Spark使用Java读取mysql数据和保存数据到mysql

最新推荐文章于 2024-05-24 17:56:33 发布

fengzhimohan

最新推荐文章于 2024-05-24 17:56:33 发布

阅读量9.4k

点赞数 3

分类专栏： spark 文章标签： mysql spark java

本文链接：https://blog.csdn.net/fengzhimohan/article/details/78471952

版权

spark 专栏收录该内容

5 篇文章 0 订阅

订阅专栏

项目应用需要利用Spark读取mysql数据进行数据分析，然后将分析结果保存到mysql中。
开发环境：
java：1.8
IDEA
spark：1.6.2

一.读取mysql数据
1.创建一个mysql数据库
user_test表结构如下：

create table user_test (
id int(11) default null comment "id",
name varchar(64) default null comment "用户名",
password varchar(64) default null comment "密码",
age int(11) default null comment "年龄"
)engine=InnoDB default charset=utf-8;

2.插入数据

insert into user_test values(12, 'cassie', '123456', 25);
insert into user_test values(11, 'zhangs', '1234562', 26);
insert into user_test values(23, 'zhangs', '2321312', 27);
insert into user_test values(22, 'tom', 'asdfg', 28);

3.创建maven工程，命名为Test，添加java类SparkMysql
这里写图片描述
添加依赖包

pom文件内容：

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>SparkSQL</groupId>
    <artifactId>com.sparksql.test</artifactId>
    <version>1.0-SNAPSHOT</version>
    <properties>
         <java.version>1.8</java.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.24</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.6.0</version>
        </dependency>
        <dependency>
            <groupId>net.sf.json-lib</groupId>
            <artifactId>json-lib</artifactId>
            <version>2.4</version>
            <classifier>jdk15</classifier>
        </dependency>

    </dependencies>

</project>

4.编写spark代码

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.SQLContext;

import java.util.Properties;

/**
 * Created by Administrator on 2017/11/6.
 */
public class SparkMysql {
    public static org.apache.log4j.Logger logger = org.apache.log4j.Logger.getLogger(SparkMysql.class);

    public static void main(String[] args) {
        JavaSparkContext sparkContext = new JavaSparkContext(new SparkConf().setAppName("SparkMysql").setMaster("local[5]"));
        SQLContext sqlContext = new SQLContext(sparkContext);
        //读取mysql数据
        readMySQL(sqlContext);

        //停止SparkContext
        sparkContext.stop();
    }
        private static void readMySQL(SQLContext sqlContext){
        //jdbc.url=jdbc:mysql://localhost:3306/database
        String url = "jdbc:mysql://localhost:3306/test";
        //查找的表名
        String table = "user_test";
        //增加数据库的用户名(user)密码(password),指定test数据库的驱动(driver)
        Properties connectionProperties = new Properties();
        connectionProperties.put("user","root");
        connectionProperties.put("password","123456");
        connectionProperties.put("driver","com.mysql.jdbc.Driver");

        //SparkJdbc读取Postgresql的products表内容
        System.out.println("读取test数据库中的user_test表内容");
        // 读取表中所有数据
        DataFrame jdbcDF = sqlContext.read().jdbc(url,table,connectionProperties).select("*");
        //显示数据
        jdbcDF.show();
    }
}

运行结果：
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-cQJdK41p-1572347591249)(https://img-blog.csdn.net/20171107200353583?watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQvZmVuZ3poaW1vaGFu/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/SouthEast)]

二.写入数据到mysql中

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.SQLContext;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructType;

import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.Properties;

/**
 * Created by Administrator on 2017/11/6.
 */
public class SparkMysql {
    public static org.apache.log4j.Logger logger = org.apache.log4j.Logger.getLogger(SparkMysql.class);

    public static void main(String[] args) {
        JavaSparkContext sparkContext = new JavaSparkContext(new SparkConf().setAppName("SparkMysql").setMaster("local[5]"));
        SQLContext sqlContext = new SQLContext(sparkContext);
        //写入的数据内容
        JavaRDD<String> personData = sparkContext.parallelize(Arrays.asList("1 tom 5","2 jack 6","3 alex 7"));
        //数据库内容
        String url = "jdbc:mysql://localhost:3306/test";
        Properties connectionProperties = new Properties();
        connectionProperties.put("user","root");
        connectionProperties.put("password","123456");
        connectionProperties.put("driver","com.mysql.jdbc.Driver");
        /**
         * 第一步：在RDD的基础上创建类型为Row的RDD
         */
        //将RDD变成以Row为类型的RDD。Row可以简单理解为Table的一行数据
        JavaRDD<Row> personsRDD = personData.map(new Function<String,Row>(){
            public Row call(String line) throws Exception {
                String[] splited = line.split(" ");
                return RowFactory.create(Integer.valueOf(splited[0]),splited[1],Integer.valueOf(splited[2]));
            }
        });

        /**
         * 第二步：动态构造DataFrame的元数据。
         */
        List structFields = new ArrayList();
        structFields.add(DataTypes.createStructField("id",DataTypes.IntegerType,true));
        structFields.add(DataTypes.createStructField("name",DataTypes.StringType,true));
        structFields.add(DataTypes.createStructField("age",DataTypes.IntegerType,true));

        //构建StructType，用于最后DataFrame元数据的描述
        StructType structType = DataTypes.createStructType(structFields);

        /**
         * 第三步：基于已有的元数据以及RDD<Row>来构造DataFrame
         */
        DataFrame personsDF = sqlContext.createDataFrame(personsRDD,structType);

        /**
         * 第四步：将数据写入到person表中
         */
        personsDF.write().mode("append").jdbc(url,"person",connectionProperties);
        
        //停止SparkContext
        sparkContext.stop();
    }
 }

运行结果：
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-xy8h8CCz-1572347591250)(https://img-blog.csdn.net/20171107201600768?watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQvZmVuZ3poaW1vaGFu/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/SouthEast)]

代码下载：

转载请标明出处，谢谢！。

如果感觉本文对您有帮助，请留下您的赞，您的支持是我坚持写作最大的动力，谢谢！