【十五】SparkSQL访问日志分析：数据清洗、数据分析（分组、排序、窗口函数）、入库（MySQL）、性能优化

概述：

1.第一次数据清洗：从原始日志中抽取出需要的列的数据,按照需要的格式。

2.第二步数据清洗：解析第一步清洗后的数据， 处理时间，提出URL中的产品编号、得到产品类型，  由IP得到城市信息（用到开源社区的解析代码，该部分具体介绍：ipdatabase解析出IP地址所属城市） ，按照天分区进行存储 （用parquet格式）。

3.统计分析(分组、排序、窗口函数)。

4.结果写入MySQL。

5.性能优化：代码中代码优化部分有注释，其他常用优化会另写一篇，一会儿附上链接。

项目目录

pom.xml

<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/maven-v4_0_0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>com.sid.com</groupId>
  <artifactId>sparksqltrain</artifactId>
  <version>1.0-SNAPSHOT</version>
  <inceptionYear>2008</inceptionYear>
  <properties>
    <scala.version>2.11.8</scala.version>
    <spark.version>2.2.0</spark.version>
  </properties>

  <repositories>
    <repository>
      <id>scala-tools.org</id>
      <name>Scala-Tools Maven2 Repository</name>
      <url>http://scala-tools.org/repo-releases</url>
    </repository>
  </repositories>

  <pluginRepositories>
    <pluginRepository>
      <id>scala-tools.org</id>
      <name>Scala-Tools Maven2 Repository</name>
      <url>http://scala-tools.org/repo-releases</url>
    </pluginRepository>
  </pluginRepositories>

  <dependencies>
    <!-- scala依赖 因为scala和spark的包在服务器环境上有，打包的时候不用打上去，所以加scope = provided -->
    <dependency>
      <groupId>org.scala-lang</groupId>
      <artifactId>scala-library</artifactId>
      <version>${scala.version}</version>
     <!-- <scope>provided</scope> -->
    </dependency>
    <!-- spark依赖 -->
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-sql_2.11</artifactId>
      <version>${spark.version}</version>
      <!-- <scope>provided</scope> -->
    </dependency>
    <!-- hivecontext要用这个依赖-->
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-hive_2.11</artifactId>
      <version>${spark.version}</version>
      <!-- <scope>provided</scope> -->
    </dependency>

    <dependency>
      <groupId>org.spark-project.hive</groupId>
      <artifactId>hive-jdbc</artifactId>
      <version>1.2.1.spark2</version>
      <scope>provided</scope>
    </dependency>

    <!-- https://mvnrepository.com/artifact/mysql/mysql-connector-java -->
    <dependency>
      <groupId>mysql</groupId>
      <artifactId>mysql-connector-java</artifactId>
      <version>5.1.38</version>
    </dependency>

    <dependency>
      <groupId>com.ggstar</groupId>
      <artifactId>ipdatabase</artifactId>
      <version>1.0</version>
    </dependency>

    <dependency>
      <groupId>org.apache.poi</groupId>
      <artifactId>poi-ooxml</artifactId>
      <version>3.14</version>
    </dependency>

    <dependency>
      <groupId>org.apache.poi</groupId>
      <artifactId>poi</artifactId>
      <version>3.14</version>
    </dependency>

  </dependencies>

  <build>
    <sourceDirectory>src/main/scala</sourceDirectory>
    <testSourceDirectory>src/test/scala</testSourceDirectory>
    <plugins>
      <plugin>
        <groupId>org.scala-tools</groupId>
        <artifactId>maven-scala-plugin</artifactId>
        <executions>
          <execution>
            <goals>
              <goal>compile</goal>
              <goal>testCompile</goal>
            </goals>
          </execution>
        </executions>
        <configuration>
          <scalaVersion>${scala.version}</scalaVersion>
          <args>
            <arg>-target:jvm-1.5</arg>
          </args>
        </configuration>
      </plugin>
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-eclipse-plugin</artifactId>
        <configuration>
          <downloadSources>true</downloadSources>
          <buildcommands>
            <buildcommand>ch.epfl.lamp.sdt.core.scalabuilder</buildcommand>
          </buildcommands>
          <additionalProjectnatures>
            <projectnature>ch.epfl.lamp.sdt.core.scalanature</projectnature>
          </additionalProjectnatures>
          <classpathContainers>
            <classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
            <classpathContainer>ch.epfl.lamp.sdt.launching.SCALA_CONTAINER</classpathContainer>
          </classpathContainers>
        </configuration>
      </plugin>

