# /robots.txt file for http://www.flowfood4health.com

#Examples...

#This allows a crawler to access everywhere
#User-agent: mr-webcrawler
#Disallow:

#This allows a crawler no access, as all URLs on a server start with '/' which is all of them
#User-agent: mr-webcrawler
#Disallow: /

#This stops all robots visiting URLs with /images or /hub '*' means any other useragent
#User-agent: *
#Disallow: /images/
#Disallow: /hub/

#Other info from Wikipedia - http://en.wikipedia.org/wiki/Robots.txt
#Crawl-delay: 30     - in seconds to wait between successive requests to the same server
#Request-rate: 1/5         - maximum rate is one page every 5 seconds
#Visit-time: 0600-0845     - only visit between 6:00 AM and 8:45 AM UT (GMT)




#A L L O W E D

#Allow Google Bot
User-agent: Googlebot
Disallow:
Crawl-delay: 5




#D I S A L L O W E D

#Disallow all slurp as a test
User-agent: Slurp
Disallow: /images/
Disallow: /_mmServerScripts
Crawl-delay: 30

#Disallow all spidering of images and hub
User-agent: *
Disallow: /images/
Disallow: /_mmServerScripts
Crawl-delay: 30

#Disallow Baidu Bot (Japanese)
User-agent: Baiduspider
Disallow: /_mmServerScripts
Disallow: /

#Disallow Boitho dc Bot (Norway)
User-agent: boitho.com-dc
Disallow: /

#Disallow Busiverse Bot (Turkey Sirketce/Busiverse )
User-agent: Busiverse
Disallow: /

#Disallow CazoodleBot - from University of Illinois
User-agent: CazoodleBot
Disallow: /

#Disallow Exabot Bot - Exalead
User-agent: Exabot
Disallow: /

#Disallow Google Image Bot
User-agent: Googlebot-Image
Disallow: /

#Disallow heritrix Bot - from Yell.Com
User-agent: heritrix
Disallow: /

#Disallow IRLbot - IRL Texas AM research bot
User-agent: IRLbot
Disallow: /

#Disallow Jyxobot - Czech Webcrawler for Jyxo
User-agent: Jyxobot
Disallow: /

#Disallow Majestic12.co.uk
User-agent: MJ12bot
Disallow: /

#Disallow Mirago.com
User-agent: Mirago-Test-Robot (http://www.miragorobot.com)
Disallow: /

#Disallow MSN from seeing gifs and jpgsd
User-agent: msnbot
Disallow: /*.gif$
Disallow: /*.jpeg$

#Disallow NimbleCrawler (http://www.webmasterworld.com/forum93/858.htm)
UserAgent: nimblecrawler
Disallow: /

#Disallow psbot spidering of images and hub
User-agent: psbot
Disallow: /

#Disallow Sirketce Bot (Turkey Sirketce/Busiverse )
User-agent: Sirketce
Disallow: /

#Disallow Seekbot - http://www.seekport.co.uk/seekbot/
User-agent: Seekbot
Disallow: /

#Disallow semanticdiscovery - from Southern Utah University (compyter Science Dept.)
User-agent: semanticdiscovery
Disallow: /

#Disallow Sogou - Chinese Search Engine
User-agent: Sogou
Disallow: /

#Disallow SoSo - Chinese Search Engine
User-agent: Soso
Disallow: /

#Disallow SoSoImageSpider - Chinese picture Search Engine
User-agent: Sosoimagespider
Disallow: /

#Disallow TinEye - Image trawler Search Engine
User-agent: TinEye
Disallow: /

#Disallow TurnITin - "This robot collects content from the Internet for the sole purpose of helping educational institutions prevent plagiarism"
User-agent: TurnitinBot
Disallow: /

#Disallow Twiceler - Cuill (also Barred IPs on firewall)
User-agent: twiceler
Disallow: /


#Disallow Voilabot Bot - France Telecom
User-agent: VoilaBot 
Disallow: /

#Disallow WebAlta Bot - Russian
User-agent: WebAlta 
Disallow: /

#Disallow Yahoo Image Bot
User-agent: Yahoo-MMCrawler
Disallow: /

#Disallow YodaoBot - Chinese Search Engine
User-agent: YodaoBot
Disallow: /

#Disallow zermelo - Bot du Jour from Amazon - may need to block IP range
User-agent: zermelo
Disallow: /

#Disallow All Bots to see in '/flash' folder
User-agent: *
Disallow: /flash
Disallow: /404.asp




#O L D

#Not spidering ATM, but was in original robots.txt
#User-agent: Mediapartners-Google* 
#Disallow: