大数据实时计算Spark学习笔记（10）—— Spar SQL(2)

学习笔记（10）—— Spar SQL(2)"/>

大数据实时计算Spark学习笔记（10）—— Spar SQL(2)

1 Spark SQL 的 JDBC 方式

• POM 文件添加依赖

 <dependency><groupId>mysql</groupId><artifactId>mysql-connector-java</artifactId><version>5.1.38</version></dependency>

1.1 查询数据库

import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;public class SQLJDBCJava {public static void main(String[] args) {SparkSession session = SparkSession.builder().appName("JDBC").config("spark.master","local[2]").getOrCreate();String url = "jdbc:mysql://localhost:3306/weblog";String table = "city";Dataset<Row> df= session.read().format("jdbc").option("url", url).option("dbtable",table).option("user", "root").option("password", "root").option("driver","com.mysql.jdbc.Driver").load();df.show();}
}

1.1.1 向数据库写数据

import org.apache.spark.sql.Column;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;import java.util.Properties;public class SQLJDBCJava {public static void main(String[] args) {SparkSession session = SparkSession.builder().appName("JDBC").config("spark.master","local[2]").getOrCreate();String url = "jdbc:mysql://localhost:3306/weblog?useSSL=false";String table = "city";Dataset<Row> df= session.read().format("jdbc").option("url", url).option("dbtable",table).option("user", "root").option("password", "root").option("driver","com.mysql.jdbc.Driver").load();//df.show();//投影查询Dataset<Row> df2 = df.select(new Column("cms_id"),new Column("times"));df2 = df2.where("cms_id like '143%'");Properties prop = new Properties();prop.put("user","root");prop.put("password","root");prop.put("driver","com.mysql.jdbc.Driver");//写入df2.write().jdbc(url,"city2",prop);df2.show();}
}