impressiongram 0.0.4 → 0.0.5

Sign up to get free protection for your applications and to get access to all the features.
data/Rakefile CHANGED
@@ -86,7 +86,7 @@ namespace :version do
86
86
  end
87
87
 
88
88
  namespace :impressionist do
89
- require File.dirname(__FILE__) + "/lib/impressionGRAM/bots"
89
+ require File.dirname(__FILE__) + "/lib/impressionist/bots"
90
90
 
91
91
  desc "output the list of bots from http://www.user-agents.org/"
92
92
  task :bots do
data/VERSION CHANGED
@@ -1 +1 @@
1
- 0.0.4
1
+ 0.0.5
@@ -0,0 +1,68 @@
1
+ require 'digest/sha2'
2
+
3
+ module ImpressionistController
4
+ module ClassMethods
5
+ def impressionist(opts={})
6
+ before_filter { |c| c.impressionist_subapp_filter opts[:actions] }
7
+ end
8
+ end
9
+
10
+ module InstanceMethods
11
+ def self.included(base)
12
+ base.before_filter :impressionist_app_filter
13
+ end
14
+
15
+ def impressionist(obj,message=nil)
16
+ unless bypass
17
+ if obj.respond_to?("impressionable?")
18
+ obj.impressions.create(:message=> message,
19
+ :request_hash=> @impressionist_hash,
20
+ :session_hash=> request.session_options[:id],
21
+ :ip_address=> request.remote_ip,
22
+ :user_id=> user_id,
23
+ :controller_name=>controller_name,
24
+ :action_name=> action_name,
25
+ :referrer=>request.referer)
26
+ else
27
+ raise "#{obj.class.to_s} is not impressionable!"
28
+ end
29
+ end
30
+ end
31
+
32
+ def impressionist_app_filter
33
+ @impressionist_hash = Digest::SHA2.hexdigest(Time.now.to_f.to_s+rand(10000).to_s)
34
+ end
35
+
36
+ def impressionist_subapp_filter(actions=nil)
37
+ unless bypass
38
+ actions.collect!{|a|a.to_s} unless actions.blank?
39
+ if actions.blank? or actions.include?(action_name)
40
+ Impression.create(:controller_name=> controller_name,
41
+ :action_name=> action_name,
42
+ :user_id=> user_id,
43
+ :request_hash=> @impressionist_hash,
44
+ :session_hash=> request.session_options[:id],
45
+ :ip_address=> request.remote_ip,
46
+ :impressionable_type=> controller_name.singularize.camelize,
47
+ :impressionable_id=> params[:id],
48
+ :referrer=>request.referer)
49
+ end
50
+ end
51
+ end
52
+
53
+ private
54
+ def bypass
55
+ Impressionist::Bots::WILD_CARDS.each do |wild_card|
56
+ return true if request.user_agent and request.user_agent.downcase.include? wild_card
57
+ end
58
+ Impressionist::Bots::LIST.include? request.user_agent
59
+ end
60
+
61
+ #use both @current_user and current_user helper
62
+ def user_id
63
+ user_id = @current_user ? @current_user.id : nil rescue nil
64
+ user_id = current_user ? current_user.id : nil rescue nil if user_id.blank?
65
+ user_id
66
+ end
67
+ end
68
+ end
@@ -0,0 +1,1462 @@
1
+ module Impressionist
2
+ module Bots
3
+ WILD_CARDS = ["bot","yahoo","slurp","google","msn","crawler"]
4
+
5
+ LIST = ["<a href='http://www.unchaos.com/'> UnChaos </a> From Chaos To Order Hybrid Web Search Engine.(vadim_gonchar@unchaos.com)",
6
+ "<a href='http://www.unchaos.com/'> UnChaos Bot Hybrid Web Search Engine. </a> (vadim_gonchar@unchaos.com)",
7
+ "<b> UnChaosBot From Chaos To Order UnChaos Hybrid Web Search Engine at www.unchaos.com </b> (info@unchaos.com)",
8
+ "<http://www.sygol.com/> http://www.sygol.com",
9
+ "*/Nutch-0.9-dev",
10
+ "+SitiDi.net/SitiDiBot/1.0 (+Have Good Day)",
11
+ "-DIE-KRAEHE- META-SEARCH-ENGINE/1.1 http://www.die-kraehe.de",
12
+ "192.comAgent",
13
+ "4anything.com LinkChecker v2.0",
14
+ "8484 Boston Project v 1.0",
15
+ ":robot/1.0 (linux) ( admin e-mail: undefined http://www.neofonie.de/loesungen/search/robot.html )",
16
+ "A-Online Search",
17
+ "A1 Sitemap Generator/1.0 (+http://www.micro-sys.dk/products/sitemap-generator/) miggibot/2006.01.24",
18
+ "aardvark-crawler",
19
+ "AbachoBOT",
20
+ "AbachoBOT (Mozilla compatible)",
21
+ "ABCdatos BotLink/5.xx.xxx#BBL",
22
+ "Aberja Checkomat",
23
+ "abot/0.1 (abot; http://www.abot.com; abot@abot.com)",
24
+ "About/0.1libwww-perl/5.47",
25
+ "Accelatech RSSCrawler/0.4",
26
+ "accoona",
27
+ "Accoona-AI-Agent/1.1.1 (crawler at accoona dot com)",
28
+ "Accoona-AI-Agent/1.1.2 (aicrawler at accoonabot dot com)",
29
+ "Ack (http://www.ackerm.com/)",
30
+ "AcoiRobot",
31
+ "Acoon Robot v1.50.001",
32
+ "Acoon Robot v1.52 (http://www.acoon.de)",
33
+ "Acoon-Robot 4.0.x.[xx] (http://www.acoon.de)",
34
+ "Acoon-Robot v3.xx (http://www.acoon.de and http://www.acoon.com)",
35
+ "Acorn/Nutch-0.9 (Non-Profit Search Engine; acorn.isara.org; acorn at isara dot org)",
36
+ "AESOP_com_SpiderMan",
37
+ "agadine/1.x.x (+http://www.agada.de)",
38
+ "Agent-SharewarePlazaFileCheckBot/2.0+(+http://www.SharewarePlaza.com)",
39
+ "AgentName/0.1 libwww-perl/5.48",
40
+ "AIBOT/2.1 By +(www.21seek.com A Real artificial intelligence search engine China)",
41
+ "aipbot/1.0 (aipbot; http://www.aipbot.com; aipbot@aipbot.com)",
42
+ "aipbot/2-beta (aipbot dev; http://aipbot.com; aipbot@aipbot.com)",
43
+ "Aladin/3.324",
44
+ "Aleksika Spider/1.0 (+http://www.aleksika.com/)",
45
+ "AlkalineBOT/1.3",
46
+ "AlkalineBOT/1.4 (1.4.0326.0 RTM)",
47
+ "Allesklar/0.1 libwww-perl/5.46",
48
+ "Allrati/1.1 (+)",
49
+ "AltaVista Intranet V2.0 AVS EVAL search@freeit.com",
50
+ "AltaVista Intranet V2.0 Compaq Altavista Eval sveand@altavista.net",
51
+ "AltaVista Intranet V2.0 evreka.com crawler@evreka.com",
52
+ "AltaVista V2.0B crawler@evreka.com",
53
+ "AmfibiBOT",
54
+ "Amfibibot/0.06 (Amfibi Web Search; http://www.amfibi.com; agent@amfibi.com)",
55
+ "Amfibibot/0.07 (Amfibi Robot; http://www.amfibi.com; agent@amfibi.com)",
56
+ "amibot",
57
+ "AnnoMille spider 0.1 alpha - http://www.annomille.it",
58
+ "AnswerBus (http://www.answerbus.com/)",
59
+ "antibot-V1.1.5/i586-linux-2.2",
60
+ "AnzwersCrawl/2.0 (anzwerscrawl@anzwers.com.au;Engine)",
61
+ "Apexoo Spider 1.x",
62
+ "Aport",
63
+ "appie 1.1 (www.walhello.com)",
64
+ "ArabyBot (compatible; Mozilla/5.0; GoogleBot; FAST Crawler 6.4; http://www.araby.com;)",
65
+ "ArachBot",
66
+ "Arachnoidea (arachnoidea@euroseek.com)",
67
+ "ArchitextSpider",
68
+ "archive.org_bot",
69
+ "Arikus_Spider",
70
+ "Arquivo-web-crawler (compatible; heritrix/1.12.1 +http://arquivo-web.fccn.pt)",
71
+ "ASAHA Search Engine Turkey V.001 (http://www.asaha.com/)",
72
+ "Asahina-Antenna/1.x",
73
+ "Asahina-Antenna/1.x (libhina.pl/x.x ; libtime.pl/x.x)",
74
+ "ask.24x.info",
75
+ "AskAboutOil/0.06-rcp (Nutch; http://www.nutch.org/docs/en/bot.html; nutch-agent@askaboutoil.com)",
76
+ "asked/Nutch-0.8 (web crawler; http://asked.jp; epicurus at gmail dot com)",
77
+ "ASPSeek/1.2.5",
78
+ "ASPseek/1.2.9d",
79
+ "ASPSeek/1.2.x",
80
+ "ASPSeek/1.2.xa",
81
+ "ASPseek/1.2.xx",
82
+ "ASPSeek/1.2.xxpre",
83
+ "ASSORT/0.10",
84
+ "asterias/2.0",
85
+ "AtlocalBot/1.1 +(http://www.atlocal.com/local-web-site-owner.html)",
86
+ "Atomic_Email_Hunter/4.0",
87
+ "Atomz/1.0",
88
+ "atSpider/1.0",
89
+ "Attentio/Nutch-0.9-dev (Attentio's beta blog crawler; www.attentio.com; info@attentio.com)",
90
+ "augurfind",
91
+ "augurnfind V-1.x",
92
+ "autoemailspider",
93
+ "autowebdir 1.1 (www.autowebdir.com)",
94
+ "AV Fetch 1.0",
95
+ "AVSearch-1.0(peter.turney@nrc.ca)",
96
+ "AVSearch-3.0(AltaVista/AVC)",
97
+ "axadine/ (Axadine Crawler; http://www.axada.de/; )",
98
+ "AxmoRobot - Crawling your site for better indexing on www.axmo.com search engine.",
99
+ "BabalooSpider/1.3 (BabalooSpider; http://www.babaloo.si; spider@babaloo.si)",
100
+ "BaboomBot/1.x.x (+http://www.baboom.us)",
101
+ "BaiduImagespider+(+http://www.baidu.jp/search/s308.html)",
102
+ "BaiDuSpider",
103
+ "Baiduspider+(+http://help.baidu.jp/system/05.html)",
104
+ "Baiduspider+(+http://www.baidu.com/search/spider.htm)",
105
+ "Baiduspider+(+http://www.baidu.com/search/spider_jp.html)",
106
+ "Balihoo/Nutch-1.0-dev (Crawler for Balihoo.com search engine - obeys robots.txt and robots meta tags ; http://balihoo.com/index.aspx; robot at balihoo dot com)",
107
+ "BarraHomeCrawler (albertof@barrahome.org)",
108
+ "bdcindexer_2.6.2 (research@bdc)",
109
+ "BDFetch",
110
+ "BDNcentral Crawler v2.3 [en] (http://www.bdncentral.com/robot.html) (X11; I; Linux 2.0.44 i686)",
111
+ "beautybot/1.0 (+http://www.uchoose.de/crawler/beautybot/)",
112
+ "BebopBot/2.5.1 ( crawler http://www.apassion4jazz.net/bebopbot.html )",
113
+ "BigCliqueBOT/1.03-dev (bigclicbot; http://www.bigclique.com; bot@bigclique.com)",
114
+ "BIGLOTRON (Beta 2;GNU/Linux)",
115
+ "Bigsearch.ca/Nutch-x.x-dev (Bigsearch.ca Internet Spider; http://www.bigsearch.ca/; info@enhancededge.com)",
116
+ "BilgiBetaBot/0.8-dev (bilgi.com (Beta) ; http://lucene.apache.org/nutch/bot.html; nutch-agent@lucene.apache.org)",
117
+ "BilgiBot/1.0(beta) (http://www.bilgi.com/; bilgi at bilgi dot com)",
118
+ "Bitacle bot/1.1",
119
+ "Bitacle Robot (V:1.0;) (http://www.bitacle.com)",
120
+ "BlackWidow",
121
+ "Blaiz-Bee/1.0 (+http://www.blaiz.net)",
122
+ "Blaiz-Bee/2.00.8222 (BE Internet Search Engine http://www.rawgrunt.com)",
123
+ "Blaiz-Bee/2.00.xxxx (+http://www.blaiz.net)",
124
+ "BlitzBOT@tricus.net",
125
+ "BlitzBOT@tricus.net (Mozilla compatible)",
126
+ "BlogBot/1.x",
127
+ "Bloglines Title Fetch/1.0 (http://www.bloglines.com)",
128
+ "Bloglines-Images/0.1 (http://www.bloglines.com)",
129
+ "Bloglines/3.1 (http://www.bloglines.com)",
130
+ "Blogpulse (info@blogpulse.com)",
131
+ "BlogPulseLive (support@blogpulse.com)",
132
+ "BlogSearch/1.x +http://www.icerocket.com/",
133
+ "blogsearchbot-pumpkin-3",
134
+ "BlogsNowBot, V 2.01 (+http://www.blogsnow.com/)",
135
+ "BlogVibeBot-v1.1 (spider@blogvibe.nl)",
136
+ "blogWatcher_Spider/0.1 (http://www.lr.pi.titech.ac.jp/blogWatcher/)",
137
+ "BlogzIce/1.0 (+http://icerocket.com; rhodes@icerocket.com)",
138
+ "BlogzIce/1.0 +http://www.icerocket.com/",
139
+ "BloobyBot",
140
+ "Bloodhound/Nutch-0.9 (Testing Crawler for Research - obeys robots.txt and robots meta tags ; http://balihoo.com/index.aspx; robot at balihoo dot com)",
141
+ "boitho.com-dc/0.xx (http://www.boitho.com/dcbot.html)",
142
+ "boitho.com-robot/1.x",
143
+ "boitho.com-robot/1.x (http://www.boitho.com/bot.html)",
144
+ "BPImageWalker/2.0 (www.bdbrandprotect.com)",
145
+ "BravoBrian SpiderEngine MarcoPolo",
146
+ "BruinBot (+http://webarchive.cs.ucla.edu/bruinbot.html) ",
147
+ "BSDSeek/1.0",
148
+ "BTbot/0.x (+http://www.btbot.com/btbot.html)",
149
+ "BuildCMS crawler (http://www.buildcms.com/crawler)",
150
+ "BullsEye",
151
+ "bumblebee@relevare.com",
152
+ "BurstFindCrawler/1.1 (crawler.burstfind.com; http://crawler.burstfind.com; crawler@burstfind.com)",
153
+ "Buscaplus Robi/1.0 (http://www.buscaplus.com/robi/)",
154
+ "bwh3_user_agent",
155
+ "Cabot/Nutch-0.9 (Amfibi's web-crawling robot; http://www.amfibi.com/cabot/; agent@amfibi.com)",
156
+ "Cabot/Nutch-1.0-dev (Amfibi's web-crawling robot; http://www.amfibi.com/cabot/; agent@amfibi.com)",