      <!-- 如果要把依赖的JAR包一起打进去，需要加这个plugin
       并且打包就不要用 mvn clean package 了
       要用 mvn assembly:assembly
      <plugin>
        <artifactId>maven-assembly-plugin</artifactId>
        <configuration>
          <archive>
            <manifest>
              <mainClass></mainClass>
            </manifest>
          </archive>
        </configuration>
      </plugin>-->
    </plugins>
  </build>
  <reporting>
    <plugins>
      <plugin>
        <groupId>org.scala-tools</groupId>
        <artifactId>maven-scala-plugin</artifactId>
        <configuration>
          <scalaVersion>${scala.version}</scalaVersion>
        </configuration>
      </plugin>
    </plugins>
  </reporting>
</project>

MySQL创建数据库

create table day_video_access_topn_stat(
day varchar (8) not null,
cms_id bigint(10) not null,
times bigint(10) not null,
primary key (day,cms_id)
);

create table day_video_city_access_topn_stat(
day varchar (8) not null,
cms_id bigint(10) not null,
city varchar (20) not null,
times bigint(10) not null,
times_rank int not null,
primary key (day,city,cms_id)
);

create table day_video_traffics_access_topn_stat(
day varchar (8) not null,
cms_id bigint(10) not null,
traffics bigint (10) not null,
primary key (day,cms_id)
);

DateUtils.scala

package com.sid.com.project

import java.text.SimpleDateFormat
import java.util.{Date, Locale}

import org.apache.commons.lang3.time.FastDateFormat

/**
  * 日期时间转化工具
  * */
object DateUtils {
  // 10/Nov/2016:00:01:02 +0800
  //输入日期格式
  //SimpleDateFormat是线程不安全的，解析的时候有些时间会解析错
  val YYYYMMDDHHMM_TIME_FORMAT =  FastDateFormat.getInstance("dd/MMM/yyyy:HH:mm:ss Z",Locale.ENGLISH)

  //目标日期格式
  val TARGET_FOMAT =  FastDateFormat.getInstance("yyyy-MM-dd HH:mm:ss")

  def parse(time:String)={
    TARGET_FOMAT.format(new Date(getTime(time)))
  }

  /**
    * 获取输入日志Long类型的时间
    * [10/Nov/2016:00:01:02 +0800]
    * */
  def getTime(time:String) ={
    try {
      YYYYMMDDHHMM_TIME_FORMAT.parse(time.substring(time.indexOf("[") + 1, time.lastIndexOf("]"))).getTime()
    }catch{
      case e :Exception =>{
        0L
      }
    }
  }

  def main(args: Array[String]): Unit = {
    println(parse("[10/Nov/2016:00:01:02 +0800]"))
  }
}

IpUtils.scala

package com.sid.com.project

import com.ggstar.util.ip.IpHelper

object IpUtils {
  def getCity(ip:String) ={
    IpHelper.findRegionByIp(ip)
  }

  def main(args: Array[String]): Unit = {
    println(getCity("117.35.88.11"))
  }
}

LogConvertUtil.scala

package com.sid.com.project

import org.apache.spark.sql.Row
import org.apache.spark.sql.types.{LongType, StringType, StructField, StructType}

/**
  * 访问日志转换工具类
  *
  * 输入：访问时间、访问URL、耗费的流量、访问IP地址信息
  * 2016-11-10 00:01:02	http://www.主站地址.com/code/1852	2345	117.35.88.11
  *
  * 输出：URL、cmsType(video/article)、cmsId(编号)、流量、ip、城市信息、访问时间、按天分区存储
  * */
object LogConvertUtil {

