spark streaming与Kafka结合

1.代码

import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.SparkConf
import org.apache.spark.streaming.kafka010.KafkaUtils
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe

/**
  * @author xxx_xx
  * @date 2018/4/17
  */
object KaflaWordCount {
  def main(args: Array[String]): Unit = {
  //在yarn上运行
    val conf = new SparkConf().setAppName("kafka_wordcount").setMaster("yarn");
    val ssc = new StreamingContext(conf, Seconds(5));
    val kafkaParams = Map[String, Object](
      "bootstrap.servers" -> "centos-1:9092",
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer],
      "group.id" -> "test",
      "auto.offset.reset" -> "latest",
      "enable.auto.commit" -> (false: java.lang.Boolean)
    )

    val topics = Array("data-syn")
    val stream = KafkaUtils.createDirectStream[String, String](
      ssc,
      PreferConsistent,
      Subscribe[String, String](topics, kafkaParams)
    )

    stream.map(record => (record.key, record.value)).print()
    ssc.start();
    ssc.awaitTermination();
  }
}

2.pom.xml这里为了避免服务器上类找不到，直接把依赖打上，不推荐

<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>4.0.0modelVersion>

    <groupId>com.tech.datagroupId>
    <artifactId>spark-testartifactId>
    <version>1.0-SNAPSHOTversion>

    <properties>
        <spark.version>2.3.0spark.version>
        <scala.version>2.11scala.version>
    properties>


    <dependencies>
        <dependency>
            <groupId>org.apache.sparkgroupId>
            <artifactId>spark-core_${scala.version}artifactId>
            <version>${spark.version}version>
        dependency>
        <dependency>
            <groupId>org.apache.sparkgroupId>
            <artifactId>spark-streaming_${scala.version}artifactId>
            <version>2.3.0version>
        dependency>
        <dependency>
            <groupId>org.apache.sparkgroupId>
            <artifactId>spark-streaming-kafka-0-10_2.11artifactId>
            <version>2.3.0version>
        dependency>
    dependencies>

    <build>
        <plugins>

            <plugin>
                <groupId>org.scala-toolsgroupId>
                <artifactId>maven-scala-pluginartifactId>
                <version>2.15.2version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compilegoal>
                            <goal>testCompilegoal>
                        goals>
                    execution>
                executions>
            plugin>

            <plugin>
                <artifactId>maven-compiler-pluginartifactId>
                <version>3.6.0version>
                <configuration>
                    <source>1.8source>
                    <target>1.8target>
                configuration>
            plugin>

            <plugin>
                <groupId>org.apache.maven.pluginsgroupId>
                <artifactId>maven-surefire-pluginartifactId>
                <version>2.19version>
                <configuration>
                    <skip>trueskip>
                configuration>
            plugin>


            <plugin>
                <artifactId>maven-assembly-pluginartifactId>
                <configuration>
                    <appendAssemblyId>falseappendAssemblyId>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependenciesdescriptorRef>
                    descriptorRefs>
                    <archive>
                        <manifest>
                            
                            <mainClass>KaflaWordCountmainClass>
                        manifest>
                    archive>
                configuration>
                <executions>
                    <execution>
                        <id>make-assemblyid>
                        <phase>packagephase>
                        <goals>
                            <goal>assemblygoal>
                        goals>
                    execution>
                executions>
            plugin>
        plugins>
    build>
project>

3.提交命令

spark-submit --master yarn --class KaflaWordCount spark-test-1.0-SNAPSHOT.jar

4.测试输入

bin/kafka-console-producer.sh --broker-list centos-3:9092 --topic data-syn