Hadoop电商日志数据分析(二)seo优化

Hadoop电商日志数据分析(二)

news/2024/9/23 14:31:47

项目要求

根据电商日志文件，分析：
1 . 统计页面浏览量（每行记录就是一次浏览）
2 . 统计各个省份的浏览量（需要解析IP）
3 . 日志的ETL操作（ETL：数据从来源端经过抽取（Extract）、转换（Transform）、加载（Load）至目的端的过程）

为什么要ETL：没有必要解析出所有数据，只需要解析出有价值的字段即可。本项目中需要解析出：ip、url、pageId（topicId对应的页面Id）、country、province、city

提供一个数据集和四个工具：
rackinfo_20130721.data

点击查看数据集示例

20939177966http://www.yihaodian.com/1/?type=3&tracker_u=107813492603YU7317CWPWJPCCKSJD83RZ35W6F1DGHT4P93PPGDPBNYMTMMVQQSX13BVW4A6Z61BCFK10781349260\N115.28.44.205,unionKey:107813492602013-07-21 01:18:59\N1\Nnull-20Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; Sicent; WoShiHoney.B; .NET CLR 2.0.50727; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729; Microsoft Windows Media Center PC 6.0)Win32北京市2北京市\N\N\N\N2013-07-21
20966958616http://www.1mall.com/item/11033978_4http://www.1mall.com/item/11033980_4?ref=1_1_51_search.keyword_13EUBCC9CG8G7G3Z331PWEV3UNWD7QZA1F3Q2Q1[{1=[{9784616=38251:1190}]}]PPH24C5RHH3GE4RUY1UKQW84PVYBXZFT7439964\N101.18.106.107msessionid:CP23DVRKZGQ67MWQQGNHN5USRK2R9W8V,unionKey:74399642013-07-21 15:11:16\Nhttp://www.2345.com/?kskypw59784615\N4-1Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTMLWin32河北省446\N\N\N\N2013-07-21
20966773971http://search.yihaodian.com/s2/c0-0/k%25E9%259B%25AA%25E7%25BA%25BA%2520t%25E6%2581%25A4/1/http://www.yihaodian.com/4/?tracker_u=7439964&type=13EUBCC9CG8G7G3Z331PWEV3UNWD7QZA1F3Q2QPPH24C5RHH3GE4RUY1UKQW84PVYBXZFT7439964\N101.18.106.107msessionid:WUEYCTYUHP7CUP4UD7Y2VHNZABPCYJ18,unionKey:74399642013-07-21 15:10:02\Nhttp://www.2345.com/?kskypw3\N4-1Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTMLWin32雪纺 t恤13661CatMenu_Keywords_100000003_18258河北省4null3\N\N\N\N2013-07-21

日志字段说明

技术架构：

浏览量统计功能实现

统计页面的浏览量
count
一行记录做成一个固定的KEY，value赋值为1
PVStatApp

点击查看代码

package com.imooc.bigdata.hadoop.mr.project.mr;import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;import java.io.IOException;/*** 第一版本浏览量的统计*/
public class PVStatApp {public static void main(String[] args) throws Exception{Configuration configuration = new Configuration();// 如果输出目录已经存在，则先删除FileSystem fileSystem = FileSystem.get(configuration);Path outputPath = new Path("output/v1/pvstat");if(fileSystem.exists(outputPath)) {fileSystem.delete(outputPath,true);}Job job = Job.getInstance(configuration);job.setJarByClass(PVStatApp.class);job.setMapperClass(MyMapper.class);job.setReducerClass(MyReducer.class);job.setMapOutputKeyClass(Text.class);job.setMapOutputValueClass(LongWritable.class);job.setOutputKeyClass(NullWritable.class);job.setOutputValueClass(LongWritable.class);FileInputFormat.setInputPaths(job,new Path("input/raw/trackinfo_20130721.data"));FileOutputFormat.setOutputPath(job,new Path("output/v1/pvstat"));job.waitForCompletion(true);}static class MyMapper extends Mapper<LongWritable,Text,Text,LongWritable> {private Text KEY = new Text("key");private LongWritable ONE = new LongWritable(1);@Overrideprotected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {context.write(KEY,ONE);}}static class MyReducer extends Reducer<Text,LongWritable,NullWritable,LongWritable>{@Overrideprotected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {long count = 0;for (LongWritable value:values){count++;}context.write(NullWritable.get(),new LongWritable(count));}}
}

Linux查看文件行数

wc -l 文件名

省份浏览量统计

1.IP库解析

统计各个省份的浏览量
select province count(1) from xxx group by province;
城市信息我们是可以通过ip解析得到的 <== ip如何转换成城市信息
ip解析：提供一个IP数据库QQWry.dat，用于将IP地址转换为相应的地理位置信息。

