SparkStreaming 实现黑名单过滤功能

pom 文件

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>com.imooc.spark</groupId>
  <artifactId>sparktrain</artifactId>
  <version>1.0</version>
  <inceptionYear>2008</inceptionYear>
  <properties>
    <scala.version>2.11.8</scala.version>
    <kafka.version>0.9.0.0</kafka.version>
    <spark.version>2.2.0</spark.version>
    <hadoop.version>2.6.0-cdh5.7.0</hadoop.version>
    <hbase.version>1.2.0-cdh5.7.0</hbase.version>
  </properties>

  <!--添加cloudera的repository-->
  <repositories>
    <repository>
      <id>cloudera</id>
      <url>https://repository.cloudera.com/artifactory/cloudera-repos</url>
    </repository>
  </repositories>

  <dependencies>
    <dependency>
      <groupId>org.scala-lang</groupId>
      <artifactId>scala-library</artifactId>
      <version>${scala.version}</version>
    </dependency>

    <!-- Kafka 依赖-->
    <!--
    <dependency>
        <groupId>org.apache.kafka</groupId>
        <artifactId>kafka_2.11</artifactId>
        <version>${kafka.version}</version>
    </dependency>
    -->

    <!-- Hadoop 依赖-->
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-client</artifactId>
      <version>${hadoop.version}</version>
    </dependency>

    <!-- HBase 依赖-->
    <!--<dependency>
      <groupId>org.apache.hbase</groupId>
      <artifactId>hbase-client</artifactId>
      <version>${hbase.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.hbase</groupId>
      <artifactId>hbase-server</artifactId>
      <version>${hbase.version}</version>
    </dependency>-->

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


    <!-- Spark Streaming整合Flume 依赖-->
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-streaming-flume_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-streaming-flume-sink_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.commons</groupId>
      <artifactId>commons-lang3</artifactId>
      <version>3.5</version>
    </dependency>

    <!-- Spark SQL 依赖-->
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-sql_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>


    <dependency>
      <groupId>com.fasterxml.jackson.module</groupId>
      <artifactId>jackson-module-scala_2.11</artifactId>
      <version>2.6.5</version>
    </dependency>

    <dependency>
      <groupId>net.jpountz.lz4</groupId>
      <artifactId>lz4</artifactId>
      <version>1.3.0</version>
    </dependency>

    <dependency>
      <groupId>mysql</groupId>
      <artifactId>mysql-connector-java</artifactId>
      <version>5.1.38</version>
    </dependency>

    <dependency>
      <groupId>org.apache.flume.flume-ng-clients</groupId>
      <artifactId>flume-ng-log4jappender</artifactId>
      <version>1.6.0</version>
    </dependency>

  </dependencies>

  <build>
    <!--
    <sourceDirectory>src/main/scala</sourceDirectory>
    <testSourceDirectory>src/test/scala</testSourceDirectory>
    -->
    <plugins>
      <plugin>
        <groupId>org.scala-tools</groupId>
        <artifactId>maven-scala-plugin</artifactId>
        <executions>
          <execution>
            <goals>
              <goal>compile</goal>
              <goal>testCompile</goal>
            </goals>
          </execution>
        </executions>
        <configuration>
          <scalaVersion>${scala.version}</scalaVersion>
          <args>
            <arg>-target:jvm-1.5</arg>
          </args>
        </configuration>
      </plugin>
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-eclipse-plugin</artifactId>
        <configuration>
          <downloadSources>true</downloadSources>
          <buildcommands>
            <buildcommand>ch.epfl.lamp.sdt.core.scalabuilder</buildcommand>
          </buildcommands>
          <additionalProjectnatures>
            <projectnature>ch.epfl.lamp.sdt.core.scalanature</projectnature>
          </additionalProjectnatures>
          <classpathContainers>
            <classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
            <classpathContainer>ch.epfl.lamp.sdt.launching.SCALA_CONTAINER</classpathContainer>
          </classpathContainers>
        </configuration>
      </plugin>
    </plugins>
  </build>
  <reporting>
    <plugins>
      <plugin>
        <groupId>org.scala-tools</groupId>
        <artifactId>maven-scala-plugin</artifactId>
        <configuration>
          <scalaVersion>${scala.version}</scalaVersion>
        </configuration>
      </plugin>
    </plugins>
  </reporting>
</project>

源码

package com.imooc

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

// 黑名单过滤
object TransformApp {

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

    val sparkConf = new SparkConf().setMaster("local[2]").setAppName("NetworkWordCount")
    val ssc = new StreamingContext(sparkConf, Seconds(5))

    // 构建黑名单
    val blacks = List("zs", "ls")
    // 把黑名单list转为RDD并把每一个内容加上true
    val blackRDD = ssc.sparkContext.parallelize(blacks).map((_,true))

    val lines = ssc.socketTextStream("192.168.108.xxx", 6789)
    // 端口接收到的数据按逗号切分，取出名字和接收到的内容拼成内容RDD
    // 内容RDD左连接（左边的数据是全的）黑名单RDD，过滤掉黑名单标记为true的内容
    // 取出内容，去掉黑名单标记
    val clicklog = lines.map(x => (x.split(",")(1), x)).transform(rdd => {
      rdd.leftOuterJoin(blackRDD)
        // 不等于true的留下来
        .filter(x => x._2._2.getOrElse(false) != true)
        .map(x => x._2._1)
    })

    clicklog.print()

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

测试命令

nc -lk 6789