# Bad bot list copied from Wikipedia.org/robots.txt:-

# 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: /


#
# Esolcourses.com access list
#
User-agent: *
Sitemap: http://www.esolcourses.com/Sitemap.xml
Disallow: /*.gif$
Disallow: /*.jpg$
Disallow: /*.swf$
Disallow: /*.txt$
Disallow: /*.doc$
Disallow: /*.docx$
Disallow: /*.rtf$
Disallow: /*.pdf$
Disallow: /*.png$
Disallow: /*.mp3$
Disallow: /2008/
Disallow: /christmas/
Disallow: /microsites/
Disallow: /sandbox/
Disallow: /content/archives/
Disallow: /content/decw1/
Disallow: /content/decw2/
Disallow: /content/decw3/
Disallow: /content/images/
Disallow: /content/reading/
Disallow: /content/wordsearch/
Disallow: /GeoIP/