使用Spark Streaming完成黑名單過濾

首先在maven工程的pom.xml文件加入以下依賴：

<properties>
        <spark.version>2.2.0</spark.version>
    </properties>
 <!-- Spark Streaming 依賴-->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>

TransformApp.scala

package spark

import org.apache.spark.SparkConf
import org.apache.spark.streaming.{Seconds, StreamingContext}

/**
  * 黑名單過濾
  */
object TransformApp {


  def main(args: Array[String]): Unit = {

    val sparkConf = new SparkConf().setMaster("local[2]").setAppName("NetworkWordCount")

    /**
      * 創建StreamingContext需要兩個參數：SparkConf和batch interval
      */
    val ssc = new StreamingContext(sparkConf, Seconds(5))


    /**
      * 構建黑名單
      */
    val blacks = List("zs", "ls")
    val blacksRDD = ssc.sparkContext.parallelize(blacks).map(x => (x, true))

    val lines = ssc.socketTextStream("localhost", 6789)
    val clicklog = lines.map(x => (x.split(",")(1), x)).transform(rdd => {
      rdd.leftOuterJoin(blacksRDD)
        .filter(x=> x._2._2.getOrElse(false) != true)
        .map(x=>x._2._1)
    })

    clicklog.print()

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