Advertisement
Guest User

Untitled

a guest
Sep 18th, 2017
1,021
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 56.17 KB | None | 0 0
  1. global headers_useragents
  2. headers_useragents.append('Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.3) Gecko/20090913 Firefox/3.5.3')
  3. headers_useragents.append('Mozilla/5.0 (Windows; U; Windows NT 6.1; en; rv:1.9.1.3) Gecko/20090824 Firefox/3.5.3 (.NET CLR 3.5.30729)')
  4. headers_useragents.append('Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US; rv:1.9.1.3) Gecko/20090824 Firefox/3.5.3 (.NET CLR 3.5.30729)')
  5. headers_useragents.append('Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.1) Gecko/20090718 Firefox/3.5.1')
  6. headers_useragents.append('Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.1 (KHTML, like Gecko) Chrome/4.0.219.6 Safari/532.1')
  7. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; InfoPath.2)')
  8. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; SLCC1; .NET CLR 2.0.50727; .NET CLR 1.1.4322; .NET CLR 3.5.30729; .NET CLR 3.0.30729)')
  9. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.2; Win64; x64; Trident/4.0)')
  10. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; SV1; .NET CLR 2.0.50727; InfoPath.2)')
  11. headers_useragents.append('Mozilla/5.0 (Windows; U; MSIE 7.0; Windows NT 6.0; en-US)')
  12. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 6.1; Windows XP)')
  13. headers_useragents.append('Opera/9.80 (Windows NT 5.2; U; ru) Presto/2.5.22 Version/10.51')
  14. headers_useragents.append('Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) BlackHawk/1.0.195.0 Chrome/127.0.0.1 Safari/62439616.534')
  15. headers_useragents.append('Mozilla/5.0 (Windows; U; Windows NT 6.1; en; rv:1.9.1.3) Gecko/20090824 Firefox/3.5.3 (.NET CLR 3.5.30729)')
  16. headers_useragents.append('Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US; rv:1.9.1.3) Gecko/20090824 Firefox/3.5.3 (.NET CLR 3.5.30729)')
  17. headers_useragents.append('Mozilla/5.0 (PlayStation 4 1.52) AppleWebKit/536.26 (KHTML, like Gecko)')
  18. headers_useragents.append('Mozilla/5.0 (Windows NT 6.1; rv:26.0) Gecko/20100101 Firefox/26.0 IceDragon/26.0.0.2')
  19. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; InfoPath.2)')
  20. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; SLCC1; .NET CLR 2.0.50727; .NET CLR 1.1.4322; .NET CLR 3.5.30729; .NET CLR 3.0.30729)')
  21. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.2; Win64; x64; Trident/4.0)')
  22. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; SV1; .NET CLR 2.0.50727; InfoPath.2)')
  23. headers_useragents.append('Mozilla/5.0 (Windows; U; MSIE 7.0; Windows NT 6.0; en-US)')
  24. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 6.1; Windows XP)')
  25. headers_useragents.append('Opera/9.80 (Windows NT 5.2; U; ru) Presto/2.5.22 Version/10.51')
  26. headers_useragents.append('agadine/1.x.x (+http://www.agada.de)')
  27. headers_useragents.append('Agent-SharewarePlazaFileCheckBot/2.0+(+http://www.SharewarePlaza.com)')
  28. headers_useragents.append('AgentName/0.1 libwww-perl/5.48')
  29. headers_useragents.append('AIBOT/2.1 By +(www.21seek.com A Real artificial intelligence search engine China)')
  30. headers_useragents.append('AideRSS/1.0 (aiderss.com)')
  31. headers_useragents.append('aipbot/1.0 (aipbot; http://www.aipbot.com; aipbot@aipbot.com)')
  32. headers_useragents.append('aipbot/2-beta (aipbot dev; http://aipbot.com; aipbot@aipbot.com)')
  33. headers_useragents.append('Akregator/1.2.9; librss/remnants')
  34. headers_useragents.append('Aladin/3.324')
  35. headers_useragents.append('Alcatel-BG3/1.0 UP.Browser/5.0.3.1.2')
  36. headers_useragents.append('Aleksika Spider/1.0 (+http://www.aleksika.com/)')
  37. headers_useragents.append('AlertInfo 2.0 (Powered by Newsbrain)')
  38. headers_useragents.append('AlkalineBOT/1.3')
  39. headers_useragents.append('AlkalineBOT/1.4 (1.4.0326.0 RTM)')
  40. headers_useragents.append('Allesklar/0.1 libwww-perl/5.46')
  41. headers_useragents.append('Alligator 1.31 (www.nearsoftware.com)')
  42. headers_useragents.append('Allrati/1.1 (+)')
  43. headers_useragents.append('AltaVista Intranet V2.0 AVS EVAL search@freeit.com')
  44. headers_useragents.append('AltaVista Intranet V2.0 Compaq Altavista Eval sveand@altavista.net')
  45. headers_useragents.append('AltaVista Intranet V2.0 evreka.com crawler@evreka.com')
  46. headers_useragents.append('AltaVista V2.0B crawler@evreka.com')
  47. headers_useragents.append('amaya/x.xx libwww/x.x.x')
  48. headers_useragents.append('AmfibiBOT')
  49. headers_useragents.append('Amfibibot/0.06 (Amfibi Web Search; http://www.amfibi.com; agent@amfibi.com)')
  50. headers_useragents.append('Amfibibot/0.07 (Amfibi Robot; http://www.amfibi.com; agent@amfibi.com)')
  51. headers_useragents.append('amibot')
  52. headers_useragents.append('Amiga-AWeb/3.4.167SE')
  53. headers_useragents.append('AmigaVoyager/3.4.4 (MorphOS/PPC native)')
  54. headers_useragents.append('AmiTCP Miami (AmigaOS 2.04)')
  55. headers_useragents.append('Amoi 8512/R21.0 NF-Browser/3.3')
  56. headers_useragents.append('amzn_assoc')
  57. headers_useragents.append('AnnoMille spider 0.1 alpha - http://www.annomille.it')
  58. headers_useragents.append('annotate_google; http://ponderer.org/download/annotate_google.user.js')
  59. headers_useragents.append('Anonymized by ProxyOS: http://www.megaproxy.com')
  60. headers_useragents.append('Anonymizer/1.1')
  61. headers_useragents.append('AnswerBus (http://www.answerbus.com/)')
  62. headers_useragents.append('AnswerChase PROve x.0')
  63. headers_useragents.append('AnswerChase x.0')
  64. headers_useragents.append('ANTFresco/x.xx')
  65. headers_useragents.append('antibot-V1.1.5/i586-linux-2.2')
  66. headers_useragents.append('AnzwersCrawl/2.0 (anzwerscrawl@anzwers.com.au;Engine)')
  67. headers_useragents.append('Apexoo Spider 1.x')
  68. headers_useragents.append('Aplix HTTP/1.0.1')
  69. headers_useragents.append('Aplix_SANYO_browser/1.x (Japanese)')
  70. headers_useragents.append('Aplix_SEGASATURN_browser/1.x (Japanese)')
  71. headers_useragents.append('Aport')
  72. headers_useragents.append('appie 1.1 (www.walhello.com)')
  73. headers_useragents.append('Apple iPhone v1.1.4 CoreMedia v1.0.0.4A102')
  74. headers_useragents.append('Apple-PubSub/65.1.1')
  75. headers_useragents.append('ArabyBot (compatible; Mozilla/5.0; GoogleBot; FAST Crawler 6.4; http://www.araby.com;)')
  76. headers_useragents.append('ArachBot')
  77. headers_useragents.append('Arachnoidea (arachnoidea@euroseek.com)')
  78. headers_useragents.append('aranhabot')
  79. headers_useragents.append('ArchitextSpider')
  80. headers_useragents.append('archive.org_bot')
  81. headers_useragents.append('Argus/1.1 (Nutch; http://www.simpy.com/bot.html; feedback at simpy dot com)')
  82. headers_useragents.append('Arikus_Spider')
  83. headers_useragents.append('Arquivo-web-crawler (compatible; heritrix/1.12.1 +http://arquivo-web.fccn.pt)')
  84. headers_useragents.append('ASAHA Search Engine Turkey V.001 (http://www.asaha.com/)')
  85. headers_useragents.append('Asahina-Antenna/1.x')
  86. headers_useragents.append('Asahina-Antenna/1.x (libhina.pl/x.x ; libtime.pl/x.x)')
  87. headers_useragents.append('ask.24x.info')
  88. headers_useragents.append('AskAboutOil/0.06-rcp (Nutch; http://www.nutch.org/docs/en/bot.html; nutch-agent@askaboutoil.com)')
  89. headers_useragents.append('asked/Nutch-0.8 (web crawler; http://asked.jp; epicurus at gmail dot com)')
  90. headers_useragents.append('ASPSeek/1.2.5')
  91. headers_useragents.append('ASPseek/1.2.9d')
  92. headers_useragents.append('ASPSeek/1.2.x')
  93. headers_useragents.append('ASPSeek/1.2.xa')
  94. headers_useragents.append('ASPseek/1.2.xx')
  95. headers_useragents.append('ASPSeek/1.2.xxpre')
  96. headers_useragents.append('ASSORT/0.10')
  97. headers_useragents.append('asterias/2.0')
  98. headers_useragents.append('AtlocalBot/1.1 +(http://www.atlocal.com/local-web-site-owner.html)')
  99. headers_useragents.append('Atomic_Email_Hunter/4.0')
  100. headers_useragents.append('Atomz/1.0')
  101. headers_useragents.append('atSpider/1.0')
  102. headers_useragents.append('Attentio/Nutch-0.9-dev (Attentios beta blog crawler; www.attentio.com; info@attentio.com)')
  103. headers_useragents.append('AU-MIC/2.0 MMP/2.0')
  104. headers_useragents.append('AUDIOVOX-SMT5600')
  105. headers_useragents.append('augurfind')
  106. headers_useragents.append('augurnfind V-1.x')
  107. headers_useragents.append('autoemailspider')
  108. headers_useragents.append('autohttp')
  109. headers_useragents.append('autowebdir 1.1 (www.autowebdir.com)')
  110. headers_useragents.append('AV Fetch 1.0')
  111. headers_useragents.append('Avant Browser (http://www.avantbrowser.com)')
  112. headers_useragents.append('AVSearch-1.0(peter.turney@nrc.ca)')
  113. headers_useragents.append('AVSearch-2.0-fusionIdx-14-CompetitorWebSites')
  114. headers_useragents.append('AVSearch-3.0(AltaVista/AVC)')
  115. headers_useragents.append('AWeb')
  116. headers_useragents.append('axadine/ (Axadine Crawler; http://www.axada.de/; )')
  117. headers_useragents.append('AxmoRobot - Crawling your site for better indexing on www.axmo.com search engine.')
