spark中jdbcRDD操作mysql的用法

spark中提供了jdbcRDD连接mysql数据库操作

import java.sql.DriverManager
import org.apache.spark.rdd.JdbcRDD
import org.apache.spark.{SparkConf, SparkContext}

object JdbcRDDDemo {
  def main(args: Array[String]): Unit = {
    //1.spark程序入口
    val conf: SparkConf = new SparkConf().setAppName("Urlcount").setMaster("local[2]")
    val sc: SparkContext = new SparkContext(conf)

    //匿名函数
    val connection =() =>{
      Class.forName("com.mysql.jdbc.Driver").newInstance()
      DriverManager.getConnection("jdbc:mysql://localhost:3306/urlcount?charatorEncoding=utf-8","root","root")


    }

    //查询数据
    val jdbcRdd: JdbcRDD[(Int,String,String)] = new JdbcRDD(
      //指定sparkcontext
      sc,
      connection,
      "SELECT * FROM url_data where uid >= ? AND uid <= ?",
      //两个任务并行 ,其中1,4代表上面sql语句中的两个占位符? ?,如果定义两个分区，
      //最好使用>= <=  而不是> <,否则容易导致一些结果丢失
      1, 4, 2,
      r => {
        val uid = r.getInt(1)
        val xueyuan = r.getString(2)
        val number_one = r.getString(3)
        (uid,xueyuan,number_one)
      }
    )

    val jrdd = jdbcRdd.collect()
    println(jrdd.toBuffer)
    sc.stop()
  }
}