#!/dev/null
#
#############################################################################
#############################################################################
##
##      Copyright (C) 2007 Rajstennaj Barrabas, Milford, NH 03055
##      All Rights Reserved.  Proprietary and Confidential.
##
##  FILE
##      robots.txt
##
##  DESCRIPTION
##      Hints for web crawlers
##
##      Generally,      1) allow the major search engines
##                      2) Disallow the major spam harvestors
##                      3) Require them to access the site slowly
##
##  VERSION
##      12/10/05    RB - Initial coding
##
#############################################################################
#############################################################################


#############################################################################
#
# Allow the local cheklink program
#
User-agent: W3C-checklink
Disallow: 

#############################################################################
#
# Disallow the wayback machine
#
User-agent: ia_archiver
Disallow: /

#############################################################################
#
# Allow the major search engines
#
User-agent: Googlebot
Disallow: 

User-agent: Googlebot-Image
Disallow: 

User-agent: MSNBot
Disallow: 

User-agent: Slurp
Disallow: 

User-agent: Teoma
Disallow: 

User-agent: Gigabot
Disallow: 

User-agent: Scrubby
Disallow: 

User-agent: Robozilla
Disallow: 

User-agent: Nutch
Disallow: 

User-agent: ia_archiver
Disallow: 

User-agent: baiduspider
Disallow: 

User-agent: yahoo-mmcrawler
Disallow: 

User-agent: psbot
Disallow: 

User-agent: asterias
Disallow: 

User-agent: yahoo-blogs/v3.9
Disallow: 

#############################################################################
#
# Disallow the advertising-related bots:
#
User-agent: Mediapartners-Google*
Disallow: /

User-agent: IsraBot
Disallow:

User-agent: Orthogaffe
Disallow:

#############################################################################
#
# Crawlers that are kind enough to obey, but which we'd rather not have
#   unless they're feeding search engines.
#
User-agent: UbiCrawler
Disallow: /

User-agent: DOC
Disallow: /

User-agent: Zao
Disallow: /

#############################################################################
#
# Some bots are known to be trouble, particularly those 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: 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: /

#
# Sorry, wget in its recursive mode is a frequent problem.
# Please read the man page and use it properly; there is a
# --wait option you can use to set the delay between hits,
# for instance.
#
User-agent: wget
Disallow: /

#
# The 'grub' distributed client has been *very* poorly behaved.
#
User-agent: grub-client
Disallow: /

#
# Doesn't follow robots.txt anyway, but...
#
User-agent: k2spider
Disallow: /

#
# Hits many times per second, not acceptable
# http://www.nameprotect.com/botinfo.html
#
User-agent: NPBot
Disallow: /

#
# A capture bot, downloads gazillions of pages with no public benefit
# http://www.webreaper.net/
#
User-agent: WebReaper
Disallow: /

#
# Disallow everyone else, don't let them drag down the site 
#   with their crawling
#
User-agent: *
Disallow: /
Disallow: /cgi-bin/
Disallow: /Images
Crawl-delay: 120