[lp_client_browser(9)]
| Link | lp_client_browser(9) |
| Author | Jonathan Guthrie |
| Category | Client |
| Version | 9.x |
| License | Public Domain |
| Posted | 11 Dec 2012 |
| Updated | 11 Dec 2012 |
| More by this author... | |
Description
Experimental port - more details to come soon.
Sample Usage
Source Code
Click the "Download" button below to retrieve a copy of this tag, including the complete documentation and sample usage shown on this page. Place the downloaded ".inc" file in your LassoStartup folder, restart Lasso, and you can begin using this tag immediately.
define lp_client_browser(user_agent = void, ...) => {
// http://www.botsvsbrowsers.com/
// http://www.quirksmode.org/js/detect.html
// http://en.wikipedia.org/wiki/User_agent
// http://browsers.garykeith.com/downloads.asp
// http://www.pgts.com.au/pgtsj/pgtsj0212d.html
// http://www.pgts.com.au/download/data/robots_list.txt
// http://www.user-agents.org/index.shtml
// http://www.robotstxt.org/wc/active/html/contact.html
// http://www.jafsoft.com/searchengines/webbots.html
// http://www.useragentstring.com/pages/useragentstring.php
/* Browser types:
B = Browser (Desktop)
C = Link/Bookmark/Server Checker
D = Download/FTP tool
E = Email Reader
F = Feed Reader
L = Library
M = Mobile Browser
O = Offline Browsing
P = Proxy, Web filter
R = Robot/Crawler/Spider
S = Spam Harvester, Bad Bot
U = Unknown
V = HTML/CSS/JS Validator
X = Suspected Robot/Crawler/Spider
*/
if(local_defined('user_agent'))
local(client_browser = #user_agent)
else
local(client_browser = client_browser)
/if
#client_browser->trim
if(#client_browser->size == 0)
return map('browser' = 'No User Agent Provided', 'version' = '', 'os' = '', 'type' = 'Suspected Robot/Crawler/Spider', 'typecode' = 'X')
/if
local('return' = map('browser' = '', 'version' = '', 'os' = '', 'type' = '', 'typecode' = ''))
//-------------------------------------------------------------------
// browser
//-------------------------------------------------------------------
if(#client_browser->beginswith('mozilla/'))
iterate(_lp_client_browser_mozilla, local(browser))
if(#client_browser->contains(#browser->name))
#return->insert('browser' = #browser->value->get(1))
#return->insert('typecode' = #browser->value->get(2))
// browser version
local(version = #client_browser->substring(#client_browser->find(#browser->name) + #browser->name->size, 255))
#version = string_findregexp(#version, -find = '\\d[^\\s;()\\]]*')
if(#version->size)
#return->insert('version' = #version->get(1))
/if
loop_abort
/if
/iterate
if(#return->find('browser')->size == 0)
/// keep trying
// handle mozilla and old netscape versions, the problem children
if(!#client_browser->contains('compatible') && !#client_browser->contains('http') && !#client_browser->contains('@') && !#client_browser->contains('www'))
local(mozver = string_findregexp(#client_browser, -find = '\\d'))
if(#mozver->size)
#mozver = integer(#mozver->get(1))
if(#mozver < 5 && #client_browser->contains('['))
// old Netscape
#return->insert('browser' = 'Netscape')
#return->insert('typecode' = 'B')
// browser version
local(version = #client_browser)
#version = string_findregexp(#version, -find = '\\d[^\\s;()\\]]*')
if(#version->size)
#return->insert('version' = #version->get(1))
/if
else(#mozver == 5 && #client_browser->contains('gecko/') && #client_browser->contains('rv:'))
if(#client_browser->split('gecko/')->last->split(' ')->size == 1)
// mozilla
#return->insert('browser' = 'Mozilla')
#return->insert('typecode' = 'B')
// browser version
local(version = #client_browser->substring(#client_browser->find('rv:') + 'rv:'->size, 255))
#version = string_findregexp(#version, -find = '\\d[^\\s;()\\]]*')
if(#version->size)
#return->insert('version' = #version->get(1))
/if
/if
/if
/if
/if
// handle msie
if(#client_browser->contains('compatible; MSIE') && !#client_browser->contains('http') && !#client_browser->contains('@') && !#client_browser->contains('www') && !#client_browser->contains('.com'))
if(#client_browser->split(')')->last->size == 0)
#return->insert('browser' = 'Internet Explorer')
#return->insert('typecode' = 'B')
// browser version
local(version = #client_browser->substring(#client_browser->find('MSIE') + 'MSIE'->size, 255))
#version = string_findregexp(#version, -find = '\\d[^\\s;()\\]]*')
if(#version->size)
#return->insert('version' = #version->get(1))
/if
/if
/if
/if
else
// lots of possibilities
iterate($_lp_client_browser_other->find(#client_browser->get(1)), local(browser))
if(#client_browser->beginswith(#browser->name))
#return->insert('browser' = #browser->value->get(1))
#return->insert('typecode' = #browser->value->get(2))
// browser version
local(version = #client_browser->substring(#client_browser->find(#browser->name) + #browser->name->size, 255))
#version = string_findregexp(#version, -find = '\\d[^\\s;()\\]]*')
if(#version->size)
#return->insert('version' = #version->get(1))
/if
loop_abort
/if
/iterate
/if
// special handling of version info for newer versions of Safari and Opera
if(#return->find('browser') == 'Safari' || #return->find('browser') == 'Opera')
local(version = #client_browser->find('Version/'))
if(#version != 0)
#version = #client_browser->substring(#version + 7, 255)
#version = string_findregexp(#version, -find = '\\d[^\\s;()\\]]*')
if(#version->size)
#return->insert('version' = #version->get(1))
/if
/if
/if
//-------------------------------------------------------------------
// os
//-------------------------------------------------------------------
local(os = array('android' = 'Android', 'blackberry' = 'Blackberry', 'ipad' = 'iPad', 'iphone' = 'iPhone', 'ipod' = 'iPod', 'palm' = 'PalmOS', 'symbian' = 'Symbian', 'windows ce' = 'WinCE', 'windows' = 'Windows', 'win16' = 'Windows', 'win32' = 'Windows', 'win64' = 'Windows', 'win95' = 'Windows', 'win98' = 'Windows', 'winNT' = 'Windows', 'macintosh' = 'Macintosh', 'darwin' = 'Macintosh', 'panther' = 'Macintosh', 'leopard' = 'Macintosh', 'osx' = 'Macintosh', 'os x' = 'Macintosh', 'powerpc' = 'Macintosh', 'linux' = 'Linux', 'kanotix' = 'Linux', 'ubuntu' = 'Linux', 'mepis' = 'Linux', 'debian' = 'Linux', 'suse' = 'Linux', 'redhat' = 'Linux', 'red hat' = 'Linux', 'slackware' = 'Linux', 'mandrake' = 'Linux', 'gentoo' = 'Linux', 'fedora' = 'Linux', 'solaris' = 'Unix', 'unix' = 'Unix', 'bsd' = 'Unix', 'sun' = 'Unix', 'irix' = 'Unix', 'irix' = 'Unix', 'hpux' = 'Unix', 'hp-ux' = 'Unix', 'aix' = 'Unix', 'sco' = 'Unix', 'mpras' = 'Unix', 'reliant' = 'Unix', 'dec' = 'Unix', 'sinix' = 'Unix', 'nintendo' = 'Nintendo', 'wii' = 'Nintendo', 'playstation' = 'PlayStation', 'risc' = 'RISC OS', 'amiga' = 'Amiga', 'beos' = 'BeOS', 'os2' = 'OS/2', 'os/2' = 'OS/2', 'webtv' = 'WebTV', 'xbox' = 'Xbox'))
iterate(#os, local(o))
if(#client_browser->contains(#o->name))
#return->insert('os' = #o->value)
loop_abort
/if
/iterate
//-------------------------------------------------------------------
// if still unknown, see if it has a bot keyword
//-------------------------------------------------------------------
if(#return->find('typecode') == 'U' || #return->find('typecode') == '')
local(bots = array('agent', 'archive', 'bot', 'check', 'crawl', 'creep', 'feed', 'fetch', 'find', 'get', 'grub', 'index', 'info', 'leech', 'libwww', 'link', 'manage', 'proxy', 'robo', 'search', 'scrub', 'seek', 'siphon', 'site', 'slurp', 'spider', 'url', 'valid', 'worm'))
iterate(#bots, local(bot))
if(#client_browser->contains(#bot))
#return->insert('browser' = 'Suspected Bot "' + #bot + '"')
#return->insert('typecode' = 'X')
loop_abort
/if
/iterate
/if
//-------------------------------------------------------------------
// check if mobile browser
//-------------------------------------------------------------------
// http://mobiforge.mobi/developing/story/mobile-sites-with-joomla-cms?dm_switcher=true
if('Android,Blackberry,iPad,iPhone,iPod,PalmOS,Symbian,WinCE' >> #return->find('OS'))
#return->insert('typecode' = 'M')
else(client_headers >> 'vnd.wap' || client_headers >> 'HTTP_X_WAP_PROFILE' || client_headers >> 'HTTP_PROFILE' || client_headers >> 'UA-pixels' || client_headers >> 'X-OperaMini')
#return->insert('typecode' = 'M')
/if
//-------------------------------------------------------------------
// assign the type based on the typecode
//-------------------------------------------------------------------
select(#return->find('typecode'))
case('B')
#return->insert('type' = 'Browser')
case('C')
#return->insert('type' = 'Link/Bookmark/Server Checker')
case('D')
#return->insert('type' = 'Download/FTP tool')
case('E')
#return->insert('type' = 'Email Reader')
case('F')
#return->insert('type' = 'Feed Reader')
case('L')
#return->insert('type' = 'Library')
case('M')
#return->insert('type' = 'Mobile Browser')
case('O')
#return->insert('type' = 'Offline Browsing')
case('P')
#return->insert('type' = 'Proxy, Web filter')
case('R')
#return->insert('type' = 'Robot/Crawler/Spider')
case('S')
#return->insert('type' = 'Spam Harvester, Bad Bot')
case('U')
#return->insert('type' = 'Unknown')
case('V')
#return->insert('type' = 'HTML/CSS/JS Validator')
case('X')
#return->insert('type' = 'Suspected Robot/Crawler/Spider')
case
#return->insert('type' = 'Unknown')
#return->insert('typecode' = 'U')
/select
return #return
}
// browsers with user agents that begin with "mozilla/"
define _lp_client_browser_mozilla => {
array(
// mobile browsers
'iemobile' = array('MSIE Mobile','M'),
'Mobile Safari' = array('Mobile Safari','M'),
'Opera Mini' = array('Opera Mini','M'),
'Opera Mobi' = array('Opera Mobi','M'),
// Other browsers
'icab' = array('iCab','B'),
'oregano' = array('Oregano','B'),
'amigavoyager' = array('AmigaVoyager','B'),
'ibrowse' = array('IBrowse','B'),
// email readers
'thunderbird' = array('Thunderbird','E'),
'Mnenhy' = array('Mnenhy Thunderbird Plug-in','E'),
// proxies
'BorderManager' = array('Novell BorderManager','P'),
// link checkers
'LinksManager.com' = array('LinksManager.com','C'),
'www.euro-directory.com' = array('www.euro-directory.com','C'),
'ZyBorg' = array('ZyBorg','C'),
// offline
'MSIECrawler' = array('MSIE Offline Favorites','O'),
// robots
'AbiLogicBot' = array('AbiLogicBot','R'),
'AnyApexBot' = array('AnyApexBot','R'),
'Arachmo' = array('Arachmo','R'),
'Ask Jeeves' = array('Ask Jeeves','R'),
'BecomeBot' = array('BecomeBot','R'),
'B-l-i-t-z-B-O-T' = array('BlitzBOT','R'),
'BlitzBOT' = array('BlitzBOT','R'),
'B_L_I_T_Z_B_O_T' = array('BlitzBOT','R'),
'Cerberian Drtrs' = array('Cerberian Drtrs','R'),
'FDSE robot' = array('FDSE robot','R'),
'Fluffy the spider' = array('www.searchhippo.com','R'),
'FurlBot' = array('FurlBot','R'),
'Girafabot' = array('Girafabot','R'),
'Googlebot' = array('Googlebot','R'),
'grub-client' = array('grub.org','R'),
'HTTrack' = array('HTTrack offline browser utility','O'),
'Larbin' = array('Larbin','R'),
'MojeekBot' = array('MojeekBot','R'),
'MuscatFerret' = array('MuscatFerret','R'),
'Paros' = array('Paros','R'),
'scan4mail' = array('scan4mail anti-spam tool','C'),
'ScoutJet' = array('ScoutJet','R'),
'Scrubby' = array('Scrubby','R'),
'SEOChat::Bot' = array('SEOChat::Bot','R'),
'Shoula robot' = array('Shoula robot','R'),
'slurp@inktomi' = array('inktomi.com','R'),
'Teoma' = array('Ask Jeeves','R'),
'VoilaBot' = array('VoilaBot','R'),
'Vonna.com' = array('Vonna.com','R'),
'www.galaxy.com' = array('Galaxy.com','R'),
'Yahoo! Slurp' = array('Yahoo!','R'),
'YahooSeeker' = array('Yahoo!','R'),
'Zealbot' = array('Zealbot','R'),
// spam bots
'Indy Library' = array('Delphi/C++ library used mostly by Asian spammers','S'),
// Gecko browsers
'iceweasel' = array('Iceweasel','B'),
'flock' = array('Flock','B'),
'epiphany' = array('Epiphany','B'),
'beonex' = array('Beonex','B'),
'camino' = array('Camino','B'),
'chimera' = array('Chimera','B'),
'galeon' = array('Galeon','B'),
'k-meleon' = array('K-Meleon','B'),
'k-ninja' = array('K-Ninja','B'),
'kazehakase' = array('Kazehakase','B'),
'kapiko' = array('Kapiko','B'),
'iceape' = array('Iceape','B'),
'multizilla' = array('MultiZilla','B'),
'netscape' = array('Netscape','B'),
'seamonkey' = array('SeaMonkey','B'),
'bonecho' = array('Firefox','B'),
'firebird' = array('Firefox','B'),
'phoenix' = array('Firefox','B'),
'granparadiso' = array('Firefox','B'),
'minefield' = array('Firefox','B'),
'firefox' = array('Firefox','B'),
// netscape and mozilla handled below
// MSIE browsers
