Skip to content

Instantly share code, notes, and snippets.



Created Jun 23, 2011
What would you like to do?
see what your bot traffic is like
#!/usr/bin/env python
Hack to look for user agent strings in typical Apache style log and
count up the number of requests by bots vs non-bots. The list of bot
user agents comes from but has had some
agents added to it, since the list is pretty out of date, e.g.
no Bing?!
import re
import fileinput
def main():
all_requests = 0
bot_requests = 0
bot_count = {}
for line in fileinput.input():
all_requests += 1
m ='".*?".*?".*?".*?"(.*?)"', line)
ua =
if ua == "-" or ua in bot_user_agents:
bot_count[ua] = bot_count.get(ua, 0) + 1
bot_requests += 1
bots = bot_count.keys()
bots.sort(lambda a, b: cmp(bot_count[a], bot_count[b]))
for bot in bots:
print "%10d %s" % (bot_count[bot], bot)
print "percentage of bot requests: %f%%" % ((bot_requests / float(all_requests)) * 100)
bot_user_agents = set([
'''( Robots.txt Validator )''',
'''(DreamPassport/3.0; isao/MyDiGiRabi)''',
''' (+Have Good Day)''',
'''123spider-Bot (Version: 1.02, powered by''',
'''1st ZipCommander (Net) -''',
'''2Bone_LinkChecker/1.0 libwww-perl/5.64''',
''' LinkChecker v2.0''',
'''8484 Boston Project v 1.0''',
''':robot/1.0 (linux) ( admin e-mail: undefined )''',
'''A-Online Search''',
'''A1 Keyword Research/1.0.2 (+ miggibot/2007.03.27''',
'''A1 Sitemap Generator/1.0 (+ miggibot/2006.01.24''',
'''AbachoBOT (Mozilla compatible)''',
'''ABCdatos BotLink/''',
'''Aberja Checkomat''',
'''abot/0.1 (abot;;''',
'''Accelatech RSSCrawler/0.4''',
'''Accoona-AI-Agent/1.1.1 (crawler at accoona dot com)''',
'''Accoona-AI-Agent/1.1.2 (aicrawler at accoonabot dot com)''',
'''Ace Explorer''',
'''Ack (''',
'''Acoon Robot v1.50.001''',
'''Acoon Robot v1.52 (''',
'''Acoon-Robot 4.0.x.[xx] (''',
'''Acoon-Robot v3.xx ( and''',
'''Acorn/Nutch-0.9 (Non-Profit Search Engine;; acorn at isara dot org)''',
'''ActiveBookmark 1.x''',
'''ActiveWorlds/3.xx (xxx)''',
'''Ad Muncher v4.xx.x''',
'''Ad Muncher v4x Build xxxxx''',
'''Adaxas Spider (''',
'''Advanced Browser (''',
'''agadine/1.x.x (+''',
'''AgentName/0.1 libwww-perl/5.48''',
'''AIBOT/2.1 By +( A Real artificial intelligence search engine China)''',
'''AideRSS/1.0 (''',
'''aipbot/1.0 (aipbot;;''',
'''aipbot/2-beta (aipbot dev;;''',
'''Akregator/1.2.9; librss/remnants''',
'''Alcatel-BG3/1.0 UP.Browser/''',
'''Aleksika Spider/1.0 (+''',
'''AlertInfo 2.0 (Powered by Newsbrain)''',
'''AlkalineBOT/1.4 (1.4.0326.0 RTM)''',
'''Allesklar/0.1 libwww-perl/5.46''',
'''Alligator 1.31 (''',
'''Allrati/1.1 (+)''',
'''AltaVista Intranet V2.0 AVS EVAL''',
'''AltaVista Intranet V2.0 Compaq Altavista Eval''',
'''AltaVista Intranet V2.0''',
'''AltaVista V2.0B''',
'''amaya/x.xx libwww/x.x.x''',
'''Amfibibot/0.06 (Amfibi Web Search;;''',
'''Amfibibot/0.07 (Amfibi Robot;;''',
'''AmigaVoyager/3.4.4 (MorphOS/PPC native)''',
'''AmiTCP Miami (AmigaOS 2.04)''',
'''Amoi 8512/R21.0 NF-Browser/3.3''',
'''AnnoMille spider 0.1 alpha -''',
'''Anonymized by ProxyOS:''',
'''AnswerBus (''',
'''AnswerChase PROve x.0''',
'''AnswerChase x.0''',
'''AnzwersCrawl/2.0 (;Engine)''',
'''Apexoo Spider 1.x''',
'''Aplix HTTP/1.0.1''',
'''Aplix_SANYO_browser/1.x (Japanese)''',
'''Aplix_SEGASATURN_browser/1.x (Japanese)''',
'''appie 1.1 (''',
'''Apple iPhone v1.1.4 CoreMedia v1.0.0.4A102''',
'''ArabyBot (compatible; Mozilla/5.0; GoogleBot; FAST Crawler 6.4;;)''',
'''Arachnoidea (''',
'''Argus/1.1 (Nutch;; feedback at simpy dot com)''',
'''Arquivo-web-crawler (compatible; heritrix/1.12.1 +''',
'''ASAHA Search Engine Turkey V.001 (''',
'''Asahina-Antenna/1.x ( ;''',
'''AskAboutOil/0.06-rcp (Nutch;;''',
'''asked/Nutch-0.8 (web crawler;; epicurus at gmail dot com)''',
'''AtlocalBot/1.1 +(''',
'''Attentio/Nutch-0.9-dev (Attentio's beta blog crawler;;''',
'''AU-MIC/2.0 MMP/2.0''',
'''augurnfind V-1.x''',
'''autowebdir 1.1 (''',
'''AV Fetch 1.0''',
'''Avant Browser (''',
'''axadine/ (Axadine Crawler;; )''',
'''AxmoRobot - Crawling your site for better indexing on search engine.''',
'''Azureus 2.x.x.x''',
'''BabalooSpider/1.3 (BabalooSpider;;''',
'''BaboomBot/1.x.x (+''',
'''BackStreet Browser 3.x''',
'''Balihoo/Nutch-1.0-dev (Crawler for search engine - obeys robots.txt and robots meta tags ;; robot at balihoo dot com)''',
'''BanBots/1.2 (''',
'''BarraHomeCrawler (''',
'''bCentral Billing Post-Process''',
'''bdcindexer_2.6.2 (research@bdc)''',
'''BDNcentral Crawler v2.3 [en] ( (X11; I; Linux 2.0.44 i686)''',
'''BeamMachine/0.5 (dead link remover of''',
'''beautybot/1.0 (+''',
'''BebopBot/2.5.1 ( crawler )''',
'''Big Brother (''',
'''Big Fish v1.0''',
'''BigCliqueBOT/1.03-dev (bigclicbot;;''',
'''BIGLOTRON (Beta 2;GNU/Linux)''',
''' ( Internet Spider;;''',
'''BilgiBetaBot/0.8-dev ( (Beta) ;;''',
'''BilgiBot/1.0(beta) (; bilgi at bilgi dot com)''',
'''Mozilla/5.0 (compatible; bingbot/2.0; +''',
'''Bitacle bot/1.1''',
'''Bitacle Robot (V:1.0;) (''',
'''Biyubi/x.x (Sistema Fenix; G11; Familia Toledo; es-mx)''',
'''BlackBerry7520/4.0.0 Profile/MIDP-2.0 Configuration/CLDC-1.1 UP.Browser/ UP.Link/ (Google WAP Proxy/1.0)''',
'''Blaiz-Bee/1.0 (+''',
'''Blaiz-Bee/2.00.8222 (BE Internet Search Engine''',
'''Blaiz-Bee/2.00.xxxx (+''',
''' (Mozilla compatible)''',
'''BlogBridge 2.13 (''',
'''Bloglines Title Fetch/1.0 (''',
'''Bloglines-Images/0.1 (''',
'''Bloglines/3.1 (''',
'''BlogMap (''',
'''Blogpulse (''',
'''BlogPulseLive (''',
'''BlogSearch/1.x +''',
'''BlogsNowBot, V 2.01 (+''',
'''BlogVibeBot-v1.1 (''',
'''blogWatcher_Spider/0.1 (''',
'''BlogzIce/1.0 (+;''',
'''BlogzIce/1.0 +''',
'''Bloodhound/Nutch-0.9 (Testing Crawler for Research - obeys robots.txt and robots meta tags ;; robot at balihoo dot com)''',
'''bluefish 0.6 HTML editor''',
'''Bobby/4.0.x RPT-HTTPClient/0.3-3E''',
''' (''',
''' (''',
'''Bookmark Buddy bookmark checker (''',
'''Bookmark Renewal Check Agent []''',
'''Bookmark Renewal Check Agent [] (Version 2.0beta)''',
'''BPImageWalker/2.0 (''',
'''BravoBrian SpiderEngine MarcoPolo''',
'''BrightCrawler (''',
'''BruinBot (+ ''',
''' Agent Detector''',
'''BTbot/0.x (+''',
'''BuildCMS crawler (''',
'''Bulkfeeds/r1752 (''',
'''BurstFindCrawler/1.1 (;;''',
'''Buscaplus Robi/1.0 (''',
'''Cabot/Nutch-0.9 (Amfibi's web-crawling robot;;''',
'''Cabot/Nutch-1.0-dev (Amfibi's web-crawling robot;;''',
'''Cancer Information and Support International;''',
'''Carnegie_Mellon_University_Research_WebBOT-->PLEASE READ-->''',
'''Catall Spider''',
'''CazoodleBot/CazoodleBot-0.1 (CazoodleBot Crawler;;''',
'''CCBot/1.0 (+''',
'''CDR/1.7.1 Simulator/0.7(+ Profile/MIDP-1.0 Configuration/CLDC-1.0''',
'''CentiverseBot - investigator''',
'''CentiverseBot/3.0 (''',
'''Ceramic Tile Installation Guide (''',
'''cg-eye interactive''',
'''Charon/1.x (Amiga)''',
'''Chat Catcher/1.0''',
'''Checkbot/1.xx LWP/5.xx''',
'''Chilkat/1.0.0 (+''',
'''China Local Browse 2.6''',
'''Chitika ContentHit 1.0''',
'''ChristCRAWLER 2.0''',
'''CHttpClient by Open Text Corporation''',
'''CipinetBot (''',
'''Cityreview Robot (+''',
'''CJ Spider/''',
'''CJB.NET Proxy''',
'''CloakDetect/0.9 (+''',
'''Clushbot/2.x (+''',
'''Clushbot/3.x-BinaryFury (+''',
'''Clushbot/3.xx-Ajax (+''',
'''Clushbot/3.xx-Hector (+''',
'''Clushbot/3.xx-Peleus (+''',
'''COAST WebMaster Pro/4.x.x.xx (Windows NT)''',
''' (v36) (Mac OS X;''',
'''Cogentbot/1.X (+''',
'''ColdFusion (''',
'''Commerce Browser Center''',
'''complex_network_group/Nutch-0.9-dev (discovering the structure of the world-wide-web;;''',
'''Comrite/0.7.1 (Nutch;;''',
'''Convera Internet Spider V6.x''',
'''ConveraCrawler/0.9d (+''',
'''ConveraMultiMediaCrawler/0.1 (+''',
'''Cooliris/1.5 CFNetwork/459 Darwin/10.0.0d3''',
'''CoralWebPrx/0.1.1x (See''',
'''CoteoNutchCrawler/Nutch-0.9 (info [at] coteo [dot] com)''',
'''CougarSearch/0.x (+''',
'''Covac TexAs Arachbot''',
'''CoverScout%203/3.0.1 CFNetwork/339.5 Darwin/9.5.0 (i386) (iMac5,1)''',
'''Cowbot-0.1 (NHN Corp. / +82-2-3011-1954 /''',
'''Cowbot-0.1.x (NHN Corp. / +82-2-3011-1954 /''',
'''CrawlConvera0.1 (''',
'''Crawler (''',
'''Crawler V 0.2.x''',
'''Crawllybot/0.1 (Crawllybot; +;''',
'''CreativeCommons/0.06-dev (Nutch;;''',
'''Cricket-A100/1.0 UP.Browser/ (GUI) MMP/2.0''',
'''CrocCrawler vx.3 [en] ( (X11; I; Linux 2.0.44 i686)''',
'''CSE HTML Validator Professional (''',
'''Cuam Ver0.050bx''',
'''Cuasarbot/0.9b ''',
'''curl/7.10.x (i386-redhat-linux-gnu) libcurl/7.10.x OpenSSL/0.9.7a ipv6 zlib/1.1.4''',
'''curl/7.7.x (i386--freebsd4.3) libcurl 7.7.x (SSL 0.9.6) (ipv6 enabled)''',
'''curl/7.8 (i686-pc-linux-gnu) libcurl 7.8 (OpenSSL 0.9.6)''',
'''curl/7.9.x (win32) libcurl 7.9.x''',
'''CurryGuide SiteScan 1.1''',
'''Custo x.x (''',
'''Custom Spider /1.0''',
'''Cyberdog/2.0 (Macintosh; 68k)''',
'''CyberPatrol SiteCat Webbot (''',
'''CyberSpyder Link Test/2.1.12 (''',
'''CydralSpider/1.x (Cydral Web Image Search;''',
'''CydralSpider/3.0 (Cydral Image Search;''',
'''DA 3.5 (''',
'''DA 4.0''',
'''DA 4.0 (''',
'''DA 5.0''',
'''DA 7.0''',
'''DAP x.x''',
'''Dart Communications PowerTCP''',
'''DataFountains/DMOZ Downloader''',
'''DataFountains/Dmoz Downloader (''',
'''DataFountains/DMOZ Feature Vector Corpus Creator (''',
'''DataparkSearch/4.47 (+''',
'''DataparkSearch/4.xx (''',
'''DataSpear/1.0 (Spider;;''',
'''DataSpearSpiderBot/0.2 (DataSpear Spider Bot;;''',
'''DaviesBot/1.7 (''',
'''DBrowse 1.4b''',
'''DBrowse 1.4d''',
'''dds explorer v1.0 beta''',
'''de.searchengine.comBot 1.2 (''',
'''DeadLinkCheck/0.4.0 libwww-perl/5.xx''',
'''Deep Link Calculator v1.0''',
'''DeepIndex ( )''',
'''DeepIndex (''',
''' Mozilla/5.0 (compatible; Konqueror/3.4; FreeBSD) KHTML/3.4.2 (like Gecko)''',
'''Demo Bot DOT 16b''',
'''Demo Bot Z 16b''',
'''Denmex websearch (''',
'''Der große BilderSauger 2.00u''',