157
+ "carleson/1.0",
158
+ "Carnegie_Mellon_University_Research_WebBOT-->PLEASE READ-->http://www.andrew.cmu.edu/~brgordon/webbot/index.html http://www.andrew.cmu.edu/~brgordon/webbot/index.html",
159
+ "Carnegie_Mellon_University_WebCrawler http://www.andrew.cmu.edu/~brgordon/webbot/index.html",
160
+ "Catall Spider",
161
+ "CazoodleBot/CazoodleBot-0.1 (CazoodleBot Crawler; http://www.cazoodle.com/cazoodlebot; cazoodlebot@cazoodle.com)",
162
+ "CCBot/1.0 (+http://www.commoncrawl.org/bot.html)",
163
+ "ccubee/x.x",
164
+ "Ceramic Tile Installation Guide (http://www.floorstransformed.com)",
165
+ "cfetch/1.0",
166
+ "China Local Browse 2.6",
167
+ "ChristCRAWLER 2.0",
168
+ "CipinetBot (http://www.cipinet.com/bot.html)",
169
+ "ClariaBot/1.0",
170
+ "Claymont.com",
171
+ "CloakDetect/0.9 (+http://fulltext.seznam.cz/)",
172
+ "Clushbot/2.x (+http://www.clush.com/bot.html)",
173
+ "Clushbot/3.x-BinaryFury (+http://www.clush.com/bot.html)",
174
+ "Clushbot/3.xx-Ajax (+http://www.clush.com/bot.html)",
175
+ "Clushbot/3.xx-Hector (+http://www.clush.com/bot.html)",
176
+ "Clushbot/3.xx-Peleus (+http://www.clush.com/bot.html)",
177
+ "Cogentbot/1.X (+http://www.cogentsoftwaresolutions.com/bot.html)",
178
+ "combine/0.0",
179
+ "Combine/2.0 http://combine.it.lth.se/",
180
+ "Combine/3 http://combine.it.lth.se/",
181
+ "Combine/x.0",
182
+ "cometrics-bot, http://www.cometrics.de",
183
+ "Computer_and_Automation_Research_Institute_Crawler crawler@ilab.sztaki.hu",
184
+ "Comrite/0.7.1 (Nutch; http://lucene.apache.org/nutch/bot.html; nutch-agent@lucene.apache.org)",
185
+ "ContactBot/0.2",
186
+ "ContentSmartz",
187
+ "Convera Internet Spider V6.x",
188
+ "ConveraCrawler/0.2",
189
+ "ConveraCrawler/0.9d (+http://www.authoritativeweb.com/crawl)",
190
+ "ConveraMultiMediaCrawler/0.1 (+http://www.authoritativeweb.com/crawl)",
191
+ "CoolBot",
192
+ "cosmos/0.8_(robot@xyleme.com)",
193
+ "cosmos/0.9_(robot@xyleme.com)",
194
+ "CougarSearch/0.x (+http://www.cougarsearch.com/faq.shtml)",
195
+ "Covac TexAs Arachbot",
196
+ "Cowbot-0.1 (NHN Corp. / +82-2-3011-1954 / nhnbot@naver.com)",
197
+ "Cowbot-0.1.x (NHN Corp. / +82-2-3011-1954 / nhnbot@naver.com)",
198
+ "CrawlConvera0.1 (CrawlConvera@yahoo.com)",
199
+ "Crawler (cometsearch@cometsystems.com)",
200
+ "Crawler admin@crawler.de",
201
+ "Crawler V 0.2.x admin@crawler.de",
202
+ "crawler@alexa.com",
203
+ "CrawlerBoy Pinpoint.com",
204
+ "Crawllybot/0.1 (Crawllybot; +http://www.crawlly.com; crawler@crawlly.com)",
205
+ "CreativeCommons/0.06-dev (Nutch; http://www.nutch.org/docs/en/bot.html; nutch-agent@lists.sourceforge.net)",
206
+ "CrocCrawler vx.3 [en] (http://www.croccrawler.com) (X11; I; Linux 2.0.44 i686)",
207
+ "csci_b659/0.13",
208
+ "Cuasarbot/0.9b http://www.cuasar.com/spider_beta/ ",
209
+ "CurryGuide SiteScan 1.1",
210
+ "Custom Spider www.bisnisseek.com /1.0",
211
+ "CyberPatrol SiteCat Webbot (http://www.cyberpatrol.com/cyberpatrolcrawler.asp)",
212
+ "CydralSpider/1.x (Cydral Web Image Search; http://www.cydral.com)",
213
+ "CydralSpider/3.0 (Cydral Image Search; http://www.cydral.com)",
214
+ "DataCha0s/2.0",
215
+ "DataCha0s/2.0",
216
+ "DataFountains/DMOZ Downloader",
217
+ "DataFountains/Dmoz Downloader (http://ivia.ucr.edu/useragents.shtml)",
218
+ "DataFountains/DMOZ Feature Vector Corpus Creator (http://ivia.ucr.edu/useragents.shtml)",
219
+ "DataparkSearch/4.47 (+http://dataparksearch.org/bot)",
220
+ "DataparkSearch/4.xx (http://www.dataparksearch.org/)",
221
+ "DataSpear/1.0 (Spider; http://www.dataspear.com/spider.html; spider@dataspear.com)",
222
+ "DataSpearSpiderBot/0.2 (DataSpear Spider Bot; http://dssb.dataspear.com/bot.html; dssb@dataspear.com)",
223
+ "DatenBot( http://www.sicher-durchs-netz.de/bot.html)",
224
+ "DaviesBot/1.7 (www.wholeweb.net)",
225
+ "daypopbot/0.x",
226
+ "dbDig(http://www.prairielandconsulting.com)",
227
+ "DBrowse 1.4b",
228
+ "DBrowse 1.4d",
229
+ "dCSbot/1.1",
230
+ "de.searchengine.comBot 1.2 (http://de.searchengine.com/spider)",
231
+ "deepak-USC/ISI",
232
+ "DeepIndex",
233
+ "DeepIndex ( http://www.zetbot.com )",
234
+ "DeepIndex (www.en.deepindex.com)",
235
+ "DeepIndexer.ca",
236
+ "Demo Bot DOT 16b",
237
+ "Demo Bot Z 16b",
238
+ "Denmex websearch (http://search.denmex.com)",
239
+ "dev-spider2.searchpsider.com/1.3b",
240
+ "DiaGem/1.1 (http://www.skyrocket.gr.jp/diagem.html)",
241
+ "Diamond/x.0",
242
+ "DiamondBot",
243
+ "Digger/1.0 JDK/1.3.0rc3",
244
+ "DigOut4U",
245
+ "DIIbot/1.2",
246
+ "disco/Nutch-0.9 (experimental crawler; www.discoveryengine.com; disco-crawl@discoveryengine.com)",
247
+ "disco/Nutch-1.0-dev (experimental crawler; www.discoveryengine.com; disco-crawl@discoveryengine.com)",
248
+ "DittoSpyder",
249
+ "dloader(NaverRobot)/1.0",
250
+ "DoCoMo/1.0/Nxxxi/c10",
251
+ "DoCoMo/1.0/Nxxxi/c10/TB",
252
+ "DoCoMo/2.0 P900iV(c100;TB;W24H11) ",
253
+ "DoCoMo/2.0 SH902i (compatible; Y!J-SRD/1.0; http://help.yahoo.co.jp/help/jp/search/indexing/indexing-27.html)",
254
+ "DoCoMo/2.0/SO502i (compatible; Y!J-SRD/1.0; http://help.yahoo.co.jp/help/jp/search/indexing/indexing-27.html)",
255
+ "dodgebot/experimental",
256
+ "Download-Tipp Linkcheck (http://download-tipp.de/)",
257
+ "Drecombot/1.0 (http://career.drecom.jp/bot.html)",
258
+ "DSurf15a 01",
259
+ "DSurf15a 71",
260
+ "DSurf15a 81",
261
+ "DSurf15a VA",
262
+ "dtSearchSpider",
263
+ "DuckDuckBot/1.0; (+http://duckduckgo.com/duckduckbot.html)",
264
+ "Dumbot(version 0.1 beta - dumbfind.com)",
265
+ "Dumbot(version 0.1 beta - http://www.dumbfind.com/dumbot.html)",
266
+ "Dumbot(version 0.1 beta)",
267
+ "e-sense 1.0 ea(www.vigiltech.com/esensedisclaim.html)",
268
+ "e-SocietyRobot(http://www.yama.info.waseda.ac.jp/~yamana/es/)",
269
+ "eApolloBot/2.0 (compatible; heritrix/2.0.0-SNAPSHOT-20071024.170148 +http://www.eapollo-opto.com)",
270
+ "EARTHCOM.info/1.x [www.earthcom.info]",
271
+ "EARTHCOM.info/1.xbeta [www.earthcom.info]",
272
+ "EasyDL/3.xx",
273
+ "EasyDL/3.xx http://keywen.com/Encyclopedia/Bot",
274
+ "EBrowse 1.4b",
275
+ "EchO!/2.0",
276
+ "Educate Search VxB",
277
+ "egothor/3.0a (+http://www.xdefine.org/robot.html)",
278
+ "EgotoBot/4.8 (+http://www.egoto.com/about.htm)",
279
+ "ejupiter.com",
280
+ "elfbot/1.0 (+http://www.uchoose.de/crawler/elfbot/)",
281
+ "ELI/20070402:2.0 (DAUM RSS Robot, Daum Communications Corp.; +http://ws.daum.net/aboutkr.html)",
282
+ "EmailSiphon",
283
+ "EmailSpider",
284
+ "EmailWolf 1.00",
285
+ "EMPAS_ROBOT",
286
+ "EnaBot/1.x (http://www.enaball.com/crawler.html)",
287
+ "Enfish Tracker",
288
+ "Enterprise_Search/1.0",
289
+ "Enterprise_Search/1.0.xxx",
290
+ "Enterprise_Search/1.00.xxx;MSSQL (http://www.innerprise.net/es-spider.asp)",
291
+ "envolk/1.7 (+http://www.envolk.com/envolkspiderinfo.php)",
292
+ "envolk[ITS]spider/1.6(+http://www.envolk.com/envolkspider.html)",
293
+ "EroCrawler",
294
+ "ES.NET_Crawler/2.0 (http://search.innerprise.net/)",
295
+ "eseek-larbin_2.6.2 (crawler@exactseek.com)",
296
+ "ESISmartSpider",
297
+ "eStyleSearch 4 (compatible; MSIE 6.0; Windows NT 5.0)",
298
+ "ESurf15a 15",
299
+ "EuripBot/0.x (+http://www.eurip.com) GetFile",
300
+ "EuripBot/0.x (+http://www.eurip.com) GetRobots",
301
+ "EuripBot/0.x (+http://www.eurip.com) PreCheck",
302
+ "Eurobot/1.0 (http://www.ayell.eu)",
303
+ "EvaalSE - bot@evaal.com",
304
+ "eventax/1.3 (eventax; http://www.eventax.de/; info@eventax.de)",
305
+ "Everest-Vulcan Inc./0.1 (R&D project; host=e-1-24; http://everest.vulcan.com/crawlerhelp)",
306
+ "Everest-Vulcan Inc./0.1 (R&D project; http://everest.vulcan.com/crawlerhelp)",
307
+ "Exabot-Images/1.0",
308
+ "Exabot-Test/1.0",
309
+ "Exabot/2.0",
310
+ "Exabot/3.0",
311
+ "ExactSeek Crawler/0.1",
312
+ "exactseek-crawler-2.63 (crawler@exactseek.com)",
313
+ "exactseek-pagereaper-2.63 (crawler@exactseek.com)",
314
+ "exactseek.com",
315
+ "Exalead NG/MimeLive Client (convert/http/0.120)",
316
+ "Excalibur Internet Spider V6.5.4",
317
+ "Execrawl/1.0 (Execrawl; http://www.execrawl.com/; bot@execrawl.com)",
318
+ "exooba crawler/exooba crawler (crawler for exooba.com; http://www.exooba.com/; info at exooba dot com)",
319
+ "exooba/exooba crawler (exooba; exooba)",
320
+ "ExperimentalHenrytheMiragoRobot",
321
+ "ExtractorPro",
322
+ "EyeCatcher (Download-tipp.de)/1.0",
323
+ "Factbot 1.09 (see http://www.factbites.com/webmasters.php)",
324
+ "factbot : http://www.factbites.com/robots",
325
+ "Fast Crawler Gold Edition",
326
+ "FAST Enterprise Crawler 6 (Experimental)",
327
+ "FAST Enterprise Crawler 6 / Scirus scirus-crawler@fast.no; http://www.scirus.com/srsapp/contactus/",
328
+ "FAST Enterprise Crawler 6 used by Cobra Development (admin@fastsearch.com)",
329
+ "FAST Enterprise Crawler 6 used by Comperio AS (sts@comperio.no)",
330
+ "FAST Enterprise Crawler 6 used by FAST (FAST)",
331
+ "FAST Enterprise Crawler 6 used by Pages Jaunes (pvincent@pagesjaunes.fr)",
332
+ "FAST Enterprise Crawler 6 used by Sensis.com.au Web Crawler (search_comments\\at\\sensis\\dot\\com\\dot\\au)",
333
+ "FAST Enterprise Crawler 6 used by Singapore Press Holdings (crawler@sphsearch.sg)",
334
+ "FAST Enterprise Crawler/6 (www.fastsearch.com)",
335
+ "FAST Enterprise Crawler/6.4 (helpdesk at fast.no)",
336
+ "FAST FirstPage retriever (compatible; MSIE 5.5; Mozilla/4.0)",
337
+ "FAST MetaWeb Crawler (helpdesk at fastsearch dot com)",
338
+ "Fast PartnerSite Crawler",
339
+ "FAST-WebCrawler/2.2.10 (Multimedia Search) (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)",
340
+ "FAST-WebCrawler/2.2.6 (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)",
341
+ "FAST-WebCrawler/2.2.7 (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)http://www.fast.no",
342
+ "FAST-WebCrawler/2.2.8 (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)http://www.fast.no",
343
+ "FAST-WebCrawler/3.2 test",
344
+ "FAST-WebCrawler/3.3 (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)",
345
+ "FAST-WebCrawler/3.4/Nirvana (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)",
346
+ "FAST-WebCrawler/3.4/PartnerSite (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)",
347
+ "FAST-WebCrawler/3.5 (atw-crawler at fast dot no; http://fast.no/support.php?c=faqs/crawler)",
348
+ "FAST-WebCrawler/3.6 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)",
349
+ "FAST-WebCrawler/3.6/FirstPage (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)",
350
+ "FAST-WebCrawler/3.7 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)",
351
+ "FAST-WebCrawler/3.7/FirstPage (atw-crawler at fast dot no;http://fast.no/support/crawler.asp)",
352
+ "FAST-WebCrawler/3.8 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)",
353
+ "FAST-WebCrawler/3.8/Fresh (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)",