    //输出字段的schema
    val struct = StructType(
      Array(
        StructField("url", StringType),
        StructField("cmsType", StringType),
        StructField("cmsId", LongType),
        StructField("traffic", LongType),
        StructField("ip", StringType),
        StructField("city", StringType),
        StructField("time", StringType),
        StructField("day", StringType)
      )
    )

    //根据输入的每行信息转换成输出的样式
    def parseLog(log: String)={
      try{
      val splits = log.split("\t")
      val url = splits(1)
      val traffic = splits(2).toLong
      val ip = splits(3)

      val domain = "http://www.imooc.com/"
      val cms = url.substring(url.indexOf(domain) + domain.length)
      val cmsTypeId = cms.split("/")

      var cmsType = ""
      var cmsId = 0L

      if (cmsTypeId.length > 1) {
        cmsType = cmsTypeId(0)
        cmsId = cmsTypeId(1).toLong

      }

      val city = IpUtils.getCity(ip)
      val time = splits(0)
      val day = time.substring(0, 10).replaceAll("-", "")

      //row中的字段要和struct中的字段对应上
      Row(url, cmsType, cmsId, traffic, ip, city, time, day)
    }catch{
        case e : Exception =>Row(0)
      }
  }
}

MySQLUtils.scala

package com.sid.com.project


import java.sql.{Connection, DriverManager, PreparedStatement}


/**
  * MySQL操作工具类
  * */
object MySQLUtils {

  //获取数据库连接
    def getConnection()={
      DriverManager.getConnection("jdbc:mysql://localhost:3306/sid?user=root&password=密码")
    }

  //释放数据库连接的资源
  def release(connection:Connection,pstmt:PreparedStatement)={
    try{
      if(pstmt!=null){
        pstmt.close()
      }
    }catch {
      case e:Exception => e.printStackTrace()
    }finally {
        if(connection!=null){
          connection.close()
        }
    }
  }

  def main(args: Array[String]): Unit = {
    println(getConnection())
  }
}

CleanDataApp.scala

package com.sid.com.project

import org.apache.spark.sql.{SaveMode, SparkSession}
import com.sid.com.project.LogConvertUtil


object CleanDataApp {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession.builder().master("local[3]").appName("CleanDataApp").getOrCreate()

    /**
      * 第一步数据清洗，从原始日志中抽取出需要的列的数据,按照需要的格式
      * */
    //dataCleaning(spark)

   /**
     * 第二步数据清洗，解析第一步清洗后的数据，
     *    处理时间，提出URL中的产品编号、得到产品类型，
     *    由IP得到城市信息（用到开源社区的解析代码）
     *    按照天分区进行存储
     */
    dataCleaning2(spark)


    spark.stop()
  }

  //输入数据  .log文件
  //183.162.52.7 - - [10/Nov/2016:00:01:02 +0800] "POST /api3/getadv HTTP/1.1" 200 813 "www.主站地址.com" "-" cid=0&timestamp=1478707261865&uid=2871142&marking=androidbanner&secrect=a6e8e14701ffe9f6063934780d9e2e6d&token=f51e97d1cb1a9caac669ea8acc162b96 "mukewang/5.0.0 (Android 5.1.1; Xiaomi Redmi 3 Build/LMY47V),Network 2G/3G" "-" 10.100.134.244:80 200 0.027 0.027
  //输出数据 没有schema
  //2016-11-10 00:01:02	http://www.主站地址.com/code/1852	2345	117.35.88.11
  def dataCleaning(spark:SparkSession): Unit ={
    val acc = spark.sparkContext.textFile("file:///F:\\mc\\SparkSQL\\data\\access1000.log")
    //acc.take(10).foreach(println)
    //line:183.162.52.7 - - [10/Nov/2016:00:01:02 +0800] "POST /api3/getadv HTTP/1.1" 200 813 "www.主站地址.com" "-" cid=0&timestamp=1478707261865&uid=2871142&marking=androidbanner&secrect=a6e8e14701ffe9f6063934780d9e2e6d&token=f51e97d1cb1a9caac669ea8acc162b96 "mukewang/5.0.0 (Android 5.1.1; Xiaomi Redmi 3 Build/LMY47V),Network 2G/3G" "-" 10.100.134.244:80 200 0.027 0.027
    acc.map(line => {
      val splits = line.split(" ")
      val ip = splits(0)
      val time = splits(3)+" "+splits(4)//第四个字段和第五个字段拼接起来就是完成的访问时间。
      val url = splits(11).replaceAll("\"","")
      val traffic = splits(9)//访问流量

