python消费kafka数据批量插入到es的方法

1、es的批量插入

这是为了方便后期配置的更改，把配置信息放在logging.conf中

用elasticsearch来实现批量操作，先安装依赖包，sudo pip install elasticsearch2

from elasticsearch import elasticsearch 
class importesdata:

  logging.config.fileconfig("logging.conf")
  logger = logging.getlogger("msg")

  def __init__(self,hosts,index,type):
    self.es = elasticsearch(hosts=hosts.strip(',').split(','), timeout=5000)
    self.index = index
    self.type = type


  def set_date(self,data): 
    # 批量处理 
    # es.index(index="test-index",doc_type="test-type",id=42,body={"any":"data","timestamp":datetime.now()})
    self.es.index(index=self.index,doc_type=self.index,body=data)

2、使用pykafka消费kafka

1.因为kafka是0.8，pykafka不支持zk，只能用get_simple_consumer来实现

2.为了实现多个应用同时消费而且不重消费，所以一个应用消费一个partition

3. 为是确保消费数据量在不满足10000这个批量值，能在一个时间范围内插入到es中，这里设置consumer_timeout_ms一个超时等待时间，退出等待消费阻塞。

4.退出等待消费阻塞后导致无法再消费数据，因此在获取self.consumer 的外层加入了while true 一个死循环

#!/usr/bin/python
# -*- coding: utf-8 -*-
from pykafka import kafkaclient
import logging
import logging.config
from configutil import configutil
import datetime


class kafkapython:
  logging.config.fileconfig("logging.conf")
  logger = logging.getlogger("msg")
  logger_data = logging.getlogger("data")

  def __init__(self):
    self.server = configutil().get("kafka","kafka_server")
    self.topic = configutil().get("kafka","topic")
    self.group = configutil().get("kafka","group")
    self.partition_id = int(configutil().get("kafka","partition"))
    self.consumer_timeout_ms = int(configutil().get("kafka","consumer_timeout_ms"))
    self.consumer = none
    self.hosts = configutil().get("es","hosts")
    self.index_name = configutil().get("es","index_name")
    self.type_name = configutil().get("es","type_name")


  def getconnect(self):
    client = kafkaclient(self.server)
    topic = client.topics[self.topic]
    p = topic.partitions
    ps={p.get(self.partition_id)}

    self.consumer = topic.get_simple_consumer(
      consumer_group=self.group,
      auto_commit_enable=true,
      consumer_timeout_ms=self.consumer_timeout_ms,
      # num_consumer_fetchers=1,
      # consumer_id='test1',
      partitions=ps
      )
    self.starttime = datetime.datetime.now()


  def beginconsumer(self):
    print("beginconsumer kafka-python")
    imprtesdata = importesdata(self.hosts,self.index_name,self.type_name)
    #创建actions 
    count = 0
    actions = [] 

    while true:
      endtime = datetime.datetime.now()
      print (endtime - self.starttime).seconds
      for message in self.consumer:
        if message is not none:
          try:
            count = count + 1
            # print(str(message.partition.id)+","+str(message.offset)+","+str(count))
            # self.logger.info(str(message.partition.id)+","+str(message.offset)+","+str(count))
            action = { 
              "_index": self.index_name, 
              "_type": self.type_name, 
              "_source": message.value
            }
            actions.append(action)
            if len(actions) >= 10000:
              imprtesdata.set_date(actions)
              actions = []
              self.consumer.commit_offsets()
              endtime = datetime.datetime.now()
              print (endtime - self.starttime).seconds
              #break
          except (exception) as e:
            # self.consumer.commit_offsets()
            print(e)
            self.logger.error(e)
            self.logger.error(str(message.partition.id)+","+str(message.offset)+","+message.value+"\n")
            # self.logger_data.error(message.value+"\n")
          # self.consumer.commit_offsets()


      if len(actions) > 0:
        self.logger.info("等待时间超过，consumer_timeout_ms，把集合数据插入es")
        imprtesdata.set_date(actions)
        actions = []
        self.consumer.commit_offsets()




  def disconnect(self):
    self.consumer.close()


from elasticsearch import elasticsearch 
from elasticsearch.helpers import bulk
class importesdata:

  logging.config.fileconfig("logging.conf")
  logger = logging.getlogger("msg")

  def __init__(self,hosts,index,type):
    self.es = elasticsearch(hosts=hosts.strip(',').split(','), timeout=5000)
    self.index = index
    self.type = type


  def set_date(self,data): 
    # 批量处理 
    success = bulk(self.es, data, index=self.index, raise_on_error=true) 
    self.logger.info(success) 

3、运行

if __name__ == '__main__':
  kp = kafkapython()
  kp.getconnect()
  kp.beginconsumer()
  # kp.disconnect()

注：简单的写了一个从kafka中读取数据到一个list里，当数据达到一个阈值时，在批量插入到 es的插件

现在还在批量的压测中。。。

以上这篇python消费kafka数据批量插入到es的方法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。