''' HtmlDocument Object''',
'''DiaGem/1.1 (''',
'''Digger/1.0 JDK/1.3.0rc3''',
'''disastrous/1.0.5 (running with Python 2.5.1;;''',
'''DISCo Pump x.x''',
'''disco/Nutch-0.9 (experimental crawler;;''',
'''disco/Nutch-1.0-dev (experimental crawler;;''',
''' WebBot Link Ckeck Tool. Report abuse to:''',
'''DoCoMo/1.0/P502i/c10 (Google CHTML Proxy/1.0)''',
'''DoCoMo/2.0 P900iV(c100;TB;W24H11) ''',
'''DoCoMo/2.0 SH901iS(c100;TB;W24H12),gzip(gfe) (via''',
'''DoCoMo/2.0 SH902i (compatible; Y!J-SRD/1.0;''',
'''DoCoMo/2.0/SO502i (compatible; Y!J-SRD/1.0;''',
'''DoCoMo/2.0 N905i(c100;TB;W24H16) (compatible; Googlebot-Mobile/2.1; +'''
'''DocZilla/1.0 (Windows; U; WinNT4.0; en-US; rv:1.0.0) Gecko/20020804''',
'''DonutP; Windows98SE''',
'''Doubanbot/1.0 (''',
'''Download Demon/3.x.x.x''',
'''Download Druid 2.x''',
'''Download Express 1.0''',
'''Download Master''',
'''Download Ninja 3.0''',
'''Download Wonder''',
'''Download-Tipp Linkcheck (''',
'''Download.exe(1.1) (+''',
'''Dr.Web (R) online scanner:''',
'''Dragonfly File Reader''',
'''Drecombot/1.0 (''',
'''Drupal (+''',
'''DSurf15a 01''',
'''DSurf15a 71''',
'''DSurf15a 81''',
'''DSurf15a VA''',
'''Dual Proxy''',
'''DuckDuckBot/1.0; (+''',
'''Dumbot(version 0.1 beta -''',
'''Dumbot(version 0.1 beta -''',
'''Dumbot(version 0.1 beta)''',
'''e-sense 1.0 ea(''',
'''eApolloBot/2.0 (compatible; heritrix/2.0.0-SNAPSHOT-20071024.170148 +''',
''' []''',
''' []''',
'''EBrowse 1.4b''',
'''Educate Search VxB''',
'''egothor/3.0a (+''',
'''EgotoBot/4.8 (+''',
'''EldoS TimelyWeb/3.x''',
'''elfbot/1.0 (+''',
'''ELI/20070402:2.0 (DAUM RSS Robot, Daum Communications Corp.; +''',
'''ELinks (0.x.x; Linux 2.4.20 i586; 132x60)''',
'''ELinks/0.x.x (textmode; NetBSD 1.6.2 sparc; 132x43)''',
'''EmailWolf 1.00''',
''' WebBot''',
''' WebBot (''',
'''EnaBot/1.x (''',
'''endo/1.0 (Mac OS X; ppc i386;''',
'''Enfish Tracker''',
'''Enterprise_Search/;MSSQL (''',
'''envolk/1.7 (+''',
'''ES.NET_Crawler/2.0 (''',
'''eseek-larbin_2.6.2 (''',
'''eStyleSearch 4 (compatible; MSIE 6.0; Windows NT 5.0)''',
'''ESurf15a 15''',
'''EuripBot/0.x (+ GetFile''',
'''EuripBot/0.x (+ GetRobots''',
'''EuripBot/0.x (+ PreCheck''',
'''Eurobot/1.0 (''',
'''EvaalSE -''',
'''eventax/1.3 (eventax;;''',
'''Everest-Vulcan Inc./0.1 (R&D project; host=e-1-24;''',
'''Everest-Vulcan Inc./0.1 (R&D project;''',
'''ExactSeek Crawler/0.1''',
'''exactseek-crawler-2.63 (''',
'''exactseek-pagereaper-2.63 (''',
'''Exalead NG/MimeLive Client (convert/http/0.120)''',
'''Excalibur Internet Spider V6.5.4''',
'''Execrawl/1.0 (Execrawl;;''',
'''exooba crawler/exooba crawler (crawler for;; info at exooba dot com)''',
'''exooba/exooba crawler (exooba; exooba)''',
'''Expired Domain Sleuth''',
'''Express WebPictures (''',
'''Extreme Picture Finder''',
'''EyeCatcher (''',
'''Factbot 1.09 (see''',
'''factbot :''',
'''FairAd Client''',
''' link verifier''',
'''Fast Crawler Gold Edition''',
'''FAST Enterprise Crawler 6 (Experimental)''',
'''FAST Enterprise Crawler 6 / Scirus;''',
'''FAST Enterprise Crawler 6 used by Cobra Development (''',
'''FAST Enterprise Crawler 6 used by Comperio AS (''',
'''FAST Enterprise Crawler 6 used by FAST (FAST)''',
'''FAST Enterprise Crawler 6 used by Pages Jaunes (''',
'''FAST Enterprise Crawler 6 used by Web Crawler (search_comments\at\sensis\dot\com\dot\au)''',
'''FAST Enterprise Crawler 6 used by Singapore Press Holdings (''',
'''FAST Enterprise Crawler 6 used by WWU (''',
'''FAST Enterprise Crawler/6 (''',
'''FAST Enterprise Crawler/6.4 (helpdesk at''',
'''FAST FirstPage retriever (compatible; MSIE 5.5; Mozilla/4.0)''',
'''FAST MetaWeb Crawler (helpdesk at fastsearch dot com)''',
'''Fast PartnerSite Crawler''',
'''FAST-WebCrawler/2.2.10 (Multimedia Search) (;''',
'''FAST-WebCrawler/2.2.6 (;''',
'''FAST-WebCrawler/2.2.7 (;''',
'''FAST-WebCrawler/2.2.8 (;''',
'''FAST-WebCrawler/3.2 test''',
'''FAST-WebCrawler/3.3 (;''',
'''FAST-WebCrawler/3.4/Nirvana (;''',
'''FAST-WebCrawler/3.4/PartnerSite (;''',
'''FAST-WebCrawler/3.5 (atw-crawler at fast dot no;''',
'''FAST-WebCrawler/3.6 (atw-crawler at fast dot no;''',
'''FAST-WebCrawler/3.6/FirstPage (;''',
'''FAST-WebCrawler/3.7 (atw-crawler at fast dot no;''',
'''FAST-WebCrawler/3.7/FirstPage (atw-crawler at fast dot no;''',
'''FAST-WebCrawler/3.8 (atw-crawler at fast dot no;''',
'''FAST-WebCrawler/3.8/Fresh (atw-crawler at fast dot no;''',
'''FAST-WebCrawler/3.x Multimedia''',
'''FAST-WebCrawler/3.x Multimedia (mm dash crawler at fast dot no)''',
'''fastbot crawler beta 2.0 (+''',
'''FastCrawler 3.0.1 (''',
'''FastSearch Web Crawler for Verizon SuperPages (''',
'''Favcollector/2.0 (''',
''' crawler/0.6 (''',
'''Favorites Checking (''',
'''Favorites Sweeper v.2.03''',
'''FDM 1.x''',
'''FDM 2.x''',
'''Feed Seeker Bot (RSS Feed Seeker''',
'''Feedable/0.1 (compatible; MSIE 6.0; Windows NT 5.1)''',
'''FeedDemon/2.7 (; Microsoft Windows XP)''',
'''Feedfetcher-Google-iGoogleGadgets; (+''',
'''Feedfetcher-Google; (+''',
'''FeedForAll rss2html.php v2''',
'''FeedHub FeedDiscovery/1.0 (''',
'''FeedHub MetaDataFetcher/1.0 (''',
'''Feedjit Favicon Crawler 1.0''',
'''Feedreader 3.xx (Powered by Newsbrain)''',
'''Feedshow/x.0 (; 1 subscriber)''',
'''FeedshowOnline (''',
'''Feedster Crawler/3.0; Feedster, Inc.''',
'''FeedZcollector v1.x (Platinum)''',
'''Felix - Mixcat Crawler (+''',
'''fetch libfetch/2.0''',
'''FFC Trap Door Spider''',
'''Filangy/0.01-beta (Filangy;;''',
'''Filangy/1.0x (Filangy;;''',
'''Filangy/1.0x (Filangy;;''',
''' (+''',
'''FileHound x.x''',
'''Findexa Crawler (''',
'''findlinks/ (+ ''',
'''Firefly/1.0 (compatible; Mozilla 4.0; MSIE 5.5)''',
'''Firefox (''',
'''Firefox_1.0.6 (''',
''' Search -''',
'''Flapbot/0.7.2 (Flaptor Crawler;; crawler at flaptor period com)''',
'''Flexum spider''',
'''FlickBot 2.0 RPT-HTTPClient/0.3-3''',
'''fly/6.01 libwww/4.0D''',
''' 1.0/''',
'''FnooleBot/2.5.2 (+''',
''' Spider/0.1 beta 1 (''',
'''FollowSite Bot ( )''',
''' ( )''',
'''Francis/1.0 (''',
'''Franklin Locator 1.8''',
''' download-link validator /0.1''',
''' (;''',
'''Frelicbot/1.0 +''',
'''FreshNotes crawler< report problems to crawler-at-freshnotes-dot-com''',
'''FSurf15a 01''',
'''Full Web Bot 0416B''',
'''Full Web Bot 0516B''',
'''Full Web Bot 2816B''',
'''FyberSpider (+''',
'''GAIS Robot/1.0B2''',
'''Gaisbot/3.0 (;''',
'''GalaxyBot/1.0 (''',
'''Gallent Search Spider v1.4 Robot 2 (''',
'''gamekitbot/1.0 (+''',
'''gazz/x.x (''',
'''Generic Mobile Phone (compatible; Googlebot-Mobile/2.1; +''',
'''GenesisBrowser (HTTP 1.1; 0.9; XP SP2; .NET CLR 2.0.50727)''',
'''genieBot (''',
'''GeonaBot 1.x;''',
'''GeoURLBot 1.0 (''',
'''GetRight/6.1 (Pro)''',
'''GetWeb/0.1 libwww-perl/5.16''',
'''GhostRouteHunter/20021130 (;''',
'''gigabaz/3.1x (;''',
'''Gigabot/2.0 (''',
'''Gigabot/3.0 (''',
'''GigabotSiteSearch/2.0 (''',
'''Go!Zilla 3.x (''',
'''Goblin/0.9 (''',
'''Goblin/0.9.x (''',
'''GOFORITBOT ( )''',
'''GoGuides.Org Link Check''',
'''GoldenFeed Spider 1.0 (''',
'''Goldfire Server''',
'''gonzo1[P] +''',
'''gonzo2[P] +''',
'''Google Talk''',
'''googlebot (larbin2.6.0@unspecified.mail)''',
'''Googlebot-Image/1.0 (''',
'''Googlebot/2.1 (''',
'''Googlebot/2.1 (''',
'''Googlebot/Test (''',
'''Gordon's Spider/Nutch-0.9 (;''',
'''GrapeFX/0.3 libwww/5.4.0''',
'''great-plains-web-spider/flatlandbot (Flatland Industries Web Spider;;''',
'''gridwell (''',
'''GrigorBot 0.8 (''',
'''grub crawler(''',
'''gsa-crawler (Enterprise; GID-01422;''',
'''gsa-crawler (Enterprise; GID-01742;''',
'''gsa-crawler (Enterprise; GIX-02057;''',
'''gsa-crawler (Enterprise; GIX-03519;''',
'''gsa-crawler (Enterprise; GIX-0xxxx;''',
'''GSiteCrawler/v1.xx rev. xxx (''',
'''Guestbook Auto Submitter''',
'''Gulper Web Bot 0.2.4 (''',
'''Gungho/0.08004 (''',
'''GurujiBot/1.0 (+''',
'''GurujiImageBot/1.0 (+''',
'''Haier-T10C/1.0 iPanel/2.0 WAP2.0 (compatible; UP.Browser/; UPG1; UP/4.0; Embedded)''',
'''Haste/0.12 (HOME:''',
'''Hatena Antenna/0.4 (''',
'''Hatena Mobile Gateway/1.0''',
'''Hatena Pagetitle Agent/1.0''',
'''Hatena RSS/0.3 (''',
'''HatenaScreenshot/1.0 (checker)''',
'''hbtronix.spider.2 --''',
'''HeinrichderMiragoRobot (''',
'''Helix/1.x (''',
'''HenriLeRobotMirago (''',
'''HenryTheMiragoRobot (''',
'''Hi! I'm CsCrawler my homepage: RPT-HTTPClient/0.3-3''',
'''Hippias/0.9 Beta''',
'''Hitwise Spider v1.0''',
'''holmes/3.11 (''',
'''holmes/3.9 (''',
'''holmes/3.xx (OnetSzukaj/5.0; +''',
'''HolmesBot (''',
'''Honda-Search/0.7.2 (Nutch;;''',
'''HooWWWer/2.1.3 (debugging run) (+ | mailto:crawler-info<at>''',
'''HooWWWer/2.1.x ( | mailto:crawler-info<at>''',
'''HPL/Nutch-0.9 -''',
'''htdig/3.1.6 (''',
'''htdig/3.1.6 (unconfigured@htdig.searchengine.maintainer)''',
'''htdig/3.1.x (root@localhost)''',
'''Html Link Validator (''',
'''HTML2JPG Blackbox,''',
'''HTML2JPG Enterprise''',
'''HTTP Retriever''',
''' (Unix)''',
'''http://Ask.24x.Info/ (''',
''' ACONTBOT''',
''' []''',
''' [wf216]''',
'''HTTPResume v. 1.x''',
'''Hybrid/1.2 [en] (OS Independent)''',
'''i1searchbot/2.0 (i1search web crawler;;''',
'''iaskspider2 (''',
'''IBrowse/2.2 (AmigaOS 3.5)''',
'''IBrowse/2.2 (Windows 3.1)''',
'''iCab/2.5.2 (Macintosh; I; PPC)''',
'''ICC-Crawler(Mozilla-compatible;; icc-crawl(at)ml(dot)nict(dot)go(dot)jp)''',
'''iCCrawler (''',
'''ICCrawler - ICjobs (''',
'''ICE Browser/5.05 (Java 1.4.0; Windows 2000 5.0 x86)''',
'''ichiro/x.0 (''',
'''ichiro/x.0 (''',
'''IconSurf/2.0 favicon finder (see''',
'''IconSurf/2.0 favicon monitor (see''',
'''ICOO Loader v.x.x.x''',
'''ideare - SignSite/1.x''',
''' (; 0 subscribers)''',
'''igdeSpyder (compatible;; +''',
'''iGetter/1.x (Macintosh;G;PPC)''',
'''iGetter/2 (Macintosh; U; PPC Mac OS X; en)''',
'''IIITBOT/1.1 (Indian Language Web Search Engine;; pvvpr at iiit dot ac dot in)''',
