#
# robots.txt for http://mm.homeunix.org:8380/
#  (which is/was redirection of http://mar.i.am/)
#
# $Id: robots.txt,v 1.21 2006/03/11 00:38:37 mar Exp $
#


# (original, copyright 2004 by Marco Munari)
# Original Information Notice:
#
# [robots.txt has limited concepts and syntax
# so actually it do not permit to express formally the following...]
#
# 1. The keywords "here", "this file", "this site" are principally
#   related to http://mm.homeunix.org:8380/
#   so "here", "this file"  is http://mm.homeunix.org:8380/robots.txt
#   "this site"  is http://mm.homeunix.org:8380/ and subdirs
#
# 2. All permissions expressed here
#   a. MUST be considered extension of an eternity default "Disallow: /"
#     (even in case this file is unspecified or unavailable).
#   b. SHOULD be evalued immediatly(max 2 hours) after GET /robots.txt HTTP
#   c. MUST expire one year after GET unless updated
#   update of permission by this robots.txt is RECOMMENDED
#
# In other words: Every User-Agent (and simple user) have to keep checking
# if new version of this file still permits buffering the
# original information more than the default Disallow all.
# When you see "Allow" in this file you can put in a buffer memory
# unextensible in external storage capability, the original unalterated
# information contained in this web site.
#
# Note: in case of unavailability of this file, a RECOMMANDED copy of
#       its content SHELL remember permission expiration
#
# Images and text published here are almost original material
# produced by the author (Marco Munari)
# actually:
# creative PNG images ~99.9% (exception is public*.gif.png, to be removed)
# creative JPG images 100% (even sky now is math generated)
# text html css and javascript origin is specified
# TMP: before full verify
#      some public notice missing are possoble [sorry]
#      because some few reference could be stored only in local
#      repository, in case you need, you can ask to author@allerta.it

# Every original information obtained from this site
# MUST be related in some way to the original URL (the link) and this file.


#
# We reserve the right to change publishing permission
# unless explicitly expressed in this file
# in future relative even to previous data.




############################
# Options for search engines


# google
User-Agent: googlebot
# Crawl-delay: 300
Allow: /


User-agent: Googlebot-Image
Allow: /




# inktome -> yahoo
# http://help.yahoo.com/help/us/ysearch/slurp
User-agent: Slurp
Crawl-delay: 30
Allow: /
Allow: /alessandromunari

User-agent: MSNBot
Allow: /
Disallow: /ie
Disallow: /ie*


#User-Agent: Webcrawler
#Allow: /pub
#Disallow: *
#Disallow: /
#Allow: /alessandromunari

# alexa
User-Agent: ia_archive
Disallow: /

# www.altavista.com
User-Agent: scooter
Disallow:
# it seems the effect of "Disallow:" (without parameter) is an Allow

##############################
# Options for archiving engine


User-Agent: ia_archiver
Allow: /
Allow: /register/
Allow: /pub/
Allow: /co/
Allow: /images/
Disallow: /




#####################################
# Options for intranet search engines


#User-agent: MAR Intranet
#Disallow: /Out-Of-Date




##################################
# Options for others


User-agent: *
Allow: /
# 2006 open
Disallow: /cgi-bin
Disallow: /tmp
Disallow: /priv
Disallow: ie*

#Disallow: * is not standard, but comprehensive!

#following rules are not robots standard (User without "-agent", expire)
#User: *
#Disallow: /
#Disallow: *
#Content-Expire: now or tomorrow