导入依赖
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.11</artifactId>
<version>2.1.1</version>
</dependency>
代码实现
def main(args: Array[String]): Unit = {
val conf: SparkConf = new SparkConf().setAppName(this.getClass.getSimpleName).setMaster("local[*]")
val ssc = new StreamingContext(conf,Seconds(3))
val DStream: ReceiverInputDStream[String] = ssc.socketTextStream("hadoop01", 11111)
val flatDStream: DStream[String] = DStream.flatMap(_.split(" "))
val mapDStream: DStream[(String, Int)] = flatDStream.map((_, 1))
val resDStream: DStream[(String, Int)] = mapDStream.reduceByKey(_+_)
resDStream.print()
ssc.start()
ssc.awaitTermination()
}
虚拟机启动netcat进行测试
nc -lk 11111