1、url選擇

（1）必選帶

topicId=

2、目標

（1）獲取符合規則的pageId，然後進行統計

3、修改LogParser.java

src/main/java/project/utils/LogParser.java

package project.utils;

import org.apache.commons.lang.StringUtils;
import java.util.HashMap;
import java.util.Map;

//日誌解析
public class LogParser {

    IPParser ipParser = IPParser.getInstance();

    
 
public Map<String, String> parser(String log){
        Map<String, String> info = new HashMap<>();

        //IP是第13個欄位
        if (StringUtils.isNotBlank(log)){
            String[] splits = log.split("\001");

            String ip = splits[13];
            String country = "-";
            String province 
 
= "-";
            String city = "-";
            IPParser.RegionInfo regionInfo = ipParser.analyseIp(ip);

            if (regionInfo != null){
                country = regionInfo.getCountry();
                province = regionInfo.getProvince();
                city = regionInfo.getCity();
            }

            info.put(
 
"ip",ip);
            info.put("country",country);
            info.put("province",province);
            info.put("city",city);

            String url = splits[1];
            info.put("url",url);

        }
        return info;
    }
}

4、新增工具類ContentUtils.java

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

package project.utils;

import org.apache.commons.lang.StringUtils;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class ContentUtils {

    //傳入的引數為url
    public static String getPageId(String url){

        //為了防止報錯，寫一個為空的配置Id
        String pageId = "";
        //如果字串url為空，直接返回配置Id
        if (StringUtils.isBlank(url)){
            return pageId;
        }
        //對於topicId=19004，要使用正則表示式選擇0-9的資料
        Pattern pattern = Pattern.compile("topicId=[0-9]+");
        //選擇好了之後，將url傳進來，進行matcher
        Matcher matcher = pattern.matcher(url);
        //如果marcher上：從topicId=後擷取
        if(matcher.find()){
            pageId = matcher.group().split("topicId=")[1];
        }
        return pageId;
    }

}

5、進行測試，修改LogParserTest.java

src/test/java/mr/project/utils/LogParserTest.java

package mr.project.utils;

import org.junit.After;
import org.junit.Before;
import org.junit.Test;
import project.utils.ContentUtils;
import project.utils.LogParser;
import java.util.Map;

public class LogParserTest {

    LogParser logParser;

    @Before
    public void setUp(){
        logParser = new LogParser();
    }

    @After
    public void tearDown(){
        logParser = null;
    }

    @Test
    public void test01(){
        Map<String, String> map = logParser.parser("20960991758\u0001http://www.yihaodian.com/cms/view.do?topicId=19004\u0001http://www.yihaodian.com/cms/view.do?topicId=22331&cache=false&merchant=1\u0001\u00013\u00016ZD1N3J3ECTNX96DSGESX9GN12U1JD2R9YGP\u0001\u0001\u0001\u0001\u0001PPHK3755F3XK3HDYT1AHW7XNS9GZBECK\u000110931041909\u0001\\N\u0001101.85.27.156\u0001\u0001msessionid:D7UNQY44Z6GYKXHWB7QW8NMT6TPVQZKK,unionKey:10931041909\u0001\u00012013-07-21 13:34:10\u0001\\N\u0001http://hao.360.cn/?wd_xp1\u00015\u0001\u0001\\N\u00011\u0001-10\u0001\u0001\u0001\u0001\u0001Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729)\u0001Win32\u0001\u0001\u0001\u0001\u0001\u0001上海市\u00011\u0001\u0001\u0001上海市\u0001\u00014\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());
        }
    }

    @Test
    public void test02(){
        String pageId = ContentUtils.getPageId("http://www.yihaodian.com/cms/view.do?topicId=19004");
        System.out.println(pageId);
    }
}