1、增加PageStartApp.java

src/main/java/project/mrv1/PageStartApp.java

package project.mrv1;

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 project.utils.ContentUtils;
import project.utils.IPParser;
import project.utils.LogParser;

import java.io.IOException;
import java.util.Map;

public class PageStartApp {

    public static void main(String[] args) throws Exception{

        Configuration configuration = new Configuration();

        FileSystem fileSystem = FileSystem.get(configuration);
        Path outputPath = new Path("output/v1/pagestart");
        if (fileSystem.exists(outputPath)) {
            fileSystem.delete(outputPath, true);
        }

        Job job = Job.getInstance(configuration);
        job.setJarByClass(ProvinceStartApp.class);

        job.setMapperClass(PageStartApp.MyMapper.class);
        job.setReducerClass(PageStartApp.MyReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        FileInputFormat.setInputPaths(job, new Path("access/raw/input/trackinfo_20130721.data"));
        FileOutputFormat.setOutputPath(job, new Path("output/v1/pagestart"));

        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 {
            //value：是日志
            //拿到日志
            String log = value.toString();
            //将日志传进来
            Map<String, String> info = logParser.parser(log);
            String url = info.get("url");  //拿到的是LogParser.java里的url

            if (StringUtils.isNotBlank(url)) {
                String pageId = ContentUtils.getPageId(url);

                context.write(new Text(pageId), 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;
            for(LongWritable value: values){
                count++;
            }
            context.write(key, new LongWritable(count));
        }
    }

}

 

2、修改ContentUtils.java

src/main/java/project/utils/ContentUtils.java

        //为了防止报错，写一个为空的配置Id
        String pageId = "-";