'america online' = array('AOL','B'),
'aol' = array('AOL','B'),
'opera' = array('Opera','B'),
'avant' = array('Avant','B'),
'crazy browser' = array('Crazy Browser','B'),
'maxthon' = array('Maxthon','B'),
'netcaptor' = array('NetCaptor','B'),
'myie2' = array('MyIE2','B'),
// msie handled as special case
// KHTML browsers
'konqueror' = array('Konqueror','B'),
'shiira' = array('Shiira','B'),
'omniweb' = array('OmniWeb','B'),
'cheshire' = array('Cheshire','B'),
'netnewswire' = array('NetNewsWire','B'),
'sunrise' = array('Sunrise','B'),
'chrome' = array('Chrome','B'),
'safari' = array('Safari','B')
)
}
// browsers with user agents that don't begin with "mozilla/"
define _lp_client_browser_other => {
map(
'!' = array(
'!Susie' = array('!Susie','C'),
),
'(' = array(
'(DreamPassport' = array('DreamCast DreamPassport browser','B'),
'(Privoxy' = array('Privoxy web proxy','P'),
'(Robots.txt Validator' = array('SearchEngineWorld\'s robots.txt validator','C'),
),
'*' = array(
'*/Nutch' = array('Unknown Yahoo robot','R'),
),
'+' = array(
'+SitiDi' = array('SitiDi.net search (Germany) robot','R'),
),
'-' = array(
'-DIE-KRAEHE' = array('Die Kraehe Meta-Search-Engine (Germany) link checking','R'),
),
'1' = array(
'123spider' = array('123spider.de (Germany) web directory link checking','C'),
'192.com' = array('192.com - UK web directory','R'),
'1st ZipCommander' = array('1st ZipCommander Net - IE based browser','B'),
),
'2' = array(
'2Bone' = array('2Bone online link checker','C'),
),
'4' = array(
'4anything.com' = array('4Anything robot','R'),
),
'8' = array(
'8484 Boston Project' = array('Unknown guestbook spamming or harvesting tool from diff. IPs','S'),
),
':' = array(
':robot' = array('neofonie search robot Germany','R'),
),
'a' = array(
'A-Online' = array('A-Online.at robot - now Jet2Web Search','R'),
'A1 Keyword' = array('A1 Keyword Research - search engine and keyword optimization software','C'),
'A1 Sitemap' = array('MiggiBot website crawler engine - A1 Sitemap Generator','R'),
'ABACHOBot' = array('ABACHOBot','R'),
'ABCdatos' = array('ABCdatos - Castilian program & tutorial directory','R'),
'Aberja' = array('Aberja Hybridsuchmaschine (Germany) link checking','R'),
'abot' = array('Nameprotect copyright search robot (24.177.134.x)','R'),
'About' = array('About robot','R'),
'Accelatech' = array('Accela Technology RSS feed crawler','F'),
'accoona' = array('Accoona Search robot','R'),
'Ace Explorer' = array('Ace Explorer - IE based browser','B'),
'Ack' = array('Ackerm search robot','R'),
'AcoiRobot' = array('Acoi picture finder robot','R'),
'Acoon' = array('Acoon.de robot','R'),
'Acorn' = array('Acorn Search Project','R'),
'ActiveBookmark' = array('LibMaster.com Active Bookmark HTML page creator','C'),
'Activeworlds' = array('Activeworlds 3D homepage browser','B'),
'Ad Muncher' = array('Ad Muncher - banner killer','P'),
'Adaxas' = array('website directory adaxas link checking','C'),
'Advanced Browser' = array('Avant Browser - IE based browser','B'),
'AESOP' = array('Aesop robot','R'),
'agadine' = array('Agada search (Germany) robot','R'),
'Agent-Shareware' = array('SharewarePlaza link checking','R'),
'AgentName' = array('Linkomatic submission verifier','R'),
'AIBOT' = array('21seek.com (China) robot (218.17.90.xxx)','R'),
'AideRSS' = array('AideRss - Postrank RSS and Blog filtering','C'),
'aipbot' = array('Nameprotect copyright search robot (24.177.134.x)','R'),
'Aladin' = array('Aladin robot','R'),
'Aleksika' = array('Aleksika Danmark - Search engine optimization spider','R'),
'AlkalineBOT' = array('Vestris robot','R'),
'Allesklar' = array('Allesklar.de robot','R'),
'Alligator' = array('Alligator download manager','D'),
'AltaVista' = array('Altavista robot','R'),
'Amaya' = array('Amaya','R'),
'Amfibibot' = array('Amfibibot','R'),
'amibot' = array('amibot - Amidalla search engine robot (62.241.33.xx)','R'),
'Amiga-AWeb' = array('AWeb Amiga browser','B'),
'AmigaVoyager' = array('Voyager - Amiga browser','B'),
'amzn_assoc' = array('Amazon.com robot for checking their affiliate sites','C'),
'AnnoMille' = array('Annomille Italian historical oriented robot','R'),
'annotate_google' = array('annotate Google - Firefox extension for annotating Google search results','B'),
'Anonymized by ProxyOS' = array('Megaproxy user','P'),
'Anonymizer' = array('Anonymizer.com','P'),
'AnswerBus' = array('AnswerBus','R'),
'AnswerChase' = array('AnswerChase','R'),
'ANTFresco' = array('ANT Fresco Browser','B'),
'antibot' = array('Antibot (discontinued) robot','R'),
'AnzwersCrawl' = array('Anzwers (Yahoo) Australia robot','R'),
'Apexoo Spider' = array('Apexoo Search spider','R'),
'Aplix HTTP' = array('JavaOS app. for SEGA Saturn Internet and Sanyo Internet-TV','B'),
'Aplix_SANYO_browser' = array('JavaOS app. for Sanyo Internet-TV','B'),
'Aplix_SEGASATURN_browser' = array('JavaOS app. for SEGA Saturn Internet','B'),
'Aport' = array('Aport robot','R'),
'Appie' = array('Appie','R'),
'Apple iPhone' = array('iPhone','M'),
'ArabyBot' = array('Araby search - Arabia','R'),
'Arachnoidea' = array('Euroseek spider','R'),
'aranhabot' = array('Amazon.com robot for checking their affiliate sites','C'),
'ArchitextSpider' = array('Excite spider','R'),
'archive.org' = array('Heritrix - The Internet Archive\'s open-source crawler (207.241.225.2xx)','R'),
'Argus' = array('Simpy Bookmarklet crawler (69.55.233.xx)','C'),
'Arikus' = array('Arikus inContext search engine software','R'),
'arianna.libero.it' = array('arrianna.libero.it','R'),
'Asahina-Antenna' = array('ASAHINA Antenna information detecting agent','R'),
'ask.24x.info' = array('Ask 24x Info robot','R'),
'AskAboutOil' = array('Ask About Oil - Petroleum related search (24.227.212.xxx) using Nutch','R'),
'asked' = array('askEd! / Inferret search (Japan) robot using Nutch','R'),
'ASPSeek' = array('ASPSeek search engine software -Yahoo-Inc. / Telecom Canada robot','R'),
'ASSORT' = array('Associative Sort robot','R'),
'asterias' = array('Singingfish media spider (64.12.186.2xx) via AOL search','R'),
'AtlocalBot' = array('Atlocal local business search robot','R'),
'Atomz' = array('Atomz robot','R'),
'atSpider' = array('atSpider (ceased) email harvester / spambot','S'),
'Attentio' = array('Attentio social media monitoring and analysing','R'),
'AU-MIC' = array('Samsung SPH-A660 phone with Sprint software','B'),
'augurfind' = array('Augurnet Swiss (was www.augurnet.ch) search robot','R'),
'augurnfind' = array('Augurnet Swiss (was www.augurnet.ch) search robot','R'),
'autoemailspider' = array('Auto Email Pro Email harvester','S'),
'autohttp' = array('Linkscan tool from Elsop','C'),
'AV Fetch' = array('Altavista robot ??','R'),
'Avant Browser' = array('Avant Browser - IE based browser','B'),
'AVSearch' = array('National Research Council Canada robot','R'),
'AWeb' = array('AWeb Amiga browser','B'),
'axadine' = array('Axada search Germany robot','R'),
'AxmoRobot' = array('Axmo search robot','R'),
'Azureus' = array('Azureus Java BitTorrent Client','D'),
),
'b' = array(
'BaboomBot' = array('BaBoom Web Portal (ODP) robot (66.98.254.xx)','R'),
'BackStreet Browser' = array('BackStreet Browser - Offline browser / website downloader','D'),
'Baiduspider' = array('Baiduspider','R'),
'BanBots' = array('Project BanBots Perl script robot','C'),
'Barca' = array('Barca Pro email & PIM software','B'),
'BDFetch' = array('Brandimensions Brand Protection robot','R'),
'BDNcentral' = array('Bdncentral Sitesearch robot','R'),
'BeamMachine' = array('beammachine web directory (Germany) link checking','R'),
'beautybot' = array('Beauty robot for Cosmoty - German beauty and wellness search','R'),
'BebopBot' = array('A Passion for Jazz music related search robot','R'),
'BeebwareDirectory' = array('LinkcheckerBeepware (site is down) web directory link checking','C'),
'Big Brother' = array('Big Brother link checking tool','C'),
'Big Fish' = array('GoonGee.com link popularity checking','C'),
'BigClique' = array('BigClique Search robot','R'),
'BIGLOTRON' = array('Biglotron search (France) robot','R'),
'Bigsearch' = array('Bigsearch.ca search robot','R'),
'Bilgi' = array('Bilgi.com (Beta) search robot - Turkey','R'),
'Bimbot' = array('Bimbot','R'),
'Bitacle' = array('Bitacle Blog Search Archive robot','R'),
'Biyubi' = array('Biyubi Navigator - Mexican browser for Fenix OS','B'),
'BlackBerry7520' = array('Blackberry Wireless Internet browser via Google WAP Proxy','P'),
'BlackWidow' = array('BlackWidow web site scanner / downloading tool','D'),
'Blaiz-Bee' = array('Blaiz Enterprises RawGrunt search','R'),
'BlitzBOT@tricus.net' = array('Blitzsuche Germany robot','R'),
'BlitzBOT' = array('BlitzBOT','R'),
'BlockNote' = array('BlockNote web page editor','B'),
'BlogBot' = array('blogdex robot from MIT.edu','R'),
'BlogBridge' = array('BlogBridge RSS reader','B'),
'Bloglines' = array('Bloglines','F'),
'BlogMap' = array('FeedMap / BlogMap geo coding service','C'),
'Blogpulse' = array('Intelliseek\'s BlogPulse blog search','R'),
'blogsearchbot' = array('Art of Computing blog search project','R'),
'BlogSearch' = array('IceRocket Web search robot','R'),
'BlogsNow,' = array('BlogsNow realtime link tracker robot','R'),
'blogWatcher' = array('blogWatcher robot from Okumura Group Tokyo (131.112.182.xxx)','R'),
'BlogzIce' = array('IceRocket Web search robot','R'),
'Bloodhound' = array('Balihoo - Search Engine for Advertising Media','R'),
'bluefish' = array('Bluefish HTML-editor for Linux','B'),
'BMLAUNCHER' = array('Bookmark Express bookmark manager','C'),
'boitho' = array('Boitho search (Norway) robot via 80.202.212.xx / 80.80.111.xx','R'),
'Bookdog' = array('Bookdog - Mac bookmark manager','C'),
'Bookmark Buddy' = array('Bookmark Buddy - favorite bookmark manager','C'),
'Bookmark Renewal' = array('Favourites managing program','C'),
'BravoBrian' = array('BravoBrian bSTOP parental control','P'),
'BruinBot' = array('Webarchive Project Bruinbot crawler','R'),
'BSDSeek' = array('Inktomi (Hotbot-Lycos NBCi) robot','R'),
'BStop' = array('BravoBrian bSTOP parental control','P'),
'btbot' = array('btbot','R'),
'BuildCMS' = array('BuildCMS crawler - market monitoring project of BuildCMS','R'),
'Bulkfeeds' = array('Bulkfeeds: RSS directory link checking','C'),
'BullsEye' = array('BullsEye/Intelliseek robot','R'),
'BunnySlippers' = array('Microsoft server information robot (see link)','C'),
'BurstFind' = array('BurstFind search crawler (64.34.172.xx)','R'),
'Buscaplus' = array('Buscaplus (Spain) robot','R'),
'BW-C' = array('Logitech Desktop Managers (LDM) Backweb (BW) update check','D'),
),
'c' = array(
'carleson' = array('Cosmix project crawler (204.14.48.x / 38.113.234.xxx)','R'),
'Carnegie_Mellon' = array('Carnegie Mellon University WebBOT','R'),
'Catall Spider' = array('Catall.de search & web directory (Germany)','R'),
'CazoodleBot' = array('UIUCs Cazoodle search based on MetaQuerier','R'),
'ccubee' = array('Empyreum Ccubee (Czech) search engine solution','R'),
'CE-Preload' = array('Cisco Content Engine','P'),
'Ceramic Tile' = array('Floortransformed.com robot (link ckecking ??)','R'),
'cfetch' = array('Cosmix project crawler (204.14.48.x / 38.113.234.xxx)','R'),
'Charon' = array('Charon Amiga download manager','D'),
'Checkbot' = array('Checkbot link validation','C'),
'CheckLinks' = array('Checklinks - Perl link checker','C'),
'CheckWeb' = array('CheckWeb link validation','C'),
'China Local' = array('Unknown spam bot from telekom.com.my (218.111.83.xxx)','S'),
'ChristCRAWLER' = array('Christcentral.com Christcrawler (was www.christcrawler.com)','R'),
'CipinetBot' = array('CipinetBot -Cipinet Search Engine Web Crawler','R'),
'CJ Spider' = array('Commision Junction link checking spider','C'),
'CJB.NET' = array('CJB Net anonymous socks proxy service (216.194.70.x)','P'),
'ClariaBot' = array('Claria (ex Gator) SearchScout robot (64.152.73.xx)','R'),
'Claymont' = array('Claymont Search robot','R'),
'CloakDetect' = array('Seznam Search (Czech Republic) robot','R'),
'Clushbot' = array('Clush clustered search robot','R'),
'CoBITSProbe' = array('Proposed Content-Based Image Tracking System (CoBITS) P2P crawler','R'),
'Cocoal.icio.us' = array('Cocoal.icio.us','R'),
'ColdFusion' = array('Cold Fusion server used by various IPs i.e.: - NetWORLD web catalogue link checking','L'),
'collage.cgi' = array('WebCollage Syndicator graphics crawler/collector','R'),
