#---------------------------------------------------------
# path : /web/docs/canoe/robots.txt
#
# specification :
# include *.rss.canoe.ca/
# exclude: http://canoe.ca/ (only the homepage, not the directory)
# exclude: http://www.canoe.ca/Canoe/SunMedia/home.html (only the homepage, not the directory)
# exclude: http://www.canoe.ca/OntQueTicker/ (only that page, not the directory)
# exclude: http://www.canoe.ca/WesternTicker/ (only that page, not the directory)
# exclude: http://www.canoe.ca/AtlanticTicker/ (only that page, not the directory)
# exclude: http://www.canoe.ca/CanoeMail/  (the entire directory, except the homepage)
# exclude: http://www.canoe.ca/cgi-bin/mb2/view.pl?board=slam (only that page, not the directory)
# exclude: http://www.canoe.ca/cgi-bin/reg/NR-register.pl?MODE=SUBSCRIBE&LOOK=HOME_GARDEN&PRODUCT=44 (only that page, not the directory)

# This file had pre-existing values which have remained in place as they were found.

#---------------------------------------------------------
# Domain: http://www.canoe.ca/
# Creation: 11/28/2007
# Update: 12/14/2009

User-agent: *
Disallow: /event.ng/
Disallow: /html.ng/
Disallow: /js.ng/
Disallow: /click.ng/
Disallow: /image.ng/
Disallow: /ping.ng/

User-agent: Yahoo! DE Slurp
# Disallow: /$
## 2 below commented out by ptrin, oct. 16 2008
#Disallow: /index.php
#Disallow: /home.html
Disallow: /home.php
Disallow: /CanoeMail/
Disallow: /Canoe/SunMedia/home.html
Disallow: /OntQueTicker/home.html
Disallow: /WesternTicker/home.html
Disallow: /AtlanticTicker/home.html
Disallow: /cgi-bin/mb2/view.pl?board=slam
Disallow: /cgi-bin/reg/NR-register.pl?MODE=SUBSCRIBE&LOOK=HOME_GARDEN&PRODUCT=44

# 2009 Dec 11
# User-Agents to block
# Note: match as substrings - full User-Agents will be longer, and will have
# varying version numbers

# Meltwater
User-agent: libwww
Disallow: /

User-agent: libwww-perl
Disallow: /

User-agent: mag-crawl
Disallow: /

# Moreover
User-agent: Moreoverbot
Disallow: /

# Vocus
User-agent: Vocus
Disallow: /

# CustomScoop
User-agent: ScooperBot
Disallow: /

# CyberAlert
User-Agent: CyberAlert
Disallow: /

# CEDROM
User-agent: CEDROM
Disallow: /

User-agent: Newscan
Disallow: /

User-agent: Eureka
Disallow: /

User-agent: Europresse
Disallow: /

# Radian6
User-agent: Radian6
Disallow: /

User-agent: R6_FeedFetcher
Disallow: /

User-agent: R6_CommentReader
Disallow: /

#Extra Rogue Robots
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: /

User-agent: wget 
Disallow: /

User-agent: grub-client 
Disallow: /

User-agent: k2spider 
Disallow: /

User-agent: NPBot 
Disallow: /

User-agent: WebReaper 
Disallow: /

User-agent: ia_archiver 
Disallow: /

User-agent: zeus 
Disallow: /

# Sitemap: http://www.canoe.com/sitemap_canoe_index.xml

# EOF