[大数据]Spark读取MySQL

Spark读取MySQL

import org.apache.spark.SparkConf;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;
import java.util.Properties;

public class FromMySQL {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setMaster("local[2]").setAppName("spark_mysql");
        //创建一个SparkSession类型的spark对象
        SparkSession sparkSession = SparkSession.builder().config(conf).getOrCreate();

        //创建Properties对象
        Properties properties = new Properties();
        properties.setProperty("user", "root"); // 用户名
        properties.setProperty("password", "123456"); // 密码
        properties.setProperty("driver", "com.mysql.cj.jdbc.Driver");
        //设置分区数
        properties.setProperty("numPartitions","2");
        
        Dataset<Row> words1 = sparkSession.read().jdbc("jdbc:mysql://localhost:3306/test", "words1", properties).select("word","count").where("count>=3");
        //输出数据
        words1.show();
        //输出表的结构
        words1.printSchema();
        sparkSession.stop();
    }
}

结果：