354
+ "FAST-WebCrawler/3.x Multimedia",
355
+ "FAST-WebCrawler/3.x Multimedia (mm dash crawler at fast dot no)",
356
+ "fastbot crawler beta 2.0 (+http://www.fastbot.de)",
357
+ "FastBug http://www.ay-up.com",
358
+ "FastCrawler 3.0.1 (crawler@1klik.dk)",
359
+ "FastSearch Web Crawler for Verizon SuperPages (kevin.watters@fastsearch.com)",
360
+ "Favcollector/2.0 (info@favcollector.com http://www.favcollector.com/)",
361
+ "favo.eu crawler/0.6 (http://www.favo.eu)",
362
+ "Faxobot/1.0",
363
+ "Feed Seeker Bot (RSS Feed Seeker http://www.MyNewFavoriteThing.com/fsb.php)",
364
+ "Feed24.com",
365
+ "FeedChecker/0.01",
366
+ "Feedfetcher-Google; (+http://www.google.com/feedfetcher.html)",
367
+ "FeedHub FeedDiscovery/1.0 (http://www.feedhub.com)",
368
+ "FeedHub MetaDataFetcher/1.0 (http://www.feedhub.com)",
369
+ "Feedjit Favicon Crawler 1.0",
370
+ "Feedster Crawler/3.0; Feedster, Inc.",
371
+ "Felix - Mixcat Crawler (+http://mixcat.com)",
372
+ "FFC Trap Door Spider",
373
+ "Filtrbox/1.0",
374
+ "Findexa Crawler (http://www.findexa.no/gulesider/article26548.ece)",
375
+ "findlinks/x.xxx (+http://wortschatz.uni-leipzig.de/findlinks/) ",
376
+ "FineBot",
377
+ "Firefly/1.0",
378
+ "Firefly/1.0 (compatible; Mozilla 4.0; MSIE 5.5)",
379
+ "Firefox (kastaneta03@hotmail.com)",
380
+ "Firefox_1.0.6 (kasparek@naparek.cz)",
381
+ "FirstGov.gov Search - POC:firstgov.webmasters@gsa.gov",
382
+ "firstsbot",
383
+ "Flapbot/0.7.2 (Flaptor Crawler; http://www.flaptor.com; crawler at flaptor period com)",
384
+ "Flexum spider",
385
+ "Flexum/2.0",
386
+ "FlickBot 2.0 RPT-HTTPClient/0.3-3",
387
+ "flunky",
388
+ "FnooleBot/2.5.2 (+http://www.fnoole.com/addurl.html)",
389
+ "FocusedSampler/1.0",
390
+ "Folkd.com Spider/0.1 beta 1 (www.folkd.com)",
391
+ "Fooky.com/ScorpionBot/ScoutOut; http://www.fooky.com/scorpionbots",
392
+ "Francis/1.0 (francis@neomo.de http://www.neomo.de/)",
393
+ "Franklin Locator 1.8",
394
+ "FreeFind.com-SiteSearchEngine/1.0 (http://freefind.com; spiderinfo@freefind.com)",
395
+ "FreshNotes crawler< report problems to crawler-at-freshnotes-dot-com",
396
+ "FSurf15a 01",
397
+ "FTB-Bot http://www.findthebest.co.uk/",
398
+ "Full Web Bot 0416B",
399
+ "Full Web Bot 0516B",
400
+ "Full Web Bot 2816B",
401
+ "FuseBulb.Com",
402
+ "FyberSpider (+http://www.fybersearch.com/fyberspider.php)",
403
+ "GAIS Robot/1.0B2",
404
+ "Gaisbot/3.0 (indexer@gais.cs.ccu.edu.tw; http://gais.cs.ccu.edu.tw/robot.php)",
405
+ "Gaisbot/3.0+(robot06@gais.cs.ccu.edu.tw;+http://gais.cs.ccu.edu.tw/robot.php)",
406
+ "GalaxyBot/1.0 (http://www.galaxy.com/galaxybot.html)",
407
+ "Gallent Search Spider v1.4 Robot 2 (http://robot.GallentSearch.com)",
408
+ "gamekitbot/1.0 (+http://www.uchoose.de/crawler/gamekitbot/)",
409
+ "GammaSpider/1.0",
410
+ "gazz/x.x (gazz@nttrd.com)",
411
+ "generic_crawler/01.0217/",
412
+ "genieBot (http://64.5.245.11/faq/faq.html)",
413
+ "geniebot wgao@genieknows.com",
414
+ "GeonaBot 1.x; http://www.geona.com/",
415
+ "gigabaz/3.1x (baz@gigabaz.com; http://gigabaz.com/gigabaz/)",
416
+ "Gigabot/2.0 (gigablast.com)",
417
+ "Gigabot/2.0/gigablast.com/spider.html",
418
+ "Gigabot/2.0; http://www.gigablast.com/spider.html",
419
+ "Gigabot/2.0att",
420
+ "Gigabot/3.0 (http://www.gigablast.com/spider.html)",
421
+ "Gigabot/x.0",
422
+ "GigabotSiteSearch/2.0 (sitesearch.gigablast.com)",
423
+ "GNODSPIDER (www.gnod.net)",
424
+ "Goblin/0.9 (http://www.goguides.org/)",
425
+ "Goblin/0.9.x (http://www.goguides.org/goblin-info.html)",
426
+ "GoForIt.com",
427
+ "GOFORITBOT ( http://www.goforit.com/about/ )",
428
+ "gonzo1[P] +http://www.suchen.de/popups/faq.jsp",
429
+ "gonzo2[P] +http://www.suchen.de/faq.html",
430
+ "Goofer/0.2",
431
+ "Googlebot-Image/1.0",
432
+ "Googlebot-Image/1.0 ( http://www.googlebot.com/bot.html)",
433
+ "Googlebot/2.1 ( http://www.google.com/bot.html)",
434
+ "Googlebot/2.1 ( http://www.googlebot.com/bot.html)",
435
+ "Googlebot/Test ( http://www.googlebot.com/bot.html)",
436
+ "GrapeFX/0.3 libwww/5.4.0",
437
+ "great-plains-web-spider/flatlandbot (Flatland Industries Web Spider; http://www.flatlandindustries.com/flatlandbot.php; jason@flatlandindustries.com)",
438
+ "GrigorBot 0.8 (http://www.grigor.biz/bot.html)",
439
+ "Gromit/1.0",
440
+ "grub crawler(http://www.grub.org)",
441
+ "grub-client",
442
+ "gsa-crawler (Enterprise; GID-01422; jplastiras@google.com)",
443
+ "gsa-crawler (Enterprise; GID-01742;gsatesting@rediffmail.com)",
444
+ "gsa-crawler (Enterprise; GIX-02057; dm@enhesa.com)",
445
+ "gsa-crawler (Enterprise; GIX-03519; cknuetter@stubhub.com)",
446
+ "gsa-crawler (Enterprise; GIX-0xxxx; enterprise-training@google.com)",
447
+ "Guestbook Auto Submitter",
448
+ "Gulliver/1.3",
449
+ "Gulper Web Bot 0.2.4 (www.ecsl.cs.sunysb.edu/~maxim/cgi-bin/Link/GulperBot)",
450
+ "Gungho/0.08004 (http://code.google.com/p/gungho-crawler/wiki/Index)",
451
+ "GurujiBot/1.0 (+http://www.guruji.com/WebmasterFAQ.html)",
452
+ "GurujiImageBot/1.0 (+http://www.guruji.com/en/WebmasterFAQ.html)",
453
+ "HappyFunBot/1.1",
454
+ "Harvest-NG/1.0.2",
455
+ "Hatena Antenna/0.4 (http://a.hatena.ne.jp/help#robot)",
456
+ "Hatena Pagetitle Agent/1.0",
457
+ "Hatena RSS/0.3 (http://r.hatena.ne.jp)",
458
+ "hbtronix.spider.2 -- http://hbtronix.de/spider.php",
459
+ "HeinrichderMiragoRobot",
460
+ "HeinrichderMiragoRobot (http://www.miragorobot.com/scripts/deinfo.asp)",
461
+ "Helix/1.x ( http://www.sitesearch.ca/helix/)",
462
+ "HenriLeRobotMirago (http://www.miragorobot.com/scripts/frinfo.asp)",
463
+ "HenrytheMiragoRobot",
464
+ "HenryTheMiragoRobot (http://www.miragorobot.com/scripts/mrinfo.asp)",
465
+ "Hi! I'm CsCrawler my homepage: http://www.kde.cs.uni-kassel.de/lehre/ss2005/googlespam/crawler.html RPT-HTTPClient/0.3-3",
466
+ "Hippias/0.9 Beta",
467
+ "HitList",
468
+ "Hitwise Spider v1.0 http://www.hitwise.com",
469
+ "holmes/3.11 (http://morfeo.centrum.cz/bot)",
470
+ "holmes/3.9 (onet.pl)",
471
+ "holmes/3.xx (OnetSzukaj/5.0; +http://szukaj.onet.pl)",
472
+ "holmes/x.x",
473
+ "HolmesBot (http://holmes.ge)",
474
+ "HomePageSearch(hpsearch.uni-trier.de)",
475
+ "Homerbot: www.homerweb.com",
476
+ "Honda-Search/0.7.2 (Nutch; http://lucene.apache.org/nutch/bot.html; search@honda-search.com)",
477
+ "HooWWWer/2.1.3 (debugging run) (+http://cosco.hiit.fi/search/hoowwwer/ | mailto:crawler-info<at>hiit.fi)",
478
+ "HooWWWer/2.1.x ( http://cosco.hiit.fi/search/hoowwwer/ | mailto:crawler-info<at>hiit.fi)",
479
+ "HPL/Nutch-0.9 -",
480
+ "htdig/3.1.6 (http://computerorgs.com)",
481
+ "htdig/3.1.6 (unconfigured@htdig.searchengine.maintainer)",
482
+ "htdig/3.1.x (root@localhost)",
483
+ "http://Ask.24x.Info/ (http://narres.it/)",
484
+ "http://hilfe.acont.de/bot.html ACONTBOT",
485
+ "http://www.almaden.ibm.com/cs/crawler",
486
+ "http://www.almaden.ibm.com/cs/crawler [rc1.wf.ibm.com]",
487
+ "http://www.almaden.ibm.com/cs/crawler [wf216]",
488
+ "http://www.istarthere.com_spider@istarthere.com",
489
+ "http://www.monogol.de",
490
+ "http://www.trendtech.dk/spider.asp)",
491
+ "i1searchbot/2.0 (i1search web crawler; http://www.i1search.com; crawler@i1search.com)",
492
+ "IAArchiver-1.0",
493
+ "iaskspider2 (iask@staff.sina.com.cn)",
494
+ "ia_archiver",
495
+ "ia_archiver-web.archive.org",
496
+ "ia_archiver/1.6",
497
+ "ICC-Crawler(Mozilla-compatible; http://kc.nict.go.jp/icc/crawl.html; icc-crawl(at)ml(dot)nict(dot)go(dot)jp)",
498
+ "ICC-Crawler(Mozilla-compatible;http://kc.nict.go.jp/icc/crawl.html;icc-crawl-contact(at)ml(dot)nict(dot)go(dot)jp)",
499
+ "iCCrawler (http://www.iccenter.net)",
500
+ "ICCrawler - ICjobs (http://www.icjobs.de/bot.htm)",
501
+ "ichiro/x.0 (http://help.goo.ne.jp/door/crawler.html)",
502
+ "ichiro/x.0 (ichiro@nttr.co.jp)",
503
+ "IconSurf/2.0 favicon finder (see http://iconsurf.com/robot.html)",
504
+ "IconSurf/2.0 favicon monitor (see http://iconsurf.com/robot.html)",
505
+ "ICRA_label_spider/x.0",
506
+ "icsbot-0.1",
507
+ "ideare - SignSite/1.x",
508
+ "iFeed.jp/2.0 (www.psychedelix.com/agents/agents.rss; 0 subscribers)",
509
+ "igdeSpyder (compatible; igde.ru; +http://igde.ru/doc/tech.html)",
510
+ "IIITBOT/1.1 (Indian Language Web Search Engine; http://webkhoj.iiit.net; pvvpr at iiit dot ac dot in)",
511
+ "ilial/Nutch-0.9 (Ilial, Inc. is a Los Angeles based Internet startup company. For more information please visit http://www.ilial.com/crawler; http://www.ilial.com/crawler; crawl@ilial.com)",
512
+ "ilial/Nutch-0.9-dev",
513
+ "IlseBot/1.x",
514
+ "IlTrovatore-Setaccio ( http://www.iltrovatore.it)",
515
+ "Iltrovatore-Setaccio/0.3-dev (Indexing; http://www.iltrovatore.it/bot.html; info@iltrovatore.it)",
516
+ "IlTrovatore-Setaccio/1.2 ( http://www.iltrovatore.it/aiuto/faq.html)",
517
+ "Iltrovatore-Setaccio/1.2 (It-bot; http://www.iltrovatore.it/bot.html; info@iltrovatore.it)",
518
+ "iltrovatore-setaccio/1.2-dev (spidering; http://www.iltrovatore.it/aiuto/.....)",
519
+ "IlTrovatore/1.2 (IlTrovatore; http://www.iltrovatore.it/bot.html; bot@iltrovatore.it)",
520
+ "ImageWalker/2.0 (www.bdbrandprotect.com)",
521
+ "IncyWincy data gatherer(webmaster@loopimprovements.com",
522
+ "IncyWincy page crawler(webmaster@loopimprovements.com",
523
+ "IncyWincy(http://www.look.com)",
524
+ "IncyWincy(http://www.loopimprovements.com/robot.html)",
525
+ "IncyWincy/2.1(loopimprovements.com/robot.html)",
526
+ "IndexTheWeb.com Crawler7",
527
+ "Industry Program 1.0.x",
528
+ "Inet library",
529
+ "info@pubblisito.com- (http://www.pubblisito.com) il Sud dei Motori di Ricerca",
530
+ "InfoFly/1.0 (http://www.versions-project.org/)",
531
+ "INFOMINE/8.0 Adders",
532
+ "INFOMINE/8.0 RemoteServices",
533
+ "INFOMINE/8.0 VLCrawler (http://infomine.ucr.edu/useragents)",
534
+ "InfoNaviRobot(F107)",
535
+ "InfoSeek Sidewinder/0.9",
536
+ "InfoSeek Sidewinder/1.0A",
537
+ "InfoSeek Sidewinder/1.1A",
538
+ "Infoseek SideWinder/1.45 (Compatible; MSIE 10.0; UNIX)",
539
+ "Infoseek SideWinder/2.0B (Linux 2.4 i686)",
540
+ "INGRID/3.0 MT (webcrawler@NOSPAMexperimental.net; http://webmaster.ilse.nl/jsp/webmaster.jsp)",
541
+ "Inktomi Search",
542
+ "InnerpriseBot/1.0 (http://www.innerprise.com/)",
543
+ "Insitor.com search and find world wide!",
544
+ "Insitornaut",
545
+ "Internet Ninja x.0",
546
+ "InternetArchive/0.8-dev(Nutch;http://lucene.apache.org/nutch/bot.html;nutch-agent@lucene.apache",
547
+ "InternetSeer.com",
548
+ "IOI/2.0 (ISC Open Index crawler; http://index.isc.org/; bot@index.isc.org)",
549
+ "IPiumBot laurion(dot)com",
550
+ "IpselonBot/0.xx-beta (Ipselon; http://www.ipselon.com; ipselonbot@ipselon.com)",
551
+ "IRLbot/1.0 ( http://irl.cs.tamu.edu/crawler)",
552
+ "IRLbot/3.0 (compatible; MSIE 6.0; http://irl.cs.tamu.edu/crawler/)",
553
+ "ISC Systems iRc Search 2.1",
