User-agent: *
Disallow: /blog/wp-admin
Disallow: /blog/wp-content/plugins
Disallow: /blog/wp-content/cache
Disallow: /blog/wp-content/themes
Disallow: /blog/wp-includes
Disallow: /blog/author
Disallow: /blog/category
Disallow: /blog/contact
Disallow: /blog/trackback
Disallow: /content/pdf
Disallow: /content/images
Disallow: /tmp
Disallow: /blog/wp-atom.php
Disallow: /blog/wp-commentsrss2.php
Disallow: /blog/wp-rss.php
Disallow: /blog/wp-rss2.php
Disallow: */comments
Disallow: /*?*
Disallow: /*?
Disallow: */feed

# robots.txt based on the work of http://wikipedia.org and friends
#
# Please note: There are a lot of pages on this site, and there are
# some misbehaved spiders out there that go _way_ too fast. If you're
# irresponsible, your access to the site will be blocked.

# 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: /

User-agent: TurnitinBot
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: /

User-agent: k2spider
Disallow: /

# Hits many times per second, not acceptable
User-agent: NPBot
Disallow: /

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

User-agent: Fasterfox
Disallow: /

User-agent: duggmirror
Disallow: /

User-agent: Referrer Karma/2.0
Disallow: / 

User-agent: Teoma
Crawl-Delay: 60

User-agent: Slurp
Crawl-delay: 300

User-agent: Yahoo! Slurp
Crawl-delay: 300

Sitemap: http://spreadopenmedia.org/sitemap.xml.gz