'combine' = array('Combine harvesting & indexing robot','R'),
'cometrics' = array('cometrics Web Content Mining solution - Germany','R'),
'Commerce Browser Center' = array('Wildsoft Germany (closed) Internet client system user-agent (was www.oskarweb.de)','B'),
'complex_network_group' = array('UCLA Complex Networks Groups Complex Network Analysis','C'),
'Computer_and_Automation' = array('Hungarian Academy of Sciences data mining search','R'),
'Comrite' = array('ComRite Chinese Search Engine for Oversea Web Sites (69.248.26.xx)','R'),
'ContactBot' = array('Probably E-Mail harvesting robot - same as LMQueueBot','S'),
'Contact' = array('Probably E-Mail harvesting robot','S'),
'ContentSmartz' = array('ContentSmartz e-mail harvesting tools','S'),
'contype' = array('Internet Explorer versions 4.x and 5 plugin content','B'),
'Convera' = array('Converas RetrievalWare Internet Spider (63.241.61.x)','R'),
'CoolBot' = array('Suchmaschine21 (Germany) robot','R'),
'CoralWeb' = array('Coral Content Distribution Network','P'),
'cosmos' = array('cosmos','R'),
'Coteo' = array('Coteo.com - local French directory link checking','C'),
'CougarSearch' = array('Cougarsearch.com robot','R'),
'Cowbot' = array('Naver Japan / Korea robot','R'),
'CrawlConvera' = array('Converas RetrievalWare Internet Spider','R'),
'Crawler admin@crawler.de' = array('Crawler.de / Abacho robot','R'),
'crawler@alexa.com' = array('Alexa crawler','R'),
'CrawlerBoy' = array('Pinpoint WAP search robot','R'),
'Crawler' = array('Cometsystems Comet Search robot via Findwhat (now Miva)','R'),
'Crawllybot' = array('Crawlly Beta search - Germany (72.232.194.2xx)','R'),
'CreativeCommons' = array('Creatice Commons using Nutch open source robot','R'),
'CrocCrawler' = array('Croccrawler robot','R'),
'csci_b659' = array('Web mining project from CSCI 659 (computer science course) at Indiana Univerity','R'),
'CSE HTML' = array('CSE HTML Validator','V'),
'CSSCheck' = array('CSSCheck','V'),
'Cuam' = array('Cuam - IE based browser','B'),
'Cuasarbot' = array('Cuasar (Spain) music / ringtone search spider','R'),
'curl' = array('Curl file transferring tool','D'),
'CurryGuide' = array('CurryGuide UK link check robot','R'),
'Custo' = array('Custo web site spidering tool (link checking)','C'),
'Custom Spider' = array('Bisnisseek (was www.bisnisseek.com) robot','R'),
'Cyberdog' = array('Cyberdog Mac Browser (was www.cyberdog.org)','B'),
'CyberSpyder' = array('CyberSpyder Link Test software','C'),
'CydralSpider' = array('Cydral image & site search spider','R'),
'Cynthia' = array('Cynthia','V'),
),
'd' = array(
'DA' = array('Downloadaccelerator download manager','D'),
'DataCha0s' = array('Unknown bot from Kornet Korea (218.149.129.xxx) scans for Perl Awstats','S'),
'DataFountains' = array('INFOMINE/iVia Scholary Internet Resource Collections robot','R'),
'DataparkSearch' = array('DataparkSearch','R'),
'DataSpear' = array('DataSpear Directory robot (24.109.29.xx)','R'),
'DatenBot' = array('Sicher-durchs-Netz German security related search (62.75.220.xxx)','R'),
'DaviesBot' = array('Wholeweb robot','R'),
'daypopbot' = array('Daypop blog - weblog - online mag search spider','R'),
'dbDig' = array('dbDig search engine','R'),
'DBrowse' = array('Some site scanning tool via diff. IPs i.e.: - wanweb.net (208.6.163.xxx) - cox.net (68.4.xxx.xxx)','S'),
'DC-Sakura' = array('DC-Sakura download manager','D'),
'dCSbot' = array('unknown divine/Openmarket.com robot','R'),
'DDD' = array('some (website) downloading tool','D'),
'de.searchengine' = array('Searchengine.com (Germany) submission checking / robot (84.73.57.xx)','R'),
'DeadLinkCheck' = array('DLC Perl HTTP link checking','C'),
'Deep Link' = array('Sootle Web Directory deep link checker','C'),
'deepak' = array('deepak-USC/ISI robot from USC/Information Science Institute','R'),
'DeepIndex' = array('Deepindex robot','R'),
'del.icio.us' = array('del.icio.us picture robot for thumbnail preview via Yahoo','D'),
'DeleGate' = array('DeleGate application level gateway / proxy server','P'),
'Demo Bot' = array('Some site scanning tool from 68.154.96.xx (bellsouth.net)','S'),
'Denmex' = array('Denmex Websearch robot/link checking','R'),
'Der gro' = array('DataBecker Bilder Sauger (discontinued) web graphics downloader','D'),
'dev-spider2.searchpsider.com' = array('Searchspider.com robot (72.245.225.xxx)','R'),
'DiaGem' = array('DiaGem Japan web crawler','R'),
'DiamondBot' = array('DiamondBot','R'),
'Diamond' = array('Claria (ex Gator) SearchScout robot (64.152.73.xx)','R'),
'Digger' = array('Diggit! robot','R'),
'DigOut4U' = array('OpenPortal4U robot','R'),
'DIIbot' = array('Findsame.com (site is offline) / Digital-Integrity robot','R'),
'dillo' = array('Dillo','B'),
'DISCo Pump' = array('DISCo Pump offline browser / website ripper','D'),
'DittoSpyder' = array('Ditto picture search robot','R'),
'dlman' = array('some download agent','D'),
'dloader' = array('Naver Japan / Korea robot','R'),
'DoCoMo' = array('NTT DoCoMo (Japan) robot','R'),
'DocZilla' = array('DocZilla - Mozilla-based SGML/XML/HTML- browser','B'),
'dodgebot' = array('unknown robot from AGMLAB Information Technologies (Information retrieval system ?)','R'),
'DomainsDB.net' = array('DomainsDB.net MetaCrawler','R'),
'DonutP' = array('Donut P - Japanese IE based browser','B'),
'Download Demon' = array('Download Demon/Netzip download manager','D'),
'Download Druid' = array('Download Druid IE plugin download manager','D'),
'Download Express' = array('Download Express download manager','D'),
'Download Master' = array('Download Master download manager','D'),
'Download Ninja' = array('Download Ninja download manager (Japan)','D'),
'Download Wonder' = array('Download Wonder download manager','D'),
'Download-Tipp' = array('Download-Tipp Germany link checking','R'),
'Download.exe' = array('download.exe .NET based downloading tool','D'),
'Dragonfly' = array('Dragonfly CMS - Open Source content management system','B'),
'Drecombot' = array('Drecom Japan (210.233.67.xxx) - Blog search ??','R'),
'Drupal' = array('Drupal - open source content management platform','C'),
'DSurf' = array('Some site scanning tool via diff. IPs i.e.: - cox.net (68.5.xxx.xxx) - pacbell.net (64.16x.xxx.xxx)','S'),
'DTAAgent' = array('DTAAgent Java object for data collecting','R'),
'dtSearchSpider' = array('dt Search Spider software','R'),
'Dual Proxy' = array('Fourelle Venturi proxy server','P'),
'Dumbot' = array('DumbFind.com robot','R'),
),
'e' = array(
'e-sense' = array('Vigiltech e-Sense user research robot (website is offline)','R'),
'e-SocietyRobot' = array('e-Society Project (Japan) crawler (133.9.238.xx)','R'),
'EARTHCOM' = array('Earthcom (Czech Republic) search robot (194.108.39.xx)','R'),
'EasyDL' = array('Keywen Encyclopedia Bot','R'),
'EBrowse' = array('Some site scanning tool via diff. IPs i.e.: - swbell.net (65.66.xxx.xxx)','S'),
'eCatch' = array('eCatch (now Wysigot) offline browser','D'),
'EchO!' = array('Echo.fr robot','R'),
'Educate Search' = array('Some site scanning tool via diff. IPs i.e.: - cox.net (68.4.xxx.xxx)','S'),
'egothor' = array('Xdefine text search engine robot - based on Egothor open source crawler','R'),
'EgotoBot' = array('Egoto Search robot','R'),
'ejupiter' = array('eJupiter searcg robot (206.191.49.xx)','R'),
'EldoS TimelyWeb' = array('TimelyWeb web page monitoring tool','C'),
'elfbot' = array('Elftales crawler for uChoose theme based search (Germany)','R'),
'ELI' = array('DAUMOA - RSS search robot of Daum','R'),
'elinks' = array('ELinks','B'),
'emailsiphon' = array('EmailSiphon','S'),
'EmailWolf' = array('Trellian EMailWolf E-mail collector','S'),
'EmeraldShield' = array('EmeraldShield.com WebBot','R'),
'EMPAS_ROBOT' = array('Empas search Korea robot (220.95.22x.xxx)','R'),
'endo' = array('endo - Mac news site and blog aggregator','B'),
'Enfish' = array('Enfish Personal search tool','R'),
'enigma' = array('Enigma','B'),
'Enterprise_Search' = array('Enterprise Search engine software (64.202.165.xxx)','R'),
'envolk' = array('Envolk Web Search robot','R'),
'EroCrawler' = array('EroCrawler adult search robot','R'),
'ES.NET' = array('Enterprise Search engine software (64.202.165.xxx)','R'),
'eseek-larbin' = array('ExactSEEK (Jayde Online) robot','R'),
'ESISmartSpider' = array('ESI Smart-Spider toolkit','R'),
'EsperanzaBot' = array('EsperanzaBot','R'),
'eStyleSearch' = array('e-Style ISP search (Russia) robot (217.174.103.xxx)','R'),
'ESurf' = array('Some site scanning tool via diff. IPs','S'),
'EuripBot' = array('Eurip.com - European Internet Portal robot','R'),
'EvaalSE' = array('Evaal Search Engine robot','R'),
'eventax' = array('Eventax event search (Germany)','R'),
'Everest-Vulcan' = array('Vulcan Inc. Everest crawler (in development)','R'),
'everyfeed-spider' = array('everyfeed-spider','F'),
'Exabot' = array('Exabot','R'),
'ExactSearch' = array('eXact Search Bar for IE','B'),
'exactseek' = array('ExactSEEK (Jayde Online) robot (69.9.181.1xx)','R'),
'Exalead' = array('Exalead (France) search robot (193.47.80.xx)','R'),
'Excalibur' = array('Excalibur (now Convera) spider software','R'),
'Execrawl' = array('Execrawl software search using nutch','R'),
'ExperimentalHenrytheMiragoRobot' = array('Mirago UK Robot','R'),
'Expired Domain Sleuth' = array('Expired Domain Sleuth domain name tool','R'),
'Express WebPictures' = array('Express Web Pictures image browser','D'),
'ExtractorPro' = array('Extractor Pro e-mail collector','S'),
'Extreme Picture' = array('Exisoftware image grabber and downloading tool','D'),
'EyeCatcher' = array('Download-Tipp Germany robot','R'),
),
'f' = array(
'Factbot' = array('Factbites search robot','R'),
'FaEdit' = array('FaEdit Professional - Japanese bookmark manager','C'),
'FairAd' = array('FairAd user','P'),
'FANGCrawl' = array('Safe-t.net web filtering service','P'),
'FARK.com' = array('Drew Curtis\' FARK.com link checking','C'),
'Fast Crawler' = array('FAST Crawler','R'),
'FAST Enterprise' = array('FAST Crawler','R'),
'FAST FirstPage' = array('FAST Crawler','R'),
'FAST MetaWeb' = array('FAST Crawler','R'),
'Fast PartnerSite Crawler' = array('Fast/Alltheweb crawler (66.151.181.xx)','R'),
'FAST-WebCrawler' = array('FAST Crawler','R'),
'fastbot' = array('Fastbot search Germany crawler (80.252.104.1xx)','R'),
'FastBug' = array('Ay-Up geo sync search robot','R'),
'FastCrawler' = array('Fast/Alltheweb crawler (66.151.181.xx)','R'),
'FastSearch' = array('Fast/Alltheweb crawler used by SuperPages.com','R'),
'FavIconizer' = array('FavIconizer - IE favorites icons refreshing tool','D'),
'favicon finder' = array('IconSurf.com - Visual Surf Engine','R'),
'favicon monitor' = array('IconSurf.com - Visual Surf Engine','R'),
'favo.eu' = array('favo.eu (Germany) search robot','R'),
'FavOrg' = array('ZD\'s FavOrg favourites managing program','C'),
'Favorites Sweeper' = array('Favorites Sweeper bookmark checker','C'),
'Faxobot' = array('FaXo Search robot (69.152.89.xx)','R'),
'FDM' = array('Free Download Manager (FDM) download accelerator','D'),
'Feed Seeker' = array('RSS Feed Seeker bot (68.225.95.2xx)','R'),
'Feed24' = array('Feed24 news feed and blog search','R'),
'Feed::Find' = array('Feed::Find - Syndication feed (RSS/Atom) auto-discovery','D'),
'Feedable' = array('Feedable beta web based RSS service','B'),
'FeedChecker' = array('Unknown robot from the University of Tokyo (157.82.157.xx)','R'),
'Feedfetcher-Google' = array('Google Feedfetcher - RSS and Atom feed crawler','R'),
'FeedForAll' = array('FeedForAll RSS feed robot','C'),
'Feedshow' = array('FeedShow online RSS feed reader','B'),
'Feedster Crawler' = array('Feedster RSS feed search','R'),
'FeedZcollector' = array('FeedZcollector - Feed (RSS, ATOM and RDF) capturing software','B'),
'Felix' = array('MixCat robot','R'),
'fetch libfetch' = array('FreeBSD download tool','D'),
'FFC Trap' = array('Frequent Finders spider via Sitefusion.com','R'),
'Filangy' = array('Filangy search and bookmark service','R'),
'fileboost' = array('File Boost Network link checking','R'),
'FileHound' = array('FileHound download manager','D'),
'FindAnISP' = array('Find An ISP robot','R'),
'Findexa' = array('Yelo.no business search (Norway) via Findexa','R'),
'FindLinks' = array('FindLinks','R'),
'FineBot' = array('Finesearch robot','R'),
'Finjan' = array('Finjan Vital Security Web Appliance security solution','P'),