      // (ip,DateUtils.parse(time),url,traffic)

      DateUtils.parse(time)+"\t"+url+"\t"+traffic+"\t"+ip
    }).saveAsTextFile("file:///F:\\mc\\SparkSQL\\data\\access1000step1")
  }

  //输入数据
  //2016-11-10 00:01:02	http://www.主站地址.com/code/1852	2345	117.35.88.11
  //输出数据 带schema信息 parquet格式存储
  //http://www.主站地址.com/code/1852 code 1852 2345 117.35.88.11 陕西省 2016-11-10 00:01:02 20161110
  def dataCleaning2(spark:SparkSession): Unit ={
    val logRDD = spark.sparkContext.textFile("file:///F:\\mc\\SparkSQL\\data\\access.log")
    //val logRDD = spark.sparkContext.textFile("file:///F:\\mc\\SparkSQL\\data\\access1000step1.log\\part-00000")
    //logRDD.take(10).foreach(println)
    val logDF = spark.createDataFrame(logRDD.map(x => LogConvertUtil.parseLog(x)),LogConvertUtil.struct)

    //logDF.printSchema()
    //logDF.show(false)

    /**partitionBy("day")   数据写的时候要按照天进行分区
    coalesce(1)  生成的part-00000文件只有一个且较大，不然3个线程会生成3个part-0000*文件 可以用此参数调优
    mode(SaveMode.Overwrite) 指定路径下如果有文件，覆盖*/
    logDF.coalesce(1).write.format("parquet")
      .mode(SaveMode.Overwrite)
      .partitionBy("day")
      .save("file:///F:\\mc\\SparkSQL\\data\\afterclean")//存储清洗后的数据
  }
}

StatApp.scala

package com.sid.com.project

import com.sid.com.project.dao.StatDao
import com.sid.com.project.domain.{DayVideoAccessStat, DayVideoCityAccessStat, DayVideoTrafficsTopN}
import org.apache.spark.sql.expressions.Window
import org.apache.spark.sql.{DataFrame, SparkSession}
import org.apache.spark.sql.functions._

import scala.collection.mutable.ListBuffer
/**
  * 统计分析
  * */
object StatApp {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession.builder()
      .master("local[3]")
      /**参数优化
        * 关闭分区字段的数据类型自动推导，
        * 不然day分区字段我们要string类型，会被自动推导成integer类型
        * 而且没有必要浪费这个资源*/
      .config("spark.sql.sources.partitionColumnTypeInference.enabled",false)
      .appName("statApp").getOrCreate()

    val logDF = spark.read.format("parquet")
      .load("file:///F:\\mc\\SparkSQL\\data\\afterclean")
    val day = "20170511"


    /**
      * 代码优化：复用已有数据
      * 既然每次统计都是统计的当天的视频，
      * 先把该数据拿出来，然后直接传到每个具体的统计方法中
      * 不要在每个具体的统计方法中都执行一次同样的过滤
      *
      * 用$列名得到列值，需要隐式转换 import spark.implicits._
      * */
    import spark.implicits._
    val dayVideoDF = logDF.filter($"day" ===day&&$"cmsType"==="video")
    /**
      * 将这个在后文中会复用多次的dataframe缓存到内存中
      * 这样后文在复用的时候会快很多
      *
      * default storage level (`MEMORY_AND_DISK`).
      * */
    dayVideoDF.cache()

