消费kafka的消息,并将其SparkStreaming结果保存到mysql

将数据保存到mysql,需要用到jdbc。为了提高保存速度,我写了一个连接池

1.保存到mysql的代码

package test05

import org.apache.log4j.{Level, Logger}
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.types._
import org.apache.spark.sql._
import org.apache.spark.streaming.dstream.DStream
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.kafka.KafkaUtils

object SaveDataToMysql {
def main(args: Array[String]): Unit = {

// 屏蔽不必要的日志 ,在终端上显示需要的日志
Logger.getLogger("org.apache.spark").setLevel(Level.OFF)
Logger.getLogger("org.eclipse.jetty.server").setLevel(Level.OFF)
Logger.getLogger("org.apache.kafka.clients.consumer").setLevel(Level.OFF)

//初始化sparkStreaming
val conf = new SparkConf().setAppName("SaveDataToMysql").setMaster("local[*]")
val sc = new SparkContext(conf)
val ssc = new StreamingContext(sc, Seconds(10))
    //连接s3需要的key和密码
ssc.sparkContext.hadoopConfiguration.set("fs.s3a.access.key","aws的key")
ssc.sparkContext.hadoopConfiguration.set("fs.s3a.secret.key","aws的密码")
ssc.sparkContext.hadoopConfiguration.set("fs.s3a.endpoint", "s3.cn-north-1.amazonaws.com.cn")


//设置连接Kafka的配置信息
val zkQuorum = "192.168.1.112:2181" //zookeeper集群的IP:port,IP:port,IP:port
val group = "testgroup" //在consumer.properties配置group.id
val topics = "huiliyang" //选择要连接的producer,它是以topic来区分每个producer的。例如:我这里的创建的topic是huiliyang
val numThreads = 2 //线程
val topicpMap = topics.split("\n").map((_,numThreads.toInt)).toMap //这个是有可能有好几个topic同时提供数据,那么我们要把它用空格分割开,然后映射成(topic,2),再转换成map集合
    ssc.checkpoint("checkpoint"
    val lines: DStream[String] = KafkaUtils.createStream(ssc,zkQuorum,group,topicpMap).map(_._2)    //创建流

lines.print()

//保存到mysql
lines.map(x=>x.split(",")).foreachRDD(line =>{
line.foreachPartition(rdd =>{
val conn = ConnectPoolUtil.getConnection //
ConnectPoolUtil是我创建的一个数据库连接池,getConnection是它的一个方法

conn.setAutoCommit(false); //设为手动提交
        val  stmt = conn.createStatement()
rdd.foreach(word=>{
stmt.addBatch("insert into test_log2(time, ip, user_id, user_type, source, scene) values('" + word(0)+"','"+word(1)+"','"+word(2)+"','"+word(3)+"','"+word(4)+"','"+word(5) + "')")
})
stmt.executeBatch()
conn.commit()
conn.close()
})
})
ssc.start()
ssc.awaitTermination()
  }

}


数据库连接池代码:
package test05

import java.sql.{Connection, PreparedStatement, ResultSet}
import org.apache.commons.dbcp.BasicDataSource


object ConnectPoolUtil {

private var bs:BasicDataSource = null

/**
* 创建数据源
* @return
*/
def getDataSource():BasicDataSource={
if(bs==null){
bs = new BasicDataSource()
bs.setDriverClassName("com.mysql.jdbc.Driver")
bs.setUrl("jdbc:mysql://localhost:3306/school")
bs.setUsername("root")
bs.setPassword("123456")
bs.setMaxActive(200) //设置最大并发数
bs.setInitialSize(30) //数据库初始化时,创建的连接个数
bs.setMinIdle(50) //最小空闲连接数
bs.setMaxIdle(200) //数据库最大连接数
bs.setMaxWait(1000)
bs.setMinEvictableIdleTimeMillis(60*1000) //空闲连接60秒中后释放
bs.setTimeBetweenEvictionRunsMillis(5*60*1000) //5分钟检测一次是否有死掉的线程
bs.setTestOnBorrow(true)
}
bs
}

/**
* 释放数据源
*/
def shutDownDataSource(){
if(bs!=null){
bs.close()
}
}

/**
* 获取数据库连接
* @return
*/
def getConnection():Connection={
var con:Connection = null
try {
if(bs!=null){
con = bs.getConnection()
}else{
con = getDataSource().getConnection()
}
} catch{
case e:Exception => println(e.getMessage)
}
con
}

/**
* 关闭连接
*/
def closeCon(rs:ResultSet ,ps:PreparedStatement,con:Connection){
if(rs!=null){
try {
rs.close()
} catch{
case e:Exception => println(e.getMessage)
}
}
if(ps!=null){
try {
ps.close()
} catch{
case e:Exception => println(e.getMessage)
}
}
if(con!=null){
try {
con.close()
} catch{
case e:Exception => println(e.getMessage)
}
}
}
}

pom文件

2.11.8
2.2.0
2.7.2
compile




org.apache.spark
spark-core_2.11
${spark.version}



org.apache.spark
spark-streaming_2.11
${spark.version}


org.apache.spark
spark-streaming-kafka-0-8_2.11
2.2.0


org.apache.spark
spark-sql_2.11
${spark.version}



mysql
mysql-connector-java
5.1.39

 
   
 


 

转载于:https://www.cnblogs.com/yhl-yh/p/7741525.html

你可能感兴趣的:(消费kafka的消息,并将其SparkStreaming结果保存到mysql)