'''ilial/Nutch-0.9 (Ilial, Inc. is a Los Angeles based Internet startup company. For more information please visit;;''',
'''IlTrovatore-Setaccio (''',
'''Iltrovatore-Setaccio/0.3-dev (Indexing;;''',
'''IlTrovatore-Setaccio/1.2 (''',
'''Iltrovatore-Setaccio/1.2 (It-bot;;''',
'''iltrovatore-setaccio/1.2-dev (spidering;''',
'''IlTrovatore/1.2 (IlTrovatore;;''',
'''ImageWalker/2.0 (''',
'''Incutio HttpClient v0.x''',
'''IncyWincy data gatherer(''',
'''IncyWincy page crawler(''',
''' Crawler7''',
'''Industry Program 1.0.x''',
'''Inet library''',
''' ( il Sud dei Motori di Ricerca''',
'''infoConveraCrawler/0.8 (''',
'''InfoFly/1.0 (''',
'''INFOMINE/8.0 Adders''',
'''INFOMINE/8.0 RemoteServices''',
'''INFOMINE/8.0 VLCrawler (''',
'''InfoSeek Sidewinder/0.9''',
'''InfoSeek Sidewinder/1.0A''',
'''InfoSeek Sidewinder/1.1A''',
'''Infoseek SideWinder/1.45 (Compatible; MSIE 10.0; UNIX)''',
'''Infoseek SideWinder/2.0B (Linux 2.4 i686)''',
'''INGRID/3.0 MT (;''',
'''Inktomi Search''',
'''InnerpriseBot/1.0 (''',
''' search and find world wide!''',
'''InstallShield DigitalWizard''',
'''Intelix/0.x (cs;;''',
'''Interarchy/x.x.x (InterarchyCrawler)''',
'''Internet Ninja x.0''',
'''IOI/2.0 (ISC Open Index crawler;;''',
'''IP*Works! V5 HTTP/S Component - by /n software -''',
'''IP2MapBot/1.1 <a href=></a>''',
'''IPiumBot laurion(dot)com''',
'''IpselonBot/0.xx-beta (Ipselon;;''',
'''IRLbot/1.0 (''',
'''IRLbot/3.0 (compatible; MSIE 6.0;''',
'''ISC Systems iRc Search 2.1''',
'''iSiloX/4.xx Windows/32''',
'''isurf (''',
'''IUPUI Research Bot v 1.9a''',
'''iVia Page Fetcher (''',
'''iVia/4.0 CanonizeUrl (''',
'''IWAgent/ 1.0 -''',
'''Jabot/6.x (''',
'''Jabot/7.x.x (''',
'''Jakarta Commons-HttpClient/2.0xxx''',
'''Jakarta Commons-HttpClient/3.0-rcx''',
'''Jambot/0.1.x (Jambot;;''',
'''Jambot/0.2.1 (Jambot;;''',
'''Java 1.1''',
'''Jayde Crawler.''',
'''JBH Agent 2.0''',
'''jBrowser/J2ME Profile/MIDP-1.0 Configuration/CLDC-1.0 (Google WAP Proxy/1.0)''',
'''JCheckLinks/0.1 RPT-HTTPClient/0.3-1''',
'''JetBrains Omea Reader 1.0.x (''',
'''JetBrains Omea Reader 2.0 Release Candidate 1 (''',
'''Jigsaw/2.2.x W3C_CSS_Validator_JFouffa/2.0''',
'''JoBo/1.x (''',
'''JOC Web Spider''',
'''JordoMedia/1.0 RSS File Reader (''',
'''Journster [alpha] (''',
''' RSS/Atom aggregator 0.5 (''',
'''JRTS Check Favorites Utility''',
'''JRTwine Software Check Favorites Utility''',
'''K-Meleon/0.6 (Windows; U; Windows NT 5.1; en-US; rv:0.9.5) Gecko/20011011''',
'''KAIST AITrc Crawler''',
'''KakleBot - (KakleBot -; http://;''',
'''kalooga/kalooga-4.0-dev-datahouse (Kalooga;;''',
'''kalooga/KaloogaBot (Kalooga;;''',
'''Kapere (''',
'''KDDI-SN22 UP.Browser/6.0.7 (GUI) MMP/1.1 (Google WAP Proxy/1.0)''',
'''Kenjin Spider''',
'''KE_1.0/2.0 libwww/5.2.8''',
'''KFSW-Bot (Version: 1.01 powered by KFSW''',
'''kinja-imagebot (''',
'''kinjabot (''',
'''KIT-Fireball/2.0 (compatible; Mozilla 4.0; MSIE 5.5)''',
'''Klondike/1.50 (WSP Win32) (Google WAP Proxy/1.0)''',
'''Kontiki Client x.xx''',
'''Krugle/Krugle,Nutch/0.8+ (Krugle web crawler;;''',
'''KSbot/1.0 (KnowledgeStorm crawler;;''',
'''KummHttp/1.1 (compatible; KummClient; Linux rulez)''',
'''KWC-KX9/1109 UP.Browser/ (GUI) MMP/2.0 UP.Link/''',
'''lanshanbot/1.0 (+''',
'''LapozzBot/1.4 (''',
'''LapozzBot/1.5 (+''',
'''larbin (''',
'''larbin_2.2.0 (''',
'''larbin_2.2.1_de_Viennot (''',
'''larbin_2.2.2 (''',
'''larbin_2.2.2_guillaume (''',
'''larbin_2.6.0 (larbin2.6.0@unspecified.mail)''',
'''larbin_2.6.1 (larbin2.6.1@unspecified.mail)''',
'''larbin_2.6.2 (''',
'''larbin_2.6.2 (larbin2.6.2@unspecified.mail)''',
'''larbin_2.6.2 (listonATccDOTgatechDOTedu)''',
'''larbin_2.6.2 (''',
'''larbin_2.6.2 (''',
'''larbin_2.6.2 (''',
'''larbin_2.6.3 (''',
'''larbin_2.6.3 (''',
'''larbin_2.6_basileocaml (''',
'''larbin_devel (''',
'''lawinfo-crawler/Nutch-0.9-dev (Crawler for pages;;''',
'''lc/$ROADS::Version libwww-perl/5.00''',
'''lcabotAccept: */*''',
'''LeapTag/0.8.1.beta081.r3750 (compatible; Mozilla 4.0; MSIE 5.5;''',
'''LECodeChecker/3.0 libgetdoc/1.0''',
'''LeechGet 200x (''',
'''LEIA/3.01pr (LEIAcrawler; [SNIP])''',
''' +''',
'''LG-LX260 POLARIS-LX260/2.0 MMP/2.0 Profile/MIDP-2.0 Configuration/CLDC-1.1''',
'''LibertyW (+''',
'''libWeb/clsHTTP --''',
'''libwww-perl/5.52 FP/2.1''',
'''libwww-perl/5.52 FP/4.0''',
'''Liferea/0.x.x (Linux; en_US.UTF-8;''',
'''Liferea/1.x.x (Linux; es_ES.UTF-8;''',
'''LightningDownload/1.x.x [Accelerated x]''',
'''LijitSpider/Nutch-0.9 (Reports crawler;; info(a)lijit(d)com)''',
'''Lincoln State Web Browser''',
'''Link Valet Online 1.x''',
'''Linkbot x.0''',
'''LinkCheck (''',
'''LinkPimpin v1.0''',
'''LinkProver 2.1''',
'''Links (0.9x; Linux 2.4.7-10 i686)''',
'''Links (0.9xpre12; Linux 2.2.14-5.0 i686; 80x24)''',
'''Links (2.xpre7; Linux 2.4.18 i586; x)''',
'''Links -''',
'''Links 2.0 (''',
'''Links SQL (''',
'''Links4US-Crawler, (+''',
'''LinkScan/11.0beta2 UnixShareware robot from (used by Indiafocus/Indiainfo)''',
'''LinkScan/9.0g Unix''',
'''LinkScan/x.x Unix''',
''' (''',
'''link_check3.plx libwww-perl/5.65''',
'''ListBidBot (freelance job spider<a href=>Freelance</a>''',
'''LiveTrans/Nutch-0.9 (maintainer: cobain at iis dot sinica dot edu dot tw;''',
'''Llaut/1.0 (''',
'''lmspider (''',
'''LocalBot/1.0 (''',
'''LocalcomBot/1.2.x (''',
'''Lockstep Spider/1.0''',
'''Lotus-Notes/4.5 ( Windows-NT )''',
'''LotusDiscovery/x.0 (compatible; Mozilla 4.0; MSIE 4.01; Windows NT)''',
'''Lovel as 1.0 ( +''',
'''LTI/LemurProject Nutch Spider/Nutch-1.0-dev (lti crawler for CMU;; changkuk at cmu dot edu)''',
'''LTI/LemurProject Nutch Spider/Nutch-1.0-dev (Research spider using Nutch;;''',
''' URL checker''',
'''Lynx/2-4-2 (Bobcat/0.5 [DOS] Jp Beta04)''',
'''Lynx/2.6 libwww-FM/2.14''',
'''Lynx/2.8 (;''',
'''Lynx/2.8.3dev.9 libwww-FM/2.14 SSL-MM/1.4.1 OpenSSL/0.9.6''',
'''Lynx/2.8.4rel.1 libwww-FM/2.14 SSL-MM/1.4.1 OpenSSL/0.9.6c (''',
'''Mac Finder 1.0.xx''',
'''Mackster( )''',
'''MagicWML/1.0 (forcewml)''',
'''MagpieRSS/0.7x (+''',
'''Mahiti.Com/Mahiti Crawler-1.0 (Mahiti.Com; ;''',
'''mammoth/1.0 (''',
''' (''',
'''Mariner/5.1b [de] (Win95; I ;Kolibri gncwebbot)''',
'''Marketwave Hit List''',
'''Marvin v0.3''',
'''MaSagool/1.0 (MaSagool;;''',
'''Mass Downloader 2.x''',
'''Mata Hari/2.00 ''',
'''Matrix S.p.A. - FAST Enterprise Crawler 6 (Unknown admin e-mail address)''',
'''maxomobot/dev-20051201 (maxomo;;''',
'''McBot/5.001 (windows; U; NT4.0; en-us)''',
'''MDbot/1.0 (+''',
'''Media Player Classic''',
'''MediaCrawler-1.0 (Experimental)''',
'''Mediapartners-Google/2.1 (''',
'''MegaSheep v1.0 ( internet sheep)''',
'''Megite2.0 (''',
'''Metaeuro Web Crawler/0.2 (MetaEuro Web Search Clustering Engine;; crawler at metaeuro dot com)''',
'''MetagerBot/0.8-dev (MetagerBot;; )''',
'''MetaProducts Download Express/1.x''',
'''Metaspinner/0.01 (Metaspinner;;''',
'''metatagsdir/0.7 (+''',
'''MFC Foundation Class Library 4.0''',
'''Microsoft Data Access Internet Publishing Provider Cache Manager''',
'''Microsoft Data Access Internet Publishing Provider DAV''',
'''Microsoft Data Access Internet Publishing Provider Protocol Discovery''',
'''Microsoft Data Access Internet Publishing Provider Protocol Discovery''',
'''Microsoft Log Parser 2.2''',
'''Microsoft Small Business Indexer''',
'''Microsoft URL Control - 6.00.8xxx''',
'''MicrosoftPrototypeCrawler (How's my crawling?''',
'''Microsoft_Internet_Explorer_5.00.438 (''',
'''Mindjet MindManager''',
'''miniRank/1.6 (Website ranking;; robot)''',
'''Missauga Locate 1.0.0''',
'''Missigua Locator 1.9''',
'''Missouri College Browse''',
'''Mister Pix II 2.02a''',
'''Mister PiX version.dll''',
'''Misterbot-Nutch/0.7.1 (Misterbot-Nutch;;''',
'''Miva (''',
'''Mizzu Labs 2.2''',
'''MJ12bot/vx.x.x (''',
'''MJ12bot/vx.x.x (''',
'''MJBot (SEO assessment)''',
'''MLBot (''',
'''Mo College 1.9''',
'''moget/x.x (''',
'''moiNAG 0.02''',
'''MojeekBot/0.x (archi;''',
'''MoonBrowser (version 0.41 Beta4)''',
'''Moreoverbot/x.00 (+''',
'''Morris - Mixcat Crawler (''',
'''Motoricerca-Robots.txt-Checker/1.0 (''',
'''Motorola-V3m Obigo''',
'''Mouse-House/7.4 (spider_monkey spider info at''',
'''mozDex/0.xx-dev (mozDex;;''',
'''Mozilla (libwhisker/2.4)''',
'''Mozilla (''',
'''Mozilla 4.0(compatible; BotSeer/1.0; +''',
'''Mozilla/1.1 (compatible; MSPIE 2.0; Windows CE)''',
'''Mozilla/1.10 [en] (Compatible; RISC OS 3.70; Oregano 1.10)''',
'''Mozilla/1.22 (compatible; MSIE 2.0d; Windows NT)''',
'''Mozilla/1.22 (compatible; MSIE 5.01; PalmOS 3.0) EudoraWeb 2''',
'''Mozilla/2.0 (compatible; AOL 3.0; Mac_PowerPC)''',
'''Mozilla/2.0 (Compatible; AOL-IWENG 3.0; Win16)''',
'''Mozilla/2.0 (compatible; Ask Jeeves)''',
'''Mozilla/2.0 (compatible; Ask Jeeves/Teoma)''',
'''Mozilla/2.0 (compatible; Ask Jeeves/Teoma; ''',
'''Mozilla/2.0 (compatible; Ask Jeeves/Teoma;''',
'''Mozilla/2.0 (compatible; EZResult -- Internet Search Engine)''',
'''Mozilla/2.0 (compatible; MS FrontPage x.0)''',
'''Mozilla/2.0 (compatible; MSIE 2.1; Mac_PowerPC)''',
'''Mozilla/2.0 (compatible; MSIE 3.02; Update a; AK; Windows NT)''',
'''Mozilla/2.0 (compatible; MSIE 3.02; Update a; AOL 3.0; Windows 95)''',
'''Mozilla/2.0 (compatible; MSIE 3.0; AK; Windows 95)''',
'''Mozilla/2.0 (compatible; MSIE 3.0; Windows 3.1)''',
'''Mozilla/2.0 (compatible; MSIE 3.0B; Win32)''',
'''Mozilla/2.0 (compatible; NEWT ActiveX; Win32)''',
'''Mozilla/2.0 (compatible; T-H-U-N-D-E-R-S-T-O-N-E)''',
'''Mozilla/2.0 compatible; Check&Get 1.1x (Windows 98)''',
'''Mozilla/2.01 (Win16; I)''',
'''Mozilla/2.02Gold (Win95; I)''',
'''Mozilla/3.0 (compatible)''',
'''Mozilla/3.0 (compatible; AvantGo 3.2)''',
'''Mozilla/3.0 (compatible; Fluffy the spider;;''',
'''Mozilla/3.0 (compatible; HP Web PrintSmart 04b0''',
'''Mozilla/3.0 (compatible; Indy Library)''',
