我就废话不多说了,直接上代码吧!

import sys
sys.path.append("..")
from datetime import datetime
from utils.kafka2file import KafkaDownloader
import os
"""
实现取kafka数据,文件按照取数据的间隔命名
如每5分钟从kafka取数据写入文件中,文件名为当前时间加5
"""

TOPIC = "rtz_queue"
HOSTS = "ip:9092,ip:9092"
GROUP = "2001"

def get_end_time(hour,minute,time_step):
 if (minute+time_step)%60<60:
  if (minute+time_step)%60<10:
   return str(hour+int((minute+time_step)/60))+":"+"0"+str((minute+time_step)%60)
  else:
   return str(hour+int((minute+time_step)/60))+":"+str((minute+time_step)%60)
 else:
  pass

def kafkawritefile(time_step,time_num):
 start = datetime.now()
 downloader = KafkaDownloader(HOSTS, TOPIC, GROUP)
 i = 1
 while(i<=time_num):
  end_time = get_end_time(start.hour, start.minute,i*time_step)
  end_time_file = end_time.replace(':', '_')
  outfile_path = "/data/tmp/" + end_time_file + ".csv"

  if os.path.exists(outfile_path):
   os.remove(outfile_path)
  writefile = open(outfile_path, 'a+', encoding='utf-8')
  
  for msg in downloader.message():
   curr_time = datetime.now()
   curr_time = str(curr_time)
   split_curr_time = curr_time.split(' ')
   curr_time_str = split_curr_time[1][0:5]
  
   if curr_time_str >= str(end_time):  
    break
  i += 1

if __name__=='__main__':
 time_step = 15
 time_num = 1
 kafkawritefile(time_step,time_num)

以上这篇python每5分钟从kafka中提取数据的例子就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。

华山资源网 Design By www.eoogi.com
广告合作:本站广告合作请联系QQ:858582 申请时备注:广告合作(否则不回)
免责声明:本站资源来自互联网收集,仅供用于学习和交流,请遵循相关法律法规,本站一切资源不代表本站立场,如有侵权、后门、不妥请联系本站删除!
华山资源网 Design By www.eoogi.com