User-agent: *
Crawl-delay: 86400

Disallow: /redmine

Disallow: /zh-hant
Disallow: /en

# from old dennys.tiger2.net & sunnys.tiger2.net
Disallow: /album/
Disallow: /blog$

#Disallow: */trackback$
#Disallow: */feed$

########################################################
#      for new Drupal
########################################################

# log ¦³ /map/query, ¦ügoogle maps ªº marker ¦³Ã?
Disallow: /map

Disallow: /?q=
Disallow: /book/export/html
Disallow: /node?page
Disallow: /node$
Disallow: /node?
Disallow: /node/add
Disallow: /node/*/edit$
Disallow: /node/*/revisions$
Disallow: /taxonomy
Disallow: /rss.xml
Disallow: /blog/category
Disallow: /index.php
Disallow: /files
Disallow: /forward
Disallow: /blog/tag
Disallow: /blog/index.php

# $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

User-agent: *
Crawl-delay: 86400
# 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: /aggregator
Disallow: /comment/reply
Disallow: /contact
Disallow: /logout
Disallow: /node/add
Disallow: /search
Disallow: /user/login
Disallow: /user/password
Disallow: /user/register
Disallow: /users/*/track
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=aggregator/
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/
# Drupal others
Disallow: /*sort=

# for smf
Disallow: /smf/

# for phpBB
Disallow: /phpBB/

# for Gallery2
Disallow: /g2
Disallow: /gallery
#Disallow: /zh-hant/en/index.php?q=gallery
Disallow: /gallery2
#Disallow: /gallery2/v/
Disallow: /gallery2/c/
Disallow: /gallery2/d/
Disallow: /gallery2/srss/
Disallow: /gallery2/rss/
Disallow: /gallery2/main.php?
Disallow: /gallery2/admin/
Disallow: /gallery2/images/
Disallow: /gallery2/modules/
Disallow: /gallery2/themes/
Disallow: */slideshow.html
Disallow: */slideshowapplet.html

# Others
Disallow: /gallery
Disallow: /twiki/
Disallow: /wiki/
Disallow: *PHPSESSID*
Disallow: /cgi-bin/
Disallow: /*.php$
Disallow: /*.js$
Disallow: /*.inc$
Disallow: /*.css$
Disallow: /*.gz$
Disallow: /*.wmv$
Disallow: /*.avi$
Disallow: /*.cgi$
Disallow: /*.xhtml$

# IRL crawer http://irl.cs.tamu.edu/crawler/
User-agent: IRLbot 
Disallow: /
# Yodao http://www.yodao.com/help/webmaster/spider/008/
User-Agent: YodaoBot
Disallow: /
# http://yetibot.com/
User-Agent: yetibot
Disallow: /
User-Agent: Googlebot-Image
Disallow: /
# Snapbot: frequency too high and doesn't follow robots.txt (it reads blog/*/feed and blog/*/track)
User-Agent: Snapbot
Disallow: /