'Firefly' = array('Fireball.de robot','R'),
'Firefox' = array('Unknown robot from Czech Technical University Prague (147.32.141.xx)','R'),
'FirstGov' = array('AT&T/Fast Search robot for FirstGov (U.S.Government) portal','R'),
'firstsbot' = array('Firstsfind Germany robot / link checking','R'),
'Flapbot' = array('Flaptor information retrieval solutions robot','R'),
'FlashGet' = array('JetCar/FlashGet download manager','D'),
'FLATARTS' = array('FlatArts Favorites Icon Tool','C'),
'FlickBot' = array('DivX.com Movie Find robot','R'),
'flunky' = array('Metacarta / Cogent robot','R'),
'flyindex' = array('FLY Index Metasearch link checking','C'),
'FocusedSampler' = array('IBM\'s Almaden Research robot','R'),
'Fooky' = array('Fooky search Scorpionbots robot (65.12.170.xxx)','R'),
'Francis' = array('Neomo Search (Germany) robot (85.10.197.1xx)','R'),
'Franklin Locator' = array('Some spam bot','S'),
'free-downloads' = array('Free Downloads shareware directory link checking','C'),
'FreeFind' = array('FreeFind.com robot','R'),
'FreshDownload' = array('Fresh Download download manager','D'),
'FreshNotes' = array('FreshNotes - music related artist search (72.3.225.xx)','R'),
'FSurf' = array('Some site scanning tool via diff. IPs','S'),
'Full Web Bot' = array('Some site scanning tool from diff. IPs i.e.: - 66.28.240.xx (cogentco.com) - 68.5.174.xx (cox.net)','S'),
'FunnelWeb' = array('FunnelWeb','R'),
'FuseBulb' = array('FuseBulb search','R'),
'FyberSpider' = array('FyberSpider','R'),
),
'g' = array(
'g2crawler' = array('g2crawler','R'),
'Gagglebot' = array('Some user from bbnplanet.net (4.63.218.2xx) using an Innerprise robot tool','R'),
'GAIS Robot' = array('Seed Search robot','R'),
'Gaisbot' = array('Gaisbot','R'),
'GalaxyBot' = array('Galaxy robot (63.121.41.xxx)','R'),
'Gallent' = array('Gallent Search directory (UK)','R'),
'gamekitbot' = array('Gamekit game search engine - Germany','R'),
'Gamespy' = array('GameSpyHTTP/1.0','D'),
'GammaSpider' = array('GammaWare GammaSpider','R'),
'gazz' = array('nttrd.com / Infobee.ne.jp robot','R'),
'Generic Mobile Phone' = array('Google Mobile Search crawler','R'),
'Generic' = array('Unknown','R'),
'geniebot' = array('GenieKnows.com search','R'),
'GeonaBot' = array('Geona Search robot / link checking','R'),
'geourl' = array('GeoURL ICBM Address Server - a location-to-URL reverse directory','C'),
'GetBot' = array('Getbot web downloading tool / site grabber','D'),
'GetRight' = array('GetRight download manager','D'),
'GetWeb' = array('GetWeb - web page to email service','D'),
'GhostRouteHunter' = array('Sixxs Ghost Route Hunter','C'),
'gigabaz' = array('GigaBaz Brainbot (Germany) robot','R'),
'Gigabot' = array('Gigabot','R'),
'GNODSPIDER' = array('www.gnod.net spider','R'),
'Go!Zilla' = array('Go!Zilla download manager','D'),
'Go-Ahead-Got-It' = array('GotIt web accelerator (discontinued)','P'),
'Goblin' = array('GoGuides.Org (195.226.137.xx) robot','R'),
'GoForIt' = array('GoForIt Search robot','R'),
'GoGuides' = array('GoGuides.org directory & search link checking','C'),
'GoldenFeed' = array('GoldenFeed.com - RSS search engine','C'),
'Goldfire' = array('Invention Machines Goldfire Server','P'),
'gonzo1' = array('suchen.de German local search robot','R'),
'Google Talk' = array('Google instant messenger','B'),
'Googlebot' = array('Googlebot','R'),
'GoogleEarth' = array('GoogleEarth','B'),
'GrapeFX' = array('Grapeshot web search system API','R'),
'GreatNews' = array('GreatNews 1.0 Beta RSS reader','B'),
'GreenBrowser' = array('GreenBrowser - IE based browser (China)','B'),
'Gregarius' = array('Gregarius','F'),
'gridwell' = array('search gridwell favicon display','D'),
'GrigorBot' = array('Grigor Search bot','R'),
'Gromit' = array('Australasian Legal Information Institute (AustLII) robot','R'),
'grub' = array('Grub open source crawler','R'),
'gsa-crawler' = array('Google Search Appliance robot (216.239.xx.xx)','R'),
'GSiteCrawler' = array('GSiteCrawler','R'),
'Guestbook Auto Submitter' = array('Guestbook spamming tool','S'),
'Gulliver' = array('Northernlight robot','R'),
'Gulper Web Bot' = array('Yuntis Collaborative Web Resource Categorization and Ranking Project robot','R'),
'GurujiBot' = array('guruji : the Indian search engine robot','R'),
),
'h' = array(
'HappyFunBot' = array('Happy Fun Search robot','R'),
'Harvest-NG' = array('Harvest-NG web crawler used by search.yahoo.com','R'),
'Haste' = array('Haste - web mapping and monitoring system','R'),
'Hatena Antenna' = array('Hatena::Antenna Japan robot','R'),
'Hatena Mobile Gateway' = array('Hatena Japan proxy for handheld/mobile clients','P'),
'Hatena Pagetitle Agent' = array('Hatena Japan robot','R'),
'Hatena RSS' = array('Hatena Japan RSS feed robot','R'),
'HatenaScreenshot' = array('Hatena::Diary (Japan) web page screenshot robot','R'),
'HeinrichderMiragoRobot' = array('Mirago Germany robot','R'),
'Helix' = array('Helix - The SiteSearch (Canada) web crawler','R'),
'HenriLeRobotMirago' = array('Mirago France robot','R'),
'HenrytheMiragoRobot' = array('Mirago search (UK) robot','R'),
'Hi! I\'m CsCrawler' = array('University of Kassel Germany CsCrawler using the HTTPClient library','R'),
'HiDownload' = array('HiDownload download manager','D'),
'Hippias' = array('Hippias robot','R'),
'HitList' = array('Pilot Hitlist web analytics solution','R'),
'Hitwise' = array('Hitwise spider','R'),
'hl_ftien_spider' = array('hl_ftien_spider','R'),
'holmes' = array('Onet.pl (Poland) search robot','R'),
'HomePageSearch' = array('HomePageSearch robot','R'),
'Homerbot' = array('Homerweb search robot','R'),
'Honda-Search' = array('Honda-Search.com - Honda cars related search robot','R'),
'HooWWWer' = array('HooWWer - Next Generation Information Retrieval robot','R'),
'HotJava' = array('HotJava browser plus HTML Component 1.1.x','B'),
'Hotzonu' = array('Hotzuno - Japanese BBS reader client','B'),
'HPL/Nutch' = array('Unknown robot from HP Labs','R'),
'htdig' = array('htdig','R'),
'Html Link Validator' = array('Lithops Software link validation tool','C'),
'HTML2JPG' = array('HTML2JPG webpage to image converter','D'),
'HTMLParser' = array('HTMLParser','V'),
'HTTP Retriever' = array('PHP HTTP client to access Web servers','D'),
'http://Anonymouse.org' = array('Anonymous web proxy service','P'),
'http://Ask.24x.Info' = array('Ask 24x Info (Germany) DMOZ related robot','R'),
'http://www.almaden.ibm.com' = array('IBM Almaden Research Center','R'),
'http://www.istarthere.com' = array('Istarthere.com search robot','R'),
'http://www.monogol.de' = array('Monogol - German open source search engine project (195.226.167.1xx)','R'),
'http://www.trendtech.dk' = array('TrendTech Search Engine (Denmark) robot','R'),
'HTTP::Lite' = array('HTTP::Lite - Standalone Perl module for retreiving HTTP documents','D'),
'httpget' = array('httpget','D'),
'HTTPResume' = array('HTTPResume Amiga download manager','D'),
'httpunit' = array('HttpUnit - Java browser behavior simulation tool','B'),
'HyperEstraier' = array('Hyper Estraier full-text search system','D'),
),
'i' = array(
'i1searchbot' = array('i1search robot','R'),
'ia_archiver' = array('Alexa / The Internet Archive (209.237.238.1xx)','R'),
'IAArchiver' = array('Alexa / The Internet Archive (209.237.238.1xx)','R'),
'iaskspider2' = array('Iask search / Sina portal robot (China)','R'),
'ibrowse' = array('IBrowse','B'),
'icab' = array('iCab','B'),
'ICC-Crawler' = array('Knowledge Clustered Group ICC-Crawler (University of Tokyo - Japan)','R'),
'iCCrawler' = array('ICJobs - Intelligence Competence Center (Germany) robot','R'),
'ICE Browser' = array('ICE Java browser','B'),
'ichiro' = array('ichiro','R'),
'IconSurf' = array('Iconsurf.com - Visual Surf Engine / favicon finder','R'),
'ICOO Loader' = array('icooLoader download manager','D'),
'ICRA_label' = array('ICRA (Internet Content Rating Association) label spider','R'),
'icsbot' = array('ICS Robot Search Engine (International Christian school of Seoul)','R'),
'IDA' = array('Internet Download Accelerator','D'),
'ideare' = array('Janas (Ideare.com / Tiscali.it) robot','R'),
'IEFav' = array('Some bookmark manager','C'),
'iGetter' = array('iGetter download manager','D'),
'IIITBOT' = array('Webkhoj - Indian language search engine','R'),
'ilial' = array('Ilial Knowledge Search robot','R'),
'IlseBot' = array('Ilse Netherlands robot (62.69.178.xx)','R'),
'IlTrovatore' = array('Il Trovatore - Italian search engine robot','R'),
'ImageVisu' = array('ImageVisu image and graphics viewer - display files from the Web (HTTP and ECWP)','B'),
'IncyWincy' = array('Look.com robot using IncyWincy search engine','R'),
'IndexTheWeb.com' = array('Index the Web (69.57.134.xx) crawler','R'),
'Industry Program' = array('Spam bot from diff. IPs','S'),
'InelaBot' = array('inelegant.org','R'),
'Inet library' = array('Inet Library Resource Center robot','R'),
'info@pubblisito.com' = array('Pubblisito.com search - Italia','R'),
'infoConveraCrawler' = array('Converas RetrievalWare Internet Spider (63.241.61.x)','R'),
'InfoFly' = array('Versions-project.org Ingelin spider','R'),
'InfoLink' = array('InfoLink link checking tool','C'),
'INFOMINE' = array('INFOMINE Scholary Internet Resource Collection crawler','R'),
'InfoSeek' = array('Infoseek robot','R'),
'InfoWizards' = array('Reciprocal Link System PRO','C'),
'INGRID' = array('Ilse Netherlands robot (62.69.178.xx)','R'),
'Inktomi' = array('Inktomi (Hotbot-Lycos NBCi etc.) robot','R'),
'InnerpriseBot' = array('Enterprise Search engine software (64.202.165.xxx)','R'),
'Insitor' = array('Insitor Search robot (80.67.20.1xx)','R'),
'InstallShield DigitalWizard' = array('download manager','D'),
'Interarchy' = array('Interarchy file transfer software - SFTP/FTP client for Mac OS X','D'),
'Internet Ninja' = array('Dream Train (Japan) Internet search robot','R'),
'InternetArchive' = array('Heritrix - The Internet Archive\'s open-source crawler based on Nutch (207.241.225.2xx)','R'),
'InternetLinkAgent' = array('Internet Link Agent - link checking tool','C'),
'InternetSeer' = array('Internetseer Web site monitoring / Claymont robot','R'),
'intraVnews' = array('intraVNews - Feed reader & RSS aggregator for Outlook','B'),
'IP2LocationBot' = array('IP2Location - Reverse lookup geographical data and ISP by IP','R'),
'IP2MapBot' = array('IP2Map - geographical IP mapping','R'),
'IPiumBot' = array('Laurions Ipium robot','R'),
'IpselonBot' = array('Ipselon Web Search robot','R'),
'Iria' = array('Iria download manager','D'),
'IRLbot' = array('IRLbot','R'),
'Irvine' = array('Irvine downloading tool','D'),
'ISC Systems' = array('Unknown spambot / harvester from diff. IPs','S'),
'iSiloX' = array('iSiloX document converter for iSilo reader','B'),
'IssueCrawler' = array('IssueCrawler','R'),
'isurf' = array('Unknown University of Alberta link-checking ?','C'),
'IUPUI' = array('Some spam bot from 66.139.78.xx(x)','S'),
'iVia' = array('iVia robot - Open source Internet portal & virtual library system software','D'),
'IWAgent' = array('BD BrandProtect - brand, company or trademarks online monitoring','R'),
),
'j' = array(
'J-PHONE' = array('Proxy message from jp-q.ne.jp','P'),
'Jabot' = array('ODIN Directory Japan robot (163.138.95.xx)','R'),
'Jack' = array('German Domanova (offline since Feb.02) robot','R'),
'Jakarta Commons-HttpClient' = array('Jakarta Commons (Java based) HTTP client','B'),
'Jambot' = array('JamBot search robot (70.146.82.xx)','R'),
'java' = array('Java','L'),
'Jayde' = array('Jayde B2B Search robot (66.28.139.xx)','R'),
'JBH Agent' = array('some site downloading tool ? via 61.77.51.xxx','D'),
'jBrowser' = array('WAP 2.0 / jBrowser for handhelds','B'),
'JCheckLinks' = array('JCheckLinks Java hyperlink validator','C'),
'Jeode' = array('Insignias Jeode (PDA) Java platform','B'),
'Jetbot' = array('JetEye Search robot (64.62.142.xxx / 64.71.144.xxx)','R'),
'JetBrains' = array('Omea RSS - Atom - newsgroups web page reader','B'),
'JetCar' = array('JetCar / Flashget download manager','D'),
'jigsaw' = array('W3C_CSS_Validator','V'),
'JoBo' = array('Jobo website downloading program','D'),
'JobSpider' = array('Finacialbot.com - German (213.61.218.xx) job search JobRoboter','R'),
'JOC Web Spider' = array('Jocsoft Web Spider - website downloading tool','D'),
'JordoMedia' = array('Jordo Media RSS / Atom feed directory link checking','C'),
'Journster' = array('Journster.com RSS/Atom aggregator','C'),