  118. headers_useragents.append('Azureus 2.x.x.x')
  119. headers_useragents.append('BabalooSpider/1.3 (BabalooSpider; http://www.babaloo.si; spider@babaloo.si)')
  120. headers_useragents.append('BaboomBot/1.x.x (+http://www.baboom.us)')
  121. headers_useragents.append('BackStreet Browser 3.x')
  122. headers_useragents.append('BaiduImagespider+(+http://www.baidu.jp/search/s308.html)')
  123. headers_useragents.append('BaiDuSpider')
  124. headers_useragents.append('Baiduspider+(+http://help.baidu.jp/system/05.html)')
  125. headers_useragents.append('Baiduspider+(+http://www.baidu.com/search/spider.htm)')
  126. headers_useragents.append('Baiduspider+(+http://www.baidu.com/search/spider_jp.html)')
  127. headers_useragents.append('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)')
  128. headers_useragents.append('BanBots/1.2 (spider@banbots.com)')
  129. headers_useragents.append('Barca/2.0.xxxx')
  130. headers_useragents.append('(DreamPassport/3.0; isao/MyDiGiRabi)')
  131. headers_useragents.append('(Privoxy/1.0)')
  132. headers_useragents.append('*/Nutch-0.9-dev')
  133. headers_useragents.append('+SitiDi.net/SitiDiBot/1.0 (+Have Good Day)')
  134. headers_useragents.append('-DIE-KRAEHE- META-SEARCH-ENGINE/1.1 http://www.die-kraehe.de')
  135. headers_useragents.append('123spider-Bot (Version: 1.02) powered by www.123spider.de')
  136. headers_useragents.append('192.comAgent')
  137. headers_useragents.append('1st ZipCommander (Net) - http://www.zipcommander.com/')
  138. headers_useragents.append('2Bone_LinkChecker/1.0 libwww-perl/5.64')
  139. headers_useragents.append('4anything.com LinkChecker v2.0')
  140. headers_useragents.append('8484 Boston Project v 1.0')
  141. headers_useragents.append(':robot/1.0 (linux) ( admin e-mail: undefined http://www.neofonie.de/loesungen/search/robot.html )')
  142. headers_useragents.append('A-Online Search')
  143. headers_useragents.append('A1 Keyword Research/1.0.2 (+http://www.micro-sys.dk/products/keyword-research/) miggibot/2007.03.27')
  144. headers_useragents.append('A1 Sitemap Generator/1.0 (+http://www.micro-sys.dk/products/sitemap-generator/) miggibot/2006.01.24')
  145. headers_useragents.append('AbachoBOT')
  146. headers_useragents.append('AbachoBOT (Mozilla compatible)')
  147. headers_useragents.append('ABCdatos BotLink/5.xx.xxx#BBL')
  148. headers_useragents.append('Aberja Checkomat Aberja Hybridsuchmaschine (Germany)')
  149. headers_useragents.append('abot/0.1 (abot; http://www.abot.com; abot@abot.com)')
  150. headers_useragents.append('About/0.1libwww-perl/5.47')
  151. headers_useragents.append('Accelatech RSSCrawler/0.4')
  152. headers_useragents.append('accoona Accoona Search robot')
  153. headers_useragents.append('Accoona-AI-Agent/1.1.1 (crawler at accoona dot com)')
  154. headers_useragents.append('Accoona-AI-Agent/1.1.2 (aicrawler at accoonabot dot com)')
  155. headers_useragents.append('Ace Explorer')
  156. headers_useragents.append('Ack (http://www.ackerm.com/)')
  157. headers_useragents.append('AcoiRobot')
  158. headers_useragents.append('Acoon Robot v1.50.001')
  159. headers_useragents.append('Acoon Robot v1.52 (http://www.acoon.de)')
  160. headers_useragents.append('Acoon-Robot 4.0.x.[xx] (http://www.acoon.de)')
  161. headers_useragents.append('Acoon-Robot v3.xx (http://www.acoon.de and http://www.acoon.com)')
  162. headers_useragents.append('Acorn/Nutch-0.9 (Non-Profit Search Engine; acorn.isara.org; acorn at isara dot org)')
  163. headers_useragents.append('ActiveBookmark 1.x')
  164. headers_useragents.append('Activeworlds')
  165. headers_useragents.append('ActiveWorlds/3.xx (xxx)')
  166. headers_useragents.append('Ad Muncher v4.xx.x')
  167. headers_useragents.append('Ad Muncher v4x Build xxxxx')
  168. headers_useragents.append('Adaxas Spider (http://www.adaxas.net/)')
  169. headers_useragents.append('Advanced Browser (http://www.avantbrowser.com)')
  170. headers_useragents.append('AESOP_com_SpiderMan')
  171. headers_useragents.append('Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) BlackHawk/1.0.195.0 Chrome/127.0.0.1 Safari/62439616.534')
  172. headers_useragents.append('Mozilla/5.0 (Windows; U; Windows NT 6.1; en; rv:1.9.1.3) Gecko/20090824 Firefox/3.5.3 (.NET CLR 3.5.30729)')
  173. headers_useragents.append('Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US; rv:1.9.1.3) Gecko/20090824 Firefox/3.5.3 (.NET CLR 3.5.30729)')
  174. headers_useragents.append('Mozilla/5.0 (PlayStation 4 1.52) AppleWebKit/536.26 (KHTML, like Gecko)')
  175. headers_useragents.append('Mozilla/5.0 (Windows NT 6.1; rv:26.0) Gecko/20100101 Firefox/26.0 IceDragon/26.0.0.2')
  176. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; InfoPath.2)')
  177. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; SLCC1; .NET CLR 2.0.50727; .NET CLR 1.1.4322; .NET CLR 3.5.30729; .NET CLR 3.0.30729)')
  178. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.2; Win64; x64; Trident/4.0)')
  179. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; SV1; .NET CLR 2.0.50727; InfoPath.2)')
  180. headers_useragents.append('Mozilla/5.0 (Windows; U; MSIE 7.0; Windows NT 6.0; en-US)')
  181. headers_useragents.append('Mozilla/4.0 (compatible; MSIE 6.1; Windows XP)')
  182. headers_useragents.append('Opera/9.80 (Windows NT 5.2; U; ru) Presto/2.5.22 Version/10.51')
  183. headers_useragents.append('(DreamPassport/3.0; isao/MyDiGiRabi)')
  184. headers_useragents.append('(Privoxy/1.0)')
  185. headers_useragents.append('*/Nutch-0.9-dev')
  186. headers_useragents.append('+SitiDi.net/SitiDiBot/1.0 (+Have Good Day)')
  187. headers_useragents.append('-DIE-KRAEHE- META-SEARCH-ENGINE/1.1 http://www.die-kraehe.de')
  188. headers_useragents.append('123spider-Bot (Version: 1.02) powered by www.123spider.de')
  189. headers_useragents.append('192.comAgent')
  190. headers_useragents.append('1st ZipCommander (Net) - http://www.zipcommander.com/')
  191. headers_useragents.append('2Bone_LinkChecker/1.0 libwww-perl/5.64')
  192. headers_useragents.append('4anything.com LinkChecker v2.0')
  193. headers_useragents.append('8484 Boston Project v 1.0')
  194. headers_useragents.append(':robot/1.0 (linux) ( admin e-mail: undefined http://www.neofonie.de/loesungen/search/robot.html )')
  195. headers_useragents.append('A-Online Search')
  196. headers_useragents.append('A1 Keyword Research/1.0.2 (+http://www.micro-sys.dk/products/keyword-research/) miggibot/2007.03.27')
  197. headers_useragents.append('A1 Sitemap Generator/1.0 (+http://www.micro-sys.dk/products/sitemap-generator/) miggibot/2006.01.24')
  198. headers_useragents.append('AbachoBOT')
  199. headers_useragents.append('AbachoBOT (Mozilla compatible)')
  200. headers_useragents.append('ABCdatos BotLink/5.xx.xxx#BBL')
  201. headers_useragents.append('Aberja Checkomat Aberja Hybridsuchmaschine (Germany)')
  202. headers_useragents.append('abot/0.1 (abot; http://www.abot.com; abot@abot.com)')
  203. headers_useragents.append('About/0.1libwww-perl/5.47')
  204. headers_useragents.append('Accelatech RSSCrawler/0.4')
  205. headers_useragents.append('accoona Accoona Search robot')
  206. headers_useragents.append('Accoona-AI-Agent/1.1.1 (crawler at accoona dot com)')
  207. headers_useragents.append('Accoona-AI-Agent/1.1.2 (aicrawler at accoonabot dot com)')
  208. headers_useragents.append('Ace Explorer')
  209. headers_useragents.append('Ack (http://www.ackerm.com/)')
