使用SparkStreaming实现将数据写到MySQL中

（1）在pom.xml中加入如下依赖包

<dependency>
    <groupId>mysql</groupId>
    <artifactId>mysql-connector-java</artifactId>
    <version>5.1.38</version>
</dependency>
<dependency>
    <groupId>commons-dbcp</groupId>
    <artifactId>commons-dbcp</artifactId>
    <version>1.4</version>
</dependency>

（2）在MySql中创建数据库和表，命令操作如下

mysql -uroot –p
create database test;
use test;
show tables;
create table streaming(item varchar(30),count int);

（3）使用Java编写一个数据库连接池类

package cn.itcast.spark.day7;

import java.sql.Connection;
import java.sql.DriverManager;
import java.util.LinkedList;

public class ConnectionPool {
    private static LinkedList<Connection> connectionQueue;

    static {
        try {
            Class.forName("com.mysql.jdbc.Driver");
        }catch (ClassNotFoundException e) {
            e.printStackTrace();
        }
    }

    public synchronized static Connection getConnection() {
        try {
            if (connectionQueue == null) {
                connectionQueue = new LinkedList<Connection>();
                for (int i = 0;i < 5;i ++) {
                    Connection conn = DriverManager.getConnection(
                            "jdbc:mysql://localhost:3306/test?characterEncoding=utf8&useSSL=true",
                            "root",
                            "root"
                    );
                    connectionQueue.push(conn);
                }
            }
        }catch (Exception e) {
            e.printStackTrace();
        }
        return connectionQueue.poll();
    }

    public static void returnConnection(Connection conn) {
        connectionQueue.push(conn);
    }
}

（4）编写Spark代码

package cn.itcast.spark.day7

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

object sqlTest {
  def main(args: Array[String]){

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

    val lines = ssc.socketTextStream("101.132.122.75",9999)
    val words = lines.flatMap(_.split(" "))
    val wordcount = words.map(x => (x,1)).reduceByKey(_+_)
    wordcount.foreachRDD(rdd => {
      rdd.foreachPartition(eachPartition => {
        val conn = ConnectionPool.getConnection();
        eachPartition.foreach(record => {
          val sql = "insert into streaming(item,count) values('" + record._1 + "'," + record._2 + ")"
          val stmt = conn.createStatement
          stmt.executeUpdate(sql)
        })
        ConnectionPool.returnConnection(conn)
      })
    })
    ssc.start()
    ssc.awaitTermination()
  }
}

（5）打开netcat发送数据

root@spark-master:~# nc -lk 9999 
spark hadoop kafka spark hadoop kafka spark hadoop kafka spark hadoop

（6）提交

/usr/local/spark/bin/spark-submit --driver-class-path /usr/local/spark/lib/mysql-connector-java-5.1.35-bin.jar /root/Documents/SparkApps/SparkStreamApps.jar