# Allow all for Googlebot
# User-agent: Googlebot 
# Disallow: 

# Disallow all for Googlebot-image
User-agent: Googlebot-Image
Disallow: / 


User-agent: *
Crawl-delay: 180 # Once in 180 secs

Disallow: /cgi-bin/
Disallow: cgi-bin
Disallow: /tmp/
Disallow: tmp
Disallow: _
#phpBB
#wiki

# Known Search Engine bots / spiders
#
# Inktomi 
# User-agent: Slurp

# WiseNut/LookSmart 
User-agent: ZyBorg
Disallow: /

# Fast/AllTheWeb 
User-agent: fast
Disallow: /

# OpenFind 
User-agent: Openbot
Disallow: /

# Alta Vista 
User-agent: Scooter

## Ban Spambots in .htaccess
#
# SetEnvIfNoCase User-Agent "^EmailSiphon" bad_bot
# SetEnvIfNoCase User-Agent "^EmailWolf" bad_bot
# SetEnvIfNoCase User-Agent "^ExtractorPro" bad_bot
# SetEnvIfNoCase User-Agent "^CherryPicker" bad_bot
# SetEnvIfNoCase User-Agent "^NICErsPRO" bad_bot
# SetEnvIfNoCase User-Agent "^Teleport" bad_bot
# SetEnvIfNoCase User-Agent "^EmailCollector" bad_bot
# SetEnvIfNoCase User-Agent "^LinkWalker" bad_bot
# SetEnvIfNoCase User-Agent "^Zeus" bad_bot
# 
# <Limit GET POST>
# Order Allow,Deny
# Allow from all
# Deny from env=bad_bot
# </Limit>
#
# Use robots.txt to control what you want robots.txt-compliant 'good' spiders to *fetch* 
# -- bandwidth control, in other words. If they are nice by asking, give them a polite robots.txt 
# reply. I specifically said 'fetch' here, because that is what is accomplished. Some search 
# engines, including some of the majors, don't need to fetch a page to list it in their results; 
# They can create a search result based on links they find on other sites pointing to your page, 
# and the link text associated with that link. I find this annoying, but that leads us to... 
#
# Use the on-page meta-robots tag to control what search engines *list* in their results. 
# (If you mark a page as "noindex," then you must allow it to be fetched in robots.txt -- 
# otherwise the spider can't fetch and read the page to find the robots meta tag.) 
#
# Use .htaccess to stop rogue spiders that don't fetch, or that fetch and ignore robots.txt, 
# and to insure that good spiders don't wander into forbidden territory due to a bug in their 
# code or an error in your robots.txt or on-page meta-robots tags.