使用Spark Streaming完成词频统计,并将结果写入到MySQL数据库中

首先在maven工程的pom.xml文件加入以下依赖:

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

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

ForeachRDDApp.scala

package spark

import java.sql.DriverManager

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

/**
  * 使用Spark Streaming完成词频统计,并将结果写入到MySQL数据库中
  */
object ForeachRDDApp {

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

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


    val lines = ssc.socketTextStream("localhost", 6789)

    val result = lines.flatMap(_.split(" ")).map((_, 1)).reduceByKey(_ + _)

    //result.print()  //此处仅仅是将统计结果输出到控制台

    //TODO... 将结果写入到MySQL
    //    result.foreachRDD(rdd =>{
    //      val connection = createConnection()  // executed at the driver
    //      rdd.foreach { record =>
    //        val sql = "insert into wordcount(word, wordcount) values('"+record._1 + "'," + record._2 +")"
    //        connection.createStatement().execute(sql)
    //      }
    //    })

    result.print()

    result.foreachRDD(rdd => {
      rdd.foreachPartition(partitionOfRecords => {
        val connection = createConnection()
        partitionOfRecords.foreach(record => {
          val sql = "insert into wordcount(word, wordcount) values('" + record._1 + "'," + record._2 + ")"
          connection.createStatement().execute(sql)
        })

        connection.close()
      })
    })


    ssc.start()
    ssc.awaitTermination()
  }


  /**
    * 获取MySQL的连接
    */
  def createConnection() = {
    Class.forName("com.mysql.jdbc.Driver")
    DriverManager.getConnection("jdbc:mysql://localhost:3306/test", "root", "root")
  }

}

你可能感兴趣的:(Scala学习,大数据平台Spark生态系统,BigData,Spark,Streaming)