554
+ "IUPUI Research Bot v 1.9a",
555
+ "IWAgent/ 1.0 - www.brandprotect.com",
556
+ "Jabot/6.x (http://odin.ingrid.org/)",
557
+ "Jabot/7.x.x (http://odin.ingrid.org/)",
558
+ "Jack",
559
+ "Jambot/0.1.x (Jambot; http://www.jambot.com/blog; crawler@jambot.com)",
560
+ "Jambot/0.2.1 (Jambot; http://www.jambot.com/blog/static.php?page=webmaster-robot; crawler@jambot.com)",
561
+ "Jayde Crawler. http://www.jayde.com",
562
+ "Jetbot/1.0",
563
+ "JobSpider_BA/1.1",
564
+ "Jyxobot/x",
565
+ "k2spider",
566
+ "KAIST AITrc Crawler",
567
+ "KakleBot - www.kakle.com/0.1 (KakleBot - www.kakle.com; http:// www.kakle.com/bot.html; support@kakle.com)",
568
+ "kalooga/kalooga-4.0-dev-datahouse (Kalooga; http://www.kalooga.com; info@kalooga.com)",
569
+ "kalooga/KaloogaBot (Kalooga; http://www.kalooga.com/info.html?page=crawler; crawler@kalooga.com)",
570
+ "Kenjin Spider",
571
+ "Kevin http://dznet.com/kevin/",
572
+ "Kevin http://websitealert.net/kevin/",
573
+ "KE_1.0/2.0 libwww/5.2.8",
574
+ "KFSW-Bot (Version: 1.01 powered by KFSW www.kfsw.de)",
575
+ "kinja-imagebot (http://www.kinja.com/)",
576
+ "kinjabot (http://www.kinja.com)",
577
+ "KIT-Fireball/2.0",
578
+ "KIT-Fireball/2.0 (compatible; Mozilla 4.0; MSIE 5.5)",
579
+ "KnowItAll(knowitall@cs.washington.edu)",
580
+ "Knowledge.com/0.x",
581
+ "Krugle/Krugle,Nutch/0.8+ (Krugle web crawler; http://www.krugle.com/crawler/info.html; webcrawler@krugle.com)",
582
+ "KSbot/1.0 (KnowledgeStorm crawler; http://www.knowledgestorm.com/resources/content/crawler/index.html; crawleradmin@knowledgestorm.com)",
583
+ "kuloko-bot/0.x",
584
+ "kulokobot www.kuloko.com kuloko@backweave.com",
585
+ "kulturarw3/0.1",
586
+ "LapozzBot/1.4 ( http://robot.lapozz.com)",
587
+ "LapozzBot/1.5 (+http://robot.lapozz.hu)",
588
+ "larbin (samualt9@bigfoot.com)",
589
+ "LARBIN-EXPERIMENTAL (efp@gmx.net)",
590
+ "larbin_2.1.1 larbin2.1.1@somewhere.com",
591
+ "larbin_2.2.0 (crawl@compete.com)",
592
+ "larbin_2.2.1_de_Viennot (Laurent.Viennot@inria.fr)",
593
+ "larbin_2.2.2 (sugayama@lab7.kuis.kyoto-u.ac.jp)",
594
+ "larbin_2.2.2_guillaume (guillaume@liafa.jussieu.fr)",
595
+ "larbin_2.6.0 (larbin2.6.0@unspecified.mail)",
596
+ "larbin_2.6.1 (larbin2.6.1@unspecified.mail)",
597
+ "larbin_2.6.2 (hamasaki@grad.nii.ac.jp)",
598
+ "larbin_2.6.2 (larbin2.6.2@unspecified.mail)",
599
+ "larbin_2.6.2 (listonATccDOTgatechDOTedu)",
600
+ "larbin_2.6.2 (pimenas@systems.tuc.gr)",
601
+ "larbin_2.6.2 (tom@lemurconsulting.com)",
602
+ "larbin_2.6.2 (vitalbox1@hotmail.com)",
603
+ "larbin_2.6.3 (ltaa_web_crawler@groupes.epfl.ch)",
604
+ "larbin_2.6.3 (wgao@genieknows.com)",
605
+ "larbin_2.6.3_for_(http://cosco.hiit.fi/search/) tsilande@hiit.fi",
606
+ "larbin_2.6_basileocaml (basile.starynkevitch@cea.fr)",
607
+ "larbin_devel (http://pauillac.inria.fr/~ailleret/prog/larbin/)",
608
+ "lawinfo-crawler/Nutch-0.9-dev (Crawler for lawinfo.com pages; http://www.lawinfo.com; webmaster@lawinfo.com)",
609
+ "LECodeChecker/3.0 libgetdoc/1.0",
610
+ "LEIA/2.90",
611
+ "LEIA/3.01pr (LEIAcrawler; [SNIP])",
612
+ "LetsCrawl.com/1.0 +http://letscrawl.com/",
613
+ "LexiBot/1.00",
614
+ "Libby_1.1/libwww-perl/5.47",
615
+ "LibertyW (+http://www.lw01.com)",
616
+ "libWeb/clsHTTP -- hiongun@kt.co.kr",
617
+ "libwww-perl/5.41",
618
+ "libwww-perl/5.45",
619
+ "libwww-perl/5.48",
620
+ "libwww-perl/5.52 FP/2.1",
621
+ "libwww-perl/5.52 FP/4.0",
622
+ "libwww-perl/5.65",
623
+ "libwww-perl/5.800",
624
+ "libwww/5.3.2",
625
+ "LijitSpider/Nutch-0.9 (Reports crawler; http://www.lijit.com/; info(a)lijit(d)com)",
626
+ "Lincoln State Web Browser",
627
+ "linkbot",
628
+ "linknzbot",
629
+ "Links 2.0 (http://gossamer-threads.com/scripts/links/)",
630
+ "Links SQL (http://gossamer-threads.com/scripts/links-sql/)",
631
+ "LinkScan/11.0beta2 UnixShareware robot from Elsop.com (used by Indiafocus/Indiainfo)",
632
+ "LinkScan/9.0g Unix",
633
+ "LinkScan/x.x Unix",
634
+ "LiveTrans/Nutch-0.9 (maintainer: cobain at iis dot sinica dot edu dot tw; http://wkd.iis.sinica.edu.tw/LiveTrans/)",
635
+ "Llaut/1.0 (http://mnm.uib.es/~gallir/llaut/bot.html)",
636
+ "LMQueueBot/0.2",
637
+ "lmspider (lmspider@scansoft.com)",
638
+ "LNSpiderguy",
639
+ "LocalBot/1.0 ( http://www.localbot.co.uk/)",
640
+ "LocalcomBot/1.2.x ( http://www.local.com/bot.htm)",
641
+ "Lockstep Spider/1.0",
642
+ "Look.com",
643
+ "Lovel as 1.0 ( +http://www.everatom.com)",
644
+ "LTI/LemurProject Nutch Spider/Nutch-1.0-dev (lti crawler for CMU; http://www.lti.cs.cmu.edu; changkuk at cmu dot edu)",
645
+ "LTI/LemurProject Nutch Spider/Nutch-1.0-dev (Research spider using Nutch; http://www.lemurproject.org; mhoy@cs.cmu.edu)",
646
+ "lwp-trivial/1.32",
647
+ "lwp-trivial/1.34",
648
+ "lwp-trivial/1.34",
649
+ "LWP::Simple/5.22",
650
+ "LWP::Simple/5.36",
651
+ "LWP::Simple/5.48",
652
+ "LWP::Simple/5.50",
653
+ "LWP::Simple/5.51",
654
+ "LWP::Simple/5.53",
655
+ "LWP::Simple/5.63",
656
+ "LWP::Simple/5.803",
657
+ "Lycos_Spider_(modspider)",
658
+ "Lycos_Spider_(T-Rex)",
659
+ "Lynx/2.8.4rel.1 libwww-FM/2.14 SSL-MM/1.4.1 OpenSSL/0.9.6c (human-guided@lerly.net)",
660
+ "Mac Finder 1.0.xx",
661
+ "Mackster( http://www.ukwizz.com )",
662
+ "Mahiti.Com/Mahiti Crawler-1.0 (Mahiti.Com; http://mahiti.com ; mahiti.com)",
663
+ "Mail.Ru/1.0",
664
+ "mailto:webcraft@bea.com",
665
+ "mammoth/1.0 ( http://www.sli-systems.com/)",
666
+ "MantraAgent",
667
+ "MapoftheInternet.com ( http://MapoftheInternet.com)",
668
+ "Mariner/5.1b [de] (Win95; I ;Kolibri gncwebbot)",
669
+ "Marketwave Hit List",
670
+ "Martini",
671
+ "MARTINI",
672
+ "Marvin v0.3",
673
+ "MaSagool/1.0 (MaSagool; http://sagool.jp/; info@sagool.jp)",
674
+ "MasterSeek",
675
+ "Mata Hari/2.00 ",
676
+ "Matrix S.p.A. - FAST Enterprise Crawler 6 (Unknown admin e-mail address)",
677
+ "maxomobot/dev-20051201 (maxomo; http://67.102.134.34:4047/MAXOMO/MAXOMObot.html; maxomobot@maxomo.com)",
678
+ "MDbot/1.0 (+http://www.megadownload.net/bot.html)",
679
+ "MediaCrawler-1.0 (Experimental)",
680
+ "Mediapartners-Google/2.1 ( http://www.googlebot.com/bot.html)",
681
+ "MediaSearch/0.1",
682
+ "MegaSheep v1.0 (www.searchuk.com internet sheep)",
683
+ "Megite2.0 (http://www.megite.com)",
684
+ "Mercator-1.x",
685
+ "Mercator-2.0",
686
+ "Mercator-Scrub-1.1",
687
+ "Metaeuro Web Crawler/0.2 (MetaEuro Web Search Clustering Engine; http://www.metaeuro.com; crawler at metaeuro dot com)",
688
+ "MetaGer-LinkChecker",
689
+ "MetagerBot/0.8-dev (MetagerBot; http://metager.de; )",
690
+ "MetaGer_PreChecker0.1",
691
+ "Metaspinner/0.01 (Metaspinner; http://www.meta-spinner.de/; support@meta-spinner.de/)",
692
+ "metatagsdir/0.7 (+http://metatagsdir.com/directory/)",
693
+ "MFC Foundation Class Library 4.0",
694
+ "MicroBaz",
695
+ "Microsoft Small Business Indexer",
696
+ "Microsoft URL Control - 6.00.8xxx",
697
+ "MicrosoftPrototypeCrawler (How's my crawling? mailto:newbiecrawler@hotmail.com)",
698
+ "Missauga Locate 1.0.0",
699
+ "Missigua Locator 1.9",
700
+ "Missouri College Browse",
701
+ "Misterbot-Nutch/0.7.1 (Misterbot-Nutch; http://www.misterbot.fr; admin@misterbot.fr)",
702
+ "Miva (AlgoFeedback@miva.com)",
703
+ "Mizzu Labs 2.2",
704
+ "MJ12bot/vx.x.x (http://majestic12.co.uk/bot.php?+)",
705
+ "MJ12bot/vx.x.x (http://www.majestic12.co.uk/projects/dsearch/mj12bot.php)",
706
+ "MJBot (SEO assessment)",
707
+ "MLBot (www.metadatalabs.com)",
708
+ "MnogoSearch/3.2.xx",
709
+ "Mo College 1.9",
710
+ "moget/x.x (moget@goo.ne.jp)",
711
+ "mogimogi/1.0",
712
+ "MojeekBot/0.x (archi; http://www.mojeek.com/bot.html)",
713
+ "Morris - Mixcat Crawler ( http://mixcat.com)",
714
+ "Mouse-House/7.4 (spider_monkey spider info at www.mobrien.com/sm.shtml)",
715
+ "mozDex/0.xx-dev (mozDex; http://www.mozdex.com/en/bot.html; spider@mozdex.com)",
716
+ "Mozilla (Mozilla@somewhere.com)",
717
+ "Mozilla 4.0(compatible; BotSeer/1.0; +http://botseer.ist.psu.edu)",
718
+ "Mozilla/2.0 (compatible; Ask Jeeves)",
719
+ "Mozilla/2.0 (compatible; Ask Jeeves/Teoma)",
720
+ "Mozilla/2.0 (compatible; Ask Jeeves/Teoma; http://about.ask.com/en/docs/about/webmasters.shtml) ",
721
+ "Mozilla/2.0 (compatible; Ask Jeeves/Teoma; http://sp.ask.com/docs/about/tech_crawling.html)",
722
+ "Mozilla/2.0 (compatible; EZResult -- Internet Search Engine)",
723
+ "Mozilla/2.0 (compatible; NEWT ActiveX; Win32)",
724
+ "Mozilla/2.0 (compatible; T-H-U-N-D-E-R-S-T-O-N-E)",
725
+ "Mozilla/3.0 (compatible; Fluffy the spider; http://www.searchhippo.com/; info@searchhippo.com)",
726
+ "Mozilla/3.0 (compatible; Indy Library)",
727
+ "Mozilla/3.0 (compatible; MuscatFerret/1.5.4; claude@euroferret.com)",
728
+ "Mozilla/3.0 (compatible; MuscatFerret/1.5; olly@muscat.co.uk)",
729
+ "Mozilla/3.0 (compatible; MuscatFerret/1.6.x; claude@euroferret.com)",
730
+ "Mozilla/3.0 (compatible; scan4mail (advanced version) http://www.peterspages.net/?scan4mail)",
731
+ "Mozilla/3.0 (compatible; ScollSpider; http://www.webwobot.com)",
732
+ "Mozilla/3.0 (compatible; Webinator-DEV01.home.iprospect.com/2.56)",
733
+ "Mozilla/3.0 (compatible; Webinator-indexer.cyberalert.com/2.56)",
734
+ "Mozilla/3.0 (INGRID/3.0 MT; webcrawler@NOSPAMexperimental.net; http://aanmelden.ilse.nl/?aanmeld_mode=webhints)",
735
+ "Mozilla/3.0 (Slurp.so/Goo; slurp@inktomi.com; http://www.inktomi.com/slurp.html)",
736
+ "Mozilla/3.0 (Slurp/cat; slurp@inktomi.com; http://www.inktomi.com/slurp.html)",
737
+ "Mozilla/3.0 (Slurp/si; slurp@inktomi.com; http://www.inktomi.com/slurp.html)",
738
+ "Mozilla/3.0 (Vagabondo/1.1 MT; webcrawler@NOSPAMwise-guys.nl; http://webagent.wise-guys.nl/)",
739
+ "Mozilla/3.0 (Vagabondo/1.x MT; webagent@wise-guys.nl; http://webagent.wise-guys.nl/)",
740
+ "Mozilla/3.0 (Vagabondo/2.0 MT; webcrawler@NOSPAMexperimental.net; http://aanmelden.ilse.nl/?aanmeld_mode=webhints)",
741
+ "Mozilla/3.0 (Vagabondo/2.0 MT; webcrawler@NOSPAMwise-guys.nl; http://webagent.wise-guys.nl/)",
742
+ "Mozilla/3.01 (Compatible; Links2Go Similarity Engine)",
743
+ "Mozilla/4.0",
744
+ "Mozilla/4.0 (agadine3.0) www.agada.de",
745
+ "Mozilla/4.0 (compatible: AstraSpider V.2.1 : astrafind.com)",
746
+ "Mozilla/4.0 (compatible; Vagabondo/2.2; webcrawler at wise-guys dot nl; http://webagent.wise-guys.nl/)",
747
+ "Mozilla/4.0 (compatible; Vagabondo/4.0Beta; webcrawler at wise-guys dot nl; http://webagent.wise-guys.nl/)",
748
+ "Mozilla/4.0 (compatible; Advanced Email Extractor v2.xx)",
749
+ "Mozilla/4.0 (compatible; B_L_I_T_Z_B_O_T)",
750
+ "Mozilla/4.0 (compatible; ChristCrawler.com ChristCrawler@ChristCENTRAL.com)",
751
+ "Mozilla/4.0 (compatible; crawlx, crawler@trd.overture.com)",
752
+ "Mozilla/4.0 (compatible; DAUMOA-video; +http://ws.daum.net/aboutkr.html)",
753
+ "Mozilla/4.0 (compatible; FastCrawler3 support-fastcrawler3@fast.no)",
