Sitemap: http://www.numberzoom.com/sitemap_index.xml.gz



# 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: libwww
Disallow: /

User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

User-agent: laycat
Disallow: /

User-agent: Charlotte
Disallow: /

User-agent: ia_archiver
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: IRLbot
Disallow: /

User-agent: larbin
Disallow: /

User-agent: Nutch
Disallow: /

User-agent: OmniExplorer_Bot
Disallow: /

User-agent: sogou spider
Disallow: /

User-agent: psbot
Disallow: /

User-agent: dotbot/1.0 
Disallow: /

User-agent: ccbot
Disallow: /
                                       
User-agent: PiplBot
Disallow: /                 

User-agent: KSCrawler
Disallow: /                      

User-agent: MLBot
Disallow: /                      

User-agent: Speedy
Disallow: /                      

User-agent: spbot
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: 3

#5 second delay

User-agent: *
Disallow: /en/Special:Random
Disallow: /en/Special%3ARandom
Disallow: /en/Special:Search
Disallow: /en/Special%3ASearch
Disallow: /en/Special:Statistics
Disallow: /en/Special%3AStatistics
Disallow: /en/Special:WhatLinksHere/
Disallow: /en/Special%3AWhatLinksHere/
Disallow: /en/Special:MovePage
Disallow: /en/Special%3AMovePage
Disallow: /en/Special:RecentChangesLinked/
Disallow: /en/Special%3ARecentChangesLinked/
Disallow: /en/*oldid
Disallow: /en/*printable
Disallow: /en/*edit
Disallow: /en/*history
Disallow: /en/*delete
Disallow: /en/*protect
Disallow: /en/*watch
Disallow: /en/*redlink

Crawl-delay: 5