SparkMySQLToHdfs

木卫二号Coding

已于 2023-04-20 09:31:37 修改

阅读量412

点赞数

分类专栏： Hadoop 文章标签： docker centos 容器

于 2022-03-26 22:33:03 首次发布

本文链接：https://blog.csdn.net/hai4321/article/details/123765429

版权

Hadoop 专栏收录该内容

7 篇文章 0 订阅

订阅专栏

Maven

<properties>
        <java.version>1.8</java.version>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</maven.compiler.target>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
        <scala.version>2.12.10</scala.version>
        <spark.version>3.0.0</spark.version>
        <encoding>UTF-8</encoding>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.12</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.12</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.12</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.49</version>
        </dependency>
    </dependencies>

Java

import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;

import java.util.HashMap;
import java.util.Map;

public class SparkMySQLToHdfs {

    public static void main(String[] args) {

        System.setProperty("HADOOP_USER_NAME","root"); //用户权限写入HDFS

        SparkSession spark = SparkSession
                .builder()
                .appName("SparkMySQLToHdfs ")
                .master("local[2]")	// 生产注掉
                .config("spark.sql.warehouse.dir", "file:///C:/GitCoder/spark/file") // 生产注掉
                .getOrCreate();


        String url = "jdbc:mysql://127.0.0.1:3306/shop_db?useUnicode=true&characterEncoding=UTF-8&serverTimezone=UTC";

        Map<String, String> options = new HashMap<>();
        options.put("driver", "com.mysql.jdbc.Driver");
        options.put("url", url);
        options.put("user", "root");
        options.put("password", "xx");
        options.put("dbtable", "t_student");


        Dataset<Row> dataset = spark.read().format("jdbc").options(options).load();

        dataset.show();

        dataset.write().mode(SaveMode.Append).format("parquet").save("hdfs://192.168.0.xxx:9000/user/root/data/mysql/student_03");

        spark.stop();

    }

}