754
+ "Mozilla/4.0 (compatible; FDSE robot)",
755
+ "Mozilla/4.0 (compatible; GPU p2p crawler http://gpu.sourceforge.net/search_engine.php)",
756
+ "Mozilla/4.0 (compatible; grub-client-0.2.x; Crawl your stuff with http://grub.org)",
757
+ "Mozilla/4.0 (compatible; grub-client-0.3.x; Crawl your own stuff with http://grub.org)",
758
+ "Mozilla/4.0 (compatible; grub-client-2.x)",
759
+ "Mozilla/4.0 (compatible; Iplexx Spider/1.0 http://www.iplexx.at)",
760
+ "Mozilla/4.0 (compatible; MSIE 4.01; Vonna.com b o t)",
761
+ "Mozilla/4.0 (compatible; MSIE 4.01; Windows CE; PPC; 240x320; SPV M700; OpVer 19.123.2.733) OrangeBot-Mobile 2008.0 (mobilesearch.support@orange-ftgroup.com)",
762
+ "Mozilla/4.0 (compatible; MSIE 4.0; Windows NT; Site Server 3.0 Robot) Indonesia Interactive",
763
+ "Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0) (samualt9@bigfoot.com)",
764
+ "Mozilla/4.0 (compatible; MSIE 5.0; NetNose-Crawler 2.0; A New Search Experience: http://www.netnose.com)",
765
+ "Mozilla/4.0 (compatible; MSIE 5.0; Windows 95) TrueRobot; 1.5",
766
+ "Mozilla/4.0 (compatible; MSIE 5.0; Windows 95) VoilaBot BETA 1.2 (http://www.voila.com/)",
767
+ "Mozilla/4.0 (compatible; MSIE 5.0; Windows 95) VoilaBot; 1.6",
768
+ "Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; DigExt; DTS Agent",
769
+ "Mozilla/4.0 (compatible; MSIE 5.0; www.galaxy.com; www.psychedelix.com)",
770
+ "Mozilla/4.0 (compatible; MSIE 5.0; www.galaxy.com; www.psychedelix.com/; http://www.galaxy.com/info/crawler.html)",
771
+ "Mozilla/4.0 (compatible; MSIE 5.0; YANDEX)",
772
+ "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 4.0; obot)",
773
+ "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 4.0; QXW03018)",
774
+ "Mozilla/4.0 (compatible; MSIE 6.0 compatible; Asterias Crawler v4; +http://www.singingfish.com/help/spider.html; webmaster@singingfish.com); SpiderThread Revision: 3.10",
775
+ "Mozilla/4.0 (compatible; MSIE 6.0; MSIE 5.5; Windows NT 5.1) Skampy/0.9.x [en]",
776
+ "Mozilla/4.0 (compatible; MSIE 6.0; TargetSeek/1.0; +http://www.targetgroups.net/TargetSeek.html)",
777
+ "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; ODP entries t_st; http://tuezilla.de/t_st-odp-entries-agent.html)",
778
+ "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; ODP links test; http://tuezilla.de/test-odp-links-agent.html)",
779
+ "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; ZoomSpider.net bot; .NET CLR 1.1.4322)",
780
+ "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; heritrix/1.3.0 http://www.cs.washington.edu/research/networking/websys/)",
781
+ "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; QihooBot 1.0 qihoobot@qihoo.net)",
782
+ "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT; MS Search 4.0 Robot)",
783
+ "Mozilla/4.0 (compatible; MSIE enviable; DAUMOA 2.0; DAUM Web Robot; Daum Communications Corp., Korea; +http://ws.daum.net/aboutkr.html)",
784
+ "Mozilla/4.0 (compatible; MSIE is not me; DAUMOA/1.0.1; DAUM Web Robot; Daum Communications Corp., Korea)",
785
+ "Mozilla/4.0 (compatible; NaverBot/1.0; http://help.naver.com/delete_main.asp)",
786
+ "Mozilla/4.0 (compatible; SpeedySpider; www.entireweb.com)",
787
+ "Mozilla/4.0 (compatible; www.galaxy.com)",
788
+ "Mozilla/4.0 (compatible; Y!J; for robot study; keyoshid)",
789
+ "Mozilla/4.0 (compatible; Yahoo Japan; for robot study; kasugiya)",
790
+ "Mozilla/4.0 (JemmaTheTourist;http://www.activtourist.com)",
791
+ "Mozilla/4.0 (MobilePhone SCP-5500/US/1.0) NetFront/3.0 MMP/2.0 (compatible; Googlebot/2.1; http://www.google.com/bot.html)",
792
+ "Mozilla/4.0 (MobilePhone SCP-5500/US/1.0) NetFront/3.0 MMP/2.0 FAKE (compatible; Googlebot/2.1; http://www.google.com/bot.html)",
793
+ "Mozilla/4.0 (Mozilla; http://www.mozilla.org/docs/en/bot.html; master@mozilla.com)",
794
+ "Mozilla/4.0 (Sleek Spider/1.2)",
795
+ "Mozilla/4.0 compatible FurlBot/Furl Search 2.0 (FurlBot; http://www.furl.net; wn.furlbot@looksmart.net)",
796
+ "Mozilla/4.0 compatible ZyBorg/1.0 (wn.zyborg@looksmart.net; http://www.WISEnutbot.com)",
797
+ "Mozilla/4.0 compatible ZyBorg/1.0 (ZyBorg@WISEnutbot.com; http://www.WISEnutbot.com)",
798
+ "Mozilla/4.0 compatible ZyBorg/1.0 Dead Link Checker (wn.zyborg@looksmart.net; http://www.WISEnutbot.com)",
799
+ "Mozilla/4.0 compatible ZyBorg/1.0 for Homepage (ZyBorg@WISEnutbot.com; http://www.WISEnutbot.com)",
800
+ "Mozilla/4.0 efp@gmx.net",
801
+ "Mozilla/4.0 [en] (Ask Jeeves Corporate Spider)",
802
+ "Mozilla/4.0(compatible; Zealbot 1.0)",
803
+ "Mozilla/4.04 (compatible; Dulance bot; +http://www.dulance.com/bot.jsp)",
804
+ "Mozilla/4.0_(compatible;_MSIE_5.0;_Windows_95)_TrueRobot/1.4 libwww/5.2.8",
805
+ "Mozilla/4.0_(compatible;_MSIE_5.0;_Windows_95)_VoilaBot/1.6 libwww/5.3.2",
806
+ "Mozilla/4.6 [en] (http://www.cnet.com/)",
807
+ "Mozilla/4.7",
808
+ "Mozilla/4.7 (compatible; http://eidetica.com/spider)",
809
+ "Mozilla/4.7 (compatible; Intelliseek; http://www.intelliseek.com)",
810
+ "Mozilla/4.7 (compatible; Whizbang)",
811
+ "Mozilla/4.7 (compatible; WhizBang; http://www.whizbang.com/crawler)",
812
+ "Mozilla/4.7 [en](BecomeBot@exava.com)",
813
+ "Mozilla/4.7 [en](Exabot@exava.com)",
814
+ "Mozilla/4.72 [en] (BACS http://www.ba.be)",
815
+ "Mozilla/5.0",
816
+ "Mozilla/5.0 (+http://www.eurekster.com/mammoth) Mammoth/0.1",
817
+ "Mozilla/5.0 (+http://www.sli-systems.com/) Mammoth/0.1",
818
+ "Mozilla/5.0 (Clustered-Search-Bot/1.0; support@clush.com; http://www.clush.com/)",
819
+ "Mozilla/5.0 (compatible; +http://www.evri.com/evrinid)",
820
+ "Mozilla/5.0 (compatible; 008/0.83; http://www.80legs.com/spider.html;) Gecko/2008032620",
821
+ "Mozilla/5.0 (compatible; Abonti/0.8 - http://www.abonti.com)",
822
+ "Mozilla/5.0 (compatible; aiHitBot/1.0; +http://www.aihit.com/)",
823
+ "Mozilla/5.0 (compatible; AnsearchBot/1.x; +http://www.ansearch.com.au/)",
824
+ "Mozilla/5.0 (compatible; archive.org_bot/1.10.0 +http://www.loc.gov/minerva/crawl.html)",
825
+ "Mozilla/5.0 (compatible; archive.org_bot/1.13.1x http://crawler.archive.org)",
826
+ "Mozilla/5.0 (compatible; archive.org_bot/1.5.0-200506132127 http://crawler.archive.org) Hurricane Katrina",
827
+ "Mozilla/5.0 (compatible; Ask Jeeves/Teoma; http://about.ask.com/en/docs/about/webmasters.shtml)",
828
+ "Mozilla/5.0 (compatible; BecomeBot/1.23; http://www.become.com/webmasters.html)",
829
+ "Mozilla/5.0 (compatible; BecomeBot/1.xx; MSIE 6.0 compatible; http://www.become.com/webmasters.html)",
830
+ "Mozilla/5.0 (compatible; BecomeBot/2.0beta; http://www.become.com/webmasters.html)",
831
+ "Mozilla/5.0 (compatible; BecomeBot/2.x; MSIE 6.0 compatible; http://www.become.com/site_owners.html)",
832
+ "Mozilla/5.0 (compatible; BecomeJPBot/2.3; MSIE 6.0 compatible; +http://www.become.co.jp/site_owners.html)",
833
+ "Mozilla/5.0 (compatible; BlogRefsBot/0.1; http://www.blogrefs.com/about/bloggers)",
834
+ "Mozilla/5.0 (compatible; Bot; +http://pressemitteilung.ws/spamfilter",
835
+ "Mozilla/5.0 (compatible; BuzzRankingBot/1.0; +http://www.buzzrankingbot.com/)",
836
+ "Mozilla/5.0 (compatible; Charlotte/1.0b; charlotte@betaspider.com)",
837
+ "Mozilla/5.0 (compatible; Charlotte/1.0b; http://www.searchme.com/support/)",
838
+ "Mozilla/5.0 (compatible; Crawling jpeg; http://www.yama.info.waseda.ac.jp)",
839
+ "Mozilla/5.0 (compatible; de/1.13.2 +http://www.de.com)",
840
+ "Mozilla/5.0 (compatible; Diffbot/0.1; +http://www.diffbot.com)",
841
+ "Mozilla/5.0 (compatible; DNS-Digger-Explorer/1.0; +http://www.dnsdigger.com)",
842
+ "Mozilla/5.0 (compatible; DNS-Digger/1.0; +http://www.dnsdigger.com)",
843
+ "Mozilla/5.0 (compatible; EARTHCOM.info/2.01; http://www.earthcom.info)",
844
+ "Mozilla/5.0 (compatible; EARTHCOM/2.2; +http://enter4u.eu)",
845
+ "Mozilla/5.0 (compatible; Exabot Test/3.0; +http://www.exabot.com/go/robot)",
846
+ "Mozilla/5.0 (compatible; FatBot 2.0; http://www.thefind.com/main/CrawlerFAQs.fhtml)",
847
+ "Mozilla/5.0 (compatible; Galbot/1.0; +http://www.galbot.com/bot.html)",
848
+ "mozilla/5.0 (compatible; genevabot http://www.healthdash.com)",
849
+ "Mozilla/5.0 (compatible; Googlebot/2.1; http://www.google.com/bot.html)",
850
+ "mozilla/5.0 (compatible; heritrix/1.0.4 http://innovationblog.com)",
851
+ "Mozilla/5.0 (compatible; heritrix/1.10.2 +http://i.stanford.edu/)",
852
+ "Mozilla/5.0 (compatible; heritrix/1.12.1 +http://newstin.com/)",
853
+ "Mozilla/5.0 (compatible; heritrix/1.12.1 +http://www.page-store.com)",
854
+ "Mozilla/5.0 (compatible; heritrix/1.12.1 +http://www.page-store.com) [email:paul@page-store.com]",
855
+ "mozilla/5.0 (compatible; heritrix/1.3.0 http://archive.crawler.org)",
856
+ "Mozilla/5.0 (compatible; heritrix/1.4.0 +http://www.chepi.net)",
857
+ "Mozilla/5.0 (compatible; heritrix/1.4t http://www.truveo.com/)",
858
+ "Mozilla/5.0 (compatible; heritrix/1.5.0 http://www.l3s.de/~kohlschuetter/projects/crawling/)",
859
+ "Mozilla/5.0 (compatible; heritrix/1.5.0-200506231921 http://pandora.nla.gov.au/crawl.html)",
860
+ "Mozilla/5.0 (compatible; heritrix/1.6.0 http://www.worio.com/)",
861
+ "Mozilla/5.0 (compatible; heritrix/1.7.0 +http://www.greaterera.com/)",
862
+ "Mozilla/5.0 (compatible; heritrix/1.x.x +http://www.accelobot.com)",
863
+ "Mozilla/5.0 (compatible; heritrix/2.0.0-RC1 +http://www.aol.com)",
864
+ "Mozilla/5.0 (compatible; Hermit Search. Com; +http://www.hermitsearch.com)",
865
+ "Mozilla/5.0 (compatible; HyperixScoop/1.3; +http://www.hyperix.com)",
866
+ "Mozilla/5.0 (compatible; IDBot/1.0; +http://www.id-search.org/bot.html)",
867
+ "Mozilla/5.0 (compatible; InterseekWeb/3.x)",
868
+ "Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Exabot-Thumbnails)",
869
+ "Mozilla/5.0 (compatible; LemSpider 0.1)",
870
+ "Mozilla/5.0 (compatible; MojeekBot/2.0; http://www.mojeek.com/bot.html)",
871
+ "Mozilla/5.0 (compatible; MSIE 6.0; Podtech Network; crawler_admin@podtech.net)",
872
+ "Mozilla/5.0 (compatible; OnetSzukaj/5.0; http://szukaj.onet.pl)",
873
+ "Mozilla/5.0 (compatible; PalmeraBot; http://www.links24h.com/help/palmera) Version 0.001",
874
+ "Mozilla/5.0 (compatible; pogodak.ba/3.x)",
875
+ "Mozilla/5.0 (compatible; Pogodak.hr/3.1)",
876
+ "Mozilla/5.0 (compatible; PWeBot/3.1; http://www.programacionweb.net/robot.php)",
877
+ "Mozilla/5.0 (compatible; Quantcastbot/1.0; www.quantcast.com)",
878
+ "Mozilla/5.0 (compatible; ScoutJet; +http://www.scoutjet.com/)",
879
+ "Mozilla/5.0 (compatible; Scrubby/2.2; http://www.scrubtheweb.com/)",
880
+ "Mozilla/5.0 (compatible; ShunixBot/1.x.x +http://www.shunix.com/robot.htm)",
881
+ "Mozilla/5.0 (compatible; ShunixBot/1.x; http://www.shunix.com/bot.htm)",
882
+ "Mozilla/5.0 (compatible; SkreemRBot +http://skreemr.com)",
883
+ "Mozilla/5.0 (compatible; SummizeBot +http://www.summize.com)",
