spark streaming 消费kafka数据

1.在虚拟机启动zookeeper和kafka，新建topic test1,这里使用的topic 是test1。

2.Scala程序

要修改 3.定义 Kafka 参数中的主机名称以及要消费的topic名称

package scala.spark
import org.apache.kafka.clients.consumer.{ConsumerConfig, ConsumerRecord}
import org.apache.spark.SparkConf
import org.apache.spark.streaming.dstream.{DStream, InputDStream}
import org.apache.spark.streaming.kafka010.{ConsumerStrategies, KafkaUtils, LocationStrategies}
import org.apache.spark.streaming.{Seconds, StreamingContext}

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

    //1.创建 SparkConf
    val sparkConf: SparkConf = new SparkConf().setAppName("ReceiverWordCount").setMaster("local[*]")

    //2.创建 StreamingContext
    val ssc = new StreamingContext(sparkConf, Seconds(3))

    //3.定义 Kafka 参数
    val kafkaPara: Map[String, Object] = Map[String, Object]( ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG ->
      "hadoop02:9092", ConsumerConfig.GROUP_ID_CONFIG -> "test1", "key.deserializer" ->
      "org.apache.kafka.common.serialization.StringDeserializer", "value.deserializer" ->
      "org.apache.kafka.common.serialization.StringDeserializer"
    )

    //4.读取 Kafka 数据创建 DStream
    val kafkaDStream: InputDStream[ConsumerRecord[String, String]] = KafkaUtils.createDirectStream[String, String](ssc,
      LocationStrategies.PreferConsistent, ConsumerStrategies.Subscribe[String, String](Set("test1"), kafkaPara))

    //5.将每条消息的 KV 取出
    val valueDStream: DStream[String] = kafkaDStream.map(record => record.value())

      //6. 计 算
    valueDStream.flatMap(_.split(" "))
      .map((_, 1))
      .reduceByKey(_ + _)
      .print()

    //7. 开 启 任 务 ssc.start() ssc.awaitTermination()
    ssc.start()
    ssc.awaitTermination()
  }
}