  210. headers_useragents.append('AcoiRobot')
  211. headers_useragents.append('Acoon Robot v1.50.001')
  212. headers_useragents.append('Acoon Robot v1.52 (http://www.acoon.de)')
  213. headers_useragents.append('Acoon-Robot 4.0.x.[xx] (http://www.acoon.de)')
  214. headers_useragents.append('Acoon-Robot v3.xx (http://www.acoon.de and http://www.acoon.com)')
  215. headers_useragents.append('Acorn/Nutch-0.9 (Non-Profit Search Engine; acorn.isara.org; acorn at isara dot org)')
  216. headers_useragents.append('ActiveBookmark 1.x')
  217. headers_useragents.append('Activeworlds')
  218. headers_useragents.append('ActiveWorlds/3.xx (xxx)')
  219. headers_useragents.append('Ad Muncher v4.xx.x')
  220. headers_useragents.append('Ad Muncher v4x Build xxxxx')
  221. headers_useragents.append('Adaxas Spider (http://www.adaxas.net/)')
  222. headers_useragents.append('Advanced Browser (http://www.avantbrowser.com)')
  223. headers_useragents.append('AESOP_com_SpiderMan')
  224. headers_useragents.append('agadine/1.x.x (+http://www.agada.de)')
  225. headers_useragents.append('Agent-SharewarePlazaFileCheckBot/2.0+(+http://www.SharewarePlaza.com)')
  226. headers_useragents.append('AgentName/0.1 libwww-perl/5.48')
  227. headers_useragents.append('AIBOT/2.1 By +(www.21seek.com A Real artificial intelligence search engine China)')
  228. headers_useragents.append('AideRSS/1.0 (aiderss.com)')
  229. headers_useragents.append('aipbot/1.0 (aipbot; http://www.aipbot.com; aipbot@aipbot.com)')
  230. headers_useragents.append('aipbot/2-beta (aipbot dev; http://aipbot.com; aipbot@aipbot.com)')
  231. headers_useragents.append('Akregator/1.2.9; librss/remnants')
  232. headers_useragents.append('Aladin/3.324')
  233. headers_useragents.append('Alcatel-BG3/1.0 UP.Browser/5.0.3.1.2')
  234. headers_useragents.append('Aleksika Spider/1.0 (+http://www.aleksika.com/)')
  235. headers_useragents.append('AlertInfo 2.0 (Powered by Newsbrain)')
  236. headers_useragents.append('AlkalineBOT/1.3')
  237. headers_useragents.append('AlkalineBOT/1.4 (1.4.0326.0 RTM)')
  238. headers_useragents.append('Allesklar/0.1 libwww-perl/5.46')
  239. headers_useragents.append('Alligator 1.31 (www.nearsoftware.com)')
  240. headers_useragents.append('Allrati/1.1 (+)')
  241. headers_useragents.append('AltaVista Intranet V2.0 AVS EVAL search@freeit.com')
  242. headers_useragents.append('AltaVista Intranet V2.0 Compaq Altavista Eval sveand@altavista.net')
  243. headers_useragents.append('AltaVista Intranet V2.0 evreka.com crawler@evreka.com')
  244. headers_useragents.append('AltaVista V2.0B crawler@evreka.com')
  245. headers_useragents.append('amaya/x.xx libwww/x.x.x')
  246. headers_useragents.append('AmfibiBOT')
  247. headers_useragents.append('Amfibibot/0.06 (Amfibi Web Search; http://www.amfibi.com; agent@amfibi.com)')
  248. headers_useragents.append('Amfibibot/0.07 (Amfibi Robot; http://www.amfibi.com; agent@amfibi.com)')
  249. headers_useragents.append('amibot')
  250. headers_useragents.append('Amiga-AWeb/3.4.167SE')
  251. headers_useragents.append('AmigaVoyager/3.4.4 (MorphOS/PPC native)')
  252. headers_useragents.append('AmiTCP Miami (AmigaOS 2.04)')
  253. headers_useragents.append('Amoi 8512/R21.0 NF-Browser/3.3')
  254. headers_useragents.append('amzn_assoc')
  255. headers_useragents.append('AnnoMille spider 0.1 alpha - http://www.annomille.it')
  256. headers_useragents.append('annotate_google; http://ponderer.org/download/annotate_google.user.js')
  257. headers_useragents.append('Anonymized by ProxyOS: http://www.megaproxy.com')
  258. headers_useragents.append('Anonymizer/1.1')
  259. headers_useragents.append('AnswerBus (http://www.answerbus.com/)')
  260. headers_useragents.append('AnswerChase PROve x.0')
  261. headers_useragents.append('AnswerChase x.0')
  262. headers_useragents.append('ANTFresco/x.xx')
  263. headers_useragents.append('antibot-V1.1.5/i586-linux-2.2')
  264. headers_useragents.append('AnzwersCrawl/2.0 (anzwerscrawl@anzwers.com.au;Engine)')
  265. headers_useragents.append('Apexoo Spider 1.x')
  266. headers_useragents.append('Aplix HTTP/1.0.1')
  267. headers_useragents.append('Aplix_SANYO_browser/1.x (Japanese)')
  268. headers_useragents.append('Aplix_SEGASATURN_browser/1.x (Japanese)')
  269. headers_useragents.append('Aport')
  270. headers_useragents.append('appie 1.1 (www.walhello.com)')
  271. headers_useragents.append('Apple iPhone v1.1.4 CoreMedia v1.0.0.4A102')
  272. headers_useragents.append('Apple-PubSub/65.1.1')
  273. headers_useragents.append('ArabyBot (compatible; Mozilla/5.0; GoogleBot; FAST Crawler 6.4; http://www.araby.com;)')
  274. headers_useragents.append('ArachBot')
  275. headers_useragents.append('Arachnoidea (arachnoidea@euroseek.com)')
  276. headers_useragents.append('aranhabot')
  277. headers_useragents.append('ArchitextSpider')
  278. headers_useragents.append('archive.org_bot')
  279. headers_useragents.append('Argus/1.1 (Nutch; http://www.simpy.com/bot.html; feedback at simpy dot com)')
  280. headers_useragents.append('Arikus_Spider')
  281. headers_useragents.append('Arquivo-web-crawler (compatible; heritrix/1.12.1 +http://arquivo-web.fccn.pt)')
  282. headers_useragents.append('ASAHA Search Engine Turkey V.001 (http://www.asaha.com/)')
  283. headers_useragents.append('Asahina-Antenna/1.x')
  284. headers_useragents.append('Asahina-Antenna/1.x (libhina.pl/x.x ; libtime.pl/x.x)')
  285. headers_useragents.append('ask.24x.info')
  286. headers_useragents.append('AskAboutOil/0.06-rcp (Nutch; http://www.nutch.org/docs/en/bot.html; nutch-agent@askaboutoil.com)')
  287. headers_useragents.append('asked/Nutch-0.8 (web crawler; http://asked.jp; epicurus at gmail dot com)')
  288. headers_useragents.append('ASPSeek/1.2.5')
  289. headers_useragents.append('ASPseek/1.2.9d')
  290. headers_useragents.append('ASPSeek/1.2.x')
  291. headers_useragents.append('ASPSeek/1.2.xa')
  292. headers_useragents.append('ASPseek/1.2.xx')
  293. headers_useragents.append('ASPSeek/1.2.xxpre')
  294. headers_useragents.append('ASSORT/0.10')
  295. headers_useragents.append('asterias/2.0')
  296. headers_useragents.append('AtlocalBot/1.1 +(http://www.atlocal.com/local-web-site-owner.html)')
  297. headers_useragents.append('Atomic_Email_Hunter/4.0')
  298. headers_useragents.append('Atomz/1.0')
  299. headers_useragents.append('atSpider/1.0')
  300. headers_useragents.append('Attentio/Nutch-0.9-dev (Attentios beta blog crawler; www.attentio.com; info@attentio.com)')
  301. headers_useragents.append('AU-MIC/2.0 MMP/2.0')
  302. headers_useragents.append('AUDIOVOX-SMT5600')
  303. headers_useragents.append('augurfind')
  304. headers_useragents.append('augurnfind V-1.x')
  305. headers_useragents.append('autoemailspider')
  306. headers_useragents.append('autohttp')
  307. headers_useragents.append('autowebdir 1.1 (www.autowebdir.com)')
  308. headers_useragents.append('AV Fetch 1.0')
  309. headers_useragents.append('Avant Browser (http://www.avantbrowser.com)')
  310. headers_useragents.append('AVSearch-1.0(peter.turney@nrc.ca)')
  311. headers_useragents.append('AVSearch-2.0-fusionIdx-14-CompetitorWebSites')
  312. headers_useragents.append('AVSearch-3.0(AltaVista/AVC)')
  313. headers_useragents.append('AWeb')
  314. headers_useragents.append('axadine/ (Axadine Crawler; http://www.axada.de/; )')
  315. headers_useragents.append('AxmoRobot - Crawling your site for better indexing on www.axmo.com search engine.')
