# Robots.txt file
#

User-agent: *
Disallow: /search/
Disallow: /admin/
Disallow: /1/
Disallow: /rss/
Disallow: /ScriptResource.axd
Disallow: /WebResource.axd
Disallow: /notrk/
Disallow: /redir.aspx
Disallow: /workarea/
Disallow: /widgets/
Disallow: /cm/Files/NonIndex/
Disallow: /*.axd$


Sitemap: http://www.michiganbusiness.org/sitemap/sitemap.ashx

#common for all sites..
#
# robots.txt for http://www.michiganbusiness.org/
#
# Please note: There are a lot of pages on this site, and there are
# some misbehaved spiders out there. If you're
# irresponsible, your access to the site may be blocked.
#

# Trap Bots that do not respect robots.txt
Disallow: /bot-trap/


# don't want the following to crawl..

User-agent: UbiCrawler
Disallow: /

User-agent: DOC
Disallow: /

User-agent: Zao
Disallow: /

# Some of these 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: Teleport
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: linko
Disallow: /

User-agent: HTTrack
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: rogerBot
Crawl-Delay: 10

User-Agent: msnbot
Crawl-Delay: 1

User-Agent: YandexBot
Crawl-Delay: 10

User-Agent: TweetedTimes
Crawl-Delay: 30

User-Agent: TweetedTimes Bot/1.0
Crawl-Delay: 30

User-Agent: Motorola
Crawl-Delay: 30

User-Agent: Jakarta Commons-HttpClient/3.1
Crawl-Delay: 30

# END OF FILE