SparkMysql.scala代码
package com.sid.com
import org.apache.spark.sql.SparkSession
import java.util.Properties
/**
* 操作mysql的数据
* */
object SparkMysql {
def main(args: Array[String]): Unit = {
val spark = SparkSession.builder().master("local[2]").appName("SparkMysql").getOrCreate()
//第一种方法
val jdbcDF = spark.read.format("jdbc")
.option("url","jdbc:mysql://localhost:3306/sid")
.option("dbtable","wordcount")
.option("user","root").option("password","Liyijie331")
.option("driver","com.mysql.jdbc.Driver")load()
//第二种方法
//val connectionProperties = new Properties()
// connectionProperties.put("user","root")
//connectionProperties.put("password","Liyijie331")
// connectionProperties.put("driver","com.mysql.jdbc.Driver")
//val jdbc2DF = spark.read.jdbc("jdbc:mysql://localhost:3306/sid","wordcount",connectionProperties)
jdbcDF.printSchema()
jdbcDF.show()
}
}
pom.xml
<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/maven-v4_0_0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.sid.com</groupId>
<artifactId>sparksqltrain</artifactId>
<version>1.0-SNAPSHOT</version>
<inceptionYear>2008</inceptionYear>
<properties>
<scala.version>2.11.8</scala.version>
<spark.version>2.2.0</spark.version>
</properties>
<repositories>
<repository>
<id>scala-tools.org</id>
<name>Scala-Tools Maven2 Repository</name>
<url>http://scala-tools.org/repo-releases</url>
</repository>
</repositories>
<pluginRepositories>
<pluginRepository>
<id>scala-tools.org</id>
<name>Scala-Tools Maven2 Repository</name>
<url>http://scala-tools.org/repo-releases</url>
</pluginRepository>
</pluginRepositories>
<dependencies>
<!-- scala依赖 -->
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${scala.version}</version>
</dependency>
<!-- spark依赖 -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<!-- hivecontext要用这个依赖-->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.spark-project.hive</groupId>
<artifactId>hive-jdbc</artifactId>
<version>1.2.1.spark2</version>
</dependency>
<!-- https://mvnrepository.com/artifact/mysql/mysql-connector-java -->
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.38</version>
</dependency>
</dependencies>
<build>
<sourceDirectory>src/main/scala</sourceDirectory>
<testSourceDirectory>src/test/scala</testSourceDirectory>
<plugins>
<plugin>
<groupId>org.scala-tools</groupId>
<artifactId>maven-scala-plugin</artifactId>
<executions>
<execution>
<goals>
<goal>compile</goal>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
<configuration>
<scalaVersion>${scala.version}</scalaVersion>
<args>
<arg>-target:jvm-1.5</arg>
</args>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-eclipse-plugin</artifactId>
<configuration>
<downloadSources>true</downloadSources>
<buildcommands>
<buildcommand>ch.epfl.lamp.sdt.core.scalabuilder</buildcommand>
</buildcommands>
<additionalProjectnatures>
<projectnature>ch.epfl.lamp.sdt.core.scalanature</projectnature>
</additionalProjectnatures>
<classpathContainers>
<classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
<classpathContainer>ch.epfl.lamp.sdt.launching.SCALA_CONTAINER</classpathContainer>
</classpathContainers>
</configuration>
</plugin>
</plugins>
</build>
<reporting>
<plugins>
<plugin>
<groupId>org.scala-tools</groupId>
<artifactId>maven-scala-plugin</artifactId>
<configuration>
<scalaVersion>${scala.version}</scalaVersion>
</configuration>
</plugin>
</plugins>
</reporting>
</project>
运行结果
官网介绍