# drb 17 Nov 2012 Enable msnbot again
# batchange drb 24 nov 2010 add 'msnbot' section to ban it
# batchange drb 08 nov 2010 add line for BOOST module
# batchange drb 29 Jun 2009 Only search main image node, not thumbnails, etc. see http://tips.webdesign10.com/drupal/image-module-332.html
# batchange drb 11 jun 2006 add disallows for drupal. see http://drupal.org/node/22265 for details
# batchange drb 09 Oct 2006 also add disallows for drupal in /drupal subdir
# batchange drb 22 Apr 2007 awstats show /node/add/forum and /node/add/forum/2 are popular
#                            entry pages, ranked #3 and #5. Add them to disallows below.

# more information about this file can be found at
# http://www.robotstxt.org/wc/robots.html

# lines beginning with the pund ("#") sign are comments and can be deleted.

# if case your drupal site is in a directory
# lower than your docroot (e.g. /drupal)
# please add this before the /-es below

# to stop a polite robot indexing an exampledir
# add a line like (delte the #'s)
# user-agent: polite-bot
# Disallow: /exampledir/

# a list of know bots can be found at
# http://www.robotstxt.org/wc/active/html/index.html

# see http://www.sxw.org.uk/computing/robots/check.html
# for syntax checking

# The MSNbot was visiting around every 17 seconds, making up around one third of hits
# Because of the weird urls it uses, it was bypassing caching.
# ban it for now, consider re-instating later. If we do, remember it needs to see all the 
# same 'Disallow:' lines we have under "User-agent: *" 
# User-agent: msnbot
# Disallow: /

User-agent: *
Crawl-Delay: 15
Disallow: /boost_stats.php
Disallow: /CHANGELOG.txt
Disallow: /place-list-by-completion-year
Disallow: /aggregator
Disallow: /tracker
Disallow: /comment/reply
Disallow: /node/add
Disallow: /node/add/forum
Disallow: /node/add/forum/2
Disallow: /user
Disallow: /files
Disallow: /search
Disallow: /book/print
Disallow: /drupal/aggregator
Disallow: /drupal/tracker
Disallow: /drupal/comment/reply
Disallow: /drupal/node/add
Disallow: /drupal/user
Disallow: /drupal/files
Disallow: /drupal/search
Disallow: /drupal/book/print
Disallow: /phpBB2/
Disallow: /3drupal/
Disallow: /4drupal/
Disallow: /rdrupal/
Disallow: /tdrupal/
# Only search main image node, not thumbnails, etc. see http://tips.webdesign10.com/drupal/image-module-332.html
Disallow: /*size=
#Disallow robots from two files with links to all Places. It seems the robots
#(specifically Google) were coming back to check each entry in the list of 1,000+ Places
Disallow: /node/8522
Disallow: /node/8530
Disallow: /placesWithoutYearDemolished
# another couple of pages that were generating lots of googlebot visits, and using lots of GPUs
Disallow: /taxonomy/term/138
Disallow: /taxonomy/term/138/