884
+ "Mozilla/5.0 (compatible; Synoobot/0.9; http://www.synoo.com/search/bot.html)",
885
+ "Mozilla/5.0 (compatible; Theophrastus/x.x; http://users.cs.cf.ac.uk/N.A.Smith/theophrastus.php)",
886
+ "Mozilla/5.0 (compatible; TridentSpider/3.1)",
887
+ "Mozilla/5.0 (compatible; Vagabondo/2.1; webcrawler at wise-guys dot nl; http://webagent.wise-guys.nl/)",
888
+ "Mozilla/5.0 (compatible; Webduniabot/1.0; +http://search.webdunia.com/bot.aspx)",
889
+ "Mozilla/5.0 (compatible; worio bot heritrix/1.10.0 +http://worio.com)",
890
+ "Mozilla/5.0 (compatible; WoW Lemmings Kathune/2.0;http://www.wowlemmings.com/kathune.html)",
891
+ "Mozilla/5.0 (compatible; Yahoo! DE Slurp; http://help.yahoo.com/help/us/ysearch/slurp)",
892
+ "Mozilla/5.0 (compatible; Yahoo! Slurp China; http://misc.yahoo.com.cn/help.html)",
893
+ "Mozilla/5.0 (compatible; Yahoo! Slurp; http://help.yahoo.com/help/us/ysearch/slurp)",
894
+ "Mozilla/5.0 (compatible; Yoono; http://www.yoono.com/)",
895
+ "Mozilla/5.0 (compatible; YoudaoBot/1.0; http://www.youdao.com/help/webmaster/spider/; )",
896
+ "Mozilla/5.0 (compatible; Zenbot/1.3; +http://zen.co.za/webmasters/)",
897
+ "Mozilla/5.0 (compatible; zermelo +http://www.powerset.com) [email:paul@page-store.com,crawl@powerset.com]",
898
+ "Mozilla/5.0 (compatible;archive.org_bot/1.7.1; collectionId=316; Archive-It; +http://www.archive-it.org)",
899
+ "Mozilla/5.0 (compatible;archive.org_bot/heritrix-1.9.0-200608171144 +http://pandora.nla.gov.au/crawl.html)",
900
+ "Mozilla/5.0 (compatible;MAINSEEK_BOT)",
901
+ "Mozilla/5.0 (Slurp/cat; slurp@inktomi.com; http://www.inktomi.com/slurp.html)",
902
+ "Mozilla/5.0 (Slurp/si; slurp@inktomi.com; http://www.inktomi.com/slurp.html)",
903
+ "Mozilla/5.0 (Twiceler-0.9 http://www.cuill.com/twiceler/robot.html)",
904
+ "Mozilla/5.0 (Version: xxxx Type:xx)",
905
+ "Mozilla/5.0 (wgao@genieknows.com)",
906
+ "Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.7.7) NimbleCrawler 1.11 obeys UserAgent NimbleCrawler For problems contact: crawler_at_dataalchemy.com",
907
+ "Mozilla/5.0 (Windows; U; Windows NT 5.1; fr; rv:1.8.1) VoilaBot BETA 1.2 (support.voilabot@orange-ftgroup.com)",
908
+ "Mozilla/5.0 (Windows; U; Windows NT 5.1; fr; rv:1.8.1) VoilaBot BETA 1.2 (support.voilabot@orange-ftgroup.com)",
909
+ "Mozilla/5.0 (Windows;) NimbleCrawler 1.12 obeys UserAgent NimbleCrawler For problems contact: crawler@health",
910
+ "Mozilla/5.0 (Windows;) NimbleCrawler 1.12 obeys UserAgent NimbleCrawler For problems contact: crawler@healthline.com",
911
+ "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2.1; aggregator:Spinn3r (Spinn3r 3.1); http://spinn3r.com/robot) Gecko/20021130",
912
+ "Mozilla/5.0 URL-Spider",
913
+ "Mozilla/5.0 usww.com-Spider-for-w8.net",
914
+ "Mozilla/5.0 wgao@genieknows.com",
915
+ "Mozilla/5.0 [en] (compatible; Gulper Web Bot 0.2.4 www.ecsl.cs.sunysb.edu/~maxim/cgi-bin/Link/GulperBot)",
916
+ "MQbot metaquerier.cs.uiuc.edu/crawler",
917
+ "MQBOT/Nutch-0.9-dev (MQBOT Nutch Crawler; http://falcon.cs.uiuc.edu; mqbot@cs.uiuc.edu)",
918
+ "msnbot-media/1.0 (+http://search.msn.com/msnbot.htm)",
919
+ "msnbot-Products/1.0 (+http://search.msn.com/msnbot.htm)",
920
+ "MSNBOT/0.xx (http://search.msn.com/msnbot.htm)",
921
+ "msnbot/x.xx ( http://search.msn.com/msnbot.htm)",
922
+ "MSNBOT_Mobile MSMOBOT Mozilla/2.0 (compatible; MSIE 4.02; Windows CE; Default)",
923
+ "MSNPTC/1.0",
924
+ "MSRBOT (http://research.microsoft.com/research/sv/msrbot)",
925
+ "multicrawler ( http://sw.deri.org/2006/04/multicrawler/robots.html)",
926
+ "MultiText/0.1",
927
+ "MusicWalker2.0 ( http://www.somusical.com)",
928
+ "MVAClient",
929
+ "Mylinea.com Crawler 2.0",
930
+ "Naamah 1.0.1/Blogbot (http://blogbot.de/)",
931
+ "Naamah 1.0a/Blogbot (http://blogbot.de/)",
932
+ "NABOT/5.0",
933
+ "nabot_1.0",
934
+ "NameOfAgent (CMS Spider)",
935
+ "NASA Search 1.0",
936
+ "NationalDirectory-WebSpider/1.3",
937
+ "NationalDirectoryAddURL/1.0",
938
+ "NaverBot-1.0 (NHN Corp. / +82-2-3011-1954 / nhnbot@naver.com)",
939
+ "NaverBot_dloader/1.5",
940
+ "NavissoBot",
941
+ "NavissoBot/1.7 (+http://navisso.com/)",
942
+ "NCSA Beta 1 (http://vias.ncsa.uiuc.edu/viasarchivinginformation.html)",
943
+ "Nebullabot/2.2 (http://bot.nebulla.info)",
944
+ "NEC Research Agent -- compuman at research.nj.nec.com",
945
+ "Net-Seekr Bot/Net-Seekr Bot V1 (http://www.net-seekr.com)",
946
+ "NetinfoBot/1.0 (http://netinfo.bg/netinfobot.html)",
947
+ "NetLookout/2.24",
948
+ "Netluchs/0.8-dev ( ; http://www.netluchs.de/; ___don't___spam_me_@netluchs.de)",
949
+ "NetNoseCrawler/v1.0",
950
+ "Netprospector JavaCrawler",
951
+ "NetResearchServer(http://www.look.com)",
952
+ "NetResearchServer/x.x(loopimprovements.com/robot.html)",
953
+ "NetSeer/Nutch-0.9 (NetSeer Crawler; http://www.netseer.com; crawler@netseer.com)",
954
+ "NetSprint -- 2.0",
955
+ "NetWhatCrawler/0.06-dev (NetWhatCrawler from NetWhat.com; http://www.netwhat.com; support@netwhat.com)",
956
+ "NetZippy",
957
+ "NextGenSearchBot 1 (for information visit http://www.eliyon.com/NextGenSearchBot)",
958
+ "NextopiaBOT (+http://www.nextopia.com) distributed crawler client beta v0.x",
959
+ "NG-Search/0.90 (NG-SearchBot; http://www.ng-search.com; )",
960
+ "NG/1.0",
961
+ "NG/4.0.1229",
962
+ "NITLE Blog Spider/0.01",
963
+ "Noago Spider",
964
+ "Nokia-WAPToolkit/1.2 googlebot(at)googlebot.com",
965
+ "Nokia6610/1.0 (3.09) Profile/MIDP-1.0 Configuration/CLDC-1.0 (compatible;YahooSeeker/M1A1-R2D2; http://help.yahoo.com/help/us/ysearch/crawling/crawling-01.html)",
966
+ "NokodoBot/1.x (+http://nokodo.com/bot.htm)",
967
+ "Norbert the Spider(Burf.com)",
968
+ "noxtrumbot/1.0 (crawler@noxtrum.com)",
969
+ "noyona_0_1",
970
+ "NP/0.1 (NP; http://www.nameprotect.com; npbot@nameprotect.com)",
971
+ "NPBot (http://www.nameprotect.com/botinfo.html)",
972
+ "NPBot-1/2.0",
973
+ "Nsauditor/1.x",
974
+ "nsyght.com/Nutch-1.0-dev (nsyght.com; Nsyght.com)",
975
+ "nsyght.com/Nutch-x.x (nsyght.com; search.nsyght.com)",
976
+ "nttdirectory_robot/0.9 (super-robot@super.navi.ocn.ne.jp)",
977
+ "nuSearch Spider <a href='http://www.nusearch.com'>www.nusearch.com</a> (compatible; MSIE 4.01)",
978
+ "NuSearch Spider (compatible; MSIE 6.0)",
979
+ "NuSearch Spider www.nusearch.com",
980
+ "Nutch",
981
+ "Nutch crawler/Nutch-0.9 (picapage.com; admin@picapage.com)",
982
+ "Nutch/Nutch-0.9 (Eurobot; http://www.ayell.eu )",
983
+ "NutchCVS/0.0x-dev (Nutch; http://www.nutch.org/docs/bot.html; nutch-agent@lists.sourceforge.net)",
984
+ "NutchCVS/0.7.1 (Nutch running at UW; http://www.nutch.org/docs/en/bot.html; sycrawl@cs.washington.edu)",
985
+ "NutchEC2Test/Nutch-0.9-dev (Testing Nutch on Amazon EC2.; http://lucene.apache.org/nutch/bot.html; ec2test at lucene.com)",
986
+ "NutchOrg/0.0x-dev (Nutch; http://www.nutch.org/docs/bot.html; nutch-agent@lists.sourceforge.net)",
987
+ "nutchsearch/Nutch-0.9 (Nutch Search 1.0; herceg_novi at yahoo dot com)",
988
+ "NutchVinegarCrawl/Nutch-0.8.1 (Vinegar; http://www.cs.washington.edu; eytanadar at gmail dot com)",
989
+ "obidos-bot (just looking for books.)",
990
+ "ObjectsSearch/0.01-dev (ObjectsSearch;http://www.ObjectsSearch.com/bot.html; support@thesoftwareobjects.com)",
991
+ "ObjectsSearch/0.0x (ObjectsSearch; http://www.ObjectsSearch.com/bot.html; support@thesoftwareobjects.com)",
992
+ "oBot ((compatible;Win32))",
993
+ "Ocelli/1.x (http://www.globalspec.com/Ocelli)",
994
+ "Octora Beta - www.octora.com",
995
+ "Octora Beta Bot - www.octora.com",
996
+ "OmniExplorer_Bot/1.0x (+http://www.omni-explorer.com) Internet CategorizerOmniExplorer http://www.omni-explorer.com/ car & shopping search (64.62.175.xxx)",
997
+ "OmniExplorer_Bot/1.0x (+http://www.omni-explorer.com) Job Crawler",
998
+ "OmniExplorer_Bot/1.1x (+http://www.omni-explorer.com) Torrent Crawler",
999
+ "OmniExplorer_Bot/x.xx (+http://www.omni-explorer.com) WorldIndexer",
1000
+ "Onet.pl SA- http://szukaj.onet.pl",
1001
+ "OntoSpider/1.0 libwww-perl/5.65",
1002
+ "OOZBOT/0.20 ( http://www.setooz.com/oozbot.html ; agentname at setooz dot_com )",
1003
+ "OpenAcoon v4.0.x (www.openacoon.de)",
1004
+ "Openbot/3.0+(robot-response@openfind.com.tw;+http://www.openfind.com.tw/robot.html)",
1005
+ "Openfind data gatherer- Openbot/3.0+(robot-response@openfind.com.tw;+http://www.openfind.com.tw/robot.html)",
1006
+ "Openfind Robot/1.1A2",
1007
+ "OpenISearch/1.x (www.openisearch.com)",
1008
+ "OpenTaggerBot (http://www.opentagger.com/opentaggerbot.htm)",
1009
+ "OpenTextSiteCrawler/2.9.2",
1010
+ "OpenWebSpider/0.x.x (http://www.openwebspider.org)",
1011
+ "OpenWebSpider/x",
1012
+ "OpidooBOT (larbin2.6.3@unspecified.mail)",
1013
+ "Oracle Ultra Search",
1014
+ "OrangeSpider",
1015
+ "Orbiter/T-2.0 (+http://www.dailyorbit.com/bot.htm)",
1016
+ "Overture-WebCrawler/3.8/Fresh (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)",
1017
+ "ozelot/2.7.3 (Search engine indexer; www.flying-cat.de/ozelot; ozelot@flying-cat.de)",
1018
+ "PADLibrary Spider",
1019
+ "PageBitesHyperBot/600 (http://www.pagebites.com/)",
1020
+ "Pagebull http://www.pagebull.com/",
1021
+ "page_verifier (http://www.securecomputing.com/goto/pv)",
1022
+ "parallelContextFocusCrawler1.1parallelContextFocusCrawler1.1",
1023
+ "ParaSite/1.0b (http://www.ianett.com/parasite/)",
1024
+ "Patwebbot (http://www.herz-power.de/technik.html)",
1025
+ "PBrowse 1.4b",
1026
+ "pd02_1.0.0 pd02_1.0.0@dzimi@post.sk",
1027
+ "PEERbot www.peerbot.com",
1028
+ "PEval 1.4b",
1029
+ "PicoSearch/1.0",
1030
+ "Piffany_Web_Scraper_v0.x",
1031
+ "Piffany_Web_Spider_v0.x",
1032
+ "pipeLiner/0.3a (PipeLine Spider;http://www.pipeline-search.com/webmaster.html; webmaster'at'pipeline-search.com)",
1033
+ "pipeLiner/0.xx (PipeLine Spider; http://www.pipeline-search.com/webmaster.html)",
1034
+ "Pita",
1035
+ "PJspider/3.0 (pjspider@portaljuice.com; http://www.portaljuice.com)",
1036
+ "PlagiarBot/1.0",
1037
+ "PluckFeedCrawler/2.0 (compatible; Mozilla 4.0; MSIE 5.5; http://www.pluck.com; 1 subscribers)",
1038
+ "Pluggd/Nutch-0.9 (automated crawler http://www.pluggd.com;support at pluggd dot com)",
1039
+ "Poirot",
1040
+ "polybot 1.0 (http://cis.poly.edu/polybot/)",
1041
+ "Pompos/1.x http://dir.com/pompos.html",
1042
+ "Pompos/1.x pompos@iliad.fr",
1043
+ "Popdexter/1.0",
1044
+ "Port Huron Labs",
1045
+ "PortalBSpider/2.0 (spider@portalb.com)",
1046
+ "potbot 1.0",
1047
+ "PRCrawler/Nutch-0.9 (data mining development project; crawler@projectrialto.com)",
1048
+ "PrivacyFinder Cache Bot v1.0",
1049
+ "PrivacyFinder/1.1",
1050
+ "Production Bot 0116B",
1051
+ "Production Bot 2016B",
1052
+ "Production Bot DOT 3016B",
1053
+ "Program Shareware 1.0.2",
1054
+ "Project XP5 [2.03.07-111203]",
1055
+ "PROve AnswerBot 4.0",
