pyflink读取kafka数据写入mysql实例

最新推荐文章于 2025-06-30 14:57:43 发布

墨痕诉清风

最新推荐文章于 2025-06-30 14:57:43 发布

阅读量1.4k

点赞数

CC 4.0 BY-SA版权

分类专栏：大数据 Python/算法文章标签： kafka mysql 分布式

本文链接：https://blog.csdn.net/u012206617/article/details/133700990

Python/算法同时被 2 个专栏收录

302 篇文章

订阅专栏

大数据

7 篇文章

订阅专栏

本文展示了如何使用ApacheFlink进行Kafka数据流的读取和处理，以及将处理后的数据写入到MySQL数据库。代码实例包括从Kafka消费JSON数据，使用JsonRowSerializationSchema序列化，以及将数据写入到JDBC表中。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

依赖包下载

https://repo.maven.apache.org/maven2/org/apache/flink/flink-sql-connector-kafka/1.17.1/

版本

flink：1.16.0

kafka：2.13-3.2.0

实例

import logging
import sys

from pyflink.common import Types
from pyflink.datastream import StreamExecutionEnvironment
from pyflink.datastream.connectors.jdbc import JdbcSink, JdbcConnectionOptions
from pyflink.datastream.connectors.kafka import FlinkKafkaProducer, FlinkKafkaConsumer
from pyflink.datastream.formats.json import JsonRowSerializationSchema, JsonRowDeserializationSchema


def write_to_kafka(env):
    type_info = Types.ROW([Types.INT(), Types.STRING()])
    ds = env.from_collection(
        [(1, 'hi'), (2, 'hello'), (3, 'hi'), (4, 'hello'), (5, 'hi'), (6, 'hello'), (6, 'hello')],
        type_info=type_info)

    serialization_schema = JsonRowSerializationSchema.Builder() \
        .with_type_info(type_info) \
        .build()
    kafka_producer = FlinkKafkaProducer(
        topic='test_json_topic',
        serialization_schema=serialization_schema,
        producer_config={'security.protocol': 'SASL_PLAINTEXT', 'sasl.mechanism': 'PLAIN', 'bootstrap.servers': '192.168.1.110:9092', 'group.id': 'test-consumer-group', 'sasl.jaas.config': 'org.apache.kafka.common.security.scram.ScramLoginModule required username=\"aaaaaaaaa\" password=\"bbbbbbb\";'}
    )

    # note that the output type of ds must be RowTypeInfo
    ds.add_sink(kafka_producer)
    env.execute()

def read_from_kafka(env):
    deserialization_schema = JsonRowDeserializationSchema.Builder() \
        .type_info(Types.ROW([Types.INT(), Types.STRING()])) \
        .build()
    kafka_consumer = FlinkKafkaConsumer(
        topics='test_json_topic',
        deserialization_schema=deserialization_schema,
        properties={'security.protocol': 'SASL_PLAINTEXT', 'sasl.mechanism': 'PLAIN', 'bootstrap.servers': '192.168.1.110:9092', 'group.id': 'test-consumer-group', 'sasl.jaas.config': 'org.apache.kafka.common.security.scram.ScramLoginModule required username=\"aaaaa\" password=\"bbbbbb\";'}
    )
    kafka_consumer.set_start_from_earliest()

    env.add_source(kafka_consumer).print()
    env.execute()

def wirte_data_todb(env, data):
    type_info = Types.ROW([Types.INT(), Types.STRING()])
    env.from_collection(
        [(101, "Stream Processing with Apache Flink"),
        (102, "Streaming Systems"),
        (103, "Designing Data-Intensive Applications"),
        (104, "Kafka: The Definitive Guide")
        ], type_info=type_info) \
        .add_sink(
        JdbcSink.sink(
            "insert into flink (id, title) values (?, ?)",
            type_info,
            JdbcConnectionOptions.JdbcConnectionOptionsBuilder()
                .with_url('jdbc:mysql://192.168.1.110:23006/test')
                .with_driver_name('com.mysql.jdbc.Driver')
                .with_user_name('sino')
                .with_password('Caib@sgcc-56')
                .build()
        ))

    env.execute()


if __name__ == '__main__':
    logging.basicConfig(stream=sys.stdout, level=logging.INFO, format="%(message)s")

    env = StreamExecutionEnvironment.get_execution_environment()
    #env.add_jars("file:///opt/flink/flink-sql-connector-kafka-1.15.0.jar")
    #env.add_jars("file:///opt/flink/kafka-clients-2.8.1.jar")
    #env.add_jars("file:///opt/flink/flink-connector-jdbc-1.16.0.jar")
    #env.add_jars("file:///opt/flink/mysql-connector-java-8.0.29.jar")
    

    print("start reading data from kafka")
    read_from_kafka(env)
    #wirte_data_todb(env, "")