spark连接mysql

pom

<?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>com.syllabus</groupId>
    <artifactId>chapter-7</artifactId>
    <version>1.0-SNAPSHOT</version>
    <!-- 额外指定可以通过如下链接下载Jar包依赖 -->
    <repositories>
        <repository>
            <id>1</id>
            <name>MAVEN-CENTRE</name>
            <url>http://central.maven.org/maven2/</url>
        </repository>
    </repositories>

    <!-- 添加相关依赖 -->
    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>2.11.12</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/mysql/mysql-connector-java -->
        <!-- https://mvnrepository.com/artifact/mysql/mysql-connector-java -->
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.48</version>
        </dependency>



        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.10</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>2.4.4</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.4.4</version>
            <!-- 排除Spark依赖中关于Hadoop和Scala的依赖，以便于添加自已的版本 -->
            <exclusions>
                <exclusion>
                    <groupId>org.apache.hadoop</groupId>
                    <artifactId>hadoop-client</artifactId>
                </exclusion>

                <exclusion>
                    <groupId>org.scala-lang</groupId>
                    <artifactId>scala-library</artifactId>
                </exclusion>
            </exclusions>
        </dependency>

        <!-- 添加自己的Hadoop版本 -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.9.0</version>
        </dependency>


        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.9.0</version>
        </dependency>
    </dependencies>

    <!-- 编译Scala代码的插件-->
    <build>
        <plugins>
            <plugin>
                <groupId>org.scala-tools</groupId>
                <artifactId>maven-scala-plugin</artifactId>
                <version>2.15.2</version>
                <executions>
                    <execution>
                        <id>scala-compile-first</id>
                        <goals>
                            <goal>compile</goal>
                        </goals>
                        <configuration>
                            <includes>
                                <include>**/*.scala</include>
                            </includes>
                        </configuration>
                    </execution>
                    <execution>
                        <id>scala-test-compile</id>
                        <goals>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>

import org.apache.spark.sql.SparkSession

/**
   * @Author: 唐松怀
   * @Date: 2020/3/18 21:49
   */
  object nihao {
    def main(args: Array[String]): Unit = {
      val spark = SparkSession
        .builder
        .master("spark://192.168.0.120:7077")
        .appName("sparkSQL")
        .getOrCreate()
      Class.forName("com.mysql.jdbc.Driver").newInstance()
      val options = Map("url" -> "jdbc:mysql://min01:3306/test",
        "driver" -> "com.mysql.jdbc.Driver",
        "user" -> "root",
        "password" -> "123456",
        "dbtable" -> "score")
      val df6 = spark.read.format("jdbc").options(options).load()
      df6.show
    }
}

提交

./bin/spark-submit --jars ./jars/mysql-connector-java-5.1.48.jar  --class nihao  --master spark://192.168.0.120:7077 --executor-memory 1G --total-executor-cores 3 chapter-7-1.0-SNAPSHOT.jar  > temp999.txt

存数据到mysql

import org.apache.spark.sql.SparkSession

/**
   * @Author: 唐松怀
   * @Date: 2020/3/18 21:49
   */
  object nihao {
    def main(args: Array[String]): Unit = {
      val spark = SparkSession
        .builder
        .master("spark://192.168.0.120:7077")
        .appName("sparkSQL")
        .getOrCreate()
      val df7_1 = spark.createDataFrame(List(
        ("Alice", "Female", "20"),
        ("Tom", "Male", "25"),
        ("Boris", "Male", "18"))).toDF("name", "sex", "age")

      val properties = new java.util.Properties()
      properties.setProperty("user", "root")
      properties.setProperty("password", "123456")

      import org.apache.spark.sql.SaveMode
      df7_1.write.mode(SaveMode.Append).jdbc("jdbc:mysql://min01:3306/test", "t_user", properties)

    }
}

 mysql  - df -mysql  操作

import org.apache.spark.sql.SparkSession

/**
   * @Author: 唐松怀
   * @Date: 2020/3/18 21:49
   */
  object nihao {
    def main(args: Array[String]): Unit = {
      val spark = SparkSession
        .builder
        .master("spark://192.168.0.120:7077")
        .appName("sparkSQL")
        .getOrCreate()
//      val df7_1 = spark.createDataFrame(List(
//        ("Alice", "Female", "20"),
//        ("Tom", "Male", "25"),
//        ("Boris", "Male", "18"))).toDF("name", "sex", "age")

      import  spark.implicits._
      val options = Map("url" -> "jdbc:mysql://min01:3306/test",
        "driver" -> "com.mysql.jdbc.Driver",
        "user" -> "root",
        "password" -> "123456",
        "dbtable" -> "score")
      val df6 = spark.read.format("jdbc").options(options).load().toDF("name", "sex", "age")
      df6.count()

      val df666= df6.filter($"name"  >1).filter($"age" <100)






      val properties = new java.util.Properties()
      properties.setProperty("user", "root")
      properties.setProperty("password", "123456")

      import org.apache.spark.sql.SaveMode
      df666.write.mode(SaveMode.Append).jdbc("jdbc:mysql://min01:3306/test", "t_user02", properties)

    }
}