  316. headers_useragents.append('Azureus 2.x.x.x')
  317. headers_useragents.append('BabalooSpider/1.3 (BabalooSpider; http://www.babaloo.si; spider@babaloo.si)')
  318. headers_useragents.append('BaboomBot/1.x.x (+http://www.baboom.us)')
  319. headers_useragents.append('BackStreet Browser 3.x')
  320. headers_useragents.append('BaiduImagespider+(+http://www.baidu.jp/search/s308.html)')
  321. headers_useragents.append('BaiDuSpider')
  322. headers_useragents.append('Baiduspider+(+http://help.baidu.jp/system/05.html)')
  323. headers_useragents.append('Baiduspider+(+http://www.baidu.com/search/spider.htm)')
  324. headers_useragents.append('Baiduspider+(+http://www.baidu.com/search/spider_jp.html)')
  325. headers_useragents.append('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)')
  326. headers_useragents.append('BanBots/1.2 (spider@banbots.com)')
  327. headers_useragents.append('Barca/2.0.xxxx')
  328. headers_useragents.append('BarcaPro/1.4.xxxx')
  329. headers_useragents.append('BarraHomeCrawler (albertof@barrahome.org)')
  330. headers_useragents.append('bCentral Billing Post-Process')
  331. headers_useragents.append('bdcindexer_2.6.2 (research@bdc)')
  332. headers_useragents.append('BDFetch')
  333. headers_useragents.append('BDNcentral Crawler v2.3 [en] (http://www.bdncentral.com/robot.html) (X11; I; Linux 2.0.44 i686)')
  334. headers_useragents.append('BeamMachine/0.5 (dead link remover of www.beammachine.net)')
  335. headers_useragents.append('beautybot/1.0 (+http://www.uchoose.de/crawler/beautybot/)')
  336. headers_useragents.append('BebopBot/2.5.1 ( crawler http://www.apassion4jazz.net/bebopbot.html )')
  337. headers_useragents.append('BeebwareDirectory/v0.01')
  338. headers_useragents.append('Big Brother (http://pauillac.inria.fr/~fpottier/)')
  339. headers_useragents.append('Big Fish v1.0')
  340. headers_useragents.append('BigBrother/1.6e')
  341. headers_useragents.append('BigCliqueBOT/1.03-dev (bigclicbot; http://www.bigclique.com; bot@bigclique.com)')
  342. headers_useragents.append('BIGLOTRON (Beta 2;GNU/Linux)')
  343. headers_useragents.append('Bigsearch.ca/Nutch-x.x-dev (Bigsearch.ca Internet Spider; http://www.bigsearch.ca/; info@enhancededge.com)')
  344. headers_useragents.append('Bilbo/2.3b-UNIX')
  345. headers_useragents.append('BilgiBetaBot/0.8-dev (bilgi.com (Beta) ; http://lucene.apache.org/nutch/bot.html; nutch-agent@lucene.apache.org)')
  346. headers_useragents.append('BilgiBot/1.0(beta) (http://www.bilgi.com/; bilgi at bilgi dot com)')
  347. headers_useragents.append('billbot wjj@cs.cmu.edu')
  348. headers_useragents.append('Bitacle bot/1.1')
  349. headers_useragents.append('Bitacle Robot (V:1.0;) (http://www.bitacle.com)')
  350. headers_useragents.append('Biyubi/x.x (Sistema Fenix; G11; Familia Toledo; es-mx)')
  351. headers_useragents.append('BlackBerry7520/4.0.0 Profile/MIDP-2.0 Configuration/CLDC-1.1 UP.Browser/5.0.3.3 UP.Link/5.1.2.12 (Google WAP Proxy/1.0)')
  352. headers_useragents.append('BlackWidow')
  353. headers_useragents.append('BlackWidow')
  354. headers_useragents.append('Blaiz-Bee/1.0 (+http://www.blaiz.net)')
  355. headers_useragents.append('Blaiz-Bee/2.00.8222 (BE Internet Search Engine http://www.rawgrunt.com)')
  356. headers_useragents.append('Blaiz-Bee/2.00.xxxx (+http://www.blaiz.net)')
  357. headers_useragents.append('BlitzBOT@tricus.net')
  358. headers_useragents.append('BlitzBOT@tricus.net (Mozilla compatible)')
  359. headers_useragents.append('BlockNote.Net')
  360. headers_useragents.append('BlogBot/1.x')
  361. headers_useragents.append('BlogBridge 2.13 (http://www.blogbridge.com/)')
  362. headers_useragents.append('Bloglines Title Fetch/1.0 (http://www.bloglines.com)')
  363. headers_useragents.append('Bloglines-Images/0.1 (http://www.bloglines.com)')
  364. headers_useragents.append('Bloglines/3.1 (http://www.bloglines.com)')
  365. headers_useragents.append('BlogMap (http://www.feedmap.net)')
  366. headers_useragents.append('Blogpulse (info@blogpulse.com)')
  367. headers_useragents.append('BlogPulseLive (support@blogpulse.com)')
  368. headers_useragents.append('BlogSearch/1.x +http://www.icerocket.com/')
  369. headers_useragents.append('blogsearchbot-pumpkin-3')
  370. headers_useragents.append('BlogsNowBot) V 2.01 (+http://www.blogsnow.com/)')
  371. headers_useragents.append('BlogVibeBot-v1.1 (spider@blogvibe.nl)')
  372. headers_useragents.append('blogWatcher_Spider/0.1 (http://www.lr.pi.titech.ac.jp/blogWatcher/)')
  373. headers_useragents.append('BlogzIce/1.0 (+http://icerocket.com; rhodes@icerocket.com)')
  374. headers_useragents.append('BlogzIce/1.0 +http://www.icerocket.com/')
  375. headers_useragents.append('BloobyBot')
  376. headers_useragents.append('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)')
  377. headers_useragents.append('bluefish 0.6 HTML editor')
  378. headers_useragents.append('BMCLIENT')
  379. headers_useragents.append('BMLAUNCHER')
  380. headers_useragents.append('Bobby/4.0.x RPT-HTTPClient/0.3-3E')
  381. headers_useragents.append('boitho.com-dc/0.xx (http://www.boitho.com/dcbot.html)')
  382. headers_useragents.append('boitho.com-robot/1.x')
  383. headers_useragents.append('boitho.com-robot/1.x (http://www.boitho.com/bot.html)')
  384. headers_useragents.append('Bookdog/x.x')
  385. headers_useragents.append('Bookmark Buddy bookmark checker (http://www.bookmarkbuddy.net/)')
  386. headers_useragents.append('Bookmark Renewal Check Agent [http://www.bookmark.ne.jp/]')
  387. headers_useragents.append('Bookmark Renewal Check Agent [http://www.bookmark.ne.jp/]')
  388. headers_useragents.append('BookmarkBase(2/;http://bookmarkbase.com)')
  389. headers_useragents.append('Bot mailto:craftbot@yahoo.com')
  390. headers_useragents.append('BPImageWalker/2.0 (www.bdbrandprotect.com)')
  391. headers_useragents.append('BravoBrian bstop.bravobrian.it')
  392. headers_useragents.append('BravoBrian SpiderEngine MarcoPolo')
  393. headers_useragents.append('BrightCrawler (http://www.brightcloud.com/brightcrawler.asp)')
  394. headers_useragents.append('BruinBot (+http://webarchive.cs.ucla.edu/bruinbot.html)')
  395. headers_useragents.append('BSDSeek/1.0')
  396. headers_useragents.append('BStop.BravoBrian.it Agent Detector')
  397. headers_useragents.append('BTbot/0.x (+http://www.btbot.com/btbot.html)')
  398. headers_useragents.append('BTWebClient/180B(9704)')
  399. headers_useragents.append('BuildCMS crawler (http://www.buildcms.com/crawler)')
  400. headers_useragents.append('Bulkfeeds/r1752 (http://bulkfeeds.net/)')
  401. headers_useragents.append('BullsEye')
  402. headers_useragents.append('bumblebee@relevare.com')
  403. headers_useragents.append('BunnySlippers')
  404. headers_useragents.append('BurstFindCrawler/1.1 (crawler.burstfind.com; http://crawler.burstfind.com; crawler@burstfind.com)')
  405. headers_useragents.append('Buscaplus Robi/1.0 (http://www.buscaplus.com/robi/)')
  406. headers_useragents.append('BW-C-2.0')
  407. headers_useragents.append('bwh3_user_agent')
  408. headers_useragents.append('Cabot/Nutch-0.9 (Amfibis web-crawling robot; http://www.amfibi.com/cabot/; agent@amfibi.com)')
