def kafka_to_disk():
 print('啟動(dòng)前檢測上次運(yùn)行時(shí)是否存在意外中斷的數(shù)據(jù)文件......')
 print('搜索最近一次執(zhí)行腳本產(chǎn)生的時(shí)間目錄......')
 # 待處理臨時(shí)文件列表
 tmp_list = []
 try:
  for category_dir in os.listdir(local_file_path):
   if len(os.listdir(local_file_path+os.sep+category_dir)) > 0:
    for file in os.listdir(local_file_path+os.sep+category_dir):
     if suffix in file:
      tmp_list.append(local_file_path+os.sep+category_dir+os.sep+file)
  # print('上次運(yùn)行程序產(chǎn)生的臨時(shí)文件有---{}'.format(tmp_list))
 except Exception as e:
  pass
 if len(tmp_list) == 0:
  print('未掃描任何殘留臨時(shí)文件')
 else:
  print('開始修復(fù)殘留臨時(shí)文件......')
 tmp_num = 0
 for tmp in tmp_list:
  os.rename(tmp, tmp.split('.')[0]+'.out')
  tmp_num += 1
 print('本次啟動(dòng)共修復(fù)殘留臨時(shí)文件★★★★★-----{}個(gè)-----★★★★★'.format(tmp_num))
 
 category_poor = {
  '1': 'news', '2': 'weibo', '3': 'weixin', '4': 'app', '5': 'newspaper', '6': 'luntan',
  '7': 'blog', '8': 'video', '9': 'shangji', '10': 'shangjia', '11': 'gtzy', '12': 'zfztb',
  '13': 'gyfp', '14': 'gjz', '15': 'zfxx', '16': 'ptztb', '17': 'company', '18': 'house',
  '19': 'hospital', '20': 'bank', '21': 'zone', '22': 'express', '23': 'zpgw', '24': 'zscq',
  '25': 'hotel', '26': 'cpws', '27': 'gxqy', '28': 'gpjj', '29': 'dtyy', '30': 'bdbk'}
 
 time_stamp = utils.get_time_stamp() # 初始化毫秒級時(shí)間戳 ： 20180509103015125
 consumer = KafkaConsumer(topic, group_id=group_id, auto_offset_reset=auto_offset_reset, bootstrap_servers=eval(bootstrap_servers))
 print('連接kafka成功,數(shù)據(jù)篩選中......')
 file_poor = {}       # 子類池用于文件計(jì)數(shù)器
 time_stamp_poor = {}     # 子類時(shí)間戳池，用于觸發(fā)文件切換
 time_stamp = utils.get_time_stamp()  # 初始化毫秒級時(shí)間戳 ：20180509103015125
 for message in consumer:
  # 提取第8個(gè)字段自動(dòng)匹配目錄進(jìn)行創(chuàng)建
  if message.value.decode().split('|')[1] in category_poor:
   category = category_poor[message.value.decode().split('|')[1]]
  else:
   print(message.value.decode())
   continue
  category_dir = local_file_path + os.sep + category
  if not os.path.exists(category_dir):
   os.makedirs(category_dir)
  # 提取第2個(gè)字段，用于生成文件名
  if message.value.decode().split('|')[7] in time_stamp_poor:
   shot_file_name = time_stamp_poor[message.value.decode().split('|')[7]] + '_' + message.value.decode().split('|')[7]
  else:
   shot_file_name = time_stamp + '_' + message.value.decode().split('|')[7]
  file_name = category_dir + os.sep + shot_file_name + '.tmp'
 
  # 給每一個(gè)文件設(shè)定一個(gè)計(jì)數(shù)器
  if message.value.decode().split('|')[7] not in file_poor:
   file_poor[message.value.decode().split('|')[7]] = 0
 
  with open(file_name, 'a', encoding='utf-8')as f1:
   f1.write(message.value.decode())
   file_poor[message.value.decode().split('|')[7]] += 1
 
  # 觸發(fā)切換文件的操作,用時(shí)間戳生成第二文件名
  if file_poor[message.value.decode().split('|')[7]] == strip_number:
   time_stamp_poor[message.value.decode().split('|')[7]] = utils.get_time_stamp()
   file_poor[message.value.decode().split('|')[7]] = 0