IPTest

package com.imooc.bigdata.hadoop.mr.project.utils;import org.junit.Test;public class IPTest {@Testpublic void testIP(){IPParser.RegionInfo regionInfo = IPParser.getInstance().analyseIp("123.116.60.97");System.out.println(regionInfo.getCountry());System.out.println(regionInfo.getProvince());System.out.println(regionInfo.getCity());}
}

2.日志解析

数据集展示:

LogParseTest

public class LogParseTest {LogParser logParser;@Beforepublic void setUp(){logParser = new LogParser();}@Afterpublic void tearDown(){logParser = null;}@Testpublic void test01(){Map<String, String> map  = logParser.parse("20946835322\u0001http://www.yihaodian.com/1/?tracker_u=2225501&type=3\u0001http://www.baidu.com/s?wd=1%E5%8F%B7%E5%BA%97&rsv_bp=0&ch=&tn=baidu&bar=&rsv_spt=3&ie=utf-8&rsv_sug3=5&rsv_sug=0&rsv_sug1=4&rsv_sug4=313&inputT=4235\u00011号店\u00011\u0001SKAPHD3JZYH9EE9ACB1NGA9VDQHNJMX1NY9T\u0001\u0001\u0001\u0001\u0001PPG4SWG71358HGRJGQHQQBXY9GF96CVU\u00012225501\u0001\\N\u0001124.79.172.232\u0001\u0001msessionid:YR9H5YU7RZ8Y94EBJNZ2P5W8DT37Q9JH,unionKey:2225501\u0001\u00012013-07-21 09:30:01\u0001\\N\u0001http://www.baidu.com/s?wd=1%E5%8F%B7%E5%BA%97&rsv_bp=0&ch=&tn=baidu&bar=&rsv_spt=3&ie=utf-8&rsv_sug3=5&rsv_sug=0&rsv_sug1=4&rsv_sug4=313&inputT=4235\u00011\u0001\u0001\\N\u0001null\u0001-10\u0001\u0001\u0001\u0001\u0001Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; MATP; Media Center PC 6.0; .NET4.0C; InfoPath.2; .NET4.0E)\u0001Win32\u0001\u0001\u0001\u0001\u0001\u0001上海市\u00011\u0001\u00012013-07-21 09:30:01\u0001上海市\u0001\u000166\u0001\u0001\u0001\u0001\u0001\\N\u0001\\N\u0001\\N\u0001\\N\u00012013-07-21\n");for(Map.Entry<String,String> entry : map.entrySet()) {System.out.println(entry.getKey() + " : " + entry.getValue());}}
}

测试:

3.省份浏览量统计功能的实现

点击查看代码

package com.imooc.bigdata.hadoop.mr.project.mr;import com.imooc.bigdata.hadoop.mr.project.utils.IPParser;
import com.imooc.bigdata.hadoop.mr.project.utils.LogParser;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;import java.io.IOException;
import java.util.Map;public class ProvinceStatApp {// Driver端的代码：八股文public static void main(String[] args) throws Exception {Configuration configuration = new Configuration();// 如果输出目录已经存在，则先删除FileSystem fileSystem = FileSystem.get(configuration);Path outputPath = new Path("output/v1/provicestat");if(fileSystem.exists(outputPath)) {fileSystem.delete(outputPath,true);}Job job = Job.getInstance(configuration);job.setJarByClass(ProvinceStatApp.class);job.setMapperClass(MyMapper.class);job.setReducerClass(MyReducer.class);job.setMapOutputKeyClass(Text.class);job.setMapOutputValueClass(LongWritable.class);job.setOutputKeyClass(Text.class);job.setOutputValueClass(LongWritable.class);FileInputFormat.setInputPaths(job, new Path("/Users/rocky/data/trackinfo_20130721.data"));FileOutputFormat.setOutputPath(job, new Path("output/v1/provicestat"));job.waitForCompletion(true);}static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable> {private LogParser parser;private LongWritable ONE = new LongWritable(1);@Overrideprotected void setup(Context context) throws IOException, InterruptedException {parser = new LogParser();}@Overrideprotected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {String log = value.toString();Map<String, String> logInfo = parser.parse(log);if (StringUtils.isNotBlank(logInfo.get("ip"))) {IPParser.RegionInfo regionInfo = IPParser.getInstance().analyseIp(logInfo.get("ip"));String province = regionInfo.getProvince();if (StringUtils.isNotBlank(province)) {context.write(new Text(province), ONE);} else {context.write(new Text("-"), ONE);}} else {context.write(new Text("-"), ONE);}}}static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable> {@Overrideprotected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {long count = 0;for (LongWritable access : values) {count++;}context.write(key, new LongWritable(count));}}}

测试结果: