大数据学习练习3--第一天

今天对这次练习的第一部分进行了完成，主要目标为完成对地域名和地域码的完善。

开始的时候想着区百度地图爬取，顾及到可能会被限制访问，毕竟数据较多，所以就放弃了这个方法。

第二个想到了调用百度地图API，并通过这个完成了第一部分。

首先

第一步，我们申请百度地图API所用ak，

https://jingyan.baidu.com/article/e73e26c0b5b75124adb6a786.html（这个是申请的步骤教程），我们在网上很容易就可以搜到。

第二步，我们就可以调用百度地图API来进行地域名和地域码的获取了，方法有很多种，作者是通过搜索的地点来确定经纬，然后根据经纬来确定地域名和地域码，这种方法接口返回的数据很多种，更能满足我们的需要，当然也有很多别的用法，这里附上百度地图API官方的一个手册，里面讲解很详细很全面（http://lbsyun.baidu.com/index.php?title=webapi/guide/webservice-placeapi），接下来直接附上作者的实现代码。

Data.java

package bao;

public class Data {
String acode="";
String diyv="";
}

DBUtil.java

package bao;

import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.ResultSet;
import java.sql.SQLException;
import java.sql.Statement;

/**
 * 
 * @author zm
 *
 */
public class DBUtil {
    public static String db_url = "jdbc:mysql://localhost:3306/数据库名?&useSSL=false&serverTimezone=UTC";
    public static String db_user = "用户名";
    public static String db_password = "数据库密码";

    public static Connection getConn() {
        Connection conn = null;
        try {
            Class.forName("com.mysql.jdbc.Driver");
            conn = DriverManager.getConnection(db_url, db_user, db_password);
        } catch (Exception e) {
            e.printStackTrace();
        }
        return conn;
    }
    
    public static void close(Statement state, Connection conn) {
        if(state!=null) {
            try {
                state.close();
            } catch (SQLException e) {
                e.printStackTrace();
            }
        }
        if(conn!=null) {
            try {
                conn.close();
            } catch (SQLException e) {
                e.printStackTrace();
            }
        }
    }
    
    public static void close(ResultSet rs, Statement state, Connection conn) {
        if(rs!=null) {
            try {
                rs.close();
            } catch (SQLException e) {
                e.printStackTrace();
            }
        }
        if(state!=null) {
            try {
                state.close();
            } catch (SQLException e) {
                e.printStackTrace();
            }
        }
        if(conn!=null) {
            try {
                conn.close();
            } catch (SQLException e) {
                e.printStackTrace();
            }
        }
    }
}

getregion.java

package bao;

import java.io.IOException;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.List;

import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;

