zoukankan      html  css  js  c++  java
  • 数据爬取

    编程爬取每日最新的疫情统计数据。

    并将爬取结果导入到数据库中。

    将可视化结果与统计数据结合,实时显示当前最新数据

    package getDataTest;
    
    import java.io.IOException;
    import java.sql.SQLException;
    import java.util.HashMap;
    import java.util.Map;
    
    import javax.naming.InitialContext;
    import javax.net.ssl.HttpsURLConnection;
    
    import org.apache.commons.dbutils.QueryRunner;
    import org.jsoup.Jsoup;
    
    import com.alibaba.fastjson.JSON;
    import com.alibaba.fastjson.JSONArray;
    import com.alibaba.fastjson.JSONObject;
    import com.mchange.v2.c3p0.DataSources;
    
    import utils.DataSourceUtils;
    
    public class GetYiQing {
        
           
          public static String USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.14; rv:49.0) Gecko/20100101 Firefox/49.0";
    
          public static String HOST = "i.snssdk.com";
    
          public static String REFERER = "https://i.snssdk.com/feoffline/hot_list/template/hot_list/forum_tab.html?activeWidget=1";
          
          public static void main(String[] args) throws IOException, SQLException {
            
    
                String url = "https://i.snssdk.com/forum/home/v1/info/?activeWidget=1&forum_id=1656784762444839";
    
                String resultBody;
                try {
                    SSL.trustAllHttpsCertificates();
                } catch (Exception e) {
                    // TODO Auto-generated catch block
                    e.printStackTrace();
                }
                HttpsURLConnection.setDefaultHostnameVerifier(SSL.hv);
                
                resultBody = Jsoup.connect(url).
    
                        userAgent(USER_AGENT).header("Host", HOST).header("Referer", REFERER).execute().body();
    
                    JSONObject jsonObject = JSON.parseObject(resultBody);
    
                    String ncovStringList = jsonObject.getJSONObject("forum").getJSONObject("extra").getString("ncov_string_list");
    
                    JSONObject ncovListObj = JSON.parseObject(ncovStringList);
                    JSONArray todaydata = ncovListObj.getJSONArray("provinces");
                    QueryRunner queryRunner = new QueryRunner(DataSourceUtils.getDataSource());
                    String sql = "insert into info4 values(?,?,?,?,?,?,?,?)";
                    String confirmedNum,deathsNum,cityname,cityid,treatingNum,provinceid;
                    String reprovinceid=null;
                    int confirmedNumSum=0,deathsNumSum=0,treatingNumSum=0;
                    for(int i=0;i<todaydata.size();i++) {
                        JSONObject todayData1 = todaydata.getJSONObject(i);
                        String updateDate = todayData1.getString("updateDate");
                        JSONArray city = todayData1.getJSONArray("cities");
                        for(int j=0;j<city.size();j++) {
                            JSONObject cities = city.getJSONObject(j);
                            confirmedNum= cities.getString("confirmedNum");
                            deathsNum = cities.getString("deathsNum");
                            cityname = cities.getString("name");
                            cityid = cities.getString("id");
                            treatingNum = cities.getString("treatingNum");
                            provinceid = cityid.substring(0,2);
                            reprovinceid=provinceid;
                            confirmedNumSum+=Integer.parseInt(confirmedNum);
                            deathsNumSum+=Integer.parseInt(deathsNum);
                            treatingNumSum+=Integer.parseInt(treatingNum);
                            queryRunner.update(sql, updateDate,provinceid,cityname,confirmedNum,deathsNum,treatingNum,cityid,null);
                        }
                        queryRunner.update(sql,updateDate,reprovinceid,null,confirmedNumSum,deathsNumSum,treatingNumSum,null,null);    
                        confirmedNumSum=0;
                        deathsNumSum=0;
                        treatingNumSum=0;
                    }
                  }
    }
    
  • 相关阅读:
    软件工程作业03
    PSP0级要求02
    PSP0级要求日志
    软件工程个人作业02
    第三周学习进度
    第二周学习进度
    软件工程个人作业01
    Web网页登录设计
    第一周学习进度
    第三周学习进度条+PSP0过程文档
  • 原文地址:https://www.cnblogs.com/zhjvvvvvv/p/13088063.html
Copyright © 2011-2022 走看看