'JRTS Check' = array('Check Favorites bookmark checking','C'),
'JRTwine' = array('Check Favorites bookmark checking','C'),
'Jyxobot' = array('Jyxobot','R'),
),
'k' = array(
'K-Meleon' = array('K-meleon browser - Windows 2000','B'),
'k2spider' = array('Verity K2 Spider ( Network search software)','R'),
'KakleBot' = array('Kakle ranked metasearch robot','R'),
'Kapere' = array('Kapere site grapper / web downloader','D'),
'Kazehakase' = array('Kazehakase - Gecko based browser (Japan)','B'),
'KDDI' = array('Google WAP Proxy (216.239.33.x)','P'),
'KE_' = array('Voila.fr robot','R'),
'Kenjin Spider' = array('Kenjin Spider search agent','R'),
'Kevin http://dznet.com/kevin' = array('Dznet.com Kevin crawler (link checking ?) via 68.39.148.xx (nj.comcast.net)','R'),
'Kevin http://websitealert.net/kevin' = array('Website AlertsKevin crawler (website monitoring) via 68.39.148.xx (nj.comcast.net)','R'),
'KFSW-Bot' = array('Some Perl search script from KFSW (Germany)','R'),
'kinja' = array('kinja weblog search robot','R'),
'KIT-Fireball' = array('Fireball search (Germany) robot','R'),
'Klondike' = array('Klondike WAP Browser','B'),
'KnowItAll' = array('University of Washington KnowItAll - web information extraction','R'),
'Knowledge.com' = array('The knowledge.com (ODP) directory robot','R'),
'Kontiki' = array('Kontiki Client download manager','D'),
'Krugle' = array('Krugle source code search engine for developers (64.71.164.1xx)','R'),
'KSbot' = array('KnowledgeStorm technology industry crawler for Findtech.com','R'),
'kuloko' = array('Kuloko contextual search robot','R'),
'kulturarw' = array('National Library of Sweden Heritage Project robot','R'),
'KummHttp' = array('Link or server checking from Sanoma Budapest (195.70.35.xxx)','C'),
),
'l' = array(
'Lachesis' = array('Intels Lachesis web site response time monitoring tool','C'),
'LapozzBot' = array('LapozzBot','R'),
'Larbin' = array('Larbin','R'),
'lawinfo' = array('LawInfo - Lawyer and attorney directory','R'),
'LECodeChecker' = array('Linkexchange crawler','R'),
'LeechGet' = array('Leechget download manager','D'),
'LEIA' = array('Gseek.com (site is offline) robot','R'),
'LetsCrawl' = array('Maybe logfile spamming for Lets crawl! search (Germany)','S'),
'LexiBot' = array('Lexibot (exMataHari) search software','R'),
'LG' = array('LG 8138 Mobile Phone browser','M'),
'Libby' = array('About.com robot','R'),
'libcurl-agent' = array('libcurl\'s (multiprotocol file transfer library) standard user-agent name','D'),
'LibertyW' = array('LibertyW search for mobile (France)','R'),
'libWeb' = array('Korea Telecom Search robot','R'),
'libwww-perl' = array('libwww-perl','L'),
'Liferea' = array('Liferea - Linux feed reader','B'),
'LightningDownload' = array('Lightning Download manager','D'),
'Lincoln State' = array('Some spam bot','S'),
'Link Valet' = array('Link Valet','C'),
'Link Validity Check' = array('Link Validity Check','C'),
'link_check' = array('link check 3 - Perl HTML link checker (from Perl for Web Site Management)','C'),
'LinkAlarm' = array('Linkalarm link validation','C'),
'Linkbot' = array('Linkbot Pro link checking software','C'),
'LinkCheck' = array('Linkcheck - linkchecking tool for Unix/Linux','C'),
'LinkLint' = array('Linklint - Perl html link checker','C'),
'linknzbot' = array('Linknz - The Kiwi Search Engine (New Zealand)','R'),
'LinkPimpin' = array('Link-Pimp web directory link checking','C'),
'LinkProver' = array('TafWeb link checking program','C'),
'links (' = array('Links','B'),
'Links - http://gossamer' = array('Gossamer Links','C'),
'Links 2.0 (http://gossamer' = array('Gossamer Links','C'),
'Links SQL' = array('Links SQL directory management program','R'),
'Links4US,' = array('Links4us ODP based directory link checking','C'),
'LinkScan' = array('Shareware robot from Elsop.com (used by Indiafocus/Indiainfo and others)','R'),
'LinksManager' = array('LinksManager.com','C'),
'LinkSonar' = array('LinkSonar (Japan) link checking tool','C'),
'LinkSweeper' = array('Left Side Software\'s LinkSweeper (ceased) bookmark utility','C'),
'LinkWalker' = array('LinkWalker','C'),
'ListBidBot' = array('Listbid.com / Directnic.com link checking ?','R'),
'Llaut' = array('llaut robot - Universitat de les Illes Balears (Spain)','R'),
'LMQueueBot' = array('E-Mail harvesting robot - same as ContactBot','S'),
'lmspider' = array('lmspider','R'),
'LNSpiderguy' = array('Lexis-Nexis robot','R'),
'LocalBot' = array('LocalBot company information collector','R'),
'LocalcomBot' = array('Local.com local search robot (216.52.252.xxx)','R'),
'Lockstep' = array('Lockstep (website content protection tool) user agent','R'),
'Look.com' = array('GlobalQueue spider (64.40.105.xxx)','R'),
'Lotus-Notes' = array('Lotus Notes browser','B'),
'luchs.at' = array('Luchs.at (Linux Wiki) link checking','C'),
'Lunascape' = array('Lunascape IE based browser (Japan)','B'),
'lwp-trivial' = array('lwp-trivial','L'),
'LWP::Simple' = array('Perl LWP:Collective module','L'),
'Lycos' = array('Lycos spider','R'),
'lynx' = array('Lynx','B'),
),
'm' = array(
'mabontland' = array('mabontland','R'),
'Mac Finder' = array('Some spam bot','S'),
'Mackster' = array('UKWizz search robot','R'),
'MagicWML' = array('All Magic/Wap wml service for mobile devices','P'),
'MagpieRSS' = array('Magpie RSS - PHP RSS Parser','B'),
'Mail.Ru' = array('Mail.ru search','R'),
'mailto:webcraft@bea.com' = array('Unknown Bea robot','R'),
'mammoth' = array('SLI Systems mammoth robot','R'),
'MantraAgent' = array('Looksmart robot','R'),
'MapoftheInternet' = array('Map of the Internet visual search engine index robot','R'),
'Mariner' = array('Kolibri.de robot','R'),
'Marketwave' = array('Pilot Hitlist web site analysis','R'),
'MARTINI' = array('Looksmart directory page analysis','R'),
'Marvin' = array('Marvin Medhunt robot','R'),
'MaSagool' = array('Sagool search Japan robot','R'),
'Mass Downloader' = array('Mass Downloader download manager','D'),
'MasterSeek' = array('Masterseek (Scandinavia) Beta business search ?','R'),
'Mata Hari' = array('Lexibot (exMataHari) search software','R'),
'Matrix S.p.A.' = array('Virgilio Italy robot (212.48.11.xxx) using Fast Enterprise Search','R'),
'maxomobot' = array('Maxomo multimedia search robot','R'),
'Media Player Classic' = array('Substitute for Windows Media Player','B'),
'MediaCrawler' = array('Media Find crawler','R'),
'Mediapartners-Google' = array('Mediapartners-Google','R'),
'MediaSearch' = array('WWW.fi Media Search','R'),
'MegaSheep' = array('Search UK robot','R'),
'Mercator' = array('Mercator crawler software (used by Altavista)','R'),
'Metaeuro' = array('MetaEuro.com Clustering Web Search Engine crawler','R'),
'MetaGer' = array('MetaGer search robot (Germany)','R'),
'MetagerBot' = array('MetaGer search robot (Germany)','R'),
'MetaProducts Download Express' = array('Download Express download manager','D'),
'Metaspinner' = array('Metaspinner search robot - Germany','R'),
'metatagsdir' = array('Metatagsdir.com directory index spider','R'),
'MFC Foundation Class Library' = array('Microsoft Foundation Class Library - i.e. used for e-mail harvesting from 68.154.96.xx (bellsouth.net)','S'),
'MFHttpScan' = array('Advanced Site Crawler web site ripper and extractor','D'),
'MicroBaz' = array('GigaBaz Brainbot (Germany) robot (213.139.152.xx)','R'),
'Microsoft Data Access Internet Publishing Provider Cache Manager' = array('MS Office 2000 acting as WebDAV client','P'),
'Microsoft Data Access Internet Publishing Provider DAV' = array('MS Office 2000 acting as WebDAV client','B'),
'Microsoft Data Access Internet Publishing Provider Protocol Discovery' = array('MS Office 2000 acting as WebDAV client','C'),
'Microsoft Log Parser' = array('Microsoft Log Parser text query tool','D'),
'Microsoft Small Business Indexer' = array('MS Small Business Server content indexer','R'),
'Microsoft URL Control' = array('user agent looks for form-mail components (spam-bot)','S'),
'Microsoft_Internet_Explorer_5.00.438' = array('Secure Computing SmartFilterWhere / Bess web filter (192.55.214.xx)','P'),
'MIIxpc' = array('xpc-mii.net HTTP server message','P'),
'Mindjet MindManager' = array('The Mindjet blog MindManager category','D'),
'miniRank' = array('mini- Rank website popularity tool','C'),
'Missauga Locate' = array('Some spam bot','S'),
'Missigua Locator' = array('Some spam bot','S'),
'Missouri College Browse' = array('Some spam bot','S'),
'Mister Pix' = array('Mister PiX picture finding software','D'),
'Misterbot' = array('Misterbot search France robot','R'),
'Miva' = array('Miva / ex Findwhat.com search robot (66.150.55.2xx)','R'),
'Mizzu' = array('Some spam bot from Jasmine Internet - Bangkok (203.147.0.xx)','S'),
'MJ12bot' = array('Majestic-12 Web Crawler','R'),
'Mnogosearch' = array('Mnogosearch','R'),
'Mo College' = array('Unknown bad bot - maybe guestbook spamming or email harvesting','S'),
'moget' = array('Goo Japan / Inktomi robot (210.173.179.xx)','R'),
'mogimogi' = array('mogimogi','R'),
'moiNAG' = array('moiNag - net.art generator','R'),
'MojeekBot' = array('MojeekBot','R'),
'Mojoo' = array('Mojoo','C'),
'monkeyagent' = array('Greasemonkey Firefox extension','D'),
'MoonBrowser' = array('Moonbrowser - IE based browser (Japan)','B'),
'Moreoverbot' = array('Moreover / FeedDirect RSS feed robot','C'),
'Morning Paper' = array('Morning Paper','R'),
'Morris' = array('MixCat robot s. also Felix','R'),
'Motoricerca' = array('Robots.txt online checker','C'),
'Mouse-House' = array('MPRM Group Ltd. Spider Monkey robot','R'),
'MovableType' = array('Movable Type web-based personal publishing system','B'),
'mozdex' = array('mozdex','R'),
'Mozilla (Mozilla@somewhere.com)' = array('http://www.somewhere.com robot','R'),
'MQbot' = array('MetaExplorer project\'s MetaQuerier robot','R'),
'MQBOT/Nutch' = array('MetaExplorer project\'s MetaQuerier robot','R'),
'MSFrontPage' = array('MS Frontpage 4.x','B'),
'MSIECrawler' = array('MSIE Offline Favorites','O'),
'msnbot' = array('MSN Search Web Crawler','R'),
'MSNPTC' = array('MSN Search robot - 131.107.xxx.xxx 204.95.96.xxx - 204.95.111.xxx 207.46.xxx.xxx','R'),
'msproxy' = array('MS Proxy','P'),
'MSRBot' = array('Microsoft Research web crawler','R'),
'Mulder' = array('StreamBox VCR user agent','D'),
'multiBlocker' = array('Multiblocker (Fantomaster) anonymity software user','P'),
'multicrawler' = array('MultiCrawler for DERI Galway\'s Semantic Web Search Engine cluster','R'),
'MultiText' = array('Virginia Tech Digital Library Research Laboratory robot','R'),
'MusicWalker' = array('SoMusical! musical directory link checking','R'),
'MVAClient' = array('MVAClient','S'),
'MyGetRight' = array('GetRight download manager','D'),
'Mylinea' = array('Mylinea France web catalogue crawler','R'),
'mylinkcheck' = array('VDOG - SEO webdirecory (Germany) link checking','C'),
),
'n' = array(
'Naamah' = array('Blogbot (Germany) robot','R'),
'NABOT' = array('Naver Japan / Korea robot','R'),
'naoFavicon4IE' = array('naoFavicon4IE','D'),
'NASA Search' = array('Unknown spambot / harvester from diff. IPs','S'),
'NationalDirectory' = array('Nationaldirectory spider','R'),
'NaverBot' = array('Naver Japan / Korea robot','R'),
'NavissoBot' = array('Navisso closed beta robot (69.41.162.1xx)','R'),
'NCSA Beta' = array('Vias Information Archival robot','R'),
'Nebullabot' = array('Nebulla.info distributed crawler (Germany)','R'),
'NEC Research' = array('NEC Researchindex robot - now CiteSeer.IST scientific document index','R'),
'NetAnts' = array('NetAnts download manager','D'),
'NETCOMplete' = array('NetComplete IE browser package','B'),
'NetinfoBot' = array('Netinfo.bg search (Bulgaria) robot','R'),
'NetLookout' = array('Netlookout internet notifier','R'),
'Netluchs' = array('Netluchs (Germany) search (193.164.8.xx)','R'),
'NetMechanic' = array('NetMechanic link checker','C'),
'NetNewsWire' = array('NewsGator NetNewsWire - Mac RSS feed reader','B'),
'NetNoseCrawler' = array('unknown InCom (216.0.107.xx) robot','R'),
'Netprospector' = array('Netprospector metasearch software','R'),
'NetPumper' = array('Netpumper download manager','D'),
'NetResearchServer' = array('NetResearchServer','R'),
'NetSprint' = array('Wirtualna Polska / Netsprint search (Poland) robot','R'),
'NetWhatCrawler' = array('NetWhat Search crawler (69.9.167.1xx)','R'),
'NetZippy' = array('Netzippy robot','R'),
