转：SparkStreaming--小案例2对于爬虫来的数据进行分析

版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/qq_42721694/article/details/85267653
请注意本博客中代码头和尾是固定模式，而lines是需要根据你的数据特点进行切分和整理的，我会附上我的一部分数据供参考，附在文档末尾。

1.统计某一时间段输入数据出现次数（时间不断更新）这不是爬虫数据分析是一个热身

package Test1226

import org.apache.spark.SparkConf
import org.apache.spark.streaming.{Seconds, StreamingContext}
//统计某一时间段数据出现次数（时间不断更新）
object test01 {
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("nwc").setMaster("local[2]")
val ssc = new StreamingContext(conf, Seconds(5))
ssc.sparkContext.setLogLevel("ERROR")
ssc.checkpoint("d://123//12262")
val lines = ssc.socketTextStream("lion", 2222)
val words = lines.flatMap(_.split(" "))
val pairs = words.map(word => (word, 1))
val res = pairs.reduceByKeyAndWindow((a: Int, b: Int) => (a + b), Seconds(20), Seconds(10))
res.print()
ssc.start()
ssc.awaitTermination()
ssc.stop()
}
}
2.统计哪个网站访问量最多

package Test1226

import Test1225.Spider01.updateFunction
import org.apache.spark.SparkConf
import org.apache.spark.streaming.{Seconds, StreamingContext}

object test02 {
// 统计哪个网站访问量最多
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("nwc").setMaster("local[2]")
val ssc = new StreamingContext(conf, Seconds(5))
ssc.sparkContext.setLogLevel("ERROR")
ssc.checkpoint("d://123//122602")
val lines = ssc.socketTextStream("lion", 2222)
lines.map(x => x.split(" ")(6).split("\\?")(0)+" "+x.split(" ")(0)).map(x => (x,1)).reduceByKey(_+_)
.map(x => x._1.split(" ")(0)).countByValue().map(x => (x._2,x._1))
.transform(rdd => rdd.sortByKey(false)).map(x => (x._2,x._1))print()
ssc.start()
ssc.awaitTermination()
ssc.stop()

}
}
3.统计网站某模块访问量降序排序

package Test1226

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

object test03 {
// 统计网站某模块访问量降序排序
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("nwc").setMaster("local[2]")
val ssc = new StreamingContext(conf, Seconds(5))
ssc.sparkContext.setLogLevel("ERROR")
ssc.checkpoint("d://123//122602")
val lines = ssc.socketTextStream("lion", 3333)
lines.map(x => (x.split(" ")(6).split("\\?")(0),x.split(" ")(9).toInt)).reduceByKey(_ + _)
.map(x => (x._2,x._1)).transform(rdd => rdd.sortByKey(false)).map(x =>(x._2,x._1)).print()
ssc.start()
ssc.awaitTermination()
ssc.stop()
}
}
4.统计非200的报错访问量（200为正常访问）

package Test1226

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

object test04 {
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("nwc").setMaster("local[2]")
val ssc = new StreamingContext(conf, Seconds(5))
ssc.sparkContext.setLogLevel("ERROR")
ssc.checkpoint("d://123//122602")
val lines = ssc.socketTextStream("lion", 3333)
// 统计非200的报错访问量
lines.filter(x => if(x.split(" ").length <= 8) false else true)
lines.map(x => (x.split(" ")(6).split("\\?")(0)+" "+x.split(" ")(8),1))
.filter(x => if(x._1.split(" ")(1)=="200")false else true).reduceByKey(_+_).print()

ssc.start()
ssc.awaitTermination()
ssc.stop()
}
}
5.统计ueragent的数量（最后一对双引号中的内容）

package Test1226

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

object test05 {
//统计那个useragent数量
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("nwc").setMaster("local[2]")
val ssc = new StreamingContext(conf, Seconds(5))
ssc.sparkContext.setLogLevel("ERROR")
ssc.checkpoint("d://123//122602")
val lines = ssc.socketTextStream("lion", 3333)
lines.map(_.split("\"")(5)).map((_,1)).reduceByKey(_+_).print()
ssc.start()
ssc.awaitTermination()
ssc.stop()
}
}
6.统计前一分钟的网站总访问量

package Test1226

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

object test06 {
//统计前一分钟的访问量
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("nwc").setMaster("local[2]")
val ssc = new StreamingContext(conf, Seconds(5))
ssc.sparkContext.setLogLevel("ERROR")
ssc.checkpoint("d://123//12262")
val lines = ssc.socketTextStream("lion", 2222)
lines.window(Seconds(60)).count().print()
ssc.start()
ssc.awaitTermination()
ssc.stop()
}
}
所用部分数据：

