###################################
# Robots.txt
#
###################################
#
# My Sitemap - I don't provide it just for the fun of it
# http://www.merapahadforum.com/index.php?action=kitsitemap;xml

# Google - Most Important bot
#	Unfortunately a robots.txt will only stop it crawling certain urls, and NOT adding any
#	urls which it comes across into its index. So we're relying on a meta noindex tag.
User-agent: Googlebot
Allow: /index.php?action=kitsitemap;xml
Disallow: /*?action*
Disallow: /*sort=*
Disallow: /*msg*
Disallow: /?wap2
Disallow: /?wap

# Don't index mobile versions
Disallow: /index.php?*;wap
Disallow: /index.php?*;wap2
Disallow: /index.php?*;imode
Disallow: /attachments/
Disallow: /Packages/
Disallow: /Smileys/
Disallow: /Sources/
Disallow: /Themes/
# Default SMF Actions
Disallow: /index.php?theme


# Yahoo - Too aggressive
#	So limit it as much as possible.
User-agent: Slurp
# Disallow Everything
Disallow: /
# Now allow bits and then disallow bits
Allow: /index.php?action=kitsitemap;xml
Allow: /kitsitemap.xml$
Allow: /robots.txt$
Allow: /index.php$
Allow: /index.php?topic=*.0$
Allow: /index.php?topic=*.*0$
Allow: /index.php?topic=*.*5$
Allow: /index.php?board=*.0$
Allow: /index.php?board=*.*0$
Allow: /index.php?board=*.*5$
Disallow: /*?action*
Disallow: /*sort=*
Disallow: /*msg*
# But don't allow these
Disallow: /index.php?*.msg
Disallow: /index.php?topic=*.msg*0$
Disallow: /index.php?topic=*.msg*5$
Disallow: /index.php?*.new
Disallow: /attachments/
Disallow: /Packages/
Disallow: /Smileys/
Disallow: /Sources/
Disallow: /Themes/
# Default SMF Actions
Disallow: /index.php?theme



# Anything with a ; disallow
Disallow: /index.php?*;*

# Bad bot - Often ignores robots.txt - Waste of bandwidth
#	Despite claiming on their website to be a search engine in development
#	I'm suspicious as to whether they are a harvester pretending to be SE
User-agent: Twiceler
Disallow: /

User-Agent: W3C-checklink
Disallow: /

User-agent: TurnitinBot
Disallow: /

# Stop following PHPSESSID's
User-Agent: MJ12bot
Disallow: /index.php?PHPSESSID

# Catch all (remainder)
#	Will be followed by any bots other than ones identified above
#	Uses BASIC robots.txt directives without wildcards, end-anchors etc
#	So Spiders should understand these (including MSNBOT)
User-agent: *
# Default SMF Folders
Disallow: /attachments/
Disallow: /Packages/
Disallow: /Smileys/
Disallow: /Sources/
Disallow: /Themes/
# Default SMF Actions
Disallow: /index.php?theme
Disallow: /*?action*
Disallow: /*sort=*
Disallow: /*msg*