    //logDF.printSchema()
    //logDF.show()

    StatDao.deletaDataByDay(day)

    //统计每天最受欢迎(访问次数)的TopN视频产品
    videoAccessTopNStatDFAPI(spark,dayVideoDF)

    //按照地势统计每天最受欢迎(访问次数)TopN视频产品 每个地市只要最后欢迎的前三个
    cityAccessTopNStat(spark,dayVideoDF)

    //统计每天最受欢迎(流量)TopN视频产品
    videoTrafficsTopNStat(spark,dayVideoDF)

    //清除缓存
    dayVideoDF.unpersist(true)
    spark.stop()
  }

  /**
    * 统计每天最受欢迎(访问次数)的TopN视频产品
    *
    * 取出20170511那天访问的视频类产品。
    * 统计每种视频类产品的访问次数，并按访问次数降序排列
    * 用DataFrame API 来写逻辑
    * */
  def videoAccessTopNStatDFAPI(spark:SparkSession,logDF:DataFrame): Unit ={
    //agg(count())需要导入sparksql的函数部分 import org.apache.spark.sql.functions._
    import spark.implicits._
    val videoLogTopNDF = logDF
      .groupBy("day","cmsId")
      .agg(count("cmsId").as("times"))
      .orderBy($"times".desc)
    //videoLogTopNDF.show(false)
    /**
      * 将统计结果写入MySQL中
      * 代码优化：
      * 在进行数据库操作的时候，不要每个record都去操作一次数据库
      * 通常写法是每个partition操作一次数据库
      **/
    try {
      videoLogTopNDF.foreachPartition(partitionOfRecords => {
        val list = new ListBuffer[DayVideoAccessStat]
        partitionOfRecords.foreach(info => {
          val day = info.getAs[String]("day")
          val cmsId = info.getAs[Long]("cmsId")
          val times = info.getAs[Long]("times")

          list.append(DayVideoAccessStat(day, cmsId, times))
        })
        StatDao.insertDayVideoTopN(list)
      })
    }catch{
      case e:Exception =>e.printStackTrace()
    }
  }

  /**
    * 统计每天最受欢迎(访问次数)的TopN视频产品
    *
    * 取出20170511那天访问的视频类产品。
    * 统计每种视频类产品的访问次数，并按访问次数降序排列
    * 用SQL API 来写逻辑
    * */
  def videoAccessTopNStatSQLAPI(spark:SparkSession,logDF:DataFrame): Unit = {
    logDF.createOrReplaceTempView("tt_log")
    val videoTopNDF = spark.sql("select day,cmsId,count(1) as times from tt_log group by day,cmsId order by times desc")
    //videoTopNDF.show(false)

    /**
      * 将统计结果写入MySQL中
      **/
    try {
    videoTopNDF.foreachPartition(partitionOfRecords => {
      val list = new ListBuffer[DayVideoAccessStat]
      partitionOfRecords.foreach(info => {
        val day = info.getAs[String]("day")
        val cmsId = info.getAs[Long]("cmsId")
        val times = info.getAs[Long]("times")

        list.append(DayVideoAccessStat(day, cmsId, times))
      })
      StatDao.insertDayVideoTopN(list)
    })
   }catch{
      case e:Exception =>e.printStackTrace()
    }
  }

  /**
    * 按照地势统计每天最受欢迎(访问次数)TopN视频产品 每个地市只要最后欢迎的前三个
    * */
  def cityAccessTopNStat(spark:SparkSession,logDF:DataFrame): Unit ={
    //用$列名得到列值，需要隐式转换 import spark.implicits._
    //agg(count())需要导入sparksql的函数部分 import org.apache.spark.sql.functions._
    val videoCityLogTopNDF = logDF.groupBy("day","city","cmsId")
      .agg(count("cmsId").as("times"))
    //这里的结果是
    //日期     地域   产品ID  访问次数
    //20170511 北京市 14390 11175
    //20170511 北京市 4500 11014
    //20170511 浙江省 14390 11110
    //20170511 浙江省 14322 11151
    //然后最后需要的结果是同一天、同一个地域下，按产品访问次数降序排序