'''Mozilla/3.0 (compatible; Linkman)''',
'''Mozilla/3.0 (compatible; MuscatFerret/1.5.4;''',
'''Mozilla/3.0 (compatible; MuscatFerret/1.5;''',
'''Mozilla/3.0 (compatible; MuscatFerret/1.6.x;''',
'''Mozilla/3.0 (compatible; netart generator/1.0; libwww-perl/5.64)''',
'''Mozilla/3.0 (compatible; NetPositive/2.2)''',
'''Mozilla/3.0 (compatible; Opera/3.0; Windows 3.1) v3.1''',
'''Mozilla/3.0 (compatible; Opera/3.0; Windows 95/NT4) 3.2''',
'''Mozilla/3.0 (compatible; PerMan Surfer 3.0; Win95)''',
'''Mozilla/3.0 (compatible; REL Software Web Link Validator 2.x)''',
'''Mozilla/3.0 (compatible; scan4mail (advanced version)''',
'''Mozilla/3.0 (compatible; ScollSpider;''',
'''Mozilla/3.0 (compatible; Web Link Validator 2.x)Web Link Validator link validation software''',
'''Mozilla/3.0 (compatible; WebCapture x.x; Auto; Windows)''',
'''Mozilla/3.0 (compatible;''',
'''Mozilla/3.0 (compatible;''',
'''Mozilla/3.0 (Compatible;Viking/1.8)''',
'''Mozilla/3.0 (DreamPassport/3.0)''',
'''Mozilla/3.0 (INGRID/3.0 MT;;''',
'''Mozilla/3.0 (Liberate DTV 1.1)''',
'''Mozilla/3.0 (Planetweb/2.100 JS SSL US; Dreamcast US)''',
'''Mozilla/3.0 (;;''',
'''Mozilla/3.0 (Slurp/cat;;''',
'''Mozilla/3.0 (Slurp/si;;''',
'''Mozilla/3.0 (Vagabondo/1.1 MT;;''',
'''Mozilla/3.0 (Vagabondo/1.x MT;;''',
'''Mozilla/3.0 (Vagabondo/2.0 MT;;''',
'''Mozilla/3.0 (Vagabondo/2.0 MT;;''',
'''Mozilla/3.0 (Win16; I)''',
'''Mozilla/3.0 (Win95; I)''',
'''Mozilla/3.0 (WinNT; I)''',
'''Mozilla/3.0 (WorldGate Gazelle 3.5.1 build 11; FreeBSD2.2.8-STABLE)''',
'''Mozilla/3.0 (X11; I; OSF1 V4.0 alpha)''',
'''Mozilla/3.0 NAVIO_AOLTV (11; 13; Philips; PH200; 1; R2.0C36_AOL.0110OPTIK; R2.0.0139d_OPTIK)''',
'''Mozilla/3.0 WebTV/1.2 (compatible; MSIE 2.0)''',
'''Mozilla/3.01 (compatible; AmigaVoyager/2.95; AmigaOS/MC680x0)''',
'''Mozilla/3.01 (Compatible; Links2Go Similarity Engine)''',
'''Mozilla/3.01 (compatible; Netbox/3.5 R92; Linux 2.2)''',
'''Mozilla/3.01-C-MACOS8 (Macintosh; I; PPC)''',
'''Mozilla/3.01Gold (X11; I; Linux 2.0.32 i486)''',
'''Mozilla/3.01Gold (X11; I; SunOS 5.5.1 sun4m)''',
'''Mozilla/3.01SGoldC-SGI (X11; I; IRIX 6.3 IP32)''',
'''Mozilla/3.04 (compatible; ANTFresco/2.13; RISC OS 4.02)''',
'''Mozilla/3.04 (compatible; NCBrowser/2.35; ANTFresco/2.17; RISC OS-NC 5.13 Laz1UK1309)''',
'''Mozilla/3.04 (compatible;QNX Voyager 2.03B ;Photon)''',
'''Mozilla/3.x (I-Opener 1.1; Netpliance)''',
'''Mozilla/4.0 (agadine3.0)''',
'''Mozilla/4.0 (Compatible); URLBase 6''',
'''Mozilla/4.0 (compatible: AstraSpider V.2.1 :''',
'''Mozilla/4.0 (compatible; Vagabondo/2.2; webcrawler at wise-guys dot nl;''',
'''Mozilla/4.0 (compatible; Vagabondo/4.0Beta; webcrawler at wise-guys dot nl;''',
'''Mozilla/4.0 (compatible; <a href=>ReGet Deluxe 5.1</a>; Windows NT 5.1)''',
'''Mozilla/4.0 (compatible; Advanced Email Extractor v2.xx)''',
'''Mozilla/4.0 (compatible; Arachmo)''',
'''Mozilla/4.0 (compatible; BorderManager 3.0)''',
'''Mozilla/4.0 (compatible; BOTW Spider; +''',
'''Mozilla/4.0 (compatible; B_L_I_T_Z_B_O_T)''',
'''Mozilla/4.0 (compatible; Cerberian Drtrs Version-3.2-Build-0)''',
'''Mozilla/4.0 (compatible; Check&Get 3.0; Windows NT)''',
'''Mozilla/4.0 (compatible;''',
'''Mozilla/4.0 (compatible; crawlx,''',
'''Mozilla/4.0 (compatible; DAUMOA-video; +''',
'''Mozilla/4.0 (compatible; DepSpid/5.0x; +''',
'''Mozilla/4.0 (compatible; DnloadMage 1.0)''',
'''Mozilla/4.0 (compatible; FastCrawler3''',
'''Mozilla/4.0 (compatible; FDSE robot)''',
'''Mozilla/4.0 (compatible; GPU p2p crawler''',
'''Mozilla/4.0 (compatible; grub-client-0.2.x; Crawl your stuff with''',
'''Mozilla/4.0 (compatible; grub-client-0.3.x; Crawl your own stuff with''',
'''Mozilla/4.0 (compatible; grub-client-2.x)''',
'''Mozilla/4.0 (compatible; ibisBrowser)''',
'''Mozilla/4.0 (compatible; ICS''',
'''Mozilla/4.0 (compatible; IE-Favorites-Check-0.5)''',
'''Mozilla/4.0 (compatible; Iplexx Spider/1.0''',
'''Mozilla/4.0 (compatible; KeepNI web site monitor)''',
'''Mozilla/4.0 (compatible; Link Utility;''',
'''Mozilla/4.0 (compatible; Lotus-Notes/5.0; Windows-NT)''',
'''Mozilla/4.0 (compatible; MSIE 4.01; AOL 4.0; Windows 98)''',
'''Mozilla/4.0 (compatible; MSIE 4.01; Mac_PowerPC)''',
'''Mozilla/4.0 (compatible; MSIE 4.01; MSIECrawler; Windows 95)''',
'''Mozilla/4.0 (compatible; MSIE 4.01; b o t)''',
'''Mozilla/4.0 (compatible; MSIE 4.01; Windows 95)''',
'''Mozilla/4.0 (compatible; MSIE 4.01; Windows CE; MSN Companion 2.0; 800x600; Compaq)''',
'''Mozilla/4.0 (compatible; MSIE 4.01; Windows CE; PPC; 240x320; SPV M700; OpVer OrangeBot-Mobile 2008.0 (''',
'''Mozilla/4.0 (compatible; MSIE 4.01; Windows CE; PPS; 240x320)''',
'''Mozilla/4.0 (compatible; MSIE 4.01; Windows NT Windows CE)''',
'''Mozilla/4.0 (compatible; MSIE 4.01; Windows NT)''',
'''Mozilla/4.0 (compatible; MSIE 4.01; Windows NT; MS Search 4.0 Robot) Microsoft''',
'''Mozilla/4.0 (compatible; MSIE 4.0; Windows NT; Site Server 3.0 Robot) ACR''',
'''Mozilla/4.0 (compatible; MSIE 4.0; Windows NT; Site Server 3.0 Robot) Indonesia Interactive''',
'''Mozilla/4.0 (compatible; MSIE 4.0; Windows NT; Site Server 3.0 Robot) WebQuest Designs''',
'''Mozilla/4.0 (compatible; MSIE 5.01; Windows 95) via <B>Avirt Gateway Server</B> v4.0''',
'''Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0) (''',
'''Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0; NetCaptor 6.5.0RC1)''',
'''Mozilla/4.0 (compatible; MSIE 5.0; AOL 5.0; Windows 95; DigExt; Gateway2000;''',
'''Mozilla/4.0 (compatible; MSIE 5.0; Mac_PowerPC; AtHome021)''',
'''Mozilla/4.0 (compatible; MSIE 5.0; NetNose-Crawler 2.0; A New Search Experience:''',
'''Mozilla/4.0 (compatible; MSIE 5.0; Win32) via proxy gateway CERN-HTTPD/3.0 libwww/2.17''',
'''Mozilla/4.0 (compatible; MSIE 5.0; Windows 95) TrueRobot; 1.5''',
'''Mozilla/4.0 (compatible; MSIE 5.0; Windows 95) VoilaBot BETA 1.2 (''',
'''Mozilla/4.0 (compatible; MSIE 5.0; Windows 95) VoilaBot; 1.6''',
'''Mozilla/4.0 (compatible; MSIE 5.0; Windows ME) Opera 5.11 [en]''',
'''Mozilla/4.0 (compatible; MSIE 5.0; Windows ME; Link Checker 2.x.xx''',
'''Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; DigExt; DTS Agent''',
'''Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; Girafabot; girafabot at girafa dot com;''',
'''Mozilla/4.0 (compatible; MSIE 5.0;;''',
'''Mozilla/4.0 (compatible; MSIE 5.0;;;''',
'''Mozilla/4.0 (compatible; MSIE 5.0; YANDEX)''',
'''Mozilla/4.0 (compatible; MSIE 5.5; AOL 4.0; Windows 98; GoBeez (''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows 95; Transmission Segment; Hotbar 2.0)''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; Crazy Browser 1.x.x)''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; KITV4.7 Wanadoo)''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; SAFEXPLORER TL)''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; SYMPA; Katiesoft 7; SimulBrowse 3.0)''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; Win 9x 4.90; BTinternet V8.1)''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; Win 9x 4.90; MSIECrawler)''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 4.0; obot)''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 4.0; QXW03018)''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0) Active Cache Request''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0) Fetch API Request''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0; .NET CLR 1.0.3705)''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0; AIRF)''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0; AspTear 1.5)''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0; N_o_k_i_a)''',
'''Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0; T312461) RPT-HTTPClient/0.3-3E''',
'''Mozilla/4.0 (compatible; MSIE 6.0 compatible; Asterias Crawler v4; +;; SpiderThread Revision: 3.10''',
'''Mozilla/4.0 (compatible; MSIE 6.0; AOL 9.0; Windows 98; .NET CLR 1.1.4322; MEGAUPLOAD 2.0)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; AOL 9.0; Windows NT 5.1; SV1; HbTools 4.7.2)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; MSIE 5.5; Windows NT 5.1) Skampy/0.9.x [en]''',
'''Mozilla/4.0 (compatible; MSIE 6.0; TargetSeek/1.0; +''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Win32) WebWasher 3.0''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows 98) REL Software Web Link Validator 2.x)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows 98) Web Link Validator 2.x)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows 98; Net M@nager V3.02 -''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows 98;;''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows 98; Win 9x 4.90;''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; .NET CLR 1.1.4322; Lunascape 2.1.3)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; Google Wireless Transcoder;)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; ODP entries t_st;''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; ODP links test;''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; bot; .NET CLR 1.1.4322)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1) (''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Covac UPPS Cathan 1.2.5;)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Crayon Crawler; snprtz|T04056566514940; (R1 1.5))''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Deepnet Explorer)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; heritrix/1.3.0''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Hotbar 3.0)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; iOpus-I-M)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; iRider 2.21.1108; FDM)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; KKman3.0)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; MathPlayer2.0)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Maxthon) ''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; PeoplePal 3.0; MSIECrawler)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Q312461; IOpener Release 1.1.04)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; QihooBot 1.0''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SIMBAR Enabled; InfoPath.1)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; 1.760; .NET CLR 1.1.4322)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; Embedded Web Browser from:; MSIECrawler)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; )''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; DX-Browser''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; FunWebProducts; ezPeer+ v1.0 Beta (; ezPeer+ v1.0 (; .NET CLR 1.1.4322; MSIECrawler)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; IBP; .NET CLR 1.1.4322)''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; MRA 4.3 (build 01218))''',
