Spark Streaming 10 Spark Streaming整合kafka（一）Receiver-based

代码地址

1 添加依赖

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
    <version>${spark.version}</version>
</dependency>

2 KafKaReceiverWC.scala

package com.lihaogn.sparkKafka

import org.apache.spark.SparkConf
import org.apache.spark.streaming.kafka.KafkaUtils
import org.apache.spark.streaming.{Seconds, StreamingContext}

/**
  * spark streaming & kafka -> receiver
  */
object KafKaReceiverWC {

  def main(args: Array[String]): Unit = {

    if (args.length != 4) {
      System.err.println("usage: KafKaReceiverWC <zkQuorum> <group> <topics> <numThreads>")
    }

    val Array(zkQuorum, group, topics, numThreads) = args

    val sparkConf = new SparkConf()

    val ssc = new StreamingContext(sparkConf, Seconds(5))

    val topicMap = topics.split(",").map((_, numThreads.toInt)).toMap

    // spark straming 对接 kafka
    val messages = KafkaUtils.createStream(ssc, zkQuorum, group, topicMap)

    messages.map(_._2).flatMap(_.split(" ")).map((_, 1)).reduceByKey(_ + _).print()

    ssc.start()

    ssc.awaitTermination()
  }
}

3 编译代码

mvn clean package -DskipTests

4 启动zookeeper

zkServer.sh  start

5 启动kafka

kafka-server-start.sh -daemon $KAFKA_HOME/config/server.properties &

6 创建topic

kafka-topics.sh --create --zookeeper localhost:2181 --replication-factor 1 --partitions 1 --topic kafka-streaming-topic

7 启动producer，用来生产消息

kafka-console-producer.sh --broker-list localhost:9092 --topic kafka-streaming-topic

8 提交spark程序

spark-submit \
--class com.lihaogn.sparkKafka.KafKaReceiverWC \
--master local[2] \
--name KafKaReceiverWC \
--jars /Users/Mac/software/spark-streaming-kafka-0-8-assembly_2.11-2.2.0.jar \
/Users/Mac/my-lib/Kafka-train-1.0.jar \
localhost:2181 test kafka-streaming-topic 1

9 测试