python爬虫_自动获取seebug的poc实例

headers = { 'Host':******, 'Connection':'close', 'Accept':******, 'User-Agent':******, 'Referer':'https://www.seebug.org/vuldb/ssvid-', 'Accept-Language':'zh-CN,zh;q=0.8', 'Cookie':***********}

# coding=utf-8import requestsimport threadingimport Queueimport time headers = {   ******  }url_download = 'https://www.seebug.org/vuldb/downloadPoc/'class SeeBugPoc(threading.Thread): def __init__(self,queue):  threading.Thread.__init__(self)  self._queue = queue def run(self):  while not self._queue.empty():   url_download = self._queue.get_nowait()   self.download_file(url_download) def download_file(self,url_download):  r = requests.get(url = url_download,headers = headers)  print r.status_code  name = url_download.split('/')[-1]  print name   if r.status_code == 200:   f = open('E:/poc/'+name+'.txt','w')   f.write(r.content)   f.close()   print 'it ok!'  else:   print 'what fuck !'  time.sleep(1)''' def get_html(self,url):  r = requests.get(url = url,headers = headers)  print r.status_code  print time.time()'''def main(): queue = Queue.Queue() for i in range(93000,93236):  headers['Referer'] = 'https://www.seebug.org/vuldb/ssvid-'+str(i)  queue.put('https://www.seebug.org/vuldb/downloadPoc/'+str(i))  #queue用来存放设计好的url，将他们放入一个队列中，以便后面取用 threads = [] thread_count = 2 for i in range(thread_count):  threads.append(SeeBugPoc(queue)) for i in threads:  i.start() for i in threads:  i.join()if __name__ == '__main__': main()