'''Mozilla/4.0 (compatible; MSIE 6.0; Windows NT; MS Search 4.0 Robot)''',
'''Mozilla/4.0 (compatible; MSIE 7.0; Win32) Link Commander 4.0''',
'''Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; bgft)''',
'''Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; GTB5; User-agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; ; .NET CLR 2.0.50727)''',
'''Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; Tablet PC 2.0)''',
'''Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 1.1.4322; .NET CLR 3.0.04506.30; .NET CLR 3.0.04506.648)''',
'''Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0)''',
'''Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; Orange 8.0; GTB6.3; Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ; Embedded Web Browser from:; SLCC1; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30618; OfficeLiveConnector.1.3; OfficeLivePatch.1.3)''',
'''Mozilla/4.0 (compatible; MSIE enviable; DAUMOA 2.0; DAUM Web Robot; Daum Communications Corp., Korea; +''',
'''Mozilla/4.0 (compatible; MSIE is not me; DAUMOA/1.0.1; DAUM Web Robot; Daum Communications Corp., Korea)''',
'''Mozilla/4.0 (compatible; NaverBot/1.0;''',
'''Mozilla/4.0 (compatible; Netcraft Web Server Survey)''',
'''Mozilla/4.0 (compatible; NetPromoter Spider;''',
'''Mozilla/4.0 (compatible; Opera/3.0; Windows 4.10) 3.51 [en]''',
'''Mozilla/4.0 (compatible; Powermarks/3.5; Windows 95/98/2000/NT)''',
'''Mozilla/4.0 (compatible; RSS Popper)''',
'''Mozilla/4.0 (compatible; SiteKiosk 4.0; MSIE 5.0; Windows 98; SiteCoach 1.0)''',
'''Mozilla/4.0 (compatible; SpeedySpider;''',
'''Mozilla/4.0 (compatible; SPENG)''',
'''Mozilla/4.0 (compatible; SuperCleaner 2.xx; Windows 98)''',
'''Mozilla/4.0 (compatible; Synapse)''',
'''Mozilla/4.0 (compatible; WebCapture 3.0; Windows)''',
'''Mozilla/4.0 (compatible; Win32; WinHttp.WinHttpRequest.5)''',
'''Mozilla/4.0 (compatible; WSN Links)''',
'''Mozilla/4.0 (compatible;; urlchecker1.0)''',
'''Mozilla/4.0 (compatible;''',
'''Mozilla/4.0 (compatible; Linkguard Online 1.0; Windows NT)''',
'''Mozilla/4.0 (compatible; Y!J; for robot study; keyoshid)''',
'''Mozilla/4.0 (compatible; Yahoo Japan; for robot study; kasugiya)''',
'''Mozilla/4.0 (compatible;MSIE 6.0; Windows NT 5.0; H010818)''',
'''Mozilla/4.0 (fantomBrowser)''',
'''Mozilla/4.0 (fantomCrew Browser)''',
'''Mozilla/4.0 (''',
'''Mozilla/4.0 (JemmaTheTourist;''',
'''Mozilla/4.0 (MobilePhone PM-8200/US/1.0) NetFront/3.x MMP/2.0''',
'''Mozilla/4.0 (MobilePhone SCP-5500/US/1.0) NetFront/3.0 MMP/2.0 (compatible; Googlebot/2.1;''',
'''Mozilla/4.0 (MobilePhone SCP-5500/US/1.0) NetFront/3.0 MMP/2.0 FAKE (compatible; Googlebot/2.1;''',
'''Mozilla/4.0 (Mozilla;;''',
'''Mozilla/4.0 (Sleek Spider/1.2)''',
'''Mozilla/4.0 compatible FurlBot/Furl Search 2.0 (FurlBot;;''',
'''Mozilla/4.0 compatible ZyBorg/1.0 (;''',
'''Mozilla/4.0 compatible ZyBorg/1.0 (;''',
'''Mozilla/4.0 compatible ZyBorg/1.0 Dead Link Checker (;''',
'''Mozilla/4.0 compatible ZyBorg/1.0 for Homepage (;''',
'''Mozilla/4.0 WebTV/2.6 (compatible; MSIE 4.0)''',
'''Mozilla/4.0 [en] (Ask Jeeves Corporate Spider)''',
'''Mozilla/4.0(compatible; Zealbot 1.0)''',
'''Mozilla/4.01 (compatible; NORAD National Defence Network)''',
'''Mozilla/4.01 [en](Win95;I)''',
'''Mozilla/4.02 [en] (X11; I; SunOS 5.6 sun4u)''',
'''Mozilla/4.04 (compatible; Dulance bot; +''',
'''Mozilla/4.04 [en] (X11; I; HP-UX B.10.20 9000/712)''',
'''Mozilla/4.04 [en] (X11; I; IRIX 5.3 IP22)''',
'''Mozilla/4.05 (Macintosh; I; 68K Nav)''',
'''Mozilla/4.05 (Macintosh; I; PPC Nav)''',
'''Mozilla/4.05 [en] (X11; I; SunOS 4.1.4 sun4m)''',
'''Mozilla/4.08 [en] (Win98; U ;Nav)''',
'''Mozilla/4.08 [en] (WinNT; U)''',
'''Mozilla/4.0_(compatible;_MSIE_5.0;_Windows_95)_TrueRobot/1.4 libwww/5.2.8''',
'''Mozilla/4.0_(compatible;_MSIE_5.0;_Windows_95)_VoilaBot/1.6 libwww/5.3.2''',
'''Mozilla/4.5 (compatible; HTTrack 3.0x; Windows 98)''',
'''Mozilla/4.5 (compatible; iCab 2.5.3; Macintosh; I; PPC)''',
'''Mozilla/4.5 (compatible; OmniWeb/4.0.5; Mac_PowerPC)''',
'''Mozilla/4.5 (compatible; OmniWeb/4.1-beta-1; Mac_PowerPC)''',
'''Mozilla/4.5 RPT-HTTPClient/0.3-2''',
'''Mozilla/4.5 [en]C-CCK-MCD {RuralNet} (Win98; I)''',
'''Mozilla/4.5b1 [en] (X11; I; Linux 2.0.35 i586)''',
'''Mozilla/4.6 [en] (''',
'''Mozilla/4.61 [de] (OS/2; I)''',
'''Mozilla/4.61 [en] (X11; U; ) - BrowseX (2.0.0 Windows)''',
'''Mozilla/4.7 (compatible;''',
'''Mozilla/4.7 (compatible; Intelliseek;''',
'''Mozilla/4.7 (compatible; OffByOne; Windows 98) Webster Pro V3.2''',
'''Mozilla/4.7 (compatible; Whizbang)''',
'''Mozilla/4.7 (compatible; WhizBang;''',
'''Mozilla/4.7 [en](''',
'''Mozilla/4.7 [en](''',
'''Mozilla/4.7 [en]C-CCK-MCD {Yahoo;YIP052400} (Win95; I)''',
'''Mozilla/4.72 [en] (BACS''',
'''Mozilla/4.72C-CCK-MCD Caldera Systems OpenLinux [en] (X11; U; Linux 2.2.14 i686)''',
'''Mozilla/4.75C-ja [ja] (X11; U; OSF1 V5.1 alpha)''',
'''Mozilla/4.76 (Windows 98; U) Opera 5.12 [en]''',
'''Mozilla/4.76 [en] (X11; U; FreeBSD 4.4-STABLE i386)''',
'''Mozilla/4.76 [en] (X11; U; SunOS 5.7 sun4u)''',
'''Mozilla/4.77C-SGI [en] (X11; U; IRIX 6.5 IP32)''',
'''Mozilla/5.0 (+ Mammoth/0.1''',
'''Mozilla/5.0 (+ Mammoth/0.1''',
'''Mozilla/5.0 (Clustered-Search-Bot/1.0;;''',
'''Mozilla/5.0 (compatible) GM RSS Panel X''',
'''Mozilla/5.0 (compatible; +''',
'''Mozilla/5.0 (compatible; 008/0.83;;) Gecko/2008032620''',
'''Mozilla/5.0 (compatible; Abonti/0.8 -''',
'''Mozilla/5.0 (compatible; aiHitBot/1.0; +''',
'''Mozilla/5.0 (compatible; AnsearchBot/1.x; +''',
'''Mozilla/5.0 (compatible; archive.org_bot/1.10.0 +''',
'''Mozilla/5.0 (compatible; archive.org_bot/1.13.1x''',
'''Mozilla/5.0 (compatible; archive.org_bot/1.5.0-200506132127 Hurricane Katrina''',
'''Mozilla/5.0 (compatible; Ask Jeeves/Teoma;''',
'''Mozilla/5.0 (compatible; BanBots/2.0b; Fetch; +''',
'''Mozilla/5.0 (compatible; BecomeBot/1.23;''',
'''Mozilla/5.0 (compatible; BecomeBot/1.xx; MSIE 6.0 compatible;''',
'''Mozilla/5.0 (compatible; BecomeBot/2.0beta;''',
'''Mozilla/5.0 (compatible; BecomeBot/2.x; MSIE 6.0 compatible;''',
'''Mozilla/5.0 (compatible; BecomeJPBot/2.3; MSIE 6.0 compatible; +''',
'''Mozilla/5.0 (compatible; BlogRefsBot/0.1;''',
'''Mozilla/5.0 (compatible; Bot; +''',
'''Mozilla/5.0 (compatible; BuzzRankingBot/1.0; +''',
'''Mozilla/5.0 (compatible; Charlotte/1.0b;''',
'''Mozilla/5.0 (compatible; Charlotte/1.0b;''',
'''Mozilla/5.0 (compatible; Crawling jpeg;''',
'''Mozilla/5.0 (compatible; Custo 3 (; Windows NT 5.1)''',
'''Mozilla/5.0 (compatible; de/1.13.2 +''',
'''Mozilla/5.0 (compatible; Diffbot/0.1; +''',
'''Mozilla/5.0 (compatible; DNS-Digger-Explorer/1.0; +''',
'''Mozilla/5.0 (compatible; DNS-Digger/1.0; +''',
'''Mozilla/5.0 (compatible;;''',
'''Mozilla/5.0 (compatible; EARTHCOM/2.2; +''',
'''Mozilla/5.0 (compatible; egothor/8.0g; +''',
'''Mozilla/5.0 (compatible; Exabot Test/3.0; +''',
'''Mozilla/5.0 (compatible; FatBot 2.0;''',
'''Mozilla/5.0 (compatible; Galbot/1.0; +''',
'''mozilla/5.0 (compatible; genevabot''',
'''Mozilla/5.0 (compatible; Google Desktop) Paros/3.2.12''',
'''Mozilla/5.0 (compatible; Googlebot/2.1;''',
'''mozilla/5.0 (compatible; heritrix/1.0.4''',
'''Mozilla/5.0 (compatible; heritrix/1.10.2 +''',
'''Mozilla/5.0 (compatible; heritrix/1.12.1 +''',
'''Mozilla/5.0 (compatible; heritrix/1.12.1 +''',
'''Mozilla/5.0 (compatible; heritrix/1.12.1 + []''',
'''mozilla/5.0 (compatible; heritrix/1.3.0''',
'''Mozilla/5.0 (compatible; heritrix/1.4.0 +''',
'''Mozilla/5.0 (compatible; heritrix/1.4t''',
'''Mozilla/5.0 (compatible; heritrix/1.5.0''',
'''Mozilla/5.0 (compatible; heritrix/1.5.0-200506231921''',
'''Mozilla/5.0 (compatible; heritrix/1.6.0''',
'''Mozilla/5.0 (compatible; heritrix/1.7.0 +''',
'''Mozilla/5.0 (compatible; Heritrix/1.8.0''',
'''Mozilla/5.0 (compatible; heritrix/1.x.x +''',
'''Mozilla/5.0 (compatible; heritrix/2.0.0-RC1 +''',
'''Mozilla/5.0 (compatible; Hermit Search. Com; +''',
'''Mozilla/5.0 (compatible; http://www.IsMySiteUp.Net/bot/ )''',
'''Mozilla/5.0 (compatible; )''',
'''Mozilla/5.0 (compatible; HyperixScoop/1.3; +''',
'''Mozilla/5.0 (compatible; iaskspider/1.0; MSIE 6.0)''',
'''Mozilla/5.0 (compatible; IDBot/1.0; +''',
'''Mozilla/5.0 (compatible; InterseekWeb/3.x)''',
'''Mozilla/5.0 (compatible; Jim +''',
'''Mozilla/5.0 (compatible; Konqueror/2.0.1; X11); Supports MD5-Digest; Supports gzip encoding''',
'''Mozilla/5.0 (compatible; Konqueror/2.1.1; X11)''',
'''Mozilla/5.0 (compatible; Konqueror/2.2.2)''',
'''Mozilla/5.0 (compatible; Konqueror/2.2.2; Linux 2.4.14-xfs; X11; i686)''',
'''Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Exabot-Thumbnails)''',
'''Mozilla/5.0 (compatible; LemSpider 0.1)''',
'''Mozilla/5.0 (compatible; LinksManager.com_bot''',