'NewsGator' = array('NewsGator online RSS reader','B'),
'NextGenSearchBot' = array('Eliyon Crawler for Business People Search','R'),
'NextopiaBOT' = array('Nextopia crawler','R'),
'NG' = array('Exalead (France) search robot (193.47.80.xx)','R'),
'nicebot' = array('nicebot','R'),
'NICO' = array('NicoZone childsafe search robot','R'),
'NITLE Blog' = array('Experimental LSI (?) robot from 140.233.69.xx (Middlebury.edu)','R'),
'Nitro Downloader' = array('Download manager','D'),
'Noago Spider' = array('Noago spider','R'),
'Nokia-WAPToolkit' = array('Google WAP robot','R'),
'Nokia7110' = array('Google WAP proxy','P'),
'NokodoBot' = array('Nokodo public beta search robot (67.18.222.xx)','R'),
'Norbert the Spider' = array('Burf.com UK Search Engine robot','R'),
'noxtrumbot' = array('noxtrumbot','R'),
'noyona' = array('Noyona job search (preview)','R'),
'NP' = array('Nameprotect copyright search robot (24.177.134.x)','R'),
'Nsauditor' = array('Nsauditor Network Security Auditor','S'),
'NSPlayer' = array('NetShow Media Player = Windows Media Player 10','B'),
'nttdirectory' = array('NTT Directory robot','R'),
'Nucleus SiteList' = array('Nucleus CMS SiteList link managing plugin','C'),
'Nusearch Spider' = array('Nusearch Spider','R'),
'Nutch' = array('Nutch open source robot','R'),
),
'o' = array(
'obidos-bot' = array('Weblog bookwatch robot','R'),
'ObjectsSearch' = array('Objects Search robot','R'),
'obot' = array('obot','R'),
'Ocelli' = array('GlobalSpec Engineering Search robot (66.194.55.xxx)','R'),
'Octopus' = array('Octopus download manager','D'),
'Octora' = array('Octora blog or RSS information crawler - beta (66.228.114.xx)','R'),
'oegp' = array('oegp','S'),
'Offline Explorer' = array('Offline Explorer','O'),
'OliverPerry' = array('Claymont robot / Internetseer Web Site Monitoring','R'),
'OmniExplorer' = array('OmniExplorer_Bot','R'),
'onCHECK' = array('onsearch.de German web directory link checking','C'),
'Onet.pl' = array('onet.pl Szukaj (Search) robot (213.180.128.1xx)','R'),
'online link validator' = array('Online Link Validator','C'),
'Online24' = array('Online24 shopping portal (Germany) link checking','C'),
'OntoSpider' = array('OntoSpider - Dutch robot for a research project. (195.11.244.xx)','R'),
'Openbot' = array('Openfind.com.tw robot','R'),
'Openfind' = array('Openfind.com.tw robot','R'),
'OpenISearch' = array('open i search robot - search engine in development','R'),
'OpenTaggerBot' = array('Opentagger social bookmarking system','R'),
'OpenTextSiteCrawler' = array('OpenText crawler','R'),
'OpenWebSpider' = array('OpenWebSpider - Open Source web search engine','R'),
'opera' = array('Opera','B'),
'OpidooBOT' = array('Opidoo Search Belgium robot (62.4.83.xxx)','R'),
'Oracle Application Server Web Cache' = array('Oracle Application Server cache','P'),
'Oracle iMTCrawler' = array('Oracle interMedia Text - Text and web documents indexing','D'),
'Oracle Ultra Search' = array('Oracle Search','R'),
'OrangeSpider' = array('Orangeslicer semantic search (Beta) Germany (193.201.52.1xx)','R'),
'Orbiter' = array('Orbiter','R'),
'Orca Browser' = array('Avant Browser - IE based browser','B'),
'OSSProxy' = array('Marketscore (was Netsetter) internet accelerator','P'),
'Overture-WebCrawler' = array('Overture/Fast/Alltheweb crawler (66.77.73.xxx)','R'),
'ozelot' = array('Ozelot - Flying Cat\'s search engine robot (Germany)','R'),
),
'p' = array(
'P3P Validator' = array('P3P Validator','V'),
'page_verifier' = array('Secure Computing SmartFilter Tools - malware crawler','R'),
'PageBitesHyperBot' = array('PageBitesHyperBot','R'),
'Pagebull' = array('Pagebull visual search engine','R'),
'PagmIEDownload' = array('Downloadmanager ?','D'),
'parallelContext' = array('CFC crawler used by Italian academic and research network (GARR)','R'),
'ParaSite' = array('http://www.ianett.com robot','R'),
'Patwebbot' = array('Patsearch (Germany) robot','R'),
'pavuk' = array('Pavuk web downloading program for Unix','D'),
'PBrowse' = array('Some site scanning tool via diff. IPs- i.e.: - cox.net (68.4.xxx.xxx)','S'),
'pd02' = array('Post.sk / Eurotel.sk robot','R'),
'pear' = array('PEAR','L'),
'PEERbot' = array('Peerbot - favicon search robot','R'),
'PEval' = array('Some site scanning tool via diff. IPs','S'),
'php' = array('PHP','L'),
'PicoSearch' = array('Pico Search robot','R'),
'Piffany' = array('Piffany targeted search web spider','R'),
'PigeonBot' = array('Whois Source domain name information robot (66.249.26.xx)- s.also: - SurveyBot','R'),
'PingALink' = array('PingALink website monitoring','R'),
'Pingdom' = array('Pingdom web site monitoring','C'),
'pipeLiner' = array('pipeline search (DMOZ based) search robot (24.106.39. xxx)','R'),
'Pita' = array('Pita crawler','R'),
'Pizilla Ver' = array('Private user-agent via Hurricane Electric Internet Services','?'),
'PJspider' = array('Portaljuice spider','R'),
'Plagger' = array('Plagger - pluggable RSS/Atom feed aggregator written in Perl','B'),
'PlantyNet' = array('Plantynet web filtering services - Blacklist DB robot','R'),
'PluckFeedCrawler' = array('Pluck RSS feed crawler','R'),
'Pluggd' = array('Pluggd Podcast search engine','R'),
'Pockey' = array('Yutaka Endo\'s Pockey / GetHTML / GetHTMLW - some downloading tool from Japan','D'),
'Poirot' = array('ThePlanet/jaja-jak-globusy.com Google Adsense refferer spam bot from 70.85.116.* / 70.84.128.xxx / 70.85.193.xxx','S'),
'polybot' = array('polybot','R'),
'Pompos' = array('Pompos','R'),
'Popdexter' = array('Popdex - web site popularity crawler','R'),
'Port Huron Labs' = array('Unknown spam bot / harvester (63.223.10.***)','S'),
'PortalBSpider' = array('PortalB (now Alacra search) spider','R'),
'portalmmm' = array('portalmmm IMode mobile browser','M'),
'PostFavorites' = array('Yahoo (66.94.237.1xx / 216.109.121.xx) favorites tracking robot','C'),
'potbot' = array('Potbot http://sourceforge.net/projects/potbot/: A simple IRC bot written in Perl','R'),
'PrivacyFinder' = array('CUPS robot for AT&T Privacy Bird Privacy Preferences (P3P) enhancements','R'),
'Privoxy' = array('Privoxy web proxy','P'),
'Production Bot' = array('Some site scanning tool from diff. IPs- i.e.: - 67.99.33.x (lightningcon.broadwing.net)','S'),
'Program Shareware' = array('Some spam bot','S'),
'Project XP5' = array('XP5 robot','R'),
'PROve AnswerBot' = array('Answerchase PROve Answerbot','R'),
'ProWebGuide' = array('ProWebguide robot','R'),
'psbot' = array('psbot','R'),
'PSurf' = array('Some site scanning tool via diff. IPs- i.e.: -QWest Net','S'),
'psycheclone' = array('Unknown website grabbing / ripping for unknown purposes from 208.66.195.x - Digitalinfinity.org Russia','S'),
'puf' = array('Parallel URL Fetcher downloading tool','D'),
'pulseBot' = array('WebarooBot - Webaroo web site search / theme based downloading tool (64.124.122.2xx)','R'),
'PureSight' = array('PureSight Internet content filter','P'),
'PuxaRapido' = array('Puxa Rapido download manager','D'),
'PycURL' = array('PycURL','L'),
'Python-urllib' = array('Python-urllib','L'),
),
'q' = array(
'Qango' = array('Qango.com Web Directory robot','R'),
'QPCreep' = array('Quepasa!com (Latin American search) robot','R'),
'QuepasaCreep' = array('Quepasa!com (Latin American search) robot','R'),
'QueryN' = array('QueryN Metasearch robot','R'),
'QuickTime' = array('Quicktime for Macintosh','B'),
'Qweery' = array('Qweerybot for the Qweery search engine (in development) - Netherland','R'),
),
'r' = array(
'rabaz' = array('gigaBaz - the brainbot (Germany) robot','R'),
'RaBot' = array('Daum Korea robot (211.115.109.xxx)','R'),
'ramBot' = array('Intersearch.de (was www.intersearch.de) robot (Germany)','R'),
'RAMPyBot' = array('RAMPyBot','R'),
'Rank Exec' = array('Rank Exec reciprocal link checking','C'),
'Rational SiteCheck' = array('Innova/IBM Rational SiteCheck - Rational robot','R'),
'ReadABlog' = array('Read A Blog - RSS feed and blog search engine','C'),
'RealDownload' = array('RealDownload download manager','D'),
'Reaper' = array('Reaper robot for SiteSearch','R'),
'REBOL View' = array('REBOL/View - machine independent internet client application','B'),
'Rebusnet' = array('Rebusnet software site - link / submission checking','R'),
'reciprocal links checker' = array('Online reciprocal link checker','C'),
'RedBot' = array('rediff.com search link checking','C'),
'RedCarpet' = array('RedCarpet crawler for Pronto price comparison search(66.179.107.1xx)','R'),
'RedCell' = array('Der Bot for telegenetic.net\'s security related search (65.220.67.2xx)','R'),
'RedKernel' = array('RedKernel Softwares robot','R'),
'REL Link Checker' = array('REL Link Checker','C'),
'Rewebber' = array('Rewebber proxy service','P'),
'rico' = array('Applied Semantics Auto-Categorizer for QWestDex Direct','R'),
'RixBot' = array('RixBot Rebol Indexer for the RIX - Rebol related search (195.204.121.xx)','R'),
'RMA' = array('Real Media server acting as client','P'),
'RoboCrawl' = array('Canadian Content search crawler','R'),
'RoboPal' = array('FindPal Australia metasearch robot (61.68.139.xx)','R'),
'Robot/www.pj-search.com' = array('PopJapanSearch robot','R'),
'Robot: NutchCrawler- Owner: wdavies@acm.org' = array('Experimental robot using Wget via attbi.net','R'),
'Robot@SuperSnooper.Com' = array('Supersnooper robot','R'),
'Robozilla' = array('Netscape Directory / DMOZ Open Directory link crawler','R'),
'Rotondo' = array('Qualigo.de robot','R'),
'RPT-HTTPClient' = array('different IPs using the HTTPClient library (mostly link checking)','C'),
'RRC' = array('Metacarta.com (66.28.xx.xxx) robot','R'),
'RssBandit' = array('RSS Bandit RSS/Atom reader for .NET framework','B'),
'RSSMicro' = array('RSS Micro Search - RSS feed search engine','R'),
'RSSOwl' = array('RSSOwl embedded RSS feed reader','B'),
'RssReader' = array('Ykoon RssReader news feed reader','B'),
'RSurf15a' = array('Some site scanning tool via diff. IPs- i.e.: - dslx.net (208.35.1x.xxx) - Home.com','S'),
'Rubbot' = array('rubhub blog spider','C'),
'RufusBot' = array('RufusBot','R'),
'RX Bar' = array('RX (Reflexive Search) Bar for IE','B'),
),
's' = array(
'S&L Spider' = array('Search & Links directory spider','C'),
'S.T.A.L.K.E.R.' = array('SEO-Tools.net link checking ?','C'),
'SafariBookmarkChecker' = array('SafariBookmarkChecker for Mac OS X','C'),
'SandCrawler' = array('SandCrawler','R'),
'savvybot' = array('WebSavvy Directory robot','R'),
'SBIder' = array('SBIder','R'),
'SBL-BOT' = array('Softbyte Labs Black Widow web site ripper','D'),
'ScanWeb' = array('ScanWeb - regular expression based web page searching tool','R'),
'ScholarUniverse' = array('ScholarUniverse - Scholarly experts search robot','R'),
'schwarzmann.biz' = array('URL Spider Pro ("USP") used by German Schwarzmann GmbH','R'),
'Science Traveller' = array('1X Web Browser','B'),
'ScollSpider' = array('WebWobot UK search engine robot (82.43.129.2xx)','R'),
'Scooter' = array('Altavista robot','R'),
'Scope' = array('Scope Navigator mobile browser (Japan)','M'),
'ScoutAbout' = array('Some nec.com robot using Research Republic ScoutAbout Research Tool','R'),
'scoutmaster' = array('ScoutMaster information retrieval software','R'),
'Scrubby' = array('Scrubby','R'),
'Search' = array('URL Search+ search software','R'),
'Search-Engine-Studio' = array('Xtreem Search Engine Studio - SE software','R'),
'search.ch' = array('Search.ch robot','R'),
'searchbot admin@google.com' = array('Unknown robot / website grabber from Chinatelecom (219.142.78.xxx)','S'),
'SearchByUsa' = array('SearchByUSA robot (69.150.7.xxx)','R'),
'SearchdayBot' = array('Searchday (Germany) search robot','R'),
'SearchExpress' = array('Searchexpress spider','R'),
'SearchGuild' = array('Searchguild forum & directory robot (81.3.75.xxx)','R'),
'Searchit-Now' = array('Searchit robot (69.93.107.xx)','R'),
'Searchmee!' = array('Searchmee! Search Engine (prototype) robot by findanisp.com','R'),
'SearchSight' = array('SearchSight','R'),
'Searchspider' = array('SearchSpider robot','R'),
'SearchTone' = array('Janas (Ideare.com / Tiscali.it) robot','R'),
'Seekbot' = array('Seekbot','R'),
'Seeker.lookseek.com' = array('Lookseek search robot / link checking','R'),
'semaforo.net' = array('semaforo.net web filtering software','P'),
'Semager' = array('Semager.de (was NG-Search) semantic search - Germany','R'),
'semanticdiscovery' = array('semanticdiscovery','R'),
