# For more details on specific robots, check out:
# http://spiralofhope.com/website-standards-compliance.html

# User-agent: *
# Disallow: /css/
# Disallow: /i/
# Disallow: /js/

# Sitemap is non-standard, but is recognised by major search engines.
# http://en.wikipedia.org/wiki/Robots_exclusion_standard#Sitemap
# http://en.wikipedia.org/wiki/Sitemaps
# http://www.google.com/support/webmasters/bin/topic.py?topic=8476
Sitemap: http://spiralofhope.com/sitemap.xml

# ---
# User-created:
# ---

# http://validator.w3.org/docs/checklink.html#bot
User-agent: W3C-checklink
Disallow:

# Internet Archive (archive.org): http://www.alexa.com/help/webmasters
User-agent: ia_archiver
Disallow:

# google.com (aol.com)
User-agent: Googlebot
Disallow:

# bing.com (MSN, live.com)
User-agent: msnbot
Disallow:

# yahoo.com, altavista.com
User-agent: Slurp
Disallow:
# Crawl-delay is non-standard, but recognised by yahoo's engine.
# http://en.wikipedia.org/wiki/Robots_exclusion_standard#Crawl-delay_directive
Crawl-delay: 20

# cuil.com
User-agent: Twiceler
Disallow:


# ---
# Taken from http://en.wikipedia.org/robots.txt 2010-05-10
# ---
# 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: /