当前位置 主页 > 网站技术 > 代码类 >

    python 消费 kafka 数据教程

    栏目:代码类 时间:2019-12-21 21:08

    1.安装python模块

    pip install --user kafka-python==1.4.3 

    如果报错压缩相关的错尝试安装下面的依赖

    yum install snappy-devel
    yum install lz4-devel
    pip install python-snappy
    pip install lz4

    2.生产者

    #!/usr/bin/env python
    # coding : utf-8
    
    from kafka import KafkaProducer
    import json
    
    def kafkaProducer():
      producer = KafkaProducer(bootstrap_servers='ip:9092',value_serializer=lambda v: json.dumps(v).encode('utf-8'))
      producer.send('world', {'key1': 'value1'})
    
    if __name__ == '__main__':
      kafkaProducer()
    

    2.消费者

    from kafka import KafkaConsumer
    from kafka.structs import TopicPartition
    import time
    import click
    import ConfigParser
    import json
    import threading
    import datetime
    import sched
    
    
    config = ConfigParser.ConfigParser()
    config.read("amon.ini")
    
    @click.group()
    def cli():
      pass
    
    @cli.command()
    @click.option('--topic',type=str)
    @click.option('--offset', type=click.Choice(['smallest', 'earliest', 'largest']))
    @click.option("--group",type=str)
    def client(topic,offset,group):
      click.echo(topic)
      consumer = KafkaConsumer(topic,
                   bootstrap_servers=config.get("KAFKA", "Broker_Servers").split(","),
                   group_id=group,
                   auto_offset_reset=offset)
      for message in consumer:
        click.echo(message.value)
        # click.echo("%d:%d: key=%s value=%s" % (message.partition,
        #                      message.offset, message.key,
        #                      message.value))
    
    if __name__ == '__main__':
      cli()
    

    3.多线程消费

    #coding:utf-8
    import threading
    
    import os
    import sys
    from kafka import KafkaConsumer, TopicPartition, OffsetAndMetadata
    from collections import OrderedDict
    
    
    threads = []
    
    
    class MyThread(threading.Thread):
      def __init__(self, thread_name, topic, partition):
        threading.Thread.__init__(self)
        self.thread_name = thread_name
        self.partition = partition
        self.topic = topic
    
      def run(self):
        print("Starting " + self.name)
        Consumer(self.thread_name, self.topic, self.partition)
    
      def stop(self):
        sys.exit()
    
    
    def Consumer(thread_name, topic, partition):
      broker_list = 'ip1:9092,ip2:9092'
    
      '''
      fetch_min_bytes(int) - 服务器为获取请求而返回的最小数据量,否则请等待
      fetch_max_wait_ms(int) - 如果没有足够的数据立即满足fetch_min_bytes给出的要求,服务器在回应提取请求之前将阻塞的最大时间量(以毫秒为单位)
      fetch_max_bytes(int) - 服务器应为获取请求返回的最大数据量。这不是绝对最大值,如果获取的第一个非空分区中的第一条消息大于此值,
                  则仍将返回消息以确保消费者可以取得进展。注意:使用者并行执行对多个代理的提取,因此内存使用将取决于包含该主题分区的代理的数量。
                  支持的Kafka版本> = 0.10.1.0。默认值:52428800(50 MB)。
      enable_auto_commit(bool) - 如果为True,则消费者的偏移量将在后台定期提交。默认值:True。
      max_poll_records(int) - 单次调用中返回的最大记录数poll()。默认值:500
      max_poll_interval_ms(int) - poll()使用使用者组管理时的调用之间的最大延迟 。这为消费者在获取更多记录之前可以闲置的时间量设置了上限。
                    如果 poll()在此超时到期之前未调用,则认为使用者失败,并且该组将重新平衡以便将分区重新分配给另一个成员。默认300000
      '''
    
      consumer = KafkaConsumer(bootstrap_servers=broker_list,
                   group_,
                   client_id=thread_name,
                   enable_auto_commit=False,
                   fetch_min_bytes=1024 * 1024, # 1M
                   # fetch_max_bytes=1024 * 1024 * 1024 * 10,
                   fetch_max_wait_ms=60000, # 30s
                   request_timeout_ms=305000,
                   # consumer_timeout_ms=1,
                   # max_poll_records=5000,
                   )
      # 设置topic partition
      tp = TopicPartition(topic, partition)
      # 分配该消费者的TopicPartition,也就是topic和partition,根据参数,每个线程消费者消费一个分区
      consumer.assign([tp])
      #获取上次消费的最大偏移量
      offset = consumer.end_offsets([tp])[tp]
      print(thread_name, tp, offset)
    
      # 设置消费的偏移量
      consumer.seek(tp, offset)
    
      print u"程序首次运行\t线程:", thread_name, u"分区:", partition, u"偏移量:", offset, u"\t开始消费..."
      num = 0 # 记录该消费者消费次数
      while True:
        msg = consumer.poll(timeout_ms=60000)
        end_offset = consumer.end_offsets([tp])[tp]
        '''可以自己记录控制消费'''
        print u'已保存的偏移量', consumer.committed(tp), u'最新偏移量,', end_offset
        if len(msg) > 0:
          print u"线程:", thread_name, u"分区:", partition, u"最大偏移量:", end_offset, u"有无数据,", len(msg)
          lines = 0
          for data in msg.values():
            for line in data:
              print line
              lines += 1
            '''
            do something
            '''
          # 线程此批次消息条数
    
          print(thread_name, "lines", lines)
          if True:
            # 可以自己保存在各topic, partition的偏移量
            # 手动提交偏移量 offsets格式:{TopicPartition:OffsetAndMetadata(offset_num,None)}
            consumer.commit(offsets={tp: (OffsetAndMetadata(end_offset, None))})
            if True == 0:
              # 系统退出?这个还没试
              os.exit()
              '''
              sys.exit()  只能退出该线程,也就是说其它两个线程正常运行,主程序不退出
              '''
          else:
            os.exit()
        else:
          print thread_name, '没有数据'
        num += 1
        print thread_name, "第", num, "次"
    
    
    if __name__ == '__main__':
      try:
        t1 = MyThread("Thread-0", "test", 0)
        threads.append(t1)
        t2 = MyThread("Thread-1", "test", 1)
        threads.append(t2)
        t3 = MyThread("Thread-2", "test", 2)
        threads.append(t3)
    
        for t in threads:
          t.start()
    
        for t in threads:
          t.join()
    
        print("exit program with 0")
      except:
        print("Error: failed to run consumer program")