'''Mozilla/5.0 (compatible; LinkStash Bookmark Manager;''',
'''Mozilla/5.0 (compatible; MojeekBot/2.0;''',
'''Mozilla/5.0 (compatible; MOSBookmarks/v2.6-Plus; Link Checker)''',
'''Mozilla/5.0 (compatible; MSIE 6.0; Podtech Network;''',
'''Mozilla/5.0 (compatible; OnetSzukaj/5.0;''',
'''Mozilla/5.0 (compatible; PagestackerBot;''',
'''Mozilla/5.0 (compatible; PalmeraBot; Version 0.001''',
'''Mozilla/5.0 (compatible; PEAR HTTP_Request class;''',
'''Mozilla/5.0 (compatible; Phonifier; +''',
'''Mozilla/5.0 (compatible; ODP link checker; +''',
'''Mozilla/5.0 (compatible;''',
'''Mozilla/5.0 (compatible;''',
'''Mozilla/5.0 (compatible; Proximic crawler; +''',
'''Mozilla/5.0 (compatible; PWeBot/3.1;''',
'''Mozilla/5.0 (compatible; Quantcastbot/1.0;''',
'''Mozilla/5.0 (compatible; robtexbot/1.0; )''',
'''Mozilla/5.0 (compatible; ScoutJet; +''',
'''Mozilla/5.0 (compatible; Scrubby/2.2;''',
'''Mozilla/5.0 (compatible; ShunixBot/1.x.x +''',
'''Mozilla/5.0 (compatible; ShunixBot/1.x;''',
'''Mozilla/5.0 (compatible; SkreemRBot +''',
'''Mozilla/5.0 (compatible; SnapPreviewBot; en-US; rv: Gecko/20061206 Firefox/''',
'''Mozilla/5.0 (compatible; SpurlBot/0.2) ''',
'''Mozilla/5.0 (compatible; SummizeBot +''',
'''Mozilla/5.0 (compatible; SYCLIKControl/LinkChecker;)''',
'''Mozilla/5.0 (compatible; Synoobot/0.9;''',
'''Mozilla/5.0 (compatible; Theophrastus/x.x;''',
'''Mozilla/5.0 (compatible; TridentSpider/3.1)''',
'''Mozilla/5.0 (compatible; Vagabondo/2.1; webcrawler at wise-guys dot nl;''',
'''Mozilla/5.0 (compatible; Webduniabot/1.0; +''',
'''Mozilla/5.0 (compatible; Windows NT 5.0; phpwebbrainBot/0.1 -''',
'''Mozilla/5.0 (compatible; worio bot heritrix/1.10.0 +''',
'''Mozilla/5.0 (compatible; WoW Lemmings Kathune/2.0;''',
'''Mozilla/5.0 (compatible; XTbot/1.0v; +''',
'''Mozilla/5.0 (compatible; Yahoo! DE Slurp;''',
'''Mozilla/5.0 (compatible; Yahoo! Slurp China;''',
'''Mozilla/5.0 (compatible; Yahoo! Slurp;''',
'''Mozilla/5.0 (compatible; YesupBot/1.0; +''',
'''Mozilla/5.0 (compatible; Yoono;''',
'''Mozilla/5.0 (compatible; YoudaoBot/1.0;; )''',
'''Mozilla/5.0 (compatible; Zenbot/1.3; +''',
'''Mozilla/5.0 (compatible; zermelo + [,]''',
'''Mozilla/5.0 (compatible;archive.org_bot/1.7.1; collectionId=316; Archive-It; +''',
'''Mozilla/5.0 (compatible;archive.org_bot/heritrix-1.9.0-200608171144 +''',
'''Mozilla/5.0 (compatible;FindITAnswersbot/1.0;+''',
'''Mozilla/5.0 (compatible;MAINSEEK_BOT)''',
'''Mozilla/5.0 (Gecko/20070310 Mozshot/0.0.20070628;''',
'''Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.4; en-US; rv:1.9b5) Gecko/2008032619 Firefox/3.0b5''',
'''Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.0.1) Gecko/20021219 Chimera/0.6 ''',
'''Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.0.1) Gecko/20030306 Camino/0.7''',
'''Mozilla/5.0 (Macintosh; U; PPC Mac OS X; en-US) AppleWebKit/xx (KHTML like Gecko) OmniWeb/v5xx.xx''',
'''Mozilla/5.0 (Macintosh; U; PPC Mac OS X; en-us) AppleWebKit/xxx.x (KHTML like Gecko) Safari/12x.x''',
'''Mozilla/5.0 (Macintosh; U; PPC; en-US; rv:0.9.2) Gecko/20010726 Netscape6/6.1''',
'''Mozilla/5.0 (''',
'''Mozilla/5.0 (Sage)''',
'''Mozilla/5.0 (Slurp/cat;;''',
'''Mozilla/5.0 (Slurp/si;;''',
'''Mozilla/5.0 (SunOS 5.8 sun4u; U) Opera 5.0 [en]''',
'''Mozilla/5.0 (Twiceler-0.9''',
'''Mozilla/5.0 (Version: xxxx Type:xx)''',
'''Mozilla/5.0 (''',
'''Mozilla/5.0 (Windows; U; Win98; en-US; rv:0.9.2) Gecko/20010726 Netscape6/6.1''',
'''Mozilla/5.0 (Windows; U; Win98; en-US; rv:x.xx) Gecko/20030423 Firebird Browser/0.6''',
'''Mozilla/5.0 (Windows; U; Win9x; en; Stable) Gecko/20020911 Beonex/0.8.1-stable''',
'''Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.7.7) NimbleCrawler 1.11 obeys UserAgent NimbleCrawler For problems contact:''',
'''Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/ Safari/525.19''',
'''Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv: Gecko/20060731 Firefox/ Flock/''',
'''Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv: Gecko/20071127 Firefox/ x.0''',
'''Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv: Gecko/2008092215 Firefox/3.0.1 Orca/1.1 beta 3''',
'''Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:x.x.x) Gecko/20041107 Firefox/x.x''',
'''Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:x.xx) Gecko/20030504 Mozilla Firebird/0.6''',
'''Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; Gecko/20041027 Mnenhy/''',
'''Mozilla/5.0 (Windows; U; Windows NT 5.1; fr; rv:1.8.1) VoilaBot BETA 1.2 (''',
'''Mozilla/5.0 (Windows; U; Windows NT 5.1; fr; rv:1.8.1) VoilaBot BETA 1.2 (''',
'''Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9b5) Gecko/2008032620 Firefox/3.0b5''',
'''Mozilla/5.0 (Windows; U;XMPP Tiscali Communicator v.10.0.1; Windows NT 5.1; it; rv: Gecko/20070309 Firefox/''',
'''Mozilla/5.0 (Windows;) NimbleCrawler 1.12 obeys UserAgent NimbleCrawler For problems contact: crawler@health''',
'''Mozilla/5.0 (Windows;) NimbleCrawler 1.12 obeys UserAgent NimbleCrawler For problems contact:''',
'''Mozilla/5.0 (X11; Linux i686; U;rv: 1.7.13) Gecko/20070322 Kazehakase/''',
'''Mozilla/5.0 (X11; U; Linux 2.4.2-2 i586; en-US; m18) Gecko/20010131 Netscape6/6.01''',
'''Mozilla/5.0 (X11; U; Linux i686; de-AT; rv: Gecko/20060309 SeaMonkey/1.0''',
'''Mozilla/5.0 (X11; U; Linux i686; en-GB; rv:1.7.6) Gecko/20050405 Epiphany/1.6.1 (Ubuntu) (Ubuntu package 1.0.2)''',
'''Mozilla/5.0 (X11; U; Linux i686; en-US; Nautilus/1.0Final) Gecko/20020408''',
'''Mozilla/5.0 (X11; U; Linux i686; en-US; rv:0.9.3) Gecko/20010801''',
'''Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2.1; aggregator:Spinn3r (Spinn3r 3.1); Gecko/20021130''',
'''Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2b) Gecko/20021007 Phoenix/0.3''',
'''Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.6) Gecko/20040413 Epiphany/1.2.1''',
'''Mozilla/5.0 (X11; U; Linux i686; en-US; rv: Gecko/20060909 Firefox/ SnapPreviewBot''',
'''Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.1) Gecko/20061129 BonEcho/2.0''',
'''Mozilla/5.0 (X11; U; Linux i686; en-US; rv: Gecko/20061205 Iceweasel/ (Debian-''',
'''Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9a8) Gecko/2007100619 GranParadiso/3.0a8''',
'''Mozilla/5.0 Galeon/1.0.2 (X11; Linux i686; U;) Gecko/20011224''',
'''Mozilla/5.0 gURLChecker/0.x.x (Linux)''',
'''Mozilla/5.0 URL-Spider''',
'''Mozilla/5.0 whoiam []''',
'''Mozilla/5.0 [en] (compatible; Gulper Web Bot 0.2.4''',
'''MQBOT/Nutch-0.9-dev (MQBOT Nutch Crawler;;''',
'''MSIE 4.0 (Win95)''',
'''MSIE-5.13 (larbin@unspecified.mail)''',
'''msnbot-media/1.0 (+''',
'''msnbot-media/1.1 (+''',
'''msnbot-Products/1.0 (+''',
'''MSNBOT/0.xx (''',
'''msnbot/x.xx (''',
'''MSNBOT_Mobile MSMOBOT Mozilla/2.0 (compatible; MSIE 4.02; Windows CE; Default)''',
'''MSRBOT (''',
'''Mulder, VCR-1.0''',
'''multiBlocker browser''',
'''multicrawler (''',
'''MusicWalker2.0 (''',
'''My WinHTTP Connection''',
''' Crawler 2.0''',
'''Naamah 1.0.1/Blogbot (''',
'''Naamah 1.0a/Blogbot (''',
'''NameOfAgent (CMS Spider)''',
'''NASA Search 1.0''',
'''NaverBot-1.0 (NHN Corp. / +82-2-3011-1954 /''',
'''NavissoBot/1.7 (+''',
'''NCSA Beta 1 (''',
'''Nebullabot/2.2 (''',
'''NEC Research Agent -- compuman at''',
'''Net-Seekr Bot/Net-Seekr Bot V1 (''',
'''NetinfoBot/1.0 (''',
'''Netluchs/0.8-dev ( ;; ___don'''',
'''NetMechanic Vx.0''',
'''NetNewsWire/2.x (Mac OS X;''',
'''Netprospector JavaCrawler''',
'''NetSeer/Nutch-0.9 (NetSeer Crawler;;''',
'''NetSprint -- 2.0''',
'''NetWhatCrawler/0.06-dev (NetWhatCrawler from;;''',
'''newsearchengine (ThisUser@unspecified.mail)''',
'''NewsGator FetchLinks extension/0.2.0 (''',
'''NewsGatorOnline/2.0 (; 1 subscribers)''',
'''NextGenSearchBot 1 (for information visit''',
'''NextopiaBOT (+ distributed crawler client beta v0.x''',
'''NG-Search/0.90 (NG-SearchBot;; )''',
'''Nikita the Spider (''',
'''NITLE Blog Spider/0.01''',
'''Nitro Downloader 1.x (''',
'''Noago Spider''',
'''Nokia-WAPToolkit/1.2 googlebot(at)''',
'''Nokia6300/2.0 (05.50) Profile/MIDP-2.0 Configuration/CLDC-1.1 (botmobi''',
'''Nokia6610/1.0 (3.09) Profile/MIDP-1.0 Configuration/CLDC-1.0 (compatible;YahooSeeker/M1A1-R2D2;''',
'''Nokia7110/1.0 (05.01) (Google WAP Proxy/1.0)''',
'''NokodoBot/1.x (+''',
'''Norbert the Spider(''',
'''noxtrumbot/1.0 (''',
'''NP/0.1 (NP;;''',
'''NPBot (''',
'''NSPlayer/10.0.0.xxxx WMFSDK/10.0''',
''' (;''',
''' (;''',
'''nttdirectory_robot/0.9 (''',
'''Nucleus SiteList LinkChecker/1.1''',
'''nuSearch Spider <a href=''></a> (compatible; MSIE 4.01)''',
'''NuSearch Spider (compatible; MSIE 6.0)''',
'''NuSearch Spider''',
'''Nutch crawler/Nutch-0.9 (;''',
'''Nutch/Nutch-0.9 (Eurobot; )''',
'''NutchCVS/0.06-dev (Nutch;;''',
'''NutchCVS/0.0x-dev (Nutch;;''',
'''NutchCVS/0.7.1 (Nutch running at UW;;''',
'''NutchEC2Test/Nutch-0.9-dev (Testing Nutch on Amazon EC2.;; ec2test at''',
'''NutchOrg/0.0x-dev (Nutch;;''',
'''nutchsearch/Nutch-0.9 (Nutch Search 1.0; herceg_novi at yahoo dot com)''',
'''NutchVinegarCrawl/Nutch-0.8.1 (Vinegar;; eytanadar at gmail dot com)''',
'''obidos-bot (just looking for books.)''',
'''ObjectsSearch/0.01-dev (ObjectsSearch;;''',
'''ObjectsSearch/0.0x (ObjectsSearch;;''',
'''oBot ((compatible;Win32))''',
'''Ocelli/1.x (''',
'''Octora Beta -''',
'''Octora Beta Bot -''',
'''Offline Explorer 1.*''',
'''OmniExplorer_Bot/1.0x (+ Internet CategorizerOmniExplorer car & shopping search (''',
'''OmniExplorer_Bot/1.0x (+ Job Crawler''',
'''OmniExplorer_Bot/1.1x (+ Torrent Crawler''',
'''OmniExplorer_Bot/x.xx (+ WorldIndexer''',
'''onCHECK Linkchecker von fuer''',
''' SA-''',
'''online link validator (''',
'''Online24-Bot (Version: 1.0x, powered by''',
'''OntoSpider/1.0 libwww-perl/5.65''',
'''OOZBOT/0.20 ( ; agentname at setooz dot_com )''',
