# $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

# Thank you Wikipedia for, as usual, being a tremendous resource for,
# y'know, everything, and in this case, for which robots to try to block
# The following was taken from http://en.wikipedia.org/robots.txt

# 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: /
# 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: /

# User-agent: Googlebot
# User-agent: Slurp
# User-agent: MSNbot
# User-agent: Teoma # Ask.com

User-agent: *
Crawl-delay: 10
# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /sites/all/
Disallow: /sites/default/
Allow: /sites/default/files/
Disallow: /sites/manomet.org/
Allow: /sites/manomet.org/files/partnerships-pdfs/
Allow: /sites/manomet.org/files/scidocs-pdfs/
Allow: /sites/manomet.org/files/today-manomet-pdfs/
Disallow: /sites/manomet.org/files/textimage/
Disallow: /sites/ccwa/
Allow: /sites/ccwa/files/
Disallow: /sites/climateandwildlife.org/
Disallow: /sites/arcticblog.manomet.org/
Disallow: /sites/70.32.115.167.arcticblog/
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
# added April 2010 by Alison
Disallow: /favicon.ico
Disallow: /favicon.gif
Disallow: /sites/default/files/index.php
Disallow: /news.html
Disallow: /index.html
Disallow: /index.htm
Disallow: /google_map.php
Disallow: /*.htm$
Disallow: /*.html$
Disallow: /*.php$
Allow: /sites/*/files/*.pdf$
Allow: /sites/*/files/*.xls$
Allow: /sites/*/files/*.mp3$
# 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/
# added April 2010 by Alison
Disallow: /data/Unsorted/
Disallow: /data/unsorted/
Disallow: /map/
Disallow: /esp/
Disallow: /textsize/
Disallow: /admin/build/views/
Disallow: /admin/build/views/edit/
Disallow: /admin/build/views/clone/
Disallow: /admin/build/views/export/
Disallow: /views_ui_basic/
Disallow: /rightsideitem/
Disallow: /contentblockbutton/
Disallow: /contentblock/
Disallow: /contentblocksecthead/
Allow: /contact/executive-office-team
Allow: /contact/contact-whsrn
Allow: /sites/list-sites/whsrn-list-sites
# Pattern-matching (Googlebot and Slurp obey)
Disallow: /*/main.php$
Disallow: /*/news.html
Disallow: /*/index.html
Disallow: /*/index.htm
Allow: /*?$ # allow any URL that begins with your domain name, followed by a string, followed by a ?, with no characters after the ?; via http://www.google.com/support/webmasters/bin/answer.py?hl=en&answer=156449
Disallow: /*? # block any URL that begins with your domain name, followed by any string, followed by a question mark, followed by any string; via http://www.google.com/support/webmasters/bin/answer.py?hl=en&answer=156449
# 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/