# $Id: robots.txt,v 1.9 2007/06/27 22:37:44 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

User-agent: Google
Disallow:
#####################  End Wikipedia .txt  
#
# robots.txt for http://www.wikipedia.org/ and friends
#
# Please note: There are a lot of pages on this site, and there are
# some misbehaved spiders out there that go _way_ too fast. If you're
# irresponsible, your access to the site may be blocked.
#

# advertising-related bots:
User-agent: Mediapartners-Google*
Disallow: /

# Wikipedia work bots:
User-agent: IsraBot
Disallow:

User-agent: Orthogaffe
Disallow:

# Crawlers that are kind enough to obey, but which we'd rather not have
# unless they're feeding search engines.
User-agent: UbiCrawler
Disallow: /

User-agent: DOC
Disallow: /

User-agent: Zao
Disallow: /

# Some bots are known to be trouble, particularly those designed to copy
# entire sites. Please obey robots.txt.
User-agent: sitecheck.internetseer.com
Disallow: /

User-agent: Zealbot
Disallow: /

User-agent: MSIECrawler
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: Fetch
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Teleport
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: linko
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: Microsoft.URL.Control
Disallow: /

User-agent: Xenu
Disallow: /

User-agent: larbin
Disallow: /

User-agent: libwww
Disallow: /

User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

#
# Sorry, wget in its recursive mode is a frequent problem.
# Please read the man page and use it properly; there is a
# --wait option you can use to set the delay between hits,
# for instance.
#
User-agent: wget
Disallow: /

#
# The 'grub' distributed client has been *very* poorly behaved.
#
User-agent: grub-client
Disallow: /

#
# Doesn't follow robots.txt anyway, but...
#
User-agent: k2spider
Disallow: /

#
# Hits many times per second, not acceptable
# http://www.nameprotect.com/botinfo.html
User-agent: NPBot
Disallow: /

# A capture bot, downloads gazillions of pages with no public benefit
# http://www.webreaper.net/
User-agent: WebReaper
Disallow: /
#####################  End Wikipedia .txt  
# For mariagwyn.com specifically
User-agent: *
Disallow: /files
Disallow: /dev
Disallow: /random
Disallow: /snq
Disallow: /snq-orig

# Drupal settings
User-agent: *
Crawl-delay: 10
# Directories
Disallow: /drupal/database/
Disallow: /drupal/includes/
Disallow: /drupal/misc/
Disallow: /drupal/modules/
Disallow: /drupal/sites/
Disallow: /drupal/themes/
Disallow: /drupal/scripts/
Disallow: /drupal/updates/
Disallow: /drupal/profiles/
# Files
Disallow: /drupal/xmlrpc.php
Disallow: /drupal/cron.php
Disallow: /drupal/update.php
Disallow: /drupal/install.php
Disallow: /drupal/INSTALL.txt
Disallow: /drupal/INSTALL.mysql.txt
Disallow: /drupal/INSTALL.pgsql.txt
Disallow: /drupal/CHANGELOG.txt
Disallow: /drupal/MAINTAINERS.txt
Disallow: /drupal/LICENSE.txt
Disallow: /drupal/UPGRADE.txt
# Paths (clean URLs)
Disallow: /drupal/admin/
Disallow: /drupal/comment/reply/
Disallow: /drupal/contact/
Disallow: /drupal/logout/
Disallow: /drupal/node/add/
Disallow: /drupal/search/
Disallow: /drupal/user/register/
Disallow: /drupal/user/password/
Disallow: /drupal/user/login/
# Paths (no clean URLs)
Disallow: /drupal/?q=admin/
Disallow: /drupal/?q=comment/reply/
Disallow: /drupal/?q=contact/
Disallow: /drupal/?q=logout/
Disallow: /drupal/?q=node/add/
Disallow: /drupal/?q=search/
Disallow: /drupal/?q=user/password/
Disallow: /drupal/?q=user/register/
Disallow: /drupal/?q=user/login/

User-agent: *
Crawl-delay: 10
# Directories
Disallow: /drupal6/database/
Disallow: /drupal6/includes/
Disallow: /drupal6/misc/
Disallow: /drupal6/modules/
Disallow: /drupal6/sites/
Disallow: /drupal6/themes/
Disallow: /drupal6/scripts/
Disallow: /drupal6/updates/
Disallow: /drupal6/profiles/
# Files
Disallow: /drupal6/xmlrpc.php
Disallow: /drupal6/cron.php
Disallow: /drupal6/update.php
Disallow: /drupal6/install.php
Disallow: /drupal6/INSTALL.txt
Disallow: /drupal6/INSTALL.mysql.txt
Disallow: /drupal6/INSTALL.pgsql.txt
Disallow: /drupal6/CHANGELOG.txt
Disallow: /drupal6/MAINTAINERS.txt
Disallow: /drupal6/LICENSE.txt
Disallow: /drupal6/UPGRADE.txt
# Paths (clean URLs)
Disallow: /drupal6/admin/
Disallow: /drupal6/comment/reply/
Disallow: /drupal6/contact/
Disallow: /drupal6/logout/
Disallow: /drupal6/node/add/
Disallow: /drupal6/search/
Disallow: /drupal6/user/register/
Disallow: /drupal6/user/password/
Disallow: /drupal6/user/login/
# Paths (no clean URLs)
Disallow: /drupal6/?q=admin/
Disallow: /drupal6/?q=comment/reply/
Disallow: /drupal6/?q=contact/
Disallow: /drupal6/?q=logout/
Disallow: /drupal6/?q=node/add/
Disallow: /drupal6/?q=search/
Disallow: /drupal6/?q=user/password/
Disallow: /drupal6/?q=user/register/
Disallow: /drupal6/?q=user/login/

User-agent: *
Crawl-delay: 10
# 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: /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/