电商实战
工具类utils
提供四个工具类
GetPageId.java
调用getPageId方法,可从一个url中提取topicId
例如:“http://www.yihaodian.com/cms/view.do?topicId=14572”
返回结果为字符串类型:14572
没有topicId则返回空
package com.task.ds.utils;
import org.apache.commons.lang.StringUtils;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class GetPageId {
public static String getPageId(String url) {
String pageId = "";
if (StringUtils.isBlank(url)) {
return pageId;
}
Pattern pat = Pattern.compile("topicId=[0-9]+");
Matcher matcher = pat.matcher(url);
if (matcher.find()) {
pageId = matcher.group().split("topicId=")[1];
}
return pageId;
}
}
IPParser.java
提供解析ip,映射成对应的国家、省份、城市的方法: analyseIp(ip)
package com.task.ds.pro;
import com.task.ds.utils.IPParser;
import com.task.ds.utils.LogParser;
import org.apache.commons.lang3.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;
/**
* 省份浏览量统计
*/
public class ProvinceStatApp {
public static void main(String[] args) throws Exception {
Configuration configuration = new Configuration();
FileSystem fileSystem = FileSystem.get(configuration);
Path outputPath = new Path("E:\\IdeaProject\\hadoop\\project\\src\\main\\java\\com\\data\\trackInfo_out");
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("E:\\IdeaProject\\hadoop\\project\\src\\main\\java\\com\\data\\trackinfo_20130721.txt"));
FileOutputFormat.setOutputPath(job, new Path("E:\\IdeaProject\\hadoop\\project\\src\\main\\java\\com\\data\\trackInfo_out"));
job.waitForCompletion(true);
}
static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
private LongWritable ONE = new LongWritable(1);
private LogParser logParser;
@Override
protected void setup(Context context) throws IOException, InterruptedException {
logParser = new LogParser();
}
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String log = value.toString();
Map<String, String> info = logParser.parse(log);
String ip = info.get("ip");
if (StringUtils.isNotBlank(ip)) {
IPParser.RegionInfo regionInfo = IPParser.getInstance().analyseIp(ip);
if (regionInfo != null) {
String provine = regionInfo.getProvince();
if (StringUtils.isNotBlank(provine)) {
context.write(new Text(provine), ONE);
} else {
context.write(new Text("-"), ONE);
}
} else {
context.write(new Text("-"), ONE);
}
} else {
context.write(new Text("-"), ONE);
}
}
}
static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
@Override
protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
long count = 0;
System.out.println(context);
for (LongWritable value : values) {
count++;
}
context.write(key, new LongWritable(count));
}
}
}