'''OpenAcoon v4.0.x (''',
'''Openfind data gatherer- Openbot/3.0+(;+''',
'''Openfind Robot/1.1A2''',
'''OpenISearch/1.x (''',
'''OpenTaggerBot (''',
'''OpenWebSpider/0.x.x (''',
'''Opera/5.0 (Linux 2.0.38 i386; U) [en]''',
'''Opera/5.11 (Windows ME; U) [ru]''',
'''Opera/5.12 (Windows 98; U) [en]''',
'''Opera/6.01 (larbin@unspecified.mail)''',
'''Opera/6.x (Linux 2.4.8-26mdk i686; U) [en]''',
'''Opera/6.x (Windows NT 4.0; U) [de]''',
'''Opera/7.x (Windows NT 5.1; U) [en]''',
'''Opera/8.xx (Windows NT 5.1; U; en)''',
'''Opera/9.0 (Windows NT 5.1; U; en)''',
'''Opera/9.00 (Windows NT 5.1; U; de)''',
'''Opera/9.60 (Windows NT 5.1; U; de) Presto/2.1.1''',
'''OpidooBOT (larbin2.6.3@unspecified.mail)''',
'''OPWV-SDK UP.Browser/ (GUI) MMP/2.0 Push/PO''',
'''Oracle Application Server Web Cache 10g''',
'''Oracle iMTCrawler''',
'''Oracle Ultra Search''',
'''Orbiter/T-2.0 (+''',
'''Orca Browser (''',
'''OSSProxy 1.3.305.321 (Build 305.321 Win32 en-us)(Dec 21 2005 16:30:54)''',
'''OutfoxBot/0.x (For internet experiments; http://;''',
'''OutfoxMelonBot/0.5 (for internet experiments; http://;''',
'''Overture-WebCrawler/3.8/Fresh (atw-crawler at fast dot no;''',
'''OWR_Crawler 0.1''',
'''ozelot/2.7.3 (Search engine indexer;;''',
'''PADLibrary Spider''',
'''PageBitesHyperBot/600 (''',
'''Pagestacker Bot''',
'''page_verifier (''',
'''ParaSite/1.0b (''',
'''Patwebbot (''',
'''pavuk/0.9pl29b i686-pc-linux-gnu''',
'''PBrowse 1.4b''',
'''PEAR HTTP_Request class ( )''',
'''PEval 1.4b''',
'''PigeonBot1.0 BETA''',
'''PingALink Monitoring Services 1.0''',
'''PingALink Monitoring Services 1.0 (''',
'''Pingdom GIGRIB (''',
'''pipeLiner/0.3a (PipeLine Spider;; webmaster'at'''',
'''pipeLiner/0.xx (PipeLine Spider;''',
'''Pizilla++ ver 2.45''',
'''PJspider/3.0 (;''',
'''Plagger/0.x.xx (''',
'''plinki/0.1 (you got plinked! (thats a good thing..);;''',
'''PluckFeedCrawler/2.0 (compatible; Mozilla 4.0; MSIE 5.5;; 1 subscribers)''',
'''Pluggd/Nutch-0.9 (automated crawler;support at pluggd dot com)''',
'''Pockey-GetHTML/4.12.0 (Win32; GUI; ix86)''',
'''POE-Component-Client-HTTP/0.64 (perl; N; POE; en; rv:0.640000)''',
'''polybot 1.0 (''',
'''Port Huron Labs''',
'''PortalBSpider/2.0 (''',
'''portalmmm/2.0 S500i(c20;TB)''',
'''potbot 1.0''',
'''PRCrawler/Nutch-0.9 (data mining development project;''',
'''PrivacyFinder Cache Bot v1.0''',
'''Privoxy/3.0 (Anonymous)''',
'''Production Bot 0116B''',
'''Production Bot 2016B''',
'''Production Bot DOT 3016B''',
'''Program Shareware 1.0.2''',
'''Progressive Download''',
'''Progressive Download HTTP check''',
'''Project XP5 [2.03.07-111203]''',
'''PROve AnswerBot 4.0''',
'''ProWebGuide Link Checker (''',
'''psbot/0.1 (+''',
'''PSurf15a 11''',
'''PSurf15a 51''',
'''PSurf15a VA''',
'''PubCrawl (''',
'''puf/0.91beta6a (Linux 2.2.18; i686)''',
'''puf/0.93.2a (Linux 2.4.18; i686)''',
'''pulseBot (pulse Web Miner)''',
'''PuxaRapido v1.0''',
'''PWeBot/1.2 Inspector (''',
''' Web Directory (''',
'''QEAVis Agent/Nutch-0.9 (Quantitative Evaluation of Academic Websites Visibility;''',
'''QPCreep Test Rig ( We are not indexing- just testing )''',
'''QuepasaCreep ( )''',
'''QuepasaCreep v0.9.1x''',
'''QueryN Metasearch''',
'''Quicksilver (Blacktree,MacOSX)''',
'''QuickTime\xaa.7.0.4 (qtver=7.0.4;cpu=PPC;os=Mac 10.3.9)''',
'''QweeryBot/3.01 (''',
'''Qweery_robot.txt_CheckBot/3.01 (''',
'''rabaz (rabaz at gigabaz dot com)''',
'''RaBot/1.0 Agent-admin/''',
'''ramBot xtreme x.x''',
'''RAMPyBot - (RAMPyBot -;;''',
'''RAMPyBot/0.8-dev (Nutch;;''',
'''Rank Exec ( Reciprocal Link Manager 1.x/bot''',
'''Rankivabot/3.2 (; 3.2; vzmxikn)''',
'''Rational SiteCheck (Windows NT)''',
'''ReadABlog Spider (compatible; 1.1; feed update;''',
'''REAP-crawler Nutch/Nutch-1.0-dev (Reap Project;; Reap Project)''',
'''Reaper [2.03.10-031204] (''',
'''Reaper/2.0x (+''',
'''REBOL Core 2.x.x.x.x''',
'''REBOL View 1.x.x.x.x''',
'''RebusnetBot (+''',
'''RebusnetPADBot/1.5x (+''',
'''reciprocal links checker (''',
'''RedBot/redbot-1.0 ( Crawler; redbot at rediff dot com)''',
'''RedCarpet/1.2 (''',
'''RedCell/0.1 (InfoSec Search Bot (Coming Soon);;''',
'''RedCell/0.1 (RedCell;;''',
'''RedKernel WWW-Spider 2/0 (+''',
'''REL Link Checker Lite x.x''',
'''RepoMonkey Bait & Tackle/v1.01''',
'''Rewebber/1.2 libwww-perl/5.41''',
'''RixBot (''',
'''RMA/1.0 (compatible; RealMedia)''',
'''RMA/1.0 (compatible; RealMedia)''',
'''RoboCrawl (''',
'''RoboCrawl (''',
'''RoboPal (''',
'''Robot: NutchCrawler- Owner:''',
'''Rome Client ( Ver: 0.9''',
'''Rotondo/3.1 libwww/5.3.1''',
'''RRC (''',
'''RssBandit/ (.NET CLR 1.1.4322.2407; WinNT 5.1.2600.0; (.NET CLR 1.1.4322.2407; WinNT 5.1.2600.0; )''',
''' RSS/Atom Feed Robot''',
'''RSSOwl/1.2.3 2006-11-26 (Windows; U; zhtw)''',
'''RSSOwl/1.2.4 Preview Release 2007-04-15 (Windows; U; zhtw)''',
'''RssReader/1.0.xx.x ( Microsoft Windows NT 5.1.2600.0''',
'''RSurf15a 41''',
'''RSurf15a 51''',
'''RSurf15a 81''',
'''Rubbot/1.0 (+''',
'''RufusBot (Rufus Web Miner;''',
'''RufusBot (Rufus Web Miner;''',
'''RX Bar''',
'''S&L Spider (''',
'''S.T.A.L.K.E.R. (''',
'''SafariBookmarkChecker (+''',
'''sait/Nutch-0.9 (SAIT Research;''',
'''SandCrawler - Compatibility Testing''',
'''SapphireWebCrawler/1.0 (Sapphire Web Crawler using Nutch;;''',
'''SapphireWebCrawler/Nutch-1.0-dev (Sapphire Web Crawler using Nutch;;''',
'''SBIder/0.7 (SBIder;;''',
'''SBIder/0.8-dev (SBIder;;''',
'''SBL-BOT (''',
'''ScholarUniverse/0.8 (Nutch;+;''',
'''Science Traveller International 1X/1.0''',
'''ScollSpider/2.0 (+''',
'''Scooter/1.1 (custom)''',
'''Scooter/2.0 G.R.A.B. V1.1.0''',
'''Scooter/2.0 G.R.A.B. X2.0''',
'''Scope (Mars+)''',
'''ScoutAnt/0.1; +''',
'''Scrubby/2.x (''',
'''Scrubby/3.0 (+''',
''' V1.4''',
''' V1.4.2 (;''',
'''Search/1.0 (''',
'''SearchByUsa/2 (SearchByUsa;;''',
'''SearchExpress Spider0.99''',
'''SearchGuild/DMOZ/Experiment (''',
'''SearchGuild_DMOZ_Experiment (''',
'''Searchit-Now Robot/2.2 (+''',
'''Searchmee! Spider v0.98a''',
'''SearchSight/2.0 (''',
'''Searchspider/1.2 (SearchSpider;;''',
'''SearchTone2.0 - IDEARE''',
'''Seekbot/1.0 ( HTTPFetcher/0.3''',
'''Seekbot/1.0 ( RobotsTxtFetcher/1.0 (XDF)''',
'''Seekbot/1.0 ( RobotsTxtFetcher/1.2''',
'''Semager/1.1 (''',
'''Semager/1.x (''',
'''Sensis Web Crawler (search_comments\at\sensis\dot\com\dot\au)''',
''' Web Crawler (search_comments\at\sensis\dot\com\dot\au)''',
'''SeznamBot/1.0 (+''',
'''SeznamBot/2.0-test (+''',
'''ShablastBot 1.0''',
'''Shareaza v1.x.x.xx''',
'''Shim Crawler''',
'''ShopWiki/1.0 ( +''',
'''ShopWiki/1.0 ( +''',
''' Crawler 2.0''',
'''SietsCrawler/1.1 (+''',
'''Sigram/Nutch-1.0-dev (Test agent for Nutch development;; bot at sigram dot com)''',
'''Siigle Orumcex v.001 Turkey (''',
'''silk/1.0 (+''',
'''Simpy 1.x;''',
'''Simpy/1.x (Simpy;; feedback at simpy dot com)''',
'''Sirketcebot/v.01 (''',
'''SiteBar/3.x.x (Bookmark Server;''',
'''SiteBar/x.x.x (Bookmark Server;''',
''' (For more info see:''',
'''SiteSpider +(''',
'''SiteTaggerBot (''',
''' site rating system''',
'''Skampy/0.9.x (''',
'''Skimpy/0.x (''',
'''Skywalker/0.1 (Skywalker; anonymous; anonymous)''',
'''Sleipnir Version 1.xx''',
'''Sleipnir Version2.x''',
'''Slurp/2.0 (;''',
'''Slurp/2.0-KiteWeekly (;''',
'''Slurp/si (;''',
'''Slurpy Verifier/1.0''',
'''SlySearch (''',
'''SmartDownload/1.2.67 (Win32; Jan 12 1999)''',
'''SmartDownload/1.2.77 (Win32; Feb 1 2000)''',
'''SmartDownload/1.2.77 (Win32; Jun 19 2001)''',
'''sna-0.0.1 (''',
''' beta crawler v0''',
'''Snapbot/1.0 (Snap Shots, +''',
'''Snappy/1.1 ( )''',
'''Snarfer/0.x.x (''',
'''Snoopy v1.xx''',
'''Snoopy v1.xx- : User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; MyIE2)''',
'''SnykeBot/0.6 (''',
'''SocSciBot ()''',
'''SoftBank/1.0/812SH/SHJ001 Browser/NetFront/3.3 Profile/MIDP-2.0 Configuration/CLDC-1.1''',
'''Softizerbot (''',
'''sogou develop spider''',
'''Sogou Orion spider/3.0(+''',
'''sogou spider''',
'''Sogou web spider/3.0(+''',
'''sohu agent''',
'''Space Bison/0.02 [fu] (Win67; X; SK)''',
'''speedfind ramBot xtreme 8.1''',
'''Speedy Spider (Beta/x.x;''',
'''Speedy Spider (Entireweb; Beta/1.0;''',
'''Speedy_Spider (''',
'''Sphere Scout&v4.0 - scout at sphere dot com''',
'''Spider-Sleek/2.0 (+''',
''' - v:1.04''',
''' -''',
'''SpiderMonkey/7.0x ( info at''',
'''Spinne/2.0 med''',
'''Spinne/2.0 med_AH''',
'''Spock Crawler (''',
''' (Version: 1.02- powered by''',
'''sproose/0.1-alpha (sproose crawler;;''',
'''SQ Webscanner''',
'''SquidClamAV_Redirector 1.x.x''',
'''Sqworm/2.9.81-BETA (beta_release; 20011102-760; i686-pc-linux-gnu)''',
'''Sqworm/2.9.85-BETA (beta_release; 20011115-775; i686-pc-linux-gnu)''',
'''Sqworm/2.9.89-BETA (beta_release; 20020130-839; i686-pc-linux-gnu) ''',
'''SSurf15a 11 ''',
'''StackRambler/x.x ''',
'''Star Downloader''',
'''Steeler/1.x (''',
'''Steeler/3.3 (''',
'''Strategic Board Bot (+''',
'''Strategic Board Bot (+''',
'''Submission Spider at''',
''' (CrawlerAgent v0.103)''',
'''suchpadbot/1.0 (+''',
'''Sunrise XP/2.x''',
'''Sunrise/0.42g (Windows XP)''',
'''SuperBot/x.x (Win32)''',
'''SuperBot/x.x.x.xx (Windows XP)''',
'''Superdownloads Spiderman''',
'''SURF ''',
'''SurferF3 1/0''',
'''SurveyBot/2.2 <a href=''>Whois Source</a>''',
'''SurveyBot/2.3 (Whois Source)''',
'''SWB/V1.4 (HP)''',
'''swbot/0.9c libwww/5.3.1''',
'''Swooglebot/2.0. (+''',
'''Syntryx ANT Scout Chassis Pheromone; Mozilla/4.0 compatible crawler''',
'''Szukacz/1.x (robot;;''',
'''T-Online Browser''',
''' (+''',
'''Tagword (''',
'''Tagyu Agent/1.0''',
'''Talkro Web-Shot/1.0 (E-mail: Home:''',
''' bot''',
'''TCDBOT/Nutch-0.8 (PhD student research;; mcgettrs at t c d dot IE)''',
'''TeamSoft WinInet Component''',
'''Tecomi Bot (''',
'''Teemer (NetSeer, Inc. is a Los Angeles based Internet startup company.;;''',
'''Teleport Pro/1.2x(.1xxx)''',
