spark streaming 读取kafka

需要依赖

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.12</artifactId>
            <version>3.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.12</artifactId>
            <version>3.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-10_2.12</artifactId>
            <version>3.0.0</version>
        </dependency>

代码样例

package scala.spark.test

import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.streaming.kafka010.{ConsumerStrategies, KafkaUtils, LocationStrategies}
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.streaming.{Seconds, StreamingContext}

/**
 * spark streaming read kafka data test
 *
 * @author sssuperMario
 * @date 2020-08-12
 */
object SparkStreamingReadKafka {

  def main(args: Array[String]): Unit = {
    val sc = new SparkConf()
    sc.setMaster("local[*]").setAppName("SparkStreamingReadKafkaTest")
    val ssc = new StreamingContext(new SparkContext(sc), Seconds(5))

    val topics = Array("topic_1", "topic_2")
    val kafkaOptions = Map[String, Object](
      "bootstrap.servers" -> "127.0.0.1:9092",
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer],
      "group.id" -> "SparkStreamingKafkaTest",
      "auto.offset.reset" -> "earliest",
      "enable.auto.commit" -> (false: java.lang.Boolean)
    )

    val kafkaDS = KafkaUtils.createDirectStream[String, String](ssc
      , LocationStrategies.PreferConsistent
      , ConsumerStrategies.Subscribe[String, String](topics, kafkaOptions))

    val kafkaDataStreamRDD = kafkaDS.filter(data => data.value().length > 0).map(data => (data.key(), data.value()))
    kafkaDataStreamRDD.saveAsTextFiles("/read_data/")
    kafkaDataStreamRDD.foreachRDD((rdd, time) => {
      println(time)
      rdd.foreach(key => {
        println(key._1 + " => " + key._2)
      })
    })

    ssc.start()
    ssc.awaitTermination()
    ssc.stop()
  }


}