#
# robots.txt for http://www.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 may be blocked.
#

# advertising-related bots:
User-agent: Mediapartners-Google*
Disallow: /

# Wikipedia work bots:
User-agent: IsraBot
Disallow:

User-agent: Orthogaffe
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: /

#
# 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: /

User-agent: Slurp
Crawl-delay: 120

User-agent: Yahoo Slurp
Crawl-delay: 120

#
User-agent: *
Disallow: /db/admincp/
Disallow: /db/clientscript/
Disallow: /db/cpstyles/
Disallow: /db/customavatars/
Disallow: /db/customprofilepics/
Disallow: /db/images/
Disallow: /db/modcp/
Disallow: /db/announcement.php
Disallow: /db/attachment.php
Disallow: /db/calendar.php
Disallow: /db/cron.php
Disallow: /db/editpost.php
Disallow: /db/faq.php
Disallow: /db/image.php
Disallow: /db/inlinemod.php
Disallow: /db/joinrequests.php
Disallow: /db/login.php
Disallow: /db/member.php
Disallow: /db/misc.php
Disallow: /db/moderator.php
Disallow: /db/newattachment.php
Disallow: /db/newreply.php
Disallow: /db/newthread.php
Disallow: /db/online.php
Disallow: /db/printthread.php
Disallow: /db/private.php
Disallow: /db/profile.php
Disallow: /db/register.php
Disallow: /db/report.php
Disallow: /db/reputation.php
Disallow: /db/search.php
Disallow: /db/sendmessage.php
Disallow: /db/sendtofriend.php
Disallow: /db/showgroups.php
Disallow: /db/showpost.php
Disallow: /db/subscription.php
Disallow: /db/subscriptions.php
Disallow: /db/threadrate.php
Disallow: /db/usercp.php
Disallow: /db/usernote.php