SparkSteaming整合kafka----采用direct(低级Api)

废话不多说，直接上代码

1、pom.xml

<?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">
    <parent>
        <artifactId>spark-exercise</artifactId>
        <groupId>com.bigdata</groupId>
        <version>1.0-SNAPSHOT</version>
    </parent>
    <modelVersion>4.0.0</modelVersion>

    <artifactId>spark_test</artifactId>

    <properties>
        <scala.version>2.11.8</scala.version>
        <hadoop.version>2.7.4</hadoop.version>
        <spark.version>2.0.2</spark.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>2.0.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-hive_2.11</artifactId>
            <version>2.0.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>2.0.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-flume_2.11</artifactId>
            <version>2.0.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
            <version>2.0.0-preview</version>
            <scope>provided</scope>
        </dependency>


    </dependencies>

    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.2</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                        <configuration>
                            <args>
                                <arg>-dependencyfile</arg>
                                <arg>${project.build.directory}/.scala_dependencies</arg>
                            </args>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.3</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                            <transformers>
                                <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass></mainClass>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

2、低级API代码

采用KafkaUtil的方法。

package com.bigdata.kafka

import kafka.serializer.StringDecoder
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.dstream.{DStream, InputDStream}
import org.apache.spark.streaming.kafka.KafkaUtils

//todo:sparkSteaming整合kafka----采用direct(低级Api)
object SparkStreamingKafkaDirect {
  def main(args: Array[String]): Unit = {
      //1、创建sparkConf
      val sparkConf: SparkConf = new SparkConf().setAppName("SparkStreamingKafkaDirect").setMaster("local[2]")
      //2、创建sparkContext
      val sc = new SparkContext(sparkConf)
      sc.setLogLevel("WARN")
      //3、创建streamingcontext
      val ssc = new StreamingContext(sc,Seconds(5))
      ssc.checkpoint("./spark_direct") //它会保存topic的偏移量
      //4、准备kafka参数
      val kafkaParams=Map("metadata.broker.list"->"node1:9092,node2:9092,node3:9092","group.id" ->"spark_direct")
      //5、准备topic
      val topics=Set("spark_01")
      //6、获取kafka中的数据
      val dstream: InputDStream[(String, String)] = KafkaUtils
        .createDirectStream[String,String,StringDecoder,StringDecoder](ssc,kafkaParams,topics)
      //7、获取topic中的数据
        val data: DStream[String] = dstream.map(_._2)
      //8、切分每一行，每个单词计为1，把相同单词出现的次数累加
        val result: DStream[(String, Int)] = data.flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_)

      //9、打印结果数据
        result.print()

      //10、开启流式计算
        ssc.start()
        ssc.awaitTermination()

  }
}