  409. headers_useragents.append('Cabot/Nutch-1.0-dev (Amfibis web-crawling robot; http://www.amfibi.com/cabot/; agent@amfibi.com)')
  410. headers_useragents.append('CamelHttpStream/1.0')
  411. headers_useragents.append('Cancer Information and Support International;')
  412. headers_useragents.append('carleson/1.0')
  413. headers_useragents.append('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')
  414. headers_useragents.append('Carnegie_Mellon_University_WebCrawler http://www.andrew.cmu.edu/~brgordon/webbot/index.html')
  415. headers_useragents.append('Catall Spider')
  416. headers_useragents.append('CazoodleBot/CazoodleBot-0.1 (CazoodleBot Crawler; http://www.cazoodle.com/cazoodlebot; cazoodlebot@cazoodle.com)')
  417. headers_useragents.append('CCBot/1.0 (+http://www.commoncrawl.org/bot.html)')
  418. headers_useragents.append('ccubee/x.x')
  419. headers_useragents.append('CDR/1.7.1 Simulator/0.7(+http://timewe.net) Profile/MIDP-1.0 Configuration/CLDC-1.0')
  420. headers_useragents.append('CE-Preload')
  421. headers_useragents.append('CentiverseBot')
  422. headers_useragents.append('CentiverseBot - investigator')
  423. headers_useragents.append('CentiverseBot/3.0 (http://www.centiverse-project.net)')
  424. headers_useragents.append('Ceramic Tile Installation Guide (http://www.floorstransformed.com)')
  425. headers_useragents.append('CERN-LineMode/2.15')
  426. headers_useragents.append('cfetch/1.0')
  427. headers_useragents.append('CFNetwork/x.x')
  428. headers_useragents.append('cg-eye interactive')
  429. headers_useragents.append('Charon/1.x (Amiga)')
  430. headers_useragents.append('Chat Catcher/1.0')
  431. headers_useragents.append('Checkbot/1.xx LWP/5.xx')
  432. headers_useragents.append('CheckLinks/1.x.x')
  433. headers_useragents.append('CheckUrl')
  434. headers_useragents.append('CheckWeb')
  435. headers_useragents.append('Chilkat/1.0.0 (+http://www.chilkatsoft.com/ChilkatHttpUA.asp)')
  436. headers_useragents.append('China Local Browse 2.6')
  437. headers_useragents.append('Chitika ContentHit 1.0')
  438. headers_useragents.append('ChristCRAWLER 2.0')
  439. headers_useragents.append('CHttpClient by Open Text Corporation')
  440. headers_useragents.append('CipinetBot (http://www.cipinet.com/bot.html)')
  441. headers_useragents.append('Cityreview Robot (+http://www.cityreview.org/crawler/)')
  442. headers_useragents.append('CJ Spider/')
  443. headers_useragents.append('CJB.NET Proxy')
  444. headers_useragents.append('ClariaBot/1.0')
  445. headers_useragents.append('Claymont.com')
  446. headers_useragents.append('CloakDetect/0.9 (+http://fulltext.seznam.cz/)')
  447. headers_useragents.append('Clushbot/2.x (+http://www.clush.com/bot.html)')
  448. headers_useragents.append('Clushbot/3.x-BinaryFury (+http://www.clush.com/bot.html)')
  449. headers_useragents.append('Clushbot/3.xx-Ajax (+http://www.clush.com/bot.html)')
  450. headers_useragents.append('Clushbot/3.xx-Hector (+http://www.clush.com/bot.html)')
  451. headers_useragents.append('Clushbot/3.xx-Peleus (+http://www.clush.com/bot.html)')
  452. headers_useragents.append('COAST WebMaster Pro/4.x.x.xx (Windows NT)')
  453. headers_useragents.append('CoBITSProbe')
  454. headers_useragents.append('Cocoal.icio.us/1.0 (v36) (Mac OS X; http://www.scifihifi.com/cocoalicious)')
  455. headers_useragents.append('Cogentbot/1.X (+http://www.cogentsoftwaresolutions.com/bot.html)')
  456. headers_useragents.append('ColdFusion')
  457. headers_useragents.append('ColdFusion (BookmarkTracker.com)')
  458. headers_useragents.append('collage.cgi/1.xx')
  459. headers_useragents.append('combine/0.0')
  460. headers_useragents.append('Combine/2.0 http://combine.it.lth.se/')
  461. headers_useragents.append('Combine/3 http://combine.it.lth.se/')
  462. headers_useragents.append('Combine/x.0')
  463. headers_useragents.append('cometrics-bot) http://www.cometrics.de')
  464. headers_useragents.append('Commerce Browser Center')
  465. headers_useragents.append('complex_network_group/Nutch-0.9-dev (discovering the structure of the world-wide-web; http://cantor.ee.ucla.edu/~networks/crawl; nimakhaj@gmail.com)')
  466. headers_useragents.append('Computer_and_Automation_Research_Institute_Crawler crawler@ilab.sztaki.hu')
  467. headers_useragents.append('Comrite/0.7.1 (Nutch; http://lucene.apache.org/nutch/bot.html; nutch-agent@lucene.apache.org)')
  468. headers_useragents.append('Contact')
  469. headers_useragents.append('ContactBot/0.2')
  470. headers_useragents.append('ContentSmartz')
  471. headers_useragents.append('contype')
  472. headers_useragents.append('Convera Internet Spider V6.x')
  473. headers_useragents.append('ConveraCrawler/0.2')
  474. headers_useragents.append('ConveraCrawler/0.9d (+http://www.authoritativeweb.com/crawl)')
  475. headers_useragents.append('ConveraMultiMediaCrawler/0.1 (+http://www.authoritativeweb.com/crawl)')
  476. headers_useragents.append('CoolBot')
  477. headers_useragents.append('Cooliris/1.5 CFNetwork/459 Darwin/10.0.0d3')
  478. headers_useragents.append('CoralWebPrx/0.1.1x (See http://coralcdn.org/)')
  479. headers_useragents.append('cosmos/0.8_(robot@xyleme.com)')
  480. headers_useragents.append('cosmos/0.9_(robot@xyleme.com)')
  481. headers_useragents.append('CoteoNutchCrawler/Nutch-0.9 (info [at] coteo [dot] com)')
  482. headers_useragents.append('CougarSearch/0.x (+http://www.cougarsearch.com/faq.shtml)')
  483. headers_useragents.append('Covac TexAs Arachbot')
  484. headers_useragents.append('CoverScout%203/3.0.1 CFNetwork/339.5 Darwin/9.5.0 (i386) (iMac5)1)')
  485. headers_useragents.append('Cowbot-0.1 (NHN Corp. / +82-2-3011-1954 / nhnbot@naver.com)')
  486. headers_useragents.append('Cowbot-0.1.x (NHN Corp. / +82-2-3011-1954 / nhnbot@naver.com)')
  487. headers_useragents.append('CrawlConvera0.1 (CrawlConvera@yahoo.com)')
  488. headers_useragents.append('Crawler')
  489. headers_useragents.append('Crawler (cometsearch@cometsystems.com)')
  490. headers_useragents.append('Crawler admin@crawler.de')
  491. headers_useragents.append('Crawler V 0.2.x admin@crawler.de')
  492. headers_useragents.append('crawler@alexa.com')
  493. headers_useragents.append('CrawlerBoy Pinpoint.com')
  494. headers_useragents.append('Crawllybot/0.1 (Crawllybot; +http://www.crawlly.com; crawler@crawlly.com)')
  495. headers_useragents.append('CreativeCommons/0.06-dev (Nutch; http://www.nutch.org/docs/en/bot.html; nutch-agent@lists.sourceforge.net)')
  496. headers_useragents.append('Cricket-A100/1.0 UP.Browser/6.3.0.7 (GUI) MMP/2.0')
  497. headers_useragents.append('CrocCrawler vx.3 [en] (http://www.croccrawler.com) (X11; I; Linux 2.0.44 i686)')
  498. headers_useragents.append('csci_b659/0.13')
  499. headers_useragents.append('CSE HTML Validator Professional (http://www.htmlvalidator.com/)')
  500. headers_useragents.append('Cuam Ver0.050bx')
  501. headers_useragents.append('Cuasarbot/0.9b http://www.cuasar.com/spider_beta/')
  502. headers_useragents.append('curl/7.10.x (i386-redhat-linux-gnu) libcurl/7.10.x OpenSSL/0.9.7a ipv6 zlib/1.1.4')
  503. headers_useragents.append('curl/7.7.x (i386--freebsd4.3) libcurl 7.7.x (SSL 0.9.6) (ipv6 enabled)')
  504. headers_useragents.append('curl/7.8 (i686-pc-linux-gnu) libcurl 7.8 (OpenSSL 0.9.6)')
