Flink+Kafka 接收流数据并打印到控制台

最新推荐文章于 2025-06-04 13:52:38 发布

weixin_30925411

最新推荐文章于 2025-06-04 13:52:38 发布

阅读量1.5k

点赞数

CC 4.0 BY-SA版权

文章标签：大数据 python java

原文链接：http://www.cnblogs.com/chuijingjing/p/10535081.html

试验环境

Windows：IDEA

Linux：Kafka，Zookeeper

POM和Demo

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.yk</groupId>
    <artifactId>flink</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <flink.version>1.6.1</flink.version>
        <slf4j.version>1.7.7</slf4j.version>
        <log4j.version>1.2.17</log4j.version>
    </properties>

    <dependencies>
        <!--******************* flink *******************-->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.11</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_2.11</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka-0.11_2.11</artifactId>
            <version>${flink.version}</version>
            <scope> compile</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-filesystem_2.11</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-core</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>3.1.1</version>
        </dependency>

        <!--alibaba fastjson-->
        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.51</version>
        </dependency>
        <!--******************* 日志 *******************-->
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>${slf4j.version}</version>
            <scope>runtime</scope>
        </dependency>
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>${log4j.version}</version>
            <scope>runtime</scope>
        </dependency>
        <!--******************* kafka *******************-->
        <dependency>
            <groupId>org.apache.kafka</groupId>
            <artifactId>kafka-clients</artifactId>
            <version>1.1.1</version>
        </dependency>

    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.3</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
            <!--打jar包-->
            <plugin>
                <artifactId>maven-assembly-plugin</artifactId>
                <configuration>
                    <archive>
                        <manifest>
                            <mainClass>com.allen.capturewebdata.Main</mainClass>
                        </manifest>
                    </archive>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>

package flink.kafkaFlink;

import java.util.Properties;

import org.apache.flink.streaming.api.TimeCharacteristic;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer010;

public class KafkaDemo {

    public static void main(String[] args) throws Exception {

        // set up the streaming execution environment
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        //默认情况下，检查点被禁用。要启用检查点，请在StreamExecutionEnvironment上调用enableCheckpointing(n)方法，
        // 其中n是以毫秒为单位的检查点间隔。每隔5000 ms进行启动一个检查点,则下一个检查点将在上一个检查点完成后5秒钟内启动

        env.enableCheckpointing(500);
        env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);
        Properties properties = new Properties();
        properties.setProperty("bootstrap.servers", "hadoop01:9092");//kafka的节点的IP或者hostName，多个使用逗号分隔
        properties.setProperty("zookeeper.connect", "hadoop01:2181");//zookeeper的节点的IP或者hostName，多个使用逗号进行分隔
        properties.setProperty("group.id", "test-consumer-group");//flink consumer flink的消费者的group.id
        System.out.println("11111111111");
        FlinkKafkaConsumer010<String> myConsumer = new FlinkKafkaConsumer010<String>("test", new org.apache.flink.api.common.serialization.SimpleStringSchema(), properties);
        // FlinkKafkaConsumer010<String> myConsumer = new FlinkKafkaConsumer010<String>("test",new SimpleStringSchema(),properties);//test0是kafka中开启的topic
        myConsumer.assignTimestampsAndWatermarks(new CustomWatermarkEmitter());
        DataStream<String> keyedStream = env.addSource(myConsumer);//将kafka生产者发来的数据进行处理，本例子我进任何处理
        System.out.println("2222222222222");
        keyedStream.print();//直接将从生产者接收到的数据在控制台上进行打印
        // execute program
        System.out.println("3333333333333");
        env.execute("Flink Streaming Java API Skeleton");

    }
}

package flink.kafkaFlink;

import org.apache.flink.streaming.api.functions.AssignerWithPunctuatedWatermarks;
import org.apache.flink.streaming.api.watermark.Watermark;

public class CustomWatermarkEmitter implements AssignerWithPunctuatedWatermarks<String> {

    private static final long serialVersionUID = 1L;

    public long extractTimestamp(String arg0, long arg1) {
        if (null != arg0 && arg0.contains(",")) {
            String parts[] = arg0.split(",");
            return Long.parseLong(parts[0]);
        }
        return 0;
    }

    public Watermark checkAndGetNextWatermark(String arg0, long arg1) {
        if (null != arg0 && arg0.contains(",")) {
            String parts[] = arg0.split(",");
            return new Watermark(Long.parseLong(parts[0]));
        }
        return null;
    }
}

在云主机上启动服务

1.启动zookeeper；

2.启动Kafka；

3.创建topic；

4.启动生产者。

bin/zkServer.sh start
bin/kafka-server-start.sh config/server.properties
bin/kafka-topics.sh --create --zookeeper hadoop01:2181 --replication-factor 1 --partitions 1 --topic test
bin/kafka-console-producer.sh --broker-list hadoop01:9092 --topic test