一、在qianfeng01上启动:然后发数据
nc -lk qianfeng01 10086
注意:-l是监听, -k 当一个连接结束时,强制nc监听另一个连接
二、运行代码:
package com.qf.sparkStreaming.day01
import org.apache.spark.SparkConf
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.dstream.{DStream, ReceiverInputDStream}
import org.apache.spark.streaming.{Seconds, StreamingContext}
object _02SparkStreamingReadLocalFile {
def main(args: Array[String]): Unit = {
//1.获取一个配置对象
//如果是本地模式,那么最少需要两个线程。一个线程负责接收数据,另一个负责计算
val conf: SparkConf = new SparkConf().setAppName("test").setMaster("local[2]")
//2.获取SparkStreaming的上下文对象
val context: StreamingContext = new StreamingContext(conf, Seconds(5))
//3.读取TCP协议,用nc发送数据
val dStream: ReceiverInputDStream[String] = context.socketTextStream("qianfeng01", 10086)
//4.使用算子进行计算,返回新的DStream,wordCount
val value: DStream[(String, Int)] = dStream.map((_, 1)).reduceByKey(_ + _)
//5.打印
value.print()
//6.启动计算程序
context.start()
//7.等待终止,避免没接收到数据就终止程序的情况
context.awaitTermination()
}
}