Spark JDBC操作MySQL方式详细讲解

/*此为代码格式，实际中使用应替换相应字段中的内容*/
val url = "jdbc:mysql://localhost:/database"        
val tableName = "table"
// 设置连接用户&密码
val prop = new java.util.Properties
prop.setProperty("user","username")  //实际使用中替换username为相应的用户名
prop.setProperty("password","pwd")   //实际使用中替换pwd为相应的密码

/*此为代码格式，实际中使用应替换相应字段中的内容*/
def jdbc(
url: String,
table: String,
columnName: String, // 根据该字段分区，需要为整型，比如 id 等
lowerBound: Long, // 分区的下界
upperBound: Long, // 分区的上界
numPartitions: Int,  //分区的个数
connectionProperties: Properties): DataFrame

/*此为代码格式，实际中使用应替换相应字段中的内容*/
val url = "jdbc:mysql://mysqlHost:3306/database"
val tableName = "table"
val columnName = "colName"
val lowerBound = 1,
val upperBound = 10000000,
val numPartitions = 10,
// 设置连接用户&密码
val prop = new java.util.Properties
prop.setProperty("user","username")
prop.setProperty("password","pwd")

/*此为代码格式，实际中使用应替换相应字段中的内容*/
jdbc(
url: String,
table: String,
predicates: Array[String],
connectionProperties: Properties): DataFrame

/*此为代码格式，实际中使用应替换相应字段中的内容*/
val url = "jdbc:mysql://mysqlHost:3306/database"
val tableName = "table"
// 设置连接用户&密码
val prop = new java.util.Properties
prop.setProperty("user","username")
prop.setProperty("password","pwd")
/**
* 将 9 月 16-12 月 15 三个月的数据取出，按时间分为 6 个 partition
* 为了减少事例代码，这里的时间都是写死的
* modified_time 为时间字段
*/
val predicates =
Array(
"2015-09-16" -> "2015-09-30",
"2015-10-01" -> "2015-10-15",
"2015-10-16" -> "2015-10-31",
"2015-11-01" -> "2015-11-14",
"2015-11-15" -> "2015-11-30",
"2015-12-01" -> "2015-12-15"
).map {
case (start, end) =>
s"cast(modified_time as date) >= date '$start' " + s"AND cast(modified_time
as date) <= date '$end'"
}

create database test;    //创建数据库test
use test;        //进入数据库test
create table people( name varchar(12), age int);         //创建表格people并构建结构
insert into people values ("Andy",30),("Justin",19),("Dela",25),("Magi",20),("Pule",21),("Mike",12);        //向people表中插入数据
select * from people;         //输出people表中全部数据

//导入依赖环境
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.sql.{DataFrame, SQLContext}
import java.util.Properties
val url = "jdbc:mysql://localhost/test"       //MySQL地址及数据库
val username = "root"       //用户名
val sqlContext = new SQLContext(sc)       
sc.setLogLevel("WARN")
val uri = url + "?user=" + username + "&useUnicode=true&characterEncoding=UTF-8"           //设置读取路径及用户名
val properties = new Properties()      //创建JDBC连接信息
properties.put("user","root")
properties.put("driver", "com.mysql.jdbc.Driver")
val df_test: DataFrame = spark.sqlContext.read.jdbc(uri, "people", properties)  //读取数据
df_test.select("name","age").collect().foreach(row => {         //输出数据
	println("name " + row(0) + ", age" + row(1))
})
df_test.write.mode("append").jdbc(uri,"people",properties)     //向people表中写入读出的数据，相当于people表中有两份一样的数据