'Sensis' = array('Sensis Web Crawler','R'),
'SeznamBot' = array('Seznam Search (Czech Republic) robot','R'),
'Shareaza' = array('Shareaza P2P peer-to-peer download client','D'),
'SharewarePlazaFileCheckBot' = array('SharewarePlaza File Check Bot - link checking','R'),
'Shim Crawler' = array('Chikayama-Taura Lab Shim-Crawler used for The Kototoi Project (Japan) - (133.11.36.xx)','R'),
'Shim-Crawler' = array('Shim-Crawler','R'),
'ShopWiki' = array('ShopWiki','R'),
'Shoula.com Crawler' = array('Shoula Search Engine crawler','R'),
'SietsCrawler' = array('Siets Crawler - Web based site crawling application','R'),
'Siigle Orumcex' = array('Siigle search (Turkey) robot','R'),
'silk' = array('silk','R'),
'SimpleFavPanel' = array('SimpleFavPanel - IE newsfeed panel plugin','B'),
'Simpy' = array('Simpy bookmarking and personal search engine','R'),
'Sirketcebot' = array('Sirket?e search - Turkey','R'),
'SiteBar' = array('SiteBar','C'),
'sitecheck.internetseer' = array('Internetseer Web Site Monitoring / Claymont robot','R'),
'SiteRecon' = array('SiteRecon website monitoring spider at xx minute intervals','R'),
'SiteSnagger' = array('PC Magazin web site downloadmanager','D'),
'SiteSpider' = array('Site Spider robot (66.249.17.xx)','R'),
'SiteSucker' = array('SiteSucker Mac website downloading tool','D'),
'SiteTaggerBot' = array('SiteTagger.com bookmark organizer','C'),
'SiteTruth.com' = array('SiteTruth - Automatic site legitimacy rating system','R'),
'SiteWinder' = array('Webwasher.com (217.146.159.xx) internet filter','P'),
'SiteXpert' = array('Xtreeme SiteXpert sitemap & search engine builder','R'),
'Skampy' = array('Skaffe.com directory link checker','R'),
'Skimpy' = array('Skaffe.com directory link checker','R'),
'Skywalker' = array('Visvo distributed website crawler based on Nutch','R'),
'Slarp' = array('Only.com robot','R'),
'Sleipnir' = array('Sleipnir - Japanese Explorer based browser & search bar','B'),
'Slider_Search' = array('Slider Search directory robot (194.213.194.2xx)','R'),
'SlimBrowser' = array('Slim Browser (IE based browser) - uses this user agent for favicon.ico only','B'),
'Slurp' = array('Inktomi (Hotbot-Lycos-NBCi) robot','R'),
'SlySearch' = array('Slysearch robot (now Turnitin robot)','R'),
'SmartDownload' = array('Netzip/Smartdownload download manager','D'),
'smartwit' = array('Loop Improvements NRS Enterprise search (69.44.155.xx[x])','R'),
'SmiffyDCMetaSpider' = array('SmiffyDCMetaSpider - Robot to check the retro-adding of Dublin Core metadata','R'),
'snap.com' = array('Unknown bot from bb2.net (66.234.139.xxx) also as Snapbot/1.0','S'),
'Snapbot' = array('Unknown bot from bb2.net (66.234.139.xxx) - also as snap.com','S'),
'Snappy' = array('Snappy','R'),
'Snarfer' = array('Snarfer RSS reader','B'),
'snoopy' = array('Snoopy','L'),
'SnykeBot' = array('Snyke.com France robot','R'),
'SocSciBot' = array('Link crawler for the social sciences','R'),
'SoftBank' = array('NetFront browser on Softbank mobile phone','M'),
'SoftHypermarketFileCheckBot' = array('Soft Hypermarket link checking','R'),
'Softizerbot' = array('Softizer.com software directory link checking','C'),
'sogou spider' = array('sogou spider','R'),
'Sogou web spider' = array('Unknown UA from Chinanet (220.181.26.1xx) faking Sogou search robot','S'),
'sohu agent' = array('Unknown UA from Chinanet (220.181.26.1xx) faking Sogou search robot','S'),
'sohu-search' = array('Sohu (Search Fox) search robot China (61.135.131.xxx)','R'),
'Space Bison' = array('Default Proxomitron (discontinued) filtering proxy user agent identifier','P'),
'SpeedDownload' = array('Speed Download (Mac) download manager','D'),
'speedfind' = array('Speedfind.de robot','R'),
'Speedy Spider' = array('Entireweb search robot','R'),
'Speedy_Spider' = array('Entireweb search robot','R'),
'Sphider' = array('Sphider - a lightweight search engine in PHP','R'),
'Spida' = array('Only.com robot','R'),
'Spider-Sleek' = array('Search-Info ODP/DMOZ spider','R'),
'spider.batsch' = array('Batsch robot','R'),
'Spider.TerraNautic' = array('TerraNautic spider for Schnellsuchen touristic search (Germany)','C'),
'spider.yellopet' = array('Yellopet spider','R'),
'Spider/maxbot.com' = array('Maxbot .gov .mil .edu indexing robot','R'),
'SpiderKU' = array('Unknown robot from CPE at Kasetsart University (158.108.35.xxx)','R'),
'SpiderMan' = array('Yahoo Search user agent or spider (202.165.102.xxx)','R'),
'SpiderMonkey' = array('SpiderMonkey Canada robot','R'),
'Spinne' = array('Spider.de robot','R'),
'Spock Crawler' = array('Spock - people search application - via Amazon web services','R'),
'sportsuchmaschine' = array('Sportsuchmaschine (German sports related search) link checking / robot','R'),
'sproose' = array('Sproose personalized search (38.100.225.xx)','R'),
'SQ Webscanner' = array('SQ Webscanner Mac download manager','D'),
'Squid-Prefetch' = array('Simple page-prefetch for Squid web proxy','P'),
'squidclam' = array('Squidclam is a replacement for SquidClamAV-Redirector','P'),
'SquidClamAV_Redirector' = array('SCAVR - Squid helper script for scanning download URLs for viruses','P'),
'Sqworm' = array('Sqworm','R'),
'SSurf15a' = array('Some site scanning tool via diff. IPs i.e.: - choiceone.net (216.153.xxx.xxx) - epix.net (216.108.198.xx)','S'),
'StackRambler' = array('StackRambler','R'),
'Stamina' = array('Stamina download manager','D'),
'Star Downloader' = array('Star Downloader download manager','D'),
'StarDownloader' = array('Star Downloader download manager','D'),
'stat statcrawler@gmail.com' = array('Experimental search engine spider from 66.92.186.xxx','R'),
'Steeler' = array('Steeler crawler','R'),
'Strategic Board Bot' = array('Strategic Board blogs and news aggregator robot','R'),
'Submission Spider' = array('Surfsafely submission verifier','R'),
'suchbaer' = array('Suchbaer.de (Germany) search robot','R'),
'suchbot' = array('Suchbot Germany robot','R'),
'Suchknecht' = array('Suchknecht Austria robot','R'),
'suchpadbot' = array('suchpad search Germany robot (213.239.194.xx)','R'),
'Sunrise' = array('Sunrise XP web sites and newsfeeds converter and handheld reader','B'),
'SuperBot' = array('SuperBot','O'),
'Superdownloads' = array('Ubbi Superdownloads (Brazil) link checking','C'),
'SURF' = array('SurfControl Web Filtering','P'),
'SurferF3' = array('Wanadoo Rechereche robot','R'),
'SurfMaster' = array('Maskbit Surfmaster bookmark tool','C'),
'SurveyBot' = array('SurveyBot','R'),
'suzuran' = array('Yokogao Search Engine robot (Kanazawa University)','R'),
'SWB' = array('HP Secure Web Browser for OpenVMS','B'),
'Swooglebot' = array('Swooglebot Swoogle\'s semantic web crawler','R'),
'SWSBot' = array('SWSBot - SmartWareSoft (85.186.255.xx) software search engine created for Playfuls.com','R'),
'SygolBot http://www.sygol.net' = array('Sygol Search (Italy) robot','R'),
'Sylera' = array('Sylera browser (Japan)','B'),
'SyncIT' = array('SyncIT link validation','C'),
'Syndirella' = array('Syndirella desktop information aggregator (beta)','B'),
'SynoBot' = array('Synomia (France) robot','R'),
'SynooBot' = array('SynooBot','R'),
'Syntryx' = array('Syntryx Solution Suite - domain / keyword crawler (216.7.179.xx)','R'),
'Szukacz' = array('Szukacz.pl (Polish search) robot','R'),
),
't' = array(
'T-Online Browser' = array('German T-Online browser & internet suite','B'),
'tags2dir' = array('tags2dir.com directory index','R'),
'Tagword' = array('TAGword DMOZ survey - ODP link checking robot','R'),
'Talkro' = array('Daumsoft Talkro IR robot','R'),
'TAMU_CS' = array('Texas A&M University - Dept. of Computer Science crawler (server or link checking ?)','R'),
'targetblaster' = array('Targetblaster user link validation ?','R'),
'TargetYourNews' = array('Target Your News - user submitted links','C'),
'TCDBOT' = array('Trinity College Dublin (Ireland) TCDBOT','R'),
'TECOMAC' = array('Tecomac Gmbh (Germany) crawler software - now Arexera Information Technologies','R'),
'Tecomi' = array('Tecomi (Germany) beta / test robot (84.201.65.xxx)','R'),
'Teleport' = array('Teleport (website) downloading tool','D'),
'Teoma' = array('Teoma crawler (65.214.36.xx[x])','R'),
'Teradex Mapper' = array('Teradex Directory robot','R'),
'TeragramCrawler' = array('Teragram multilingual text & data processing software','D'),
'terraminds-bot' = array('Terraminds blog search (Germany)','R'),
'TerrawizBot' = array('TerrawizBot','R'),
'Test spider' = array('Noceans Information Portfolio Manager (66.35.69.x)','R'),
'TestCrawler/Nutch' = array('Balihoo - Search Engine for Advertising Media','R'),
'The Expert HTML Source Viewer' = array('Expert HTML online source viewer','D'),
'TheSuBot' = array('TheSuBot','R'),
'Thumbnail.CZ' = array('Thumbnail.CZ','R'),
'thumbshots-de-Bot' = array('ThumbShots website thumbnail service (Germany) robot','D'),
'timboBot' = array('Breaking Blogs timbo bot blog robot','R'),
'TimelyWeb' = array('TimelyWeb web page monitoring tool','C'),
'tivraSpider' = array('Tivra spider from AT&T Labs Research','R'),
'TJG/Spider' = array('Tjgroup spider','R'),
'Tkensaku' = array('Tkensaku Search (Japan) robot from 210.239.46.xxx (www.tken.com)','R'),
'Topodia' = array('Topodia search engine and personal information assistant (in development)','R'),
'TOPOS robot' = array('Topos search (Russia) robot','C'),
'Toutatis' = array('Hoppa robot (81.4.78.xxx)','R'),
'traazibot' = array('Traazi! search (Germany) robot','R'),
'Trampelpfad-Spider' = array('Trampelpfad Webkatalog spider','R'),
'tricosMetaCheck' = array('Tricos meta tag validation','C'),
'TSurf15a' = array('some bad user agent','S'),
'TulipChain' = array('Tulip Chain browser / link checker for Dmoz.org directory','C'),
'TurnitinBot' = array('TurnitinBot','R'),
'Turnpike Emporium' = array('TurnPike Emporium Directory (207.67.198.x) link checking','R'),
'TutorGig' = array('TutorGig tutorial search robot','R'),
'Tutorial Crawler' = array('TutorGig tutorial search robot','R'),
'Twiceler' = array('Twiceler experimental web crawler','R'),
'Twisted PageGetter' = array('File downloading component from Twisted Python','D'),
'Twotrees' = array('Twotrees content filter','P'),
'TygoBot' = array('Tygo Search robot','R'),
'TygoProwler' = array('Tygo Search robot','R'),
),
'u' = array(
'UCmore' = array('UCMore - IE navigation and search plugin','B'),
'UdmSearch' = array('UdmSearch / MySearch (now mnoGoSeach) offline browser/search client','R'),
'UIowaCrawler' = array('University of Iowa Crawler- possibly MySpiders','R'),
'UKWizz' = array('UKWizz search robot','R'),
'Ultraseek' = array('Infoseek robot','R'),
'Under the Rainbow' = array('Unknown mail harvester/spambot from 80.58.13.xxx (proxycache.rima-tde.net)','S'),
'UP.Browser' = array('Mobile phone browser','M'),
'UP.Link' = array('Mobile phone browser','M'),
'updated' = array('updated','R'),
'UPG1' = array('Handspring (PalmOS powered cellphone) Treo Blazer browser','M'),
'Uptimebot' = array('UptimeBot.com online link popularity check','R'),
'URI::Fetch' = array('URI::Fetch - client for fetching HTTP pages and syndication feeds (RSS Atom)','D'),
'URL Spider Pro' = array('Innerprise URL Spider Pro (now ES.NET) web indexing / site searching tool','R'),
'URLBase' = array('URLBase - Internet shortcut manager','C'),
'URLBlaze' = array('URLBlaze file sharing link toolkit','C'),
'URLGetFile' = array('URLGetFile downloading tool','D'),
'User-Agent: BoardReader Favicon' = array('BoardReader search favicon fetcher','D'),
'User-Agent: BoardReader Image' = array('BoardReader search image fetcher','D'),
'User-Agent: LjSEEK' = array('ljpic.com - LiveJournal picture feed search','C'),
'User-Agent: FileHeap' = array('FileHeap download manager','D'),
'User-Agent: Mozilla' = array('Malformed UA header from some guestbook/forum spammer','S'),
'user-agent=Mozilla' = array('unknown robot (reads robots.txt) or sitegrabber. From different IPs- ie.: 62.98.8.xx (wind.it)','R'),
'USyd-NLP-Spider' = array('University of Sydney NLP Spider for research in Natural Language Processing','R'),
'UtilMind HTTPGet' = array('Web Thief Site Grabber','D'),
'Utopia WebWasher' = array('WebWasher ad filter','P'),
'uTorrent' = array('?Torrent BitTorrent client','D'),
),
'v' = array(
'Vagabondo' = array('WiseGuys robot Netherland - 82.94.216.2','R'),
'Vakes' = array('Open Directory link checking from Vakes','R'),
