spark2.3 消费kafka数据

官网介绍

http://spark.apache.org/docs/2.3.0/streaming-kafka-0-10-integration.html#creating-a-direct-stream

 

案例pom.xml依赖

    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-streaming_2.11</artifactId>
      <version>2.3.0</version>
      <!--      <scope>provided</scope>   -->
    </dependency>
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
      <version>2.3.0</version>

 

 

 

package SpartStreamingaiqiyi
import org.apache.spark._
import org.apache.spark.streaming._
import org.apache.kafka.clients.consumer.ConsumerRecord
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.sql.SparkSession
import org.apache.spark.streaming.kafka010._
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe


object test {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession.builder()
      .appName("aiqiyi")
      .master("local[*]")
      .config("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
      .getOrCreate()
    val sc = spark.sparkContext
    val checkpointDir = "F:\\IdeaWorkspace\\aiqiyi\\ck"
    val ssc: StreamingContext = new StreamingContext(sc, Seconds(5))
    ssc.checkpoint(checkpointDir)
    val topics = Array("aiqiyi")

    // Create a local StreamingContext with two working thread and batch interval of 1 second.
    // The master requires 2 cores to prevent a starvation scenario.
    val kafkaParams = Map[String, Object](
      "bootstrap.servers" -> "dip005:9092,dip006:9092,dip007:9092",
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer],
      "group.id" -> "use_a_separate_group_id_for_each_stream",
      "auto.offset.reset" -> "latest",
      "enable.auto.commit" -> (false: java.lang.Boolean)
    )

    val stream = KafkaUtils.createDirectStream[String, String](
      ssc,
      PreferConsistent,
      Subscribe[String, String](topics, kafkaParams)
    )
    val resultDStream = stream.map(x=>x.value())
    resultDStream.print()
    ssc.start()
    ssc.awaitTermination()
  }

}
上一篇:Spark优化笔记


下一篇:c# – 在Serilog中进行解构时忽略空值