Kafka依赖

                <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-10_2.12</artifactId>
            <version>3.0.0</version>
        </dependency>
        <dependency>
            <groupId>com.fasterxml.jackson.core</groupId>
            <artifactId>jackson-core</artifactId>
            <version>2.10.1</version>
        </dependency>

Kafka数据源

package com.streaming
import org.apache.kafka.clients.consumer.{ConsumerConfig, ConsumerRecord}
import org.apache.spark.SparkConf
import org.apache.spark.streaming.dstream.InputDStream
import org.apache.spark.streaming.kafka010.{ConsumerStrategies, KafkaUtils, LocationStrategies}
import org.apache.spark.streaming.{Seconds, StreamingContext}
object Spark_Kafka {
    def main(args: Array[String]): Unit = {
        val sparkConf = new SparkConf().setMaster("local[*]").setAppName("SparkStreaming")
        val ssc = new StreamingContext(sparkConf, Seconds(3))
        val kafkaPara: Map[String, Object] = Map[String, Object](
            ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG -> "hadoop102:9092,hadoop103:9092,hadoop104:9092",
            ConsumerConfig.GROUP_ID_CONFIG -> "hao",
            "key.deserializer" -> "org.apache.kafka.common.serialization.StringDeserializer",
            "value.deserializer" -> "org.apache.kafka.common.serialization.StringDeserializer"
        )
        val kafkaDataDS: InputDStream[ConsumerRecord[String, String]] = KafkaUtils.createDirectStream[String, String](
            ssc,
            LocationStrategies.PreferConsistent,
            ConsumerStrategies.Subscribe[String, String](Set("hao"), kafkaPara)
        )
        kafkaDataDS.map(_.value()).print()
        ssc.start()
        ssc.awaitTermination()
    }
}