  505. headers_useragents.append('curl/7.9.x (win32) libcurl 7.9.x')
  506. headers_useragents.append('CurryGuide SiteScan 1.1')
  507. headers_useragents.append('Custo x.x (www.netwu.com)')
  508. headers_useragents.append('Custom Spider www.bisnisseek.com /1.0')
  509. headers_useragents.append('Cyberdog/2.0 (Macintosh; 68k)')
  510. headers_useragents.append('CyberPatrol SiteCat Webbot')
  511. headers_useragents.append('CyberSpyder Link Test/2.1.12')
  512. headers_useragents.append('CydralSpider/1.x')
  513. headers_useragents.append('CydralSpider/3.0')
  514. headers_useragents.append('DA 3.5')
  515. headers_useragents.append('DA 4.0')
  516. headers_useragents.append('DA 4.0')
  517. headers_useragents.append('DA 5.0')
  518. headers_useragents.append('DA 7.0')
  519. headers_useragents.append('DAP x.x')
  520. headers_useragents.append('Dart Communications PowerTCP')
  521. headers_useragents.append('DataCha0s/2.0')
  522. headers_useragents.append('DataCha0s/2.0')
  523. headers_useragents.append('DataFountains/DMOZ Downloader')
  524. headers_useragents.append('DataFountains/Dmoz Downloader (http://ivia.ucr.edu/useragents.shtml)')
  525. headers_useragents.append('DataFountains/DMOZ Feature Vector Corpus Creator (http://ivia.ucr.edu/useragents.shtml)')
  526. headers_useragents.append('DataparkSearch/4.47 (+http://dataparksearch.org/bot)')
  527. headers_useragents.append('DataparkSearch/4.xx (http://www.dataparksearch.org/)')
  528. headers_useragents.append('DataSpear/1.0 (Spider; http://www.dataspear.com/spider.html; spider@dataspear.com)')
  529. headers_useragents.append('DataSpearSpiderBot/0.2 (DataSpear Spider Bot; http://dssb.dataspear.com/bot.html; dssb@dataspear.com)')
  530. headers_useragents.append('DatenBot( http://www.sicher-durchs-netz.de/bot.html)')
  531. headers_useragents.append('DaviesBot/1.7')
  532. headers_useragents.append('daypopbot/0.x')
  533. headers_useragents.append('dbDig(http://www.prairielandconsulting.com)')
  534. headers_useragents.append('DBrowse 1.4b')
  535. headers_useragents.append('DBrowse 1.4d')
  536. headers_useragents.append('DC-Sakura/x.xx')
  537. headers_useragents.append('dCSbot/1.1')
  538. headers_useragents.append('DDD')
  539. headers_useragents.append('dds explorer v1.0 beta')
  540. headers_useragents.append('de.searchengine.comBot 1.2 (http://de.searchengine.com/spider)')
  541. headers_useragents.append('DeadLinkCheck/0.4.0 libwww-perl/5.xx')
  542. headers_useragents.append('Deep Link Calculator v1.0')
  543. headers_useragents.append('deepak-USC/ISI')
  544. headers_useragents.append('DeepIndex')
  545. headers_useragents.append('DeepIndex ( http://www.zetbot.com )')
  546. headers_useragents.append('DeepIndex (www.en.deepindex.com)')
  547. headers_useragents.append('DeepIndexer.ca')
  548. headers_useragents.append('del.icio.us-thumbnails/1.0 Mozilla/5.0 (compatible; Konqueror/3.4; FreeBSD) KHTML/3.4.2 (like Gecko)')
  549. headers_useragents.append('DeleGate/9.0.5-fix1')
  550. headers_useragents.append('Demo Bot DOT 16b')
  551. headers_useragents.append('Demo Bot Z 16b')
  552. headers_useragents.append('Denmex websearch (http://search.denmex.com)')
  553. headers_useragents.append('dev-spider2.searchpsider.com/1.3b')
  554. headers_useragents.append('DevComponents.com HtmlDocument Object')
  555. headers_useragents.append('DiaGem/1.1 (http://www.skyrocket.gr.jp/diagem.html)')
  556. headers_useragents.append('Diamond/x.0')
  557. headers_useragents.append('DiamondBot')
  558. headers_useragents.append('Digger/1.0 JDK/1.3.0rc3')
  559. headers_useragents.append('DigOut4U')
  560. headers_useragents.append('DIIbot/1.2')
  561. headers_useragents.append('Dillo/0.8.5-i18n-misc')
  562. headers_useragents.append('Dillo/0.x.x')
  563. headers_useragents.append('disastrous/1.0.5 (running with Python 2.5.1; http://www.bortzmeyer.org/disastrous.html; archangel77@del.icio.us)')
  564. headers_useragents.append('DISCo Pump x.x')
  565. headers_useragents.append('disco/Nutch-0.9 (experimental crawler; www.discoveryengine.com; disco-crawl@discoveryengine.com)')
  566. headers_useragents.append('disco/Nutch-1.0-dev (experimental crawler; www.discoveryengine.com; disco-crawl@discoveryengine.com)')
  567. headers_useragents.append('DittoSpyder')
  568. headers_useragents.append('dloader(NaverRobot)/1.0')
  569. headers_useragents.append('DNSRight.com WebBot Link Ckeck Tool. Report abuse to: dnsr@dnsright.com')
  570. headers_useragents.append('DoCoMo/1.0/Nxxxi/c10')
  571. headers_useragents.append('DoCoMo/1.0/Nxxxi/c10/TB')
  572. headers_useragents.append('DoCoMo/1.0/P502i/c10 (Google CHTML Proxy/1.0)')
  573. headers_useragents.append('DoCoMo/2.0 P900iV(c100;TB;W24H11)')
  574. headers_useragents.append('DoCoMo/2.0 SH901iS(c100;TB;W24H12))gzip(gfe) (via translate.google.com)')
  575. headers_useragents.append('DoCoMo/2.0 SH902i (compatible; Y!J-SRD/1.0; http://help.yahoo.co.jp/help/jp/search/indexing/indexing-27.html)')
  576. headers_useragents.append('DoCoMo/2.0/SO502i (compatible; Y!J-SRD/1.0; http://help.yahoo.co.jp/help/jp/search/indexing/indexing-27.html)')
  577. headers_useragents.append('DocZilla/1.0 (Windows; U; WinNT4.0; en-US; rv:1.0.0) Gecko/20020804')
  578. headers_useragents.append('dodgebot/experimental')
  579. headers_useragents.append('DonutP; Windows98SE')
  580. headers_useragents.append('Doubanbot/1.0 (bot@douban.com http://www.douban.com)')
  581. headers_useragents.append('Download Demon/3.x.x.x')
  582. headers_useragents.append('Download Druid 2.x')
  583. headers_useragents.append('Download Express 1.0')
  584. headers_useragents.append('Download Master')
  585. headers_useragents.append('Download Ninja 3.0')
  586. headers_useragents.append('Download Wonder')
  587. headers_useragents.append('Download-Tipp Linkcheck (http://download-tipp.de/)')
  588. headers_useragents.append('Download.exe(1.1) (+http://www.sql-und-xml.de/freeware-tools/)')
  589. headers_useragents.append('DownloadDirect.1.0')
  590. headers_useragents.append('Dr.Web (R) online scanner: http://online.drweb.com/')
  591. headers_useragents.append('Dragonfly File Reader')
  592. headers_useragents.append('Drecombot/1.0 (http://career.drecom.jp/bot.html)')
  593. headers_useragents.append('Drupal (+http://drupal.org/)')
  594. headers_useragents.append('DSurf15a 01')
  595. headers_useragents.append('DSurf15a 71')
  596. headers_useragents.append('DSurf15a 81')
  597. headers_useragents.append('DSurf15a VA')
  598. headers_useragents.append('DTAAgent')
  599. headers_useragents.append('dtSearchSpider')
  600. headers_useragents.append('Dual Proxy')
  601. headers_useragents.append('DuckDuckBot/1.0; (+http://duckduckgo.com/duckduckbot.html)')
  602. headers_useragents.append('Dumbot(version 0.1 beta - dumbfind.com)')
  603. headers_useragents.append('Dumbot(version 0.1 beta - http://www.dumbfind.com/dumbot.html)')
  604. headers_useragents.append('Dumbot(version 0.1 beta)')
  605. headers_useragents.append('e-sense 1.0 ea(www.vigiltech.com/esensedisclaim.html)')
  606. headers_useragents.append('e-SocietyRobot(http://www.yama.info.waseda.ac.jp/~yamana/es/)')
  607. headers_useragents.append('eApolloBot/2.0 (compatible; heritrix/2.0.0-SNAPSHOT-20071024.170148 +http://www.eapollo-opto.com)')