'vb wininet' = array('iNet Grabber - Internet content grabber','D'),
'versus' = array('Versus Project robot - Comparing methods for near-uniform URL sampling','R'),
'VeryGoodSearch' = array('VeryGoodSearch.com link submission checking','R'),
'Verzamelgids' = array('Verzamelgids NL link checking robot','R'),
'Vespa' = array('Unknown robot from Yahoo Norway','R'),
'virus_detector' = array('Sidewinder G2 anti-virus and anti-spyware protection','D'),
'VisBot' = array('Visbot crawler for a search software under development','R'),
'Visicom' = array('Some IE toolbar made with Visicom Media Dynamic Toolbar software','B'),
'Vision Research' = array('Vision research lab\'s Cortina - content based image retrieval (128.111.60.xx)','R'),
'Vivante Link Checker' = array('Vivante Link Checker','C'),
'VLC media player' = array('VLC - Cross-platform media player and streaming server','B'),
'VMBot' = array('VM - Vertical Search Engine (China)','R'),
'Vortex' = array('Vortex','R'),
'voyager' = array('voyager','R'),
'VSE' = array('Vivisimo search crawler (206.210.89.xxx)','R'),
'vspider' = array('Verity vspider indexing software','R'),
'VWBOT' = array('VWBot - MetaQuerier Crawler for the MetaQuerier project at the University of Illinois','R'),
'VYU2' = array('VYU2','R'),
),
'w' = array(
'W3C-checklink' = array('W3C-checklink','C'),
'W3C-WebCon' = array('WebCon - the Libwww command line tool','D'),
'W3C_Validator' = array('W3C_Validator','V'),
'W3CLineMode' = array('W3C Line Mode (character based Web browser)','B'),
'W3CRobot' = array('Unknown link checking using Libwww via Korea Telecom (221.148.44.xxx)','C'),
'w3m' = array('w3m','B'),
'W3SiteSearch' = array('W3 Site Search (Germany) search engine solution','R'),
'wadaino.jp-crawler' = array('Wadain (Japan) Blog / RSS search crawler','R'),
'WannaBe' = array('Wanna-Be text mode browser','B'),
'WapOnWindows' = array('WapOnWindows WAP browser for PCs','B'),
'Watchfire' = array('Watchfire WebXM intranet solution','P'),
'WAVcheck' = array('WAVcheck - Simple Vendor Discovery Tool for detecting client-side tags from web analytics vendors','C'),
'Wavefire' = array('Wavefire local search community engine (64.141.15.1xx)','R'),
'Waypath' = array('Waypath blog discovery engine robot','R'),
'WDG_Validator' = array('WDG_Validator','V'),
'Web Downloader' = array('Web Downloader','O'),
'Web Image Collector' = array('Datafire.com\'s Web Image Collector (graphics downloading tool)','D'),
'Web Link Validator' = array('Relsoft link checking software','C'),
'Web Snooper' = array('RankMeter ranking software','R'),
'web-bekannt' = array('Web-bekannt German web directory link checking','C'),
'Web-Bot' = array('Unkown link or server checking from W?rzburg University Germany (132.187.10.xx)','R'),
'web2express' = array('Web2Express / Web2x - Open data searching tool','R'),
'WebAlta' = array('WebAlta search Russia crawler (85.21.201.xx)','R'),
'WebarooBot' = array('WebarooBot / RufusBot from webaroo offline search service','R'),
'WebAuto' = array('Yanasoft WebAuto website copier / downloading tool','D'),
'webbandit' = array('Web Bandit personal search software','R'),
'WebBug' = array('Amansoft WebBug web server protocol test','C'),
'Webclipping' = array('WebClipping.com - online news monitoring service','R'),
'webcollage' = array('webcollage','R'),
'WebCompass' = array('Quarterdecks WebCompass search tool','R'),
'WebCopier' = array('WebCopier','O'),
'WebCorp' = array('WebCorp linguistic search engine (UK)','R'),
'webcrawl' = array('Webcrawl Search robot (64.40.105.xxx)','R'),
'WebDownloader' = array('Unix/Linux Web Downloader','D'),
'WebFetch' = array('WingFlyer WebFetch website downloading tool','D'),
'WebFilter' = array('Verso NetSpective WebFilter','P'),
'WebFindBot' = array('Webfind search robot','R'),
'Webglimpse' = array('Webglimpse search engine software','R'),
'webGobbler' = array('webGobbler - Online random image generator','R'),
'WebLight' = array('WebLight web analyzer & link checker','C'),
'Weblink\'s checker' = array('WebLink\'s link management system for HTTP- FTP and Mail hyperlinks','C'),
'Weblog Attitude Diffusion' = array('Los Alamos National Laboratoy weblog research project','R'),
'webmeasurement' = array('Unknown robot from Leipzig University (Germany) faculty for computer science','R'),
'WebMiner' = array('WebMiner bulk file downloader','D'),
'WeBoX' = array('WeBoX (Japan) - Browser and web collector','D'),
'WebPix' = array('WebPix - picture downloading tool','D'),
'WebQL' = array('Caesius WebQL - Custom robot/agent generator / web extraction software','D'),
'WebRACE' = array('WebRACE - HTTP retrieval- annotation and caching engine','P'),
'WebReaper' = array('Webreaper download manager','D'),
'WebSauger' = array('WebSauger download tool?','D'),
'WebSearch.COM.AU' = array('Websearch Australia robot','R'),
'WebSearchBench' = array('Dortmund University WebSearchBench - Open source search software','R'),
'Website Explorer' = array('Web site downloading tool and offline browser (Japan)','D'),
'Website eXtractor' = array('Website eXtractor web site downloading tool','D'),
'WebsiteWorth' = array('Sootle web directory Website Worth ranking tool','R'),
'Webspinne' = array('Webspinne.de robot','R'),
'Websquash.com' = array('Websquash.com','R'),
'WebStat' = array('WebStat - Java statistical computing environment for the web','R'),
'Webster' = array('Webster - Rev. Healeys web crawler','R'),
'webster-internet' = array('Websters Webmaster Archive (Germany) submission / pad checking','C'),
'WebStripper' = array('WebStripper download manager','D'),
'WebTrafficExpress' = array('WebTrafficExpress IBM server software','P'),
'WebTrends' = array('Web Trends link analyzer','C'),
'WebVac' = array('The Stanford WebBase Project crawler','R'),
'WebVal' = array('webval - Python link checking tool','C'),
'Webverzeichnis' = array('Webverzeichnis.de (Germany) directory robot','R'),
'WebVulnCrawl' = array('Web Vulnerability Crawler','S'),
'WebWatcherMonitor' = array('Studio Net.Idea\'s Web Watcher Monitor robot','R'),
'WebZIP' = array('WebZIP','O'),
'Wells Search' = array('Unknown spam bot / harvester (62.163.**.** / 62.194.**.*)','S'),
'WEP Search' = array('Some spam bot- see link','S'),
'West Wind' = array('wwIPStuff - Internet client tools for Visual FoxPro','D'),
'WFARC' = array('IBM\'s Almaden Research robot (Clever search project)','R'),
'Wget' = array('Wget','O'),
'Whatsup' = array('Whatsup Gold network monitor','C'),
'whatUseek' = array('WhatUSeek / Chubba robot','R'),
'WhizBang' = array('WhizBang! Labs (closed since May 2002) information extraction robot','R'),
'Wildsoft' = array('some download agent','D'),
'Willow' = array('Twotrees crawler','R'),
'Windows-Media-Player' = array('Windows Media Player 10','B'),
'WinGet' = array('Nicksoft WinGet download manager','D'),
'WinHTTP Example' = array('Example code for a WinHTTP C++ library crawler','R'),
'WinkBot' = array('Wink beta search robot (64.13.136.x)','R'),
'WinPodder' = array('WinPodder - Podcast player and RSS reader','B'),
'WinWAP' = array('WinWap - Windows PC WAP browser','B'),
'Wir sind die Borg' = array('Yammba web directory (Germany) link checking','C'),
'WIRE' = array('WIRE crawler used by the University of Pisa - Italy','R'),
'WISEbot' = array('Korea Wisenut robot','R'),
'WiseWire' = array('Wisewire domain checker (Discontinued)','R'),
'wish-project' = array('WISH academic research project for link checking','C'),
'WoFindeIch' = array('WoFindeIch','R'),
'WordChampBot' = array('Wordchamp web page vocabulary / translation robot','D'),
'WordPress' = array('WordPress personal Blog publishing platform','B'),
'worio' = array('WORIO (beta) search for computer scientists and programmers using Heritrix open-source crawler','R'),
'WorldLight' = array('Entireweb Search robot (62.13.25.xxx)','R'),
'WorQmada' = array('unknown link checking (from 4.18.57.126) ?','C'),
'Wotbox' = array('Wotbox spider','R'),
'WSB' = array('WebSearchBench crawler from Dortmund University- Germany','R'),
'wume_crawler' = array('WUME Lab\'s web crawler (128.180.121.xxx)','R'),
'Wusage' = array('Wusage log-file analysis','R'),
'Wwlib' = array('WWLib - Wolverhampton Univerity Web Library for classifying web documents','R'),
'WWSBOT' = array('WWSBOT web server version checker','C'),
'WWW-Mechanize' = array('Perl web page fetching module','D'),
'www.arianna.it' = array('Arianna robot','R'),
'www.business-socket.com' = array('Business-Socket.com link checking ?','C'),
'www.doweb.co.uk' = array('The DoWeb UK Business directory link checking','C'),
'www4mail' = array('www4mail - web navigation & database search by e-mail','O'),
'WWWC' = array('WWWC Updating check of Web pages. (Japanese only)','C'),
'WWWster' = array('Unknown robot from CIS at Munich University (129.187.254.xxx)','R'),
'WWWeasel' = array('World Wide Weasel Germany robot','R'),
'WWWOFFLE' = array('WWWoffle download manager','D'),
),
'x' = array(
'X-Crawler' = array('Arexera (Germany) crawler software','R'),
'Xaldon' = array('Xaldon_WebSpider','O'),
'Xenu' = array('Xenu Link Sleuth','C'),
'Xerka' = array('XerKa text mining and information retrieval software','D'),
'xine' = array('xine video player','D'),
'xirq' = array('XIRQ search (beta) robot (70.86.206.1xx)','R'),
'XMLSlurp' = array('XMLSlurp','R'),
'XRL' = array('Metamark URL Shorten Service','P'),
'xyro' = array('Inria Crawler','R'),
),
'y' = array(
'Y!J' = array('Yahoo Search Japan robot (211.14.8.2xx)','R'),
'Y!OASIS' = array('Yahoo picture service for mobiles','P'),
'Y!TunnelPro' = array('Y!TunnelPro - Yahoo! Messenger companion user agent','B'),
'yacy' = array('yacy','R'),
'yacybot' = array('Yacy distributed P2P web search engine robot','R'),
'Yahoo Pipes' = array('(Yahoo) Pipes interactive data aggregator robot','R'),
'Yahoo! Mindset' = array('Yahoo Mindset: Intent-driven Search (66.228.182.1xx)','R'),
'Yahoo-Blogs' = array('Yahoo blog indexing robot (209.191.83.1xx)','R'),
'Yahoo-MMAudVid' = array('Yahoo multimedia crawler (206.190.43.xx)','R'),
'Yahoo-MMCrawler' = array('Yahoo multimedia crawler via Fastsearch.net (66.77.73.xx)','R'),
'Yahoo-Test' = array('Yahoo Search robot','R'),
'Yahoo-VerticalCrawler-FormerWebCrawler' = array('Yahoo crawler via Overture (66.77.73.3x)','R'),
'YahooFeedSeeker' = array('Yahoo Publisher Network RSS crawler','R'),
'YahooSeeker' = array('Yahoo!','R'),
'Yandex' = array('Yandex Search Russia link checking (213.180.206.2xx)','R'),
'yarienavoir.net' = array('Yarienavoir search (Belgium) robot (217.71.121.xx)','R'),
'Yeti' = array('1noon.com search Korea robot (222.231.21.xxx)','R'),
'yggdrasil' = array('yggdrasil spider for GoPubMed biorelated search engine','R'),
'YodaoBot' = array('Yodao search (China)','R'),
'yoogliFetchAgent' = array('yoogliFetchAgent','R'),
'yoono' = array('Yoono - community based search (193.110.140.xxx)','R'),
'YottaCars_Bot' = array('YottaCars bot - YottaCar car search engine ( 64.62.175.xxx)','R'),
'YottaShopping_Bot' = array('YottaShopping bot - YottaShopping search engine ( 64.62.175.xxx)','R'),
'YTunnelPro' = array('Y!TunnelPro - Yahoo! Messenger companion user agent','B'),
),
'z' = array(
'Z-Add Link Checker' = array('Z-Add online link checker','C'),
'Zao' = array('Zao','R'),
'ZBot' = array('Zeus Internet Marketing Robot based on Webster Pro component','R'),
'Zearchit' = array('Zearchit German search / directory (212.227.109.1xx)','R'),
'ZeBot' = array('Ze.bz Moteur de Recherche robot (213.251.135.xx)','R'),
'zedzo' = array('ZedZo Search (beta) robot - 24.62.50.1xx','R'),
'Zend_Http_Client' = array('Zend PHP frameworks Zend_Http_Client component','D'),
'zerxbot' = array('Zerx search robot (138.88.147.xxx) ?','R'),
'Zeus ThemeSite' = array('Zeus Internet Marketing Robot (based on Webster Pro)','R'),
'Zeus xxxxx' = array('Zeus Internet Marketing Robot (based on Webster Pro)','R'),
'Zeusbot' = array('Zeusbot robot for building the Ulsysseek.com index','R'),
'Zeus' = array('Zeus email harvester from Asia','S'),
'Ziggy' = array('Unknown agent (server- or link checking ?) from 198.173.158.xx','C'),
'Zippp' = array('Zipp.net web search robot','R'),
'Zippy' = array('Zippyfinder robot','R'),
'Zoo Tycoon' = array('Microsoft Zoo Tycoon 2 game client','B'),
'ZoomSpider' = array('Zoom Search Engine software spider','R'),
'zspider' = array('zspider','R'),
'ZyBorg' = array('ZyBorg','C'),
),
)
}
lp_client_browser(null)