    //videoLogTopNDF.show(false)

    //window函数在Spark SQL中的使用 分组后组内排序
    val top3DF = videoCityLogTopNDF.select(
      videoCityLogTopNDF("day"),
      videoCityLogTopNDF("city"),
      videoCityLogTopNDF("cmsId"),
      videoCityLogTopNDF("times"),
      row_number().over(Window.partitionBy(videoCityLogTopNDF("city")).
        orderBy(videoCityLogTopNDF("times").desc)
      ).as("times_rank")
    ).filter("times_rank <= 3")//.show(false)//只要每个地势最受欢迎的前3个
    //结果
    //日期     地域   产品ID  访问次数
    //20170511 北京市 14390 11175
    //20170511 北京市 4500 11014
    //20170511 浙江省 14322 11151
    //20170511 浙江省 14390 11110


    //将统计结果写入MySQL中
    try {
      top3DF.foreachPartition(partitionOfRecords => {
        val list = new ListBuffer[DayVideoCityAccessStat]
        partitionOfRecords.foreach(info => {
          val day = info.getAs[String]("day")
          val cmsId = info.getAs[Long]("cmsId")
          val city = info.getAs[String]("city")
          val times = info.getAs[Long]("times")
          val timesRank = info.getAs[Int]("times_rank")

          list.append(DayVideoCityAccessStat(day,cmsId,city,times,timesRank))
        })
        StatDao.insertDayCityVideoTopN(list)
      })
    }catch{
      case e:Exception =>e.printStackTrace()
    }
  }



  /**
    * 统计每天最受欢迎(流量)TopN视频产品
    * */
  def videoTrafficsTopNStat(spark:SparkSession,logDF:DataFrame): Unit ={
    //用$列名得到列值，需要隐式转换 import spark.implicits._
    //agg(count())需要导入sparksql的函数部分 import org.apache.spark.sql.functions._
    import spark.implicits._
    val videoLogTopNDF = logDF.groupBy("day","cmsId")
      .agg(sum("traffic").as("traffics"))
      .orderBy($"traffics".desc)
    //videoLogTopNDF.show(false)
    /**
      * 将统计结果写入MySQL中
      **/
    try {
      videoLogTopNDF.foreachPartition(partitionOfRecords => {
        val list = new ListBuffer[DayVideoTrafficsTopN]
        partitionOfRecords.foreach(info => {
          val day = info.getAs[String]("day")
          val cmsId = info.getAs[Long]("cmsId")
          val traffics = info.getAs[Long]("traffics")

          list.append(DayVideoTrafficsTopN(day, cmsId, traffics))
        })
        StatDao.insertDayTrafficsVideoTopN(list)
      })
    }catch{
      case e:Exception =>e.printStackTrace()
    }
  }
}

StatDao.scala

package com.sid.com.project.dao



import java.sql.{Connection, PreparedStatement}

import com.sid.com.project.MySQLUtils
import com.sid.com.project.domain.{DayVideoAccessStat, DayVideoCityAccessStat, DayVideoTrafficsTopN}

import scala.collection.mutable.ListBuffer


/**
  * 统计各个维度的DAO操作
  * */
object StatDao {

  /**
    * 批量保存DayVideoAccessStat到MySQL
    * */
  def insertDayVideoTopN(list:ListBuffer[DayVideoAccessStat]): Unit ={
    var connection:Connection = null
    var pstmt : PreparedStatement = null
    try{
      connection = MySQLUtils.getConnection()

      connection.setAutoCommit(false)//关闭自动提交
      val sql = "insert into day_video_access_topn_stat(day,cms_id,times) values(?,?,?)"
      pstmt = connection.prepareStatement(sql)

      for(ele <- list){
        pstmt.setString(1,ele.day)
        pstmt.setLong(2,ele.cmsId)
        pstmt.setLong(3,ele.times)
        //加入到批次中，后续再执行批量处理 这样性能会好很多
        pstmt.addBatch()
      }
      //执行批量处理
      pstmt.executeBatch()

      connection.commit() //手工提交

    }catch {
      case e :Exception =>e.printStackTrace()
    }finally {
      MySQLUtils.release(connection,pstmt)
    }
  }

