# robots.txt for slwa.wa.gov.au
# based on the robots.txt http://www.wikipedia.org/ 

# The first part of the file instructs all WWW robots NOT to index pages all pages, but only those in certain directories 
User-agent: *
Allow: /dead_reckoning/
Allow: /findinghome/
Allow: /swan_river/
Disallow: /index
Disallow: /find
Disallow: /find/
Disallow: /for
Disallow: /for/
Disallow: /about_us
Disallow: /about_us/
Disallow: /whats_on
Disallow: /whats_on/
Disallow: /support_us
Disallow: /support_us/


# advertising-related bots:
User-agent: Mediapartners-Google*
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.

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: /