Spark 监测目录的日志获取ip的指定时间的的请求数防止攻击报警

最新推荐文章于 2023-07-16 03:11:28 发布

思cong

最新推荐文章于 2023-07-16 03:11:28 发布

阅读量355

点赞数

分类专栏： spark 文章标签： spark 数据

本文链接：https://blog.csdn.net/qq_23159975/article/details/52605724

版权

spark 专栏收录该内容

10 篇文章 0 订阅

订阅专栏

首先模拟数据的产生

import java.io.PrintWriter
import java.text.SimpleDateFormat
import java.util.Date

import scala.collection.mutable.ArrayBuffer
import scala.io.Source
import scala.util.Random

/**
  * Created by sicong on 16/9/19.
  */
object my {
  def main(args: Array[String]): Unit = {
    val sourceFileLines = Source.fromFile("/Users/sicong/sparkStream/data.txt")
    val dataLines =sourceFileLines.getLines().toList
    val datalenth = dataLines.length
    while (true) {
      val randomMu = (new util.Random).nextInt(datalenth)
      val randomList = randomNew(randomMu, datalenth)
      var syt = "";
      for (i <- 0 to (randomList.length - 1)) {
        syt += (dataLines(randomList(i)) + "\n")
      }
      val dataRaw = new PrintWriter("/Users/sicong/sparkStream/data/"+getNowDate()+"txt")
      dataRaw.print(syt)
      dataRaw.close()
      Thread.sleep(1000)
    }
  }
  //生成时间字符串
  def getNowDate():String={
    var now:Date = new Date()
    var  dateFormat:SimpleDateFormat = new SimpleDateFormat("yyyyMMddHHmmss")
    var hehe = dateFormat.format( now )
    hehe
  }
  //生成随机的长度的List聚合
  def randomNew(n:Int,x:Int)={
    var resultList:List[Int]=Nil
    while(resultList.length<n){
      val randomNum=(new Random).nextInt(x)
      if(!resultList.exists(s=>s==randomNum)){
        resultList=resultList:::List(randomNum)
      }
    }
    resultList
  }
}

sparkstreaming 监测目前的文件的变化来进行监测进来的ip量

import org.apache.spark.SparkConf
import org.apache.spark.streaming.{Seconds, StreamingContext}

import scala.util.parsing.json.JSON

/*
  * Created by sicong on 16/9/19.
  */
object sparkHDFLdata {
  def main(args: Array[String]): Unit = {
    val sparkconf = new SparkConf().setAppName("hello").setMaster("local[4]")
    val scc = new StreamingContext(sparkconf,Seconds(10))//这里是没十秒的数据监测一次  十秒内如果有达到ip请求为n的你可以将其置为攻击ip
    val data =scc.textFileStream("file:Users/sicong/sparkStream/data/")
    val lines = data.flatMap(_.split("\n"))//以每行分隔
    val dataOfRaw = lines.map(x=>x.split(" ")).map(x=>(x(0),1))//以每个空格切分成数组
    val dataOfReduce =dataOfRaw.reduceByKey(_+_).map(x=>(x._2,x._1))//将reduce完的数据进行位置的置换 方便排序
    val dataOfSort =dataOfReduce.transform(x=>x.sortByKey(false)) //将数据进行排序  按照key降序
    dataOfSort.saveAsTextFiles("file:Users/sicong/sparkStream/out")  //将最终数据保存到文件夹
    scc.start()
    scc.awaitTermination()
  }
}