  608. headers_useragents.append('EARTHCOM.info/1.x [www.earthcom.info]')
  609. headers_useragents.append('EARTHCOM.info/1.xbeta [www.earthcom.info]')
  610. headers_useragents.append('EasyDL/3.xx')
  611. headers_useragents.append('EasyDL/3.xx http://keywen.com/Encyclopedia/Bot')
  612. headers_useragents.append('EBrowse 1.4b')
  613. headers_useragents.append('eCatch/3.0')
  614. headers_useragents.append('EchO!/2.0')
  615. headers_useragents.append('Educate Search VxB')
  616. headers_useragents.append('egothor/3.0a (+http://www.xdefine.org/robot.html)')
  617. headers_useragents.append('EgotoBot/4.8 (+http://www.egoto.com/about.htm)')
  618. headers_useragents.append('ejupiter.com')
  619. headers_useragents.append('EldoS TimelyWeb/3.x')
  620. headers_useragents.append('elfbot/1.0 (+http://www.uchoose.de/crawler/elfbot/)')
  621. headers_useragents.append('ELI/20070402:2.0 (DAUM RSS Robot) Daum Communications Corp.; +http://ws.daum.net/aboutkr.html)')
  622. headers_useragents.append('ELinks (0.x.x; Linux 2.4.20 i586; 132x60)')
  623. headers_useragents.append('ELinks/0.x.x (textmode; NetBSD 1.6.2 sparc; 132x43)')
  624. headers_useragents.append('EmailSiphon')
  625. headers_useragents.append('EmailSpider')
  626. headers_useragents.append('EmailWolf 1.00')
  627. headers_useragents.append('EmeraldShield.com WebBot')
  628. headers_useragents.append('EmeraldShield.com WebBot (http://www.emeraldshield.com/webbot.aspx)')
  629. headers_useragents.append('EMPAS_ROBOT')
  630. headers_useragents.append('EnaBot/1.x (http://www.enaball.com/crawler.html)')
  631. headers_useragents.append('endo/1.0 (Mac OS X; ppc i386; http://kula.jp/endo)')
  632. headers_useragents.append('Enfish Tracker')
  633. headers_useragents.append('Enterprise_Search/1.0')
  634. headers_useragents.append('Enterprise_Search/1.0.xxx')
  635. headers_useragents.append('Enterprise_Search/1.00.xxx;MSSQL (http://www.innerprise.net/es-spider.asp)')
  636. headers_useragents.append('envolk/1.7 (+http://www.envolk.com/envolkspiderinfo.php)')
  637. headers_useragents.append('envolk[ITS]spider/1.6(+http://www.envolk.com/envolkspider.html)')
  638. headers_useragents.append('EroCrawler')
  639. headers_useragents.append('ES.NET_Crawler/2.0 (http://search.innerprise.net/)')
  640. headers_useragents.append('eseek-larbin_2.6.2 (crawler@exactseek.com)')
  641. headers_useragents.append('ESISmartSpider')
  642. headers_useragents.append('eStyleSearch 4 (compatible; MSIE 6.0; Windows NT 5.0)')
  643. headers_useragents.append('ESurf15a 15')
  644. headers_useragents.append('EuripBot/0.x (+http://www.eurip.com) GetFile')
  645. headers_useragents.append('EuripBot/0.x (+http://www.eurip.com) GetRobots')
  646. headers_useragents.append('EuripBot/0.x (+http://www.eurip.com) PreCheck')
  647. headers_useragents.append('Eurobot/1.0 (http://www.ayell.eu)')
  648. headers_useragents.append('EvaalSE - bot@evaal.com')
  649. headers_useragents.append('eventax/1.3 (eventax; http://www.eventax.de/; info@eventax.de)')
  650. headers_useragents.append('Everest-Vulcan Inc./0.1 (R&D project; host=e-1-24; http://everest.vulcan.com/crawlerhelp)')
  651. headers_useragents.append('Everest-Vulcan Inc./0.1 (R&D project; http://everest.vulcan.com/crawlerhelp)')
  652. headers_useragents.append('Exabot-Images/1.0')
  653. headers_useragents.append('Exabot-Test/1.0')
  654. headers_useragents.append('Exabot/2.0')
  655. headers_useragents.append('Exabot/3.0')
  656. headers_useragents.append('ExactSearch')
  657. headers_useragents.append('ExactSeek Crawler/0.1')
  658. headers_useragents.append('exactseek-crawler-2.63 (crawler@exactseek.com)')
  659. headers_useragents.append('exactseek-pagereaper-2.63 (crawler@exactseek.com)')
  660. headers_useragents.append('exactseek.com')
  661. headers_useragents.append('Exalead NG/MimeLive Client (convert/http/0.120)')
  662. headers_useragents.append('Excalibur Internet Spider V6.5.4')
  663. headers_useragents.append('Execrawl/1.0 (Execrawl; http://www.execrawl.com/; bot@execrawl.com)')
  664. headers_useragents.append('exooba crawler/exooba crawler (crawler for exooba.com; http://www.exooba.com/; info at exooba dot com)')
  665. headers_useragents.append('exooba/exooba crawler (exooba; exooba)')
  666. headers_useragents.append('ExperimentalHenrytheMiragoRobot')
  667. headers_useragents.append('Expired Domain Sleuth')
  668. headers_useragents.append('Express WebPictures (www.express-soft.com)')
  669. headers_useragents.append('ExtractorPro')
  670. headers_useragents.append('Extreme Picture Finder')
  671. headers_useragents.append('EyeCatcher (Download-tipp.de)/1.0')
  672. headers_useragents.append('Factbot 1.09 (see http://www.factbites.com/webmasters.php)')
  673. headers_useragents.append('factbot : http://www.factbites.com/robots')
  674. headers_useragents.append('FaEdit/2.0.x')
  675. headers_useragents.append('FairAd Client')
  676. headers_useragents.append('FANGCrawl/0.01')
  677. headers_useragents.append('FARK.com link verifier')
  678. headers_useragents.append('Fast Crawler Gold Edition')
  679. headers_useragents.append('FAST Enterprise Crawler 6 (Experimental)')
  680. headers_useragents.append('FAST Enterprise Crawler 6 / Scirus scirus-crawler@fast.no; http://www.scirus.com/srsapp/contactus/')
  681. headers_useragents.append('FAST Enterprise Crawler 6 used by Cobra Development (admin@fastsearch.com)')
  682. headers_useragents.append('FAST Enterprise Crawler 6 used by Comperio AS (sts@comperio.no)')
  683. headers_useragents.append('FAST Enterprise Crawler 6 used by FAST (FAST)')
  684. headers_useragents.append('FAST Enterprise Crawler 6 used by Pages Jaunes (pvincent@pagesjaunes.fr)')
  685. headers_useragents.append('FAST Enterprise Crawler 6 used by Sensis.com.au Web Crawler (search_comments\at\sensis\dot\com\dot\au)')
  686. headers_useragents.append('FAST Enterprise Crawler 6 used by Singapore Press Holdings (crawler@sphsearch.sg)')
  687. headers_useragents.append('FAST Enterprise Crawler 6 used by WWU (wardi@uni-muenster.de)')
  688. headers_useragents.append('FAST Enterprise Crawler/6 (www.fastsearch.com)')
  689. headers_useragents.append('FAST Enterprise Crawler/6.4 (helpdesk at fast.no)')
  690. headers_useragents.append('FAST FirstPage retriever (compatible; MSIE 5.5; Mozilla/4.0)')
  691. headers_useragents.append('FAST MetaWeb Crawler (helpdesk at fastsearch dot com)')
  692. headers_useragents.append('Fast PartnerSite Crawler')
  693. headers_useragents.append('FAST-WebCrawler/2.2.10 (Multimedia Search) (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)')
  694. headers_useragents.append('FAST-WebCrawler/2.2.6 (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)')
  695. headers_useragents.append('FAST-WebCrawler/2.2.7 (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)http://www.fast.no')
  696. headers_useragents.append('FAST-WebCrawler/2.2.8 (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)http://www.fast.no')
  697. headers_useragents.append('FAST-WebCrawler/3.2 test')
  698. headers_useragents.append('FAST-WebCrawler/3.3 (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)')
