python使用kafka

python使用kafka

1.安装包：

pip install kafka
或
pip install python-kafka

文档：
https://kafka-python.readthedocs.io/en/master/usage.html

2.生产者：

#coding:utf-8

from kafka import KafkaProducer

producer = KafkaProducer(bootstrap_servers=['192.168.137.51:9092']) #此处ip可以是多个['0.0.0.1:9092','0.0.0.2:9092','0.0.0.3:9092' ]

for i in range(3):
    msg = "msg%d" % i
    producer.send('mtest', msg)

producer.close()

3.消费者

from kafka import KafkaConsumer

consumer = KafkaConsumer('mtest', bootstrap_servers=['192.168.137.51:9092'])
for message in consumer:
    print ("%s:%d:%d: key=%s value=%s" % (message.topic, message.partition,
    message.offset, message.key,
    message.value))

定时拉取消息， poll

from kafka import KafkaConsumer
import time

consumer = KafkaConsumer(bootstrap_servers=['192.168.137.51:9092',])
consumer.subscribe(topics=['mtest'])
index = 0
while True:
    msg = consumer.poll(timeout_ms=5)
    print msg
    time.sleep(2)
    index += 1
    print '--------poll index is %s----------' % index

# To consume latest messages and auto-commit offsets
consumer = KafkaConsumer('my-topic',
                         group_id='my-group',
                         bootstrap_servers=['localhost:9092'])
for message in consumer:
    # message value and key are raw bytes -- decode if necessary!
    # e.g., for unicode: `message.value.decode('utf-8')`
    print ("%s:%d:%d: key=%s value=%s" % (message.topic, message.partition,
                                          message.offset, message.key,
                                          message.value))

# consume earliest available messages, don't commit offsets
KafkaConsumer(auto_offset_reset='earliest', enable_auto_commit=False)

# consume json messages
KafkaConsumer(value_deserializer=lambda m: json.loads(m.decode('ascii')))

# consume msgpack
KafkaConsumer(value_deserializer=msgpack.unpackb)

# StopIteration if no message after 1sec
KafkaConsumer(consumer_timeout_ms=1000)

# Subscribe to a regex topic pattern
consumer = KafkaConsumer()
consumer.subscribe(pattern='^awesome.*')

# Use multiple consumers in parallel w/ 0.9 kafka brokers
# typically you would run each on a different server / process / CPU
consumer1 = KafkaConsumer('my-topic',
                          group_id='my-group',
                          bootstrap_servers='my.server.com')
consumer2 = KafkaConsumer('my-topic',
                          group_id='my-group',
                          bootstrap_servers='my.server.com')