  /**
    * 批量保存DayVideoCityAccessStat到MySQL
    * */
  def insertDayCityVideoTopN(list:ListBuffer[DayVideoCityAccessStat]): Unit ={
    var connection:Connection = null
    var pstmt : PreparedStatement = null
    try{
      connection = MySQLUtils.getConnection()

      connection.setAutoCommit(false)//关闭自动提交
      val sql = "insert into day_video_city_access_topn_stat(day,cms_id,city,times,times_rank) values(?,?,?,?,?)"
      pstmt = connection.prepareStatement(sql)

      for(ele <- list){
        pstmt.setString(1,ele.day)
        pstmt.setLong(2,ele.cmsId)
        pstmt.setString(3,ele.city)
        pstmt.setLong(4,ele.times)
        pstmt.setInt(5,ele.timesRank)
        //加入到批次中，后续再执行批量处理 这样性能会好很多
        pstmt.addBatch()
      }
      //执行批量处理
      pstmt.executeBatch()

      connection.commit() //手工提交

    }catch {
      case e :Exception =>e.printStackTrace()
    }finally {
      MySQLUtils.release(connection,pstmt)
    }
  }


  /**
    * 批量保存DayVideoTrafficsTopN到MySQL
    * */
  def insertDayTrafficsVideoTopN(list:ListBuffer[DayVideoTrafficsTopN]): Unit ={
    var connection:Connection = null
    var pstmt : PreparedStatement = null
    try{
      connection = MySQLUtils.getConnection()

      connection.setAutoCommit(false)//关闭自动提交
      val sql = "insert into day_video_traffics_access_topn_stat(day,cms_id,traffics) values(?,?,?)"
      pstmt = connection.prepareStatement(sql)

      for(ele <- list){
        pstmt.setString(1,ele.day)
        pstmt.setLong(2,ele.cmsId)
        pstmt.setLong(3,ele.traffics)

        //加入到批次中，后续再执行批量处理 这样性能会好很多
        pstmt.addBatch()
      }
      //执行批量处理
      pstmt.executeBatch()

      connection.commit() //手工提交

    }catch {
      case e :Exception =>e.printStackTrace()
    }finally {
      MySQLUtils.release(connection,pstmt)
    }
  }

  /**
    * 删除指定日期的数据
    * */
  def deletaDataByDay(day:String): Unit ={
    val tables = Array("day_video_access_topn_stat",
    "day_video_city_access_topn_stat",
    "day_video_traffics_access_topn_stat")

    var connection:Connection=null
    var pstmt : PreparedStatement = null
    try{
      connection = MySQLUtils.getConnection()
      for(table <- tables){
        val deleteSql = s"delete from $table where day = ?"
        pstmt = connection.prepareStatement(deleteSql)
        pstmt.setString(1,day)
        pstmt.executeUpdate()
      }
    }catch {
      case e :Exception =>e.printStackTrace()
    }finally {
      MySQLUtils.release(connection,pstmt)
    }
  }
}

DayVideoAccessStat.scala

package com.sid.com.project.domain

/**
  *每天视频课程访问次数实体类
  * */
case class DayVideoAccessStat (day:String,cmsId:Long,times:Long)

DayVideoCityAccessStat.scala

package com.sid.com.project.domain

case class DayVideoCityAccessStat (day:String,cmsId:Long,city:String,times:Long,timesRank:Int)

DayVideoTrafficsTopN.scala

package com.sid.com.project.domain

case class DayVideoTrafficsTopN(day:String, cmsId:Long, traffics:Long)