120.197.87.216 - - [04/Jan/2012:00:00:02 +0800] "GET /home.php?mod=space&uid=563413&mobile=yes HTTP/1.1" 200 3388 "-" "-"
123.126.50.73 - - [04/Jan/2012:00:00:02 +0800] "GET /thread-679411-1-1.html HTTP/1.1" 200 5251 "-" "Sogou web spider/4.0(+http://www.sogou.com/docs/help/webmasters.htm#07)"
203.208.60.187 - - [04/Jan/2012:00:00:02 +0800] "GET /archiver/tid-3003.html HTTP/1.1" 200 2056 "-" "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"
114.112.141.6 - - [04/Jan/2012:00:00:02 +0800] "GET /ctp080113.php?action=getgold HTTP/1.1" 200 13886 "-" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; InfoPath.3; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729)"
114.112.141.6 - - [04/Jan/2012:00:00:02 +0800] "GET /ctp080113.php?action=getmedal HTTP/1.1" 200 13882 "-" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; InfoPath.3; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729)"
110.6.179.88 - - [04/Jan/2012:00:00:02 +0800] "GET /forum.php?mod=attachment&aid=NTczNzU3fDFjNDdjZTgzfDEzMjI4NzgwMDV8MTMzOTc4MDB8MTEwMTcxMA%3D%3D&mobile=no HTTP/1.1" 200 172 "http://www.itpub.net/forum.php?mod=attachment&aid=NTczNzU3fDFjNDdjZTgzfDEzMjI4NzgwMDV8MTMzOTc4MDB8MTEwMTcxMA%3D%3D&mobile=yes" "Mozilla/5.0 (Linux; U; Android 2.2; zh-cn; ZTE-U V880 Build/FRF91) UC AppleWebKit/530+ (KHTML, like Gecko) Mobile Safari/530"
116.205.130.2 - - [04/Jan/2012:00:00:02 +0800] "GET /popwin_js.php?fid=6 HTTP/1.1" 200 32 "http://www.itpub.net/forum-6-1.html?ts=28" "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; QQDownload 702; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; AskTbPTV/5.11.3.15590; .NET4.0E)"
114.112.141.6 - - [04/Jan/2012:00:00:02 +0800] "GET /popwin_js.php?fid=133 HTTP/1.1" 200 11 "http://www.itpub.net/thread-1558574-3-9.html" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; InfoPath.3; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729)"
114.112.141.6 - - [04/Jan/2012:00:00:02 +0800] "GET /ctp080113.php?tid=1558574 HTTP/1.1" 200 5 "http://www.itpub.net/thread-1558574-3-9.html" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; InfoPath.3; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729)"
110.75.173.35 - - [04/Jan/2012:00:00:02 +0800] "GET /forum.php?goto=lastpost&mod=redirect&tid=1380214 HTTP/1.1" 302 5 "-" "Yahoo! Slurp China"
114.112.141.6 - - [04/Jan/2012:00:00:02 +0800] "GET /popwin_js.php?fid=133 HTTP/1.1" 200 11 "http://www.itpub.net/thread-1554759-4-10.html" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; InfoPath.3; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729)"
114.112.141.6 - - [04/Jan/2012:00:00:02 +0800] "GET /ctp080113.php?tid=1554759 HTTP/1.1" 200 5 "http://www.itpub.net/thread-1554759-4-10.html" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; InfoPath.3; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729)"
120.197.87.220 - - [04/Jan/2012:00:00:02 +0800] "GET /forum.php?mod=viewthread&tid=692703&extra=&page=2&mobile=yes HTTP/1.1" 200 4903 "-" "-"
————————————————
版权声明：本文为CSDN博主「橙以」的原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/qq_42721694/article/details/85267653

爱萨萨

发布了12 篇原创文章 · 获赞 130 · 访问量 34万+

他的留言板关注

转：SparkStreaming--小案例2对于爬虫来的数据进行分析

猜你喜欢