1056
+ "ProWebGuide Link Checker (http://www.prowebguide.com)",
1057
+ "psbot/0.1 (+http://www.picsearch.com/bot.html)",
1058
+ "PSurf15a 11",
1059
+ "PSurf15a 51",
1060
+ "PSurf15a VA",
1061
+ "psycheclone",
1062
+ "PubCrawl (pubcrawl.stanford.edu)",
1063
+ "pulseBot (pulse Web Miner)",
1064
+ "PWeBot/1.2 Inspector (http://www.programacionweb.net/robot.php)",
1065
+ "PycURL",
1066
+ "Python-urllib/1.1x",
1067
+ "Python-urllib/2.0a1",
1068
+ "Qango.com Web Directory (http://www.qango.com/)",
1069
+ "QEAVis Agent/Nutch-0.9 (Quantitative Evaluation of Academic Websites Visibility; http://nlp.uned.es/qeavis",
1070
+ "QPCreep Test Rig ( We are not indexing- just testing )",
1071
+ "QuepasaCreep ( crawler@quepasacorp.com )",
1072
+ "QuepasaCreep v0.9.1x",
1073
+ "QueryN Metasearch",
1074
+ "QweeryBot/3.01 ( http://qweerybot.qweery.nl)",
1075
+ "Qweery_robot.txt_CheckBot/3.01 (http://qweerybot.qweery.com)",
1076
+ "R6_CommentReader_(www.radian6.com/crawler)",
1077
+ "R6_FeedFetcher_(www.radian6.com/crawler)",
1078
+ "rabaz (rabaz at gigabaz dot com)",
1079
+ "RaBot/1.0 Agent-admin/phortse@hanmail.net",
1080
+ "ramBot xtreme x.x",
1081
+ "RAMPyBot - www.giveRAMP.com/0.1 (RAMPyBot - www.giveRAMP.com; http://www.giveramp.com/bot.html; support@giveRAMP.com)",
1082
+ "RAMPyBot/0.8-dev (Nutch; http://lucene.apache.org/nutch/bot.html; nutch-agent@lucene.apache.org)",
1083
+ "Rankivabot/3.2 (www.rankiva.com; 3.2; vzmxikn)",
1084
+ "Rational SiteCheck (Windows NT)",
1085
+ "Reaper [2.03.10-031204] (http://www.sitesearch.ca/reaper/)",
1086
+ "Reaper/2.0x (+http://www.sitesearch.ca/reaper)",
1087
+ "RedCarpet/1.2 (http://www.redcarpet-inc.com/robots.html)",
1088
+ "RedCell/0.1 (InfoSec Search Bot (Coming Soon); http://www.telegenetic.net/bot.html; lhall@telegenetic.net)",
1089
+ "RedCell/0.1 (RedCell; telegenetic.net/bot.html; lhall_at_telegenetic.net)",
1090
+ "RedKernel WWW-Spider 2/0 (+http://www-spider.redkernel-softwares.com/)",
1091
+ "rico/0.1",
1092
+ "RixBot (http://babelserver.org/rix)",
1093
+ "RoboCrawl (http://www.canadiancontent.net)",
1094
+ "RoboCrawl (www.canadiancontent.net)",
1095
+ "RoboPal (http://www.findpal.com/)",
1096
+ "Robot/www.pj-search.com",
1097
+ "Robot: NutchCrawler- Owner: wdavies@acm.org",
1098
+ "Robot@SuperSnooper.Com",
1099
+ "Robozilla/1.0",
1100
+ "Rotondo/3.1 libwww/5.3.1",
1101
+ "RRC (crawler_admin@bigfoot.com)",
1102
+ "RSSMicro.com RSS/Atom Feed Robot",
1103
+ "RSurf15a 41",
1104
+ "RSurf15a 51",
1105
+ "RSurf15a 81",
1106
+ "RufusBot (Rufus Web Miner; http://64.124.122.252/feedback.html)",
1107
+ "RufusBot (Rufus Web Miner; http://www.webaroo.com/rooSiteOwners.html)",
1108
+ "sait/Nutch-0.9 (SAIT Research; http://www.samsung.com)",
1109
+ "SandCrawler - Compatibility Testing",
1110
+ "SapphireWebCrawler/1.0 (Sapphire Web Crawler using Nutch; http://boston.lti.cs.cmu.edu/crawler/; mhoy@cs.cmu.edu)",
1111
+ "SapphireWebCrawler/Nutch-1.0-dev (Sapphire Web Crawler using Nutch; http://boston.lti.cs.cmu.edu/crawler/; mhoy@cs.cmu.edu)",
1112
+ "savvybot/0.2",
1113
+ "SBIder/0.7 (SBIder; http://www.sitesell.com/sbider.html; http://support.sitesell.com/contact-support.html)",
1114
+ "SBIder/0.8-dev (SBIder; http://www.sitesell.com/sbider.html; http://support.sitesell.com/contact-support.html)",
1115
+ "ScanWeb",
1116
+ "ScholarUniverse/0.8 (Nutch;+http://scholaruniverse.com/bot.jsp; fetch-agent@scholaruniverse.com)",
1117
+ "schwarzmann.biz-Spider_for_paddel.org+(http://www.innerprise.net/usp-spider.asp)",
1118
+ "ScollSpider/2.0 (+http://www.webwobot.com/ScollSpider.php)",
1119
+ "Scooter-3.0.EU",
1120
+ "Scooter-3.0.FS",
1121
+ "Scooter-3.0.HD",
1122
+ "Scooter-3.0.VNS",
1123
+ "Scooter-3.0QI",
1124
+ "Scooter-3.2",
1125
+ "Scooter-3.2.BT",
1126
+ "Scooter-3.2.DIL",
1127
+ "Scooter-3.2.EX",
1128
+ "Scooter-3.2.JT",
1129
+ "Scooter-3.2.NIV",
1130
+ "Scooter-3.2.SF0",
1131
+ "Scooter-3.2.snippet",
1132
+ "Scooter-3.3dev",
1133
+ "Scooter-ARS-1.1",
1134
+ "Scooter-ARS-1.1-ih",
1135
+ "scooter-venus-3.0.vns",
1136
+ "Scooter-W3-1.0",
1137
+ "Scooter-W3.1.2",
1138
+ "Scooter/1.0",
1139
+ "Scooter/1.0 scooter@pa.dec.com",
1140
+ "Scooter/1.1 (custom)",
1141
+ "Scooter/2.0 G.R.A.B. V1.1.0",
1142
+ "Scooter/2.0 G.R.A.B. X2.0",
1143
+ "Scooter/3.3",
1144
+ "Scooter/3.3.QA.pczukor",
1145
+ "Scooter/3.3.vscooter",
1146
+ "Scooter/3.3_SF",
1147
+ "Scooter2_Mercator_x-x.0",
1148
+ "Scooter_bh0-3.0.3",
1149
+ "Scooter_trk3-3.0.3",
1150
+ "ScoutAbout",
1151
+ "ScoutAnt/0.1; +http://www.ant.com/what_is_ant.com/",
1152
+ "scoutmaster",
1153
+ "Scrubby/2.x (http://www.scrubtheweb.com/)",
1154
+ "Scrubby/3.0 (+http://www.scrubtheweb.com/help/technology.html)",
1155
+ "Search+",
1156
+ "Search-Engine-Studio",
1157
+ "search.ch V1.4",
1158
+ "search.ch V1.4.2 (spiderman@search.ch; http://www.search.ch)",
1159
+ "Search/1.0 (http://www.innerprise.net/es-spider.asp)",
1160
+ "searchbot admin@google.com",
1161
+ "SearchByUsa/2 (SearchByUsa; http://www.SearchByUsa.com/bot.html; info@SearchByUsa.com)",
1162
+ "SearchdayBot",
1163
+ "SearchExpress Spider0.99",
1164
+ "SearchGuild/DMOZ/Experiment (searchguild@gmail.com)",
1165
+ "SearchGuild_DMOZ_Experiment (chris@searchguild.com)",
1166
+ "Searchit-Now Robot/2.2 (+http://www.searchit-now.co.uk)",
1167
+ "Searchmee! Spider v0.98a",
1168
+ "SearchSight/2.0 (http://SearchSight.com/)",
1169
+ "SearchSpider.com/1.1",
1170
+ "Searchspider/1.2 (SearchSpider; http://www.searchspider.com; webmaster@searchspider.com)",
1171
+ "SearchTone2.0 - IDEARE",
1172
+ "Seekbot/1.0 (http://www.seekbot.net/bot.html) HTTPFetcher/0.3",
1173
+ "Seekbot/1.0 (http://www.seekbot.net/bot.html) RobotsTxtFetcher/1.0 (XDF)",
1174
+ "Seekbot/1.0 (http://www.seekbot.net/bot.html) RobotsTxtFetcher/1.2",
1175
+ "Seeker.lookseek.com",
1176
+ "Semager/1.1 (http://www.semager.de/blog/semager-bots/)",
1177
+ "Semager/1.x (http://www.semager.de)",
1178
+ "Sensis Web Crawler (search_comments\\at\\sensis\\dot\\com\\dot\\au)",
1179
+ "Sensis.com.au Web Crawler (search_comments\\at\\sensis\\dot\\com\\dot\\au)",
1180
+ "SeznamBot/1.0",
1181
+ "SeznamBot/1.0 (+http://fulltext.seznam.cz/)",
1182
+ "SeznamBot/2.0-test (+http://fulltext.sblog.cz/)",
1183
+ "ShablastBot 1.0",
1184
+ "Shim Crawler",
1185
+ "Shim-Crawler(Mozilla-compatible; http://www.logos.ic.i.u-tokyo.ac.jp/crawler/; crawl@logos.ic.i.u-tokyo.ac.jp)",
1186
+ "ShopWiki/1.0 ( +http://www.shopwiki.com/)",
1187
+ "ShopWiki/1.0 ( +http://www.shopwiki.com/wiki/Help:Bot)",
1188
+ "Shoula.com Crawler 2.0",
1189
+ "SietsCrawler/1.1 (+http://www.siets.biz)",
1190
+ "Sigram/Nutch-1.0-dev (Test agent for Nutch development; http://www.sigram.com/bot.html; bot at sigram dot com)",
1191
+ "Siigle Orumcex v.001 Turkey (http://www.siigle.com)",
1192
+ "silk/1.0",
1193
+ "silk/1.0 (+http://www.slider.com/silk.htm)/3.7",
1194
+ "Sirketcebot/v.01 (http://www.sirketce.com/bot.html)",
1195
+ "SiteSpider +(http://www.SiteSpider.com/)",
1196
+ "SiteTruth.com site rating system",
1197
+ "SiteXpert",
1198
+ "Skampy/0.9.x (http://www.skaffe.com/skampy-info.html)",
1199
+ "Skimpy/0.x (http://www.skaffe.com/skampy-info.html)",
1200
+ "Skywalker/0.1 (Skywalker; anonymous; anonymous)",
1201
+ "Slarp/0.1",
1202
+ "Slider_Search_v1-de",
1203
+ "Slurp/2.0 (slurp@inktomi.com; http://www.inktomi.com/slurp.html)",
1204
+ "Slurp/2.0-KiteWeekly (slurp@inktomi.com; http://www.inktomi.com/slurp.html)",
1205
+ "Slurp/si (slurp@inktomi.com; http://www.inktomi.com/slurp.html)",
1206
+ "Slurpy Verifier/1.0",
1207
+ "SlySearch (slysearch@slysearch.com)",
1208
+ "SlySearch/1.0 http://www.plagiarism.org/crawler/robotinfo.html",
1209
+ "SlySearch/1.x http://www.slysearch.com",
1210
+ "smartwit.com",
1211
+ "SmiffyDCMetaSpider/1.0",
1212
+ "snap.com beta crawler v0",
1213
+ "Snapbot/1.0",
1214
+ "Snapbot/1.0 (Snap Shots, +http://www.snap.com)",
1215
+ "SnykeBot/0.6 (http://www.snyke.com)",
1216
+ "SocSciBot ()",
1217
+ "SoftHypermarketFileCheckBot/1.0+(+http://www.softhypermaket.com)",
1218
+ "sogou develop spider",
1219
+ "Sogou Orion spider/3.0(+http://www.sogou.com/docs/help/webmasters.htm#07)",
1220
+ "sogou spider",
1221
+ "Sogou web spider/3.0(+http://www.sogou.com/docs/help/webmasters.htm#07)",
1222
+ "sohu agent",
1223
+ "sohu-search",
1224
+ "Sosospider+(+http://help.soso.com/webspider.htm)",
1225
+ "speedfind ramBot xtreme 8.1",
1226
+ "Speedy Spider (Beta/x.x; speedy@entireweb.com)",
1227
+ "Speedy Spider (Entireweb; Beta/1.0; http://www.entireweb.com/about/search_tech/speedyspider/)",
1228
+ "Speedy_Spider (http://www.entireweb.com)",
1229
+ "Sphere Scout&v4.0 - scout at sphere dot com",
1230
+ "Sphider",
1231
+ "Spida/0.1",
1232
+ "Spider-Sleek/2.0 (+http://search-info.com/linktous.html)",
1233
+ "spider.batsch.com",
1234
+ "spider.yellopet.com - www.yellopet.com",
1235
+ "Spider/maxbot.com admin@maxbot.com",
1236
+ "SpiderKU/0.x",
1237
+ "SpiderMan",
1238
+ "SpiderMonkey/7.0x (SpiderMonkey.ca info at http://spidermonkey.ca/sm.shtml)",
1239
+ "Spinne/2.0",
1240
+ "Spinne/2.0 med",
1241
+ "Spinne/2.0 med_AH",
1242
+ "Spock Crawler (http://www.spock.com/crawler)",
1243
+ "sportsuchmaschine.de-Robot (Version: 1.02- powered by www.sportsuchmaschine.de)",
1244
+ "sproose/0.1-alpha (sproose crawler; http://www.sproose.com/bot.html; crawler@sproose.com)",
1245
+ "Sqworm/2.9.81-BETA (beta_release; 20011102-760; i686-pc-linux-gnu)",
1246
+ "Sqworm/2.9.85-BETA (beta_release; 20011115-775; i686-pc-linux-gnu)",
1247
+ "SSurf15a 11 ",
1248
+ "StackRambler/x.x ",
1249
+ "stat statcrawler@gmail.com",
1250
+ "Steeler/1.x (http://www.tkl.iis.u-tokyo.ac.jp/~crawler/)",
1251
+ "Steeler/3.3 (http://www.tkl.iis.u-tokyo.ac.jp/~crawler/)",
1252
+ "Strategic Board Bot (+http://www.strategicboard.com)",
1253
+ "Strategic Board Bot (+http://www.strategicboard.com)",
1254
+ "Submission Spider at surfsafely.com",
1255
+ "suchbaer.de",
1256
+ "suchbaer.de (CrawlerAgent v0.103)",
1257
+ "suchbot",
1258
+ "Suchknecht.at-Robot",
1259
+ "suchpadbot/1.0 (+http://www.suchpad.de)",
1260
+ "SurferF3 1/0",
1261
+ "suzuran",
1262
+ "Swooglebot/2.0. (+http://swoogle.umbc.edu/swooglebot.htm)",
1263
+ "SWSBot-Images/1.2 http://www.smartwaresoft.com/swsbot12.html",
1264
+ "SygolBot http://www.sygol.net",
1265
+ "SynoBot",
1266
+ "Syntryx ANT Scout Chassis Pheromone; Mozilla/4.0 compatible crawler",
1267
+ "Szukacz/1.x",
1268
+ "Szukacz/1.x (robot; www.szukacz.pl/jakdzialarobot.html; szukacz@proszynski.pl)",
1269
+ "tags2dir.com/0.8 (+http://tags2dir.com/directory/)",
1270
+ "Tagword (http://tagword.com/dmoz_survey.php)",
1271
+ "Talkro Web-Shot/1.0 (E-mail: webshot@daumsoft.com- Home: http://222.122.15.190/webshot)",
1272
+ "TCDBOT/Nutch-0.8 (PhD student research;http://www.tcd.ie; mcgettrs at t c d dot IE)",
