sparkJDBC mysql

最新推荐文章于 2025-05-13 15:29:16 发布

原创最新推荐文章于 2025-05-13 15:29:16 发布 · 173 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#数据库 #大数据 #java

Spark篇专栏收录该内容

17 篇文章

订阅专栏

本文介绍如何使用 Apache Spark 通过 JDBC 读取 MySQL 数据并进行数据写入操作。演示了配置 Spark 应用程序、设置连接属性、从 JSON 文件中读取数据及执行具体的 JDBC 读写操作等步骤。

import java.sql.DriverManager
import org.apache.spark.rdd.JdbcRDD
import java.util.Properties
import org.apache.spark.{ SparkContext, SparkConf }
import org.apache.spark.sql.Row
import org.apache.spark.sql.types.{ IntegerType, StringType, StructField, StructType }
import org.apache.spark.sql.DataFrame

object sparkJDBC {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("Simple Application").setMaster("local[*]")
    val sc = new SparkContext(conf)

    val url = "jdbc:mysql://localhost:3306/easyui"
    val MYSQL_CONNECTION_URL = url + "?user=" + "root" + "&password=";
    val sqlContext = new org.apache.spark.sql.SQLContext(sc)

    val usersDf = sqlContext.read.json("i:/4/users.txt")
    val sets = new Properties();
    sets.put("user", "root");
    sets.put("password", "");
    sets.put("driver", "com.mysql.jdbc.Driver");
    sets.put("overwrite", "false");
    val datas = sqlContext.read.jdbc(url, "zhao", "name", 1, 3, 1, sets)
    datas.foreach { v => println("name:" + v.get(0) + " age:" + v.get(1)) }

    usersDf.write.jdbc(url, "zhao", sets)
//    usersDf.insertIntoJDBC(MYSQL_CONNECTION_URL, "zhao", false);
//    usersDf.insertIntoJDBC(url, table, overwrite)
  }

}

users.txt