spark写数据入kafka示范代码

一.pom文件

<?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>cn.piesat</groupId>
  <artifactId>SparkToKafka</artifactId>
  <version>1.0-SNAPSHOT</version>

  <name>SparkToKafka</name>
  <!-- FIXME change it to the project's website -->
  <url>http://www.example.com</url>

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <maven.compiler.source>1.7</maven.compiler.source>
    <maven.compiler.target>1.7</maven.compiler.target>
    <spark.version>2.1.0</spark.version>
    <hadoop.version>2.7.4</hadoop.version>
    <kafka.version>1.0.0</kafka.version>
  </properties>

  <dependencies>
    <!--spark框架开始-->
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-core_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-sql_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-hive_2.11</artifactId>
      <version>${spark.version}</version>
      <exclusions>
        <exclusion>
          <artifactId>commons-logging</artifactId>
          <groupId>commons-logging</groupId>
        </exclusion>
      </exclusions>
    </dependency>
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-streaming_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-client</artifactId>
      <version>${hadoop.version}</version>
      <exclusions>
        <exclusion>
          <artifactId>commons-logging</artifactId>
          <groupId>commons-logging</groupId>
        </exclusion>
        <exclusion>
          <artifactId>slf4j-log4j12</artifactId>
          <groupId>org.slf4j</groupId>
        </exclusion>
        <exclusion>
          <artifactId>log4j</artifactId>
          <groupId>log4j</groupId>
        </exclusion>
      </exclusions>
    </dependency>
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
      <version>2.1.0</version>
    </dependency>
    <dependency>
      <groupId>org.apache.kafka</groupId>
      <artifactId>kafka_2.11</artifactId>
      <version>${kafka.version}</version>
      <exclusions>
        <exclusion>
          <artifactId>slf4j-log4j12</artifactId>
          <groupId>org.slf4j</groupId>
        </exclusion>
        <exclusion>
          <artifactId>log4j</artifactId>
          <groupId>log4j</groupId>
        </exclusion>
      </exclusions>
    </dependency>
    <dependency>
      <groupId>org.apache.hbase</groupId>
      <artifactId>hbase</artifactId>
      <version>1.2.6</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hbase</groupId>
      <artifactId>hbase-client</artifactId>
      <version>1.0.2</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hbase</groupId>
      <artifactId>hbase-server</artifactId>
      <version>1.0.2</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hbase</groupId>
      <artifactId>hbase-common</artifactId>
      <version>1.0.2</version>
    </dependency>

    <!--spark框架结束-->
    <dependency>
      <groupId>com.alibaba</groupId>
      <artifactId>fastjson</artifactId>
      <version>1.2.47</version>
    </dependency>
    <dependency>
      <groupId>c3p0</groupId>
      <artifactId>c3p0</artifactId>
      <version>0.9.1.2</version>
    </dependency>
    <dependency>
      <groupId>mysql</groupId>
      <artifactId>mysql-connector-java</artifactId>
      <version>5.1.44</version>
    </dependency>
  </dependencies>
  <build>
    <plugins>
      <plugin>
        <groupId>net.alchim31.maven</groupId>
        <artifactId>scala-maven-plugin</artifactId>
        <version>3.2.2</version>
        <configuration>
          <recompileMode>incremental</recompileMode>
        </configuration>
        <executions>
          <execution>
            <goals>
              <goal>compile</goal>
              <goal>testCompile</goal>
            </goals>
          </execution>
        </executions>
      </plugin>
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-assembly-plugin</artifactId>
        <version>2.4.1</version>

        <configuration>
          <!-- get all project dependencies -->
          <descriptorRefs>
            <descriptorRef>jar-with-dependencies</descriptorRef>
          </descriptorRefs>
          <!-- MainClass in mainfest make a executable jar -->
          <!--<archive>-->
          <!--<manifest>-->
          <!--<addClasspath>true</addClasspath>-->
          <!--　　　　　//主函数入口-->
          <!--<mainClass>cn.piesat.spark.SparkStreamingKafka</mainClass>-->
          <!--</manifest>-->
          <!--</archive>-->
        </configuration>

        <executions>
          <execution>
            <id>make-assembly</id>
            <!-- bind to the packaging phase -->
            <phase>package</phase>
            <goals>
              <goal>single</goal>
            </goals>
          </execution>
        </executions>
      </plugin>
    </plugins>
  </build>
</project>

二、代码
连接序列化问题通过懒加载的方式解决，此代码不会因为每次发送数据时重新建立连接。
1.创建一个KafkaSink类
---------------------------------------------------------------------------------------

package cn.piesat
import java.util
import org.apache.kafka.clients.producer.{KafkaProducer, ProducerRecord, RecordMetadata}

class KafkaSink[K,V](createProducer:()=>KafkaProducer[K,V]) extends Serializable {
  lazy val producer=createProducer()
  def send(topic:String,key:K,value:V): util.concurrent.Future[RecordMetadata]=
    producer.send(new ProducerRecord[K,V](topic,key,value))
  def send(topic:String,value:V): util.concurrent.Future[RecordMetadata]=
    producer.send(new ProducerRecord[K,V](topic,value))
}

object  KafkaSink{
  import scala.collection.JavaConversions._
  def apply[K,V](config:Map[String,Object]):KafkaSink[K,V]={
    val createProducerFunc=()=>{
      val producer=new KafkaProducer[K,V](config)
      sys.addShutdownHook{
        producer.close()
      }
      producer
    }
    new KafkaSink(createProducerFunc)
  }
  def apply[K,V](config:java.util.Properties):KafkaSink[K,V]=apply(config.toMap)
}
------------------------------------------------------------------------------

2.创建一个任务入口类
--------------------------------------------------------------------------------

package cn.piesat

import java.util.Properties

import org.apache.spark.broadcast.Broadcast
import org.apache.spark.{SparkConf, SparkContext}

object SparkToKafka {

    def main(args:Array[String])={
      val conf=new SparkConf().setMaster("local[4]").set("spark.serializer", "org.apache.spark.serializer.KryoSerializer").setAppName("SparkToKafka")
      val sc=new SparkContext(conf)
      val kafkaProducer:Broadcast[KafkaSink[String,String]]={
        val kafkaProducerConfig={
          val p=new Properties()
          p.setProperty("bootstrap.servers","hadoop01:9092")
          p.setProperty("key.serializer","org.apache.kafka.common.serialization.StringSerializer")
          p.setProperty("value.serializer","org.apache.kafka.common.serialization.StringSerializer")
          p
        }
        sc.broadcast(KafkaSink[String,String](kafkaProducerConfig))
      }
      val worldRDD=sc.makeRDD(Array("abc","def"))
      worldRDD.foreachPartition(rdd=>{
        rdd.foreach(record=>{
          kafkaProducer.value.send("lj03",record)
        })
      })

    }
}
-----------------------------------------------------------------------------------