drop original NODE/ URLs PPH 2009-0714
# Disallow: /node/   Need for Calais' RDF file PPH 2009-0715
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/
# Since I have PathAuto drop original NODE/ URLs PPH 2009-0714
# Disallow: /?q=node/   Need for Calais' RDF file PPH 2009-0715
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/

# robots.txt for http://www.PrivacyDigest.com/
# The part below if from my old site, above is from Drupal6x install. PPH
# User-agent: *  Already set by the code copied above from Drupal PPH
Disallow: .htaccess
Disallow: .pair
Disallow: /beta/
Disallow: /data/
Disallow: /debug/
Disallow: /cgi-bin/webinator/
Disallow: /cgi-bin/texis/
Disallow: /cgi-bin/MT/
Disallow: /cgi-sys/MT/
Disallow: /images/
Disallow: /junk/
Disallow: /lists/
# blocked as part of the Drupal security  fight PPH
Disallow: /masquerade/
Disallow: /private/
Disallow: /static/
Disallow: /test/
Disallow: /temp/
# blocked as part of the trackback spammer fight PPH 
Disallow: /trackback/
Disallow: /Tools/
Disallow: /webinator/
Disallow: /WWW_REPORTS/

User-agent: WebZip 
Disallow: / 

User-agent: EmailCollector 
Disallow: / 

User-agent: EmailSiphon 
Disallow: / 

User-agent: WebBandit 
Disallow: / 

User-agent: EmailWolf 
Disallow: / 

User-agent: ExtractorPro 
Disallow: / 

User-agent: SiteSnagger 
Disallow: / 

User-agent: Harvest/1.5 
Disallow: / 

# try allowing altavista and teoma for a while 2007-0522 PPH
# I've been getting these database floods and AWS extended transactions 2007-0712 PPH
User-agent: scooter         # AltaVista web page search 
Disallow: /store

User-agent: Teoma-agent         # Ask Jeeves/Teoma web page search 
Disallow: /

User-agent: Ask Jeeves         # Ask Jeeves/Teoma web page search 
Disallow: /

User-agent: Ask Jeeves Teoma         # Ask Jeeves/Teoma web page search 
Disallow: /

User-agent: Ask Jeeves/Teoma         # Ask Jeeves/Teoma web page search 
Disallow: /