streaming从kafka中读数据

最新推荐文章于 2024-05-15 14:40:27 发布

原创最新推荐文章于 2024-05-15 14:40:27 发布 · 249 阅读

0 ·

CC 4.0 BY-SA版权

本文展示了一个使用 Apache Spark Streaming 直接从 Kafka 消费消息的示例。通过配置 Spark 和 Kafka 参数，创建了直接流处理，实现了从指定主题 kb07 接收并处理消息的功能。此示例涵盖了 Spark 配置、Kafka 参数设置及消息处理流程。

package test01


import org.apache.kafka.clients.consumer.{ConsumerConfig, ConsumerRecord}
import org.apache.spark.SparkConf
import org.apache.spark.streaming.dstream.{InputDStream, ReceiverInputDStream}
import org.apache.spark.streaming.flume.{FlumeUtils, SparkFlumeEvent}
import org.apache.spark.streaming.kafka010.{ConsumerStrategies, KafkaUtils, LocationStrategies}
import org.apache.spark.streaming.{Seconds, StreamingContext}

object SparkkafkaDirectDemo extends App {
  private val conf: SparkConf = new SparkConf().setAppName("flume01").setMaster("local[2]")
  private val ssc = new StreamingContext(conf,Seconds(5))
  val kafkaParams = Map(
    (ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG -> "192.168.106.107:9092"),
    ("key.deserializer"->"org.apache.kafka.common.serialization.StringDeserializer"),
    ("value.deserializer"-> "org.apache.kafka.common.serialization.StringDeserializer"),
    (ConsumerConfig.GROUP_ID_CONFIG-> "testGroup")
  )

  private val message: InputDStream[ConsumerRecord[String, String]] = KafkaUtils.createDirectStream(ssc,
    LocationStrategies.PreferConsistent,
    ConsumerStrategies.Subscribe(Set("kb07"), kafkaParams)
  )

message.map(x=>x.value()).flatMap(_.split("")).map((_,1)).reduceByKey(_+_)



ssc.start()
  ssc.awaitTermination()

}