1273
+ "TECOMAC-Crawler/0.x",
1274
+ "Tecomi Bot (http://www.tecomi.com/bot.htm)",
1275
+ "Teemer (NetSeer, Inc. is a Los Angeles based Internet startup company.; http://www.netseer.com/crawler.html; crawler@netseer.com)",
1276
+ "Teoma MP",
1277
+ "teomaagent crawler-admin@teoma.com",
1278
+ "teomaagent1 [crawler-admin@teoma.com]",
1279
+ "teoma_agent1",
1280
+ "Teradex Mapper; mapper@teradex.com; http://www.teradex.com",
1281
+ "terraminds-bot/1.0 (support@terraminds.de)",
1282
+ "TerrawizBot/1.0 (+http://www.terrawiz.com/bot.html)",
1283
+ "Test spider",
1284
+ "TestCrawler/Nutch-0.9 (Testing Crawler for Research ; http://balihoo.com/index.aspx; tgautier at balihoo dot com)",
1285
+ "TheRarestParser/0.2a (http://therarestwords.com/)",
1286
+ "TheSuBot/0.1 (www.thesubot.de)",
1287
+ "thumbshots-de-Bot (Version: 1.02- powered by www.thumbshots.de)",
1288
+ "timboBot/0.9 http://www.breakingblogs.com/timbo_bot.html",
1289
+ "TinEye/1.1 (http://tineye.com/crawler.html)",
1290
+ "tivraSpider/1.0 (crawler@tivra.com)",
1291
+ "TJG/Spider",
1292
+ "Tkensaku/x.x(http://www.tkensaku.com/q.html)",
1293
+ "Topodia/1.2-dev (Topodia - Crawler for HTTP content indexing; http://www.topodia.com/; support@topodia.com)",
1294
+ "Toutatis x-xx.x (hoppa.com)",
1295
+ "Toutatis x.x (hoppa.com)",
1296
+ "Toutatis x.x-x",
1297
+ "traazibot/testengine (+http://www.traazi.de)",
1298
+ "Trampelpfad-Spider",
1299
+ "Trampelpfad-Spider-v0.1",
1300
+ "TSurf15a 11",
1301
+ "Tumblr/1.0 RSS syndication (+http://www.tumblr.com/) (support@tumblr.com)",
1302
+ "TurnitinBot/x.x (http://www.turnitin.com/robot/crawlerinfo.html)",
1303
+ "Turnpike Emporium LinkChecker/0.1",
1304
+ "TutorGig/1.5 (+http://www.tutorgig.com/crawler)",
1305
+ "Tutorial Crawler 1.4 (http://www.tutorgig.com/crawler)",
1306
+ "Twiceler www.cuill.com/robots.html",
1307
+ "Twiceler-0.9 http://www.cuill.com/twiceler/robot.html",
1308
+ "Tycoon Agent/Nutch-1.0-dev",
1309
+ "TygoBot",
1310
+ "TygoProwler",
1311
+ "UIowaCrawler/1.0",
1312
+ "UKWizz/Nutch-0.8.1 (UKWizz Nutch crawler; http://www.ukwizz.com/)",
1313
+ "Ultraseek",
1314
+ "Under the Rainbow 2.2",
1315
+ "UofTDB_experiment (leehyun@cs.toronto.edu)",
1316
+ "updated/0.1-alpha (updated crawler; http://www.updated.com; crawler@updated.com)",
1317
+ "updated/0.1beta (updated.com; http://www.updated.com; crawler@updated.om)",
1318
+ "Uptimebot",
1319
+ "UptimeBot(www.uptimebot.com)",
1320
+ "URL Spider Pro/x.xx (innerprise.net)",
1321
+ "urlfan-bot/1.0; +http://www.urlfan.com/site/bot/350.html",
1322
+ "URL_Spider_Pro/x.x",
1323
+ "URL_Spider_Pro/x.x+(http://www.innerprise.net/usp-spider.asp)",
1324
+ "User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
1325
+ "User-Agent: Mozilla/4.0 (SKIZZLE! Distributed Internet Spider v1.0 - www.SKIZZLE.com)",
1326
+ "USyd-NLP-Spider (http://www.it.usyd.edu.au/~vinci/bot.html)",
1327
+ "VadixBot",
1328
+ "Vagabondo-WAP/2.0 (webcrawler at wise-guys dot nl; http://webagent.wise-guys.nl/)/1.0 Profile",
1329
+ "Vagabondo/1.x MT (webagent@wise-guys.nl)",
1330
+ "Vagabondo/2.0 MT",
1331
+ "Vagabondo/2.0 MT (webagent at wise-guys dot nl)",
1332
+ "Vagabondo/2.0 MT (webagent@NOSPAMwise-guys.nl)",
1333
+ "Vagabondo/3.0 (webagent at wise-guys dot nl)",
1334
+ "Vakes/0.01 (Vakes; http://www.vakes.com/; search@vakes.com)",
1335
+ "versus 0.2 (+http://versus.integis.ch)",
1336
+ "versus crawler eda.baykan@epfl.ch",
1337
+ "VeryGoodSearch.com.DaddyLongLegs",
1338
+ "verzamelgids.nl - Networking4all Bot/x.x",
1339
+ "Verzamelgids/2.2 (http://www.verzamelgids.nl)",
1340
+ "Vespa Crawler",
1341
+ "VisBot/2.0 (Visvo.com Crawler; http://www.visvo.com/bot.html; bot@visvo.com)",
1342
+ "Vision Research Lab image spider at vision.ece.ucsb.edu",
1343
+ "VMBot/0.x.x (VMBot; http://www.VerticalMatch.com/; vmbot@tradedot.com)",
1344
+ "Vortex/2.2 (+http://marty.anstey.ca/robots/vortex/)",
1345
+ "voyager-hc/1.0",
1346
+ "voyager/1.0",
1347
+ "voyager/2.0 (http://www.kosmix.com/html/crawler.html)",
1348
+ "VSE/1.0 (testcrawler@hotmail.com)",
1349
+ "VSE/1.0 (testcrawler@vivisimo.com)",
1350
+ "vspider",
1351
+ "vspider/3.x",
1352
+ "VWBOT/Nutch-0.9-dev (VWBOT Nutch Crawler; http://vwbot.cs.uiuc.edu;+vwbot@cs.uiuc.edu",
1353
+ "W3SiteSearch Crawler_v1.1 http://www.w3sitesearch.de",
1354
+ "wadaino.jp-crawler 0.2 (http://wadaino.jp/)",
1355
+ "Wavefire/0.8-dev (Wavefire; http://www.wavefire.com; info@wavefire.com)",
1356
+ "Waypath development crawler - info at waypath dot com",
1357
+ "Waypath Scout v2.x - info at waypath dot com",
1358
+ "Web Snooper",
1359
+ "web2express.org/Nutch-0.9-dev (leveled playing field; http://web2express.org/; info at web2express.org)",
1360
+ "WebAlta Crawler/1.2.1 (http://www.webalta.ru/bot.html)",
1361
+ "WebarooBot (Webaroo Bot; http://64.124.122.252/feedback.html)",
1362
+ "WebarooBot (Webaroo Bot; http://www.webaroo.com/rooSiteOwners.html)",
1363
+ "webbandit/4.xx.0",
1364
+ "Webclipping.com",
1365
+ "WebCompass 2.0",
1366
+ "WebCorp/1.0",
1367
+ "webcrawl.net",
1368
+ "WebFindBot(http://www.web-find.com)",
1369
+ "Webglimpse 2.xx.x (http://webglimpse.net)",
1370
+ "Weblog Attitude Diffusion 1.0",
1371
+ "webmeasurement-bot, http://rvs.informatik.uni-leipzig.de",
1372
+ "WebRankSpider/1.37 (+http://ulm191.server4you.de/crawler/)",
1373
+ "WebSearch.COM.AU/3.0.1 (The Australian Search Engine; http://WebSearch.COM.AU; Search@WebSearch.COM.AU)",
1374
+ "WebSearchBench WebCrawler v0.1(Experimental)",
1375
+ "WebsiteWorth v1.0",
1376
+ "Webspinne/1.0 webmaster@webspinne.de",
1377
+ "Websquash.com (Add url robot)",
1378
+ "WebStat/1.0 (Unix; beta; 20040314)",
1379
+ "Webster v0.3 ( http://webster.healeys.net/ )",
1380
+ "WebVac (webmaster@pita.stanford.edu)",
1381
+ "Webverzeichnis.de - Telefon: 01908 / 26005",
1382
+ "WebVulnCrawl.unknown/1.0 libwww-perl/5.803",
1383
+ "Wells Search II",
1384
+ "WEP Search 00",
1385
+ "WFARC",
1386
+ "whatUseek_winona/3.0",
1387
+ "WhizBang! Lab",
1388
+ "Willow Internet Crawler by Twotrees V2.1",
1389
+ "WinHTTP Example/1.0",
1390
+ "WinkBot/0.06 (Wink.com search engine web crawler; http://www.wink.com/Wink:WinkBot; winkbot@wink.com)",
1391
+ "WIRE/0.11 (Linux; i686; Bot,Robot,Spider,Crawler,aromano@cli.di.unipi.it)",
1392
+ "WIRE/0.x (Linux; i686; Bot,Robot,Spider,Crawler)",
1393
+ "WISEbot/1.0 (WISEbot@koreawisenut.com; http://wisebot.koreawisenut.com)",
1394
+ "worio heritrix bot (+http://worio.com/)",
1395
+ "woriobot ( http://www.worio.com/)",
1396
+ "WorldLight",
1397
+ "Wotbox/alpha0.6 (bot@wotbox.com; http://www.wotbox.com)",
1398
+ "Wotbox/alpha0.x.x (bot@wotbox.com; http://www.wotbox.com) Java/1.4.1_02",
1399
+ "WSB WebCrawler V1.0 (Beta)- cl@cs.uni-dortmund.de",
1400
+ "WSB, http://websearchbench.cs.uni-dortmund.de",
1401
+ "wume_crawler/1.1 (http://wume.cse.lehigh.edu/~xiq204/crawler/)",
1402
+ "Wwlib/Linux",
1403
+ "www.arianna.it",
1404
+ "WWWeasel Robot v1.00 (http://wwweasel.de)",
1405
+ "wwwster/1.x (Beta- mailto:gue@cis.uni-muenchen.de)",
1406
+ "X-Crawler ",
1407
+ "xirq/0.1-beta (xirq; http://www.xirq.com; xirq@xirq.com)",
1408
+ "xyro_(xcrawler@cosmos.inria.fr)",
1409
+ "Y!J-BSC/1.0 (http://help.yahoo.co.jp/help/jp/search/indexing/indexing-15.html)",
1410
+ "Y!J-SRD/1.0",
1411
+ "Y!J/1.0 (http://help.yahoo.co.jp/help/jp/search/indexing/indexing-15.html)",
1412
+ "yacy (www.yacy.net; v20040602; i386 Linux 2.4.26-gentoo-r13; java 1.4.2_06; MET/en)",
1413
+ "yacybot (x86 Windows XP 5.1; java 1.5.0_06; Europe/de) yacy.net",
1414
+ "Yahoo Pipes 1.0",
1415
+ "Yahoo! Mindset",
1416
+ "Yahoo-Blogs/v3.9 (compatible; Mozilla 4.0; MSIE 5.5; http://help.yahoo.com/help/us/ysearch/crawling/crawling-02.html )",
1417
+ "Yahoo-MMAudVid/1.0 (mms dash mmaudvidcrawler dash support at yahoo dash inc dot com)",
1418
+ "Yahoo-MMAudVid/2.0(mms dash mm aud vid crawler dash support at yahoo dash inc.com ;Mozilla 4.0 compatible; MSIE 7.0;Windows NT 5.0; .NET CLR 2.0)",
1419
+ "Yahoo-MMCrawler/3.x (mm dash crawler at trd dot overture dot com)",
1420
+ "Yahoo-Test/4.0",
1421
+ "Yahoo-VerticalCrawler-FormerWebCrawler/3.9 crawler at trd dot overture dot com; http://www.alltheweb.com/help/webmaster/crawler",
1422
+ "YahooFeedSeeker/2.0 (compatible; Mozilla 4.0; MSIE 5.5; http://publisher.yahoo.com/rssguide)",
1423
+ "YahooSeeker-Testing/v3.9 (compatible; Mozilla 4.0; MSIE 5.5; http://search.yahoo.com/)",
1424
+ "YahooSeeker/1.0 (compatible; Mozilla 4.0; MSIE 5.5; http://help.yahoo.com/help/us/shop/merchant/)",
1425
+ "YahooSeeker/1.0 (compatible; Mozilla 4.0; MSIE 5.5; http://search.yahoo.com/yahooseeker.html)",
1426
+ "YahooSeeker/1.1 (compatible; Mozilla 4.0; MSIE 5.5; http://help.yahoo.com/help/us/shop/merchant/)",
1427
+ "YahooSeeker/bsv3.9 (compatible; Mozilla 4.0; MSIE 5.5; http://help.yahoo.com/help/us/ysearch/crawling/crawling-02.html )",
1428
+ "YahooSeeker/CafeKelsa-dev (compatible; Konqueror/3.2; FreeBSD ;cafekelsa-dev-webmaster@yahoo-inc.com )",
1429
+ "Yandex/1.01.001 (compatible; Win16; I)",
1430
+ "Yanga WorldSearch Bot v1.1/beta (http://www.yanga.co.uk/)",
1431
+ "yarienavoir.net/0.2",
1432
+ "Yeti",
1433
+ "Yeti/0.01 (nhn/1noon, yetibot@naver.com, check robots.txt daily and follows it)",
1434
+ "Yeti/1.0 (NHN Corp.; http://help.naver.com/robots/)",
1435
+ "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)",
1436
+ "YodaoBot/1.0 (http://www.yodao.com/help/webmaster/spider/; )",
1437
+ "yoofind/yoofind-0.1-dev (yoono webcrawler; http://www.yoono.com ; MyEmail)",
1438
+ "yoogliFetchAgent/0.1",
1439
+ "yoono/1.0 web-crawler/1.0",
1440
+ "YottaCars_Bot/4.12 (+http://www.yottacars.com) Car Search Engine ",
1441
+ "YottaShopping_Bot/4.12 (+http://www.yottashopping.com) Shopping Search Engine",
1442
+ "Zao-Crawler",
1443
+ "Zao-Crawler 0.2b",
1444
+ "Zao/0.1 (http://www.kototoi.org/zao/)",
1445
+ "ZBot/1.00 (icaulfield@zeus.com)",
1446
+ "Zearchit",
1447
+ "ZeBot_lseek.net (bot@ze.bz)",
1448
+ "ZeBot_www.ze.bz (ze.bz@hotmail.com)",
1449
+ "zedzo.digest/0.1 (http://www.zedzo.com/)",
1450
+ "zermelo Mozilla/5.0 compatible; heritrix/1.12.1 (+http://www.powerset.com) [email:crawl@powerset.com,email:paul@page-store.com]",
1451
+ "zerxbot/Version 0.6 libwww-perl/5.79",
1452
+ "Zeus ThemeSite Viewer Webster Pro V2.9 Win32",
1453
+ "Zeus xxxxx Webster Pro V2.9 Win32",
1454
+ "Zeusbot/0.07 (Ulysseek's web-crawling robot; http://www.zeusbot.com; agent@zeusbot.com)",
1455
+ "ZipppBot/0.xx (ZipppBot; http://www.zippp.net; webmaster@zippp.net)",
1456
+ "ZIPPPCVS/0.xx (ZipppBot/.xx;http://www.zippp.net; webmaster@zippp.net)",
1457
+ "Zippy v2.0 - Zippyfinder.com",
1458
+ "ZoomSpider - wrensoft.com",
1459
+ "zspider/0.9-dev http://feedback.redkolibri.com/",
1460
+ "ZyBorg/1.0 (ZyBorg@WISEnut.com; http://www.WISEnut.com)"]
1461
+ end
1462
+ end