  699. headers_useragents.append('FAST-WebCrawler/3.4/Nirvana (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)')
  700. headers_useragents.append('FAST-WebCrawler/3.4/PartnerSite (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)')
  701. headers_useragents.append('FAST-WebCrawler/3.5 (atw-crawler at fast dot no; http://fast.no/support.php?c=faqs/crawler)')
  702. headers_useragents.append('FAST-WebCrawler/3.6 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)')
  703. headers_useragents.append('FAST-WebCrawler/3.6/FirstPage (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)')
  704. headers_useragents.append('FAST-WebCrawler/3.7 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)')
  705. headers_useragents.append('FAST-WebCrawler/3.7/FirstPage (atw-crawler at fast dot no;http://fast.no/support/crawler.asp)')
  706. headers_useragents.append('FAST-WebCrawler/3.8 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)')
  707. headers_useragents.append('FAST-WebCrawler/3.8/Fresh (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)')
  708. headers_useragents.append('FAST-WebCrawler/3.x Multimedia')
  709. headers_useragents.append('FAST-WebCrawler/3.x Multimedia (mm dash crawler at fast dot no)')
  710. headers_useragents.append('fastbot crawler beta 2.0 (+http://www.fastbot.de)')
  711. headers_useragents.append('FastBug http://www.ay-up.com')
  712. headers_useragents.append('FastCrawler 3.0.1 (crawler@1klik.dk)')
  713. headers_useragents.append('FastSearch Web Crawler for Verizon SuperPages (kevin.watters@fastsearch.com)')
  714. headers_useragents.append('Favcollector/2.0 (info@favcollector.com http://www.favcollector.com/)')
  715. headers_useragents.append('FavIconizer')
  716. headers_useragents.append('favo.eu crawler/0.6 (http://www.favo.eu)')
  717. headers_useragents.append('FavOrg')
  718. headers_useragents.append('Favorites Checking (http://campulka.net)')
  719. headers_useragents.append('Favorites Sweeper v.2.03')
  720. headers_useragents.append('Faxobot/1.0')
  721. headers_useragents.append('FDM 1.x')
  722. headers_useragents.append('FDM 2.x')
  723. headers_useragents.append('Feed Seeker Bot (RSS Feed Seeker http://www.MyNewFavoriteThing.com/fsb.php)')
  724. headers_useragents.append('Feed24.com')
  725. headers_useragents.append('Feed::Find/0.0x')
  726. headers_useragents.append('Feedable/0.1 (compatible; MSIE 6.0; Windows NT 5.1)')
  727. headers_useragents.append('FeedChecker/0.01')
  728. headers_useragents.append('FeedDemon/2.7 (http://www.newsgator.com/; Microsoft Windows XP)')
  729. headers_useragents.append('Feedfetcher-Google-iGoogleGadgets; (+http://www.google.com/feedfetcher.html)')
  730. headers_useragents.append('Feedfetcher-Google; (+http://www.google.com/feedfetcher.html)')
  731. headers_useragents.append('FeedForAll rss2html.php v2')
  732. headers_useragents.append('FeedHub FeedDiscovery/1.0 (http://www.feedhub.com)')
  733. headers_useragents.append('FeedHub MetaDataFetcher/1.0 (http://www.feedhub.com)')
  734. headers_useragents.append('Feedjit Favicon Crawler 1.0')
  735. headers_useragents.append('Feedreader 3.xx (Powered by Newsbrain)')
  736. headers_useragents.append('Feedshow/x.0 (http://www.feedshow.com; 1 subscriber)')
  737. headers_useragents.append('FeedshowOnline (http://www.feedshow.com)')
  738. headers_useragents.append('FeedZcollector v1.x (Platinum) http://www.feeds4all.com/feedzcollector')
  739. headers_useragents.append('Felix - Mixcat Crawler (+http://mixcat.com)')
  740. headers_useragents.append('fetch libfetch/2.0')
  741. headers_useragents.append('FFC Trap Door Spider')
  742. headers_useragents.append('Filangy/0.01-beta (Filangy; http://www.nutch.org/docs/en/bot.html; filangy-agent@filangy.com)')
  743. headers_useragents.append('Filangy/1.0x (Filangy; http://www.filangy.com/filangyinfo.jsp?inc=robots.jsp; filangy-agent@filangy.com)')
  744. headers_useragents.append('Filangy/1.0x (Filangy; http://www.nutch.org/docs/en/bot.html; filangy-agent@filangy.com)')
  745. headers_useragents.append('fileboost.net/1.0 (+http://www.fileboost.net)')
  746. headers_useragents.append('FileHound x.x')
  747. headers_useragents.append('Filtrbox/1.0')
  748. headers_useragents.append('FindAnISP.com_ISP_Finder_v99a')
  749. headers_useragents.append('Findexa Crawler (http://www.findexa.no/gulesider/article26548.ece)')
  750. headers_useragents.append('findlinks/x.xxx (+http://wortschatz.uni-leipzig.de/findlinks/)')
  751. headers_useragents.append('FineBot')
  752. headers_useragents.append('Finjan-prefetch')
  753. headers_useragents.append('Firefly/1.0')
  754. headers_useragents.append('Firefly/1.0 (compatible; Mozilla 4.0; MSIE 5.5)')
  755. headers_useragents.append('Firefox (kastaneta03@hotmail.com)')
  756. headers_useragents.append('Firefox_1.0.6 (kasparek@naparek.cz)')
  757. headers_useragents.append('FirstGov.gov Search - POC:firstgov.webmasters@gsa.gov')
  758. headers_useragents.append('firstsbot')
  759. headers_useragents.append('Flapbot/0.7.2 (Flaptor Crawler; http://www.flaptor.com; crawler at flaptor period com)')
  760. headers_useragents.append('FlashGet')
  761. headers_useragents.append('FLATARTS_FAVICO')
  762. headers_useragents.append('Flexum spider')
  763. headers_useragents.append('Flexum/2.0')
  764. headers_useragents.append('FlickBot 2.0 RPT-HTTPClient/0.3-3')
  765. headers_useragents.append('flunky')
  766. headers_useragents.append('fly/6.01 libwww/4.0D')
  767. headers_useragents.append('flyindex.net 1.0/http://www.flyindex.net')
  768. headers_useragents.append('FnooleBot/2.5.2 (+http://www.fnoole.com/addurl.html)')
  769. headers_useragents.append('FocusedSampler/1.0')
  770. headers_useragents.append('Folkd.com Spider/0.1 beta 1 (www.folkd.com)')
  771. headers_useragents.append('FollowSite Bot ( http://www.followsite.com/bot.html )')
  772. headers_useragents.append('FollowSite.com ( http://www.followsite.com/b.html )')
  773. headers_useragents.append('Fooky.com/ScorpionBot/ScoutOut; http://www.fooky.com/scorpionbots')
  774. headers_useragents.append('Francis/1.0 (francis@neomo.de http://www.neomo.de/)')
  775. headers_useragents.append('Franklin Locator 1.8')
  776. headers_useragents.append('free-downloads.net download-link validator /0.1')
  777. headers_useragents.append('FreeFind.com-SiteSearchEngine/1.0 (http://freefind.com; spiderinfo@freefind.com)')
  778. headers_useragents.append('Frelicbot/1.0 +http://www.frelic.com/')
  779. headers_useragents.append('FreshDownload/x.xx')
  780. headers_useragents.append('FreshNotes crawler< report problems to crawler-at-freshnotes-dot-com')
  781. headers_useragents.append('FSurf15a 01')
  782. headers_useragents.append('FTB-Bot http://www.findthebest.co.uk/')
  783. headers_useragents.append('Full Web Bot 0416B')
  784. headers_useragents.append('Full Web Bot 0516B')
  785. headers_useragents.append('Full Web Bot 2816B')
  786. headers_useragents.append('FuseBulb.Com')
  787. headers_useragents.append('FyberSpider (+http://www.fybersearch.com/fyberspider.php)')
  788. headers_useragents.append('unknownght.com Web Server IIS vs Apache Survey. See Results at www.DNSRight.com headers_useragents.append(')
  789. return(headers_useragents)
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement