spark支持通过Java JDBC 访问关系型数据库。需要通过JdbcRDD进行,示例如下:
(1)添加依赖
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.27</version>
</dependency>
(2)MySQL读取
package com.atguigu.bigdata.spark
import java.sql.{
Connection, PreparedStatement}
import org.apache.spark.{
SparkConf, SparkContext}
import org.apache.spark.rdd.{
JdbcRDD, RDD}
/**
* @com.atguigu.bigdata.spark
* @author sixrope
* @date 2019-12-17 16:54
* @version v1.0
* @description
* RDD与MySQL数据库连接
*/
object Spark01_Mysql {
def main(args: Array[String]): Unit = {
val config: SparkConf = new SparkConf().setMaster("local[*]").setAppName("Spark01_Mysql")
// 创建Spark上下文对象
val sc = new SparkContext(config)