# spinn3r and radian6 indexes feeds, diffs
# Radian6
User-agent: Radian6
Disallow: /
User-agent: R6_FeedFetcher
Disallow: /
User-agent: R6_CommentReader
Disallow: /

#still beta, and crawl bad urls
User-agent: VoilaBot
Disallow: /

#Copyright sheriff
User-agent: copyright sheriff
Disallow: /

#http://code.google.com/p/hcardvalidator/source/browse/trunk/robots.txt?r=6#
User-agent: Spinn3r
Disallow: /
User-agent: Tailrank
Disallow: /
User-agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2.1; aggregator:Tailrank (Spinn3r 2.1); http://spinn3r.com/robot) Gecko/20021130
Disallow: /

# not sur it works, but I try... russian bot which is not respectful
User-agent: Nigma
Disallow: /

# 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: /

#
# 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: /

# http://www.turnitin.com/  - Plaguerism Checker
User-agent: TurnitinBot
Disallow: /

# http://www.netseer.com/  - LA based startup spider
User-agent: Teemer
Disallow: /

# http://www.WISEnutbot.com  - LookSmart Spider
User-agent: ZyBorg
Disallow: /

# LinkWalker - Marketing Co Spider
User-agent: LinkWalker
Disallow: /

# Zeus - Marketing Co Spider
User-agent: Zeus
Disallow: /

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

# 192.com crawls all UK websites and indexes contact information
User-agent: 192.comAgent
Disallow: /

#NetinfoBot
User-agent: NetinfoBot
Disallow: /

# Picsearch -indexing pictures from the web
User-agent: psbot
Disallow: /

# Accelobot is a search engine for online marketing trens and emergin technologies.
User-agent: Accelobot
Disallow: /

# IRL-crawler is a Texas A&M research project
User-agent: IRLbot 
Disallow: /

# MSRBot is a Microsoft web crawler used to collect data from the web for further study.
User-agent: MSRBot
Disallow: /

# Friendly, low-speed bots are welcome viewing article pages, but not
# dynamically-generated pages please.
#
User-agent: *
Crawl-delay: 300
Disallow: /config/
Disallow: /quojapa/
Disallow: /files/
Disallow: /Special:AWCforum/?action=search
Disallow: /Special:Browse/
Disallow: /Special:Pages_
Disallow: /Special:WikiFeeds/
Disallow: /index.php
Disallow: /MediaWiki:
Disallow: /Discussion
Disallow: /Utilisateur:
Disallow: /User:
Disallow: /Talk
Disallow: /Trap/DO_NOT_CLICK_HERE