'''Teoma MP''',
'''teomaagent1 []''',
'''Teradex Mapper;;''',
'''terraminds-bot/1.0 (''',
'''TerrawizBot/1.0 (+''',
'''Test spider''',
'''TestCrawler/Nutch-0.9 (Testing Crawler for Research ;; tgautier at balihoo dot com)''',
'''The Expert HTML Source Viewer (''',
'''TheRarestParser/0.2a (''',
'''TheSuBot/0.1 (''',
'''thumbshots-de-Bot (Version: 1.02, powered by''',
'''thumbshots-de-Bot (Version: 1.02- powered by''',
'''TinEye/1.1 (''',
'''tivraSpider/1.0 (''',
'''TJvMultiHttpGrabber Component''',
'''Topodia/1.2-dev (Topodia - Crawler for HTTP content indexing;;''',
'''TOPOS robot/1.1 (''',
'''Toutatis x-xx.x (''',
'''Toutatis x.x (''',
'''Toutatis x.x-x''',
'''traazibot/testengine (+''',
'''Trailfire-bot/0.7.1 (Nutch;;''',
'''Trailfire-bot/0.7.1 (Trailfire page content analyzer;;''',
'''Trailfire/0.7.1 (Nutch;;''',
'''tricosMetaCheck 1.2216-08-1999 (''',
'''TSurf15a 11''',
'''TulipChain/5.x ( Java/1.x.1_0x ( Linux/2.4.17''',
'''TulipChain/5.xx ( Java/1.x.1_0x ( Mac_OS_X/10.2.8''',
'''Tumblr/1.0 RSS syndication (+ (''',
'''TurnitinBot/x.x (''',
'''Turnpike Emporium LinkChecker/0.1''',
'''TutorGig/1.5 (+''',
'''Tutorial Crawler 1.4 (''',
'''Twisted PageGetter''',
'''Twitturly / v0.x''',
'''Twotrees Reactive Filter V2.0''',
'''Tycoon Agent/Nutch-1.0-dev''',
'''UCMore Crawler App''',
'''UKWizz/Nutch-0.8.1 (UKWizz Nutch crawler;''',
'''Under the Rainbow 2.2''',
''' Web Server IIS vs Apache Survey. See Results at''',
'''UofTDB_experiment (''',
'''UP.Browser/3.01-IG01 UP.Link/''',
'''updated/0.1-alpha (updated crawler;;''',
'''updated/0.1beta (;;''',
'''UPG1 UP/4.0 (compatible; Blazer 1.0)''',
'''URL Spider Pro/x.xx (''',
'''urlfan-bot/1.0; +''',
'''User-Agent: BoardReader Favicon Fetcher /1.0''',
'''User-Agent: BoardReader Image Fetcher /1.0''',
'''User-Agent: LjSEEK Picture-Bot /1.0''',
'''User-Agent: FileHeap! file downloader (''',
'''User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)''',
'''User-Agent: Mozilla/4.0 (SKIZZLE! Distributed Internet Spider v1.0 -''',
'''USyd-NLP-Spider (''',
'''UtilMind HTTPGet''',
'''Utopia WebWasher 3.0''',
'''Vagabondo-WAP/2.0 (webcrawler at wise-guys dot nl; Profile''',
'''Vagabondo/1.x MT (''',
'''Vagabondo/2.0 MT''',
'''Vagabondo/2.0 MT (webagent at wise-guys dot nl)''',
'''Vagabondo/2.0 MT (''',
'''Vagabondo/3.0 (webagent at wise-guys dot nl)''',
'''Vakes/0.01 (Vakes;;''',
'''VayalaCreep-v0.0.1 (''',
'''Vayala|Creep-v0.0.1 (''',
'''vb wininet''',
'''versus 0.2 (+''',
'''versus crawler''',
''' - Networking4all Bot/x.x''',
'''Verzamelgids/2.2 (''',
'''Vespa Crawler''',
'''virus_detector (''',
'''VisBot/2.0 ( Crawler;;''',
'''Visicom Toolbar''',
'''Vision Research Lab image spider at''',
'''VLC media player - version 0.8.5 Janus - (c) 1996-2006 the VideoLAN team''',
'''VMBot/0.x.x (VMBot;;''',
'''Vortex/2.2 (+''',
'''voyager/2.0 (''',
'''VSE/1.0 (''',
'''VSE/1.0 (''',
'''VWBOT/Nutch-0.9-dev (VWBOT Nutch Crawler;;''',
'''W3C-checklink/3.x.x.x libwww-perl/5.xx''',
'''W3C-checklink/4.x [4.xx] libwww-perl/''',
'''W3C-WebCon/5.x.x libwww/5.x.x''',
'''W3CLineMode/5.4.0 libwww/5.x.x''',
'''W3CRobot/5.4.0 libwww/5.4.0''',
'''W3C_Validator/ libwww-perl/5.xx''',
'''W3SiteSearch Crawler_v1.1''',
''' 0.2 (''',
'''WannaBe (Macintosh; PPC)''',
'''WapOnWindows 1.0''',
'''Watchfire WebXM 1.0''',
'''WAVcheck 1.0.x (''',
'''Wavefire/0.8-dev (Wavefire;;''',
'''Waypath development crawler - info at waypath dot com''',
'''Waypath Scout v2.x - info at waypath dot com''',
'''Web Image Collector''',
'''Web Link Validator 1.5''',
'''Web Snooper''',
'''web-bekannt (Version: 1.02, powered by''',
'''web-bekannt (Version: 1.02, powered by''',
'''Web-Bot V1.03''',
'''Web-Robot/5.0 (en-US; Web-Robot Crawler/2.0.3''',
''' (leveled playing field;; info at''',
'''WebAlta Crawler/1.2.1 (''',
'''WebarooBot (Webaroo Bot;''',
'''WebarooBot (Webaroo Bot;''',
'''WebAuto/3.4xxx (WinNT; I)''',
'''WebCompass 2.0''',
'''WebCopier vx.x''',
'''WebCopier vx.xa''',
'''WebDownloader for X x.xx''',
'''WebFilter Robot 1.0''',
'''WebFilter Robot 1.x''',
'''Webglimpse 2.xx.x (''',
'''WebImages 0.3 ( )''',
'''WebLight/4.x.x (;''',
'''Weblink's checker/''',
'''Weblog Attitude Diffusion 1.0''',
'''WebMiner/x.x [en] (Win98; I)''',
'''WebPix 1.0 (''',
'''WebRACE/1.1 (University of Cyprus- Distributed Crawler)''',
'''WebRankSpider/1.37 (+''',
'''WebReaper vx.x -''',
'''WebReaper []''',
'''WebReaper []''',
'''WebSearch.COM.AU/3.0.1 (The Australian Search Engine; http://WebSearch.COM.AU; Search@WebSearch.COM.AU)''',
'''WebSearchBench WebCrawler v0.1(Experimental)''',
'''WebSearchBench WebCrawler V1.0 (Beta)- Prof. Dr.-Ing. Christoph Lindemann- Universität Dortmund-''',
'''Website Explorer/0.9.x.x''',
'''Website eXtractor''',
'''WebsiteWorth v1.0''',
''' (Add url robot)''',
'''WebStat/1.0 (Unix; beta; 20040314)''',
'''Webster v0.3 ( )''',
''' pad browser''',
'''WebTrends/3.0 (WinNT)''',
'''WebVac (''',
''' - Telefon: 01908 / 26005''',
'''WebVulnCrawl.unknown/1.0 libwww-perl/5.803''',
'''WebZIP/x.x (''',
'''Wells Search II''',
'''WEP Search 00''',
'''West Wind Internet Protocols 4.xx''',
'''Wget/1.x(.x)GNU wget - file downloader''',
'''Wget/1.x+cvs-stable (Red Hat modified)''',
'''WhizBang! Lab''',
'''Wildsoft Surfer''',
'''Willow Internet Crawler by Twotrees V2.1''',
'''WinampMPEG/2.00 (larbin@unspecified.mail)''',
'''WincerSong Agent v1.0''',
'''WinGet 1.1''',
'''WinHTTP Example/1.0''',
'''WinkBot/0.06 ( search engine web crawler;;''',
'''WinPodder (''',
'''WinWAP/3.x (3.x.x.xx; Win32) (Google WAP Proxy/1.0)''',
'''Wir sind die Borg (Version: 1.03, Sie wurden Assimiliert +''',
'''WIRE/0.11 (Linux; i686; Bot,Robot,Spider,Crawler,''',
'''WIRE/0.x (Linux; i686; Bot,Robot,Spider,Crawler)''',
'''WISEbot/1.0 (;''',
'''wish-project (''',
'''WordPress/x.x.x.x PHP/4.x.xx''',
'''worio heritrix bot (+''',
'''woriobot (''',
'''Wotbox/alpha0.6 (;''',
'''Wotbox/alpha0.x.x (; Java/1.4.1_02''',
'''WSB WebCrawler V1.0 (Beta)-''',
'''wume_crawler/1.1 (''',
'''WWSBOT 1.x [--- ---]''',
''' registry verify/1.x''',
''' crawler''',
'''www4mail/2.x libwww-FM/2.14 (Unix; I)''',
'''WWWeasel Robot v1.00 (''',
'''wwwster/1.x (Beta-''',
'''wxDownload Fast''',
'''X-Crawler ''',
'''Xaldon WebSpider''',
'''Xenu Link Sleuth 1.xx''',
'''Xenu's Link Sleuth 1.x[a-z]''',
'''Xerka WebBot v1.0.0 [UPVOpenDir]''',
'''xirq/0.1-beta (xirq;;''',
'''XMLSlurp/0.1 libwww-perl/5.805''',
'''XRL/2.00b1 (Linux; i686; en-us) (+''',
'''Y!J-BSC/1.0 (''',
'''Y!J/1.0 (''',
'''Y!OASIS/TEST no-ad Mozilla/4.08 [en] (X11; I; FreeBSD 2.2.8-STABLE i386)''',
'''yacy (; v20040602; i386 Linux 2.4.26-gentoo-r13; java 1.4.2_06; MET/en)''',
'''yacybot (x86 Windows XP 5.1; java 1.5.0_06; Europe/de)''',
'''Yahoo Pipes 1.0''',
'''Yahoo! Mindset''',
'''Yahoo-Blogs/v3.9 (compatible; Mozilla 4.0; MSIE 5.5; )''',
'''Yahoo-MMAudVid/1.0 (mms dash mmaudvidcrawler dash support at yahoo dash inc dot com)''',
'''Yahoo-MMAudVid/2.0(mms dash mm aud vid crawler dash support at yahoo dash ;Mozilla 4.0 compatible; MSIE 7.0;Windows NT 5.0; .NET CLR 2.0)''',
'''Yahoo-MMCrawler/3.x (mm dash crawler at trd dot overture dot com)''',
'''Yahoo-VerticalCrawler-FormerWebCrawler/3.9 crawler at trd dot overture dot com;''',
'''YahooFeedSeeker/2.0 (compatible; Mozilla 4.0; MSIE 5.5;''',
'''YahooSeeker-Testing/v3.9 (compatible; Mozilla 4.0; MSIE 5.5;''',
'''YahooSeeker/1.0 (compatible; Mozilla 4.0; MSIE 5.5;''',
'''YahooSeeker/1.0 (compatible; Mozilla 4.0; MSIE 5.5;''',
'''YahooSeeker/1.1 (compatible; Mozilla 4.0; MSIE 5.5;''',
'''YahooSeeker/bsv3.9 (compatible; Mozilla 4.0; MSIE 5.5; )''',
'''YahooSeeker/CafeKelsa-dev (compatible; Konqueror/3.2; FreeBSD ; )''',
'''Yandex/1.01.001 (compatible; Win16; I)''',
'''Yanga WorldSearch Bot v1.1/beta (''',
'''Yeti/0.01 (nhn/1noon,, check robots.txt daily and follows it)''',
'''Yeti/1.0 (NHN Corp.;''',
'''yggdrasil/Nutch-0.9 (yggdrasil biorelated search engine; www dot biotec dot tu minus dresden do de slash schroeder; heiko dot dietze at biotec dot tu minus dresden dot de)''',
'''YodaoBot/1.0 (; )''',
'''yoofind/yoofind-0.1-dev (yoono webcrawler; ; MyEmail)''',
'''yoono/1.0 web-crawler/1.0''',
'''YottaCars_Bot/4.12 (+ Car Search Engine ''',
'''YottaShopping_Bot/4.12 (+ Shopping Search Engine''',
'''Z-Add Link Checker (''',
'''Zao-Crawler 0.2b''',
'''Zao/0.1 (''',
'''ZBot/1.00 (''',
''' (''',
''' (''',
'''zedzo.digest/0.1 (''',
'''zermelo Mozilla/5.0 compatible; heritrix/1.12.1 (+ [,]''',
'''zerxbot/Version 0.6 libwww-perl/5.79''',
'''Zeus ThemeSite Viewer Webster Pro V2.9 Win32''',
'''Zeus xxxxx Webster Pro V2.9 Win32''',
'''Zeusbot/0.07 (Ulysseek's web-crawling robot;;''',
'''Ziggy -- The Clown From Hell!!''',
'''ZipppBot/0.xx (ZipppBot;;''',
'''ZIPPPCVS/0.xx (ZipppBot/.xx;;''',
'''Zippy v2.0 -''',
'''Zoo Tycoon 2 Client --''',
'''ZoomSpider -''',
''' Crawler/ ( Crawler''',
'''ZyBorg/1.0 (;''',
'''Mozilla/5.0 (Windows; U; Windows NT 5.1; de; rv: Gecko/20100401 Firefox/3.6.3 (FM Scene 4.6.1)''',
'''Mozilla/5.0 (Windows; U; Windows NT 5.1; de; rv: Gecko/20100401 Firefox/3.6.3 (.NET CLR 3.5.30729) (Prevx 3.0.5)''',
'''Mozilla/5.0 (compatible; YandexBot/3.0; +''',
'''3485 Mozilla/5.0 (compatible; Bender;''',
'''Mozilla/5.0 (compatible; YandexImages/3.0; +''',
'''Mozilla/5.0 (compatible; Ezooms/1.0;''',
'''librabot/2.0 (+''',
'''(GUI) MMP/2.0 (compatible; Googlebot-Mobile/2.1; +''',
'''ia_archiver (+;''',
'''Mozilla/5.0 (compatible; Falconsbot; +''',
'''Mozilla/5.0 (compatible; MJ12bot/v1.3.3;''',
'''Mozilla/5.0 (compatible; discobot/1.1; +''',
''' sitemap fetcher''',
'''Mozilla/5.0 (compatible; sindice-fetcher/0.1.0 +''',
'''Mozilla/5.0 (compatible; Googlebot/2.1; +''',
if __name__ == "__main__":
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment