###################################
# Robots.txt
#
###################################
#
Sitemap: http://www.apnauttarakhand.com/sitemap.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: /sitemap.xml
Disallow: /wp-
Disallow: /feed/
Disallow: /trackback/
Disallow: /rss/
Disallow: /comments/feed/
Disallow: /page/
Disallow: /date/
Disallow: /comments/
Disallow: /cgi-bin/
Disallow: /200*
Disallow: /*?*
Disallow: /iframes/
Disallow: /recommends/


# Yahoo - Too aggressive
#	So limit it as much as possible.
User-agent: Slurp
# Disallow Everything
Disallow: /
# Now allow bits and then disallow bits
Allow: /sitemap.xml
Allow: /index.php?*;*




# 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: /


# 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: *

Disallow: /wp-
Disallow: /feed/
Disallow: /trackback/
Disallow: /rss/
Disallow: /comments/feed/
Disallow: /page/
Disallow: /date/
Disallow: /comments/
Disallow: /cgi-bin/
Disallow: /200*
Disallow: /*?*
Disallow: /iframes/
Disallow: /recommends/