spark如何连接mysql数据库

来源：恒创科技编辑：恒创科技编辑部

2024-05-07 14:00:52

在Spark中连接MySQL数据库有两种方式：

使用JDBC连接：

import org.apache.spark.sql.SparkSession

val spark = SparkSession.builder()
  .appName("MySQLExample")
  .getOrCreate()

val url = "jdbc:mysql://hostname:port/databaseName"
val table = "tableName"
val properties = new Properties()
properties.put("user", "username")
properties.put("password", "password")

val df = spark.read.jdbc(url, table, properties)
df.show()

使用MySQL Connector for Apache Spark：

首先需要在spark-submit命令中添加MySQL Connector的jar包路径：

spark-submit --jars /path/to/mysql-connector-java.jar --class your_class your_jar.jar

然后在代码中使用MySQL Connector连接MySQL数据库：

import org.apache.spark.sql.SparkSession

val spark = SparkSession.builder()
  .appName("MySQLExample")
  .getOrCreate()

val url = "jdbc:mysql://hostname:port/databaseName"
val table = "tableName"
val properties = new Properties()
properties.put("user", "username")
properties.put("password", "password")

val df = spark.read.format("jdbc")
  .option("url", url)
  .option("dbtable", table)
  .option("user", properties.getProperty("user"))
  .option("password", properties.getProperty("password"))
  .load()

df.show()