public class getregion{
     
     public Data getLocation(String lat,String lng){
         Data data=new Data();
           String location1="";
           String location2="";
           String location3="";
           String location4="";
          String url="http://api.map.baidu.com/reverse_geocoding/v3/?ak=您申请的ak&output=xml&coordtype=wgs84ll&location="+lat+","+lng;
          //System.out.println(url);
          Document doc = null;
           HttpURLConnection conn = null;
           InputStream ins = null;
           SAXReader reader = null;
           try{
            //HttpTimeoutHandler hth = new HttpTimeoutHandler(600000);
            URL conURL = new URL(null,url);
            conn = (HttpURLConnection)conURL.openConnection();
            conn.setDoInput(true);
            conn.setDoOutput(true);
            conn.setUseCaches(false);
            ins = conn.getInputStream();
            reader =new SAXReader();
            doc= reader.read(ins);
            Element root=doc.getRootElement();
            String docXmlText=doc.asXML();
            Element e=root.element("result");
            Element location=e.element("addressComponent");
            location1=location.asXML();
            Element adcode=location.element("adcode");
            location2=adcode.asXML();
            Element province=location.element("province");
            location3=province.asXML();
            Element district=location.element("district");
            location4=district.asXML();
            location2=location2.replace("<adcode>","").replace("</adcode>", "");
            location3=location3.replace("<province>","").replace("</province>", "");
            location4=location4.replace("<district>","").replace("</district>", "");
            data.acode=location2;
            data.diyv=location3+location4;
            System.out.println(location2);
            System.out.println(location3);
            System.out.println(location4);
            ins.close();
            conn.disconnect();
           }catch (MalformedURLException e) {
            e.printStackTrace();
           } catch (IOException e) {
            e.printStackTrace();   
           } catch (DocumentException e) {
            e.printStackTrace();
           }catch(Exception e){
            e.printStackTrace();
           }finally {
            try {
             if (ins != null) {
              ins.close();
              ins = null;
             }
            } catch (IOException e1) {
             e1.printStackTrace();
            }
            try {
             if (conn != null) {
              conn.disconnect();
              conn = null;
             }
            } catch (Exception e2) {
             e2.printStackTrace();
            }
           }
           return data;
        }
    public Data getlocation1(String loc){
        String location3="";
        Data data = new Data();
          String url="http://api.map.baidu.com/geocoding/v3/?address="+loc+"&output=xml&ak=您申请的ak&callback=showLocation";
          Document doc = null;
           HttpURLConnection conn = null;
           InputStream ins = null;
           SAXReader reader = null;
           try{
            //HttpTimeoutHandler hth = new HttpTimeoutHandler(600000);
            URL conURL = new URL(null,url);
            conn = (HttpURLConnection)conURL.openConnection();
            conn.setDoInput(true);
            conn.setDoOutput(true);
            conn.setUseCaches(false);
            ins = conn.getInputStream();
            reader =new SAXReader();
            doc= reader.read(ins);
            Element root=doc.getRootElement();
           // String docXmlText=doc.asXML();
            //System.out.println(docXmlText);
            Element e=root.element("result");
            Element e1=root.element("status");
            String check=e1.asXML().replace("</status>", "").replace("<status>","");
            System.out.println(check);
            if(check.equals("0")) {
            Element location=e.element("location");
            Element lng=location.element("lng");
            Element lat=location.element("lat");
            String lng1=lng.asXML();
            String lat1=lat.asXML();
            //System.out.println("lng"+lng1);
           // System.out.println("lat"+lat1);
           // System.out.println("location"+location.asXML());
            //System.out.println("xiayukun"+e.asXML());
            lng1=lng1.substring(lng1.indexOf("<lng>")+5,lng1.indexOf("</lng>"));
            //System.out.println(lng1);
            lat1=lat1.substring(lat1.indexOf("<lat>")+5,lat1.indexOf("</lat>"));
            //System.out.println(lat1);
            //location2=getLocation(lat1,lng1);
            data=getLocation(lat1,lng1);}
            ins.close();
            conn.disconnect();
           }catch (MalformedURLException e) {
            e.printStackTrace();
           } catch (IOException e) {
            e.printStackTrace();   
           } catch (DocumentException e) {
            e.printStackTrace();
           }catch(Exception e){
            e.printStackTrace();
           }finally {
            try {
             if (ins != null) {
              ins.close();
              ins = null;
             }
            } catch (IOException e1) {
             e1.printStackTrace();
            }
            try {
             if (conn != null) {
              conn.disconnect();
              conn = null;
             }
            } catch (Exception e2) {
             e2.printStackTrace();
            }
           }
           return data;
           //return location2;
        }
    
}

YiDao.java

package bao;


import java.sql.Connection;
import java.sql.ResultSet;
import java.sql.Statement;

public class YiDao
{
    //int num_i=0;
    public void select_city()
    {
        getregion getregion=new getregion();
        Data data=new Data();
        Connection conn = DBUtil.getConn();
        Statement state = null;
        String str=new String();
        //String newStr=str;
        int i=0;
        try {
            state = conn.createStatement();
            ResultSet rs = state.executeQuery("select * from test2");
            while(rs.next()) {
                //如果有结果，是认为是通过验证了
                str=rs.getString("wanchengdanwei");
                //newStr=str;
                //int i = str.indexOf(" ");
                //if(i!=-1)
               // {
                   // newStr = str.substring(0,i);
               // }
               // city=getregion.SELECT(newStr);
                data=getregion.getlocation1(str);
                update_city(data.acode,data.diyv,str);
                i++;
                System.out.println("执行了"+i);
            }
        } catch (Exception e)
        {
            e.printStackTrace();
        }finally {
            DBUtil.close(state, conn);
        }
    }
    public void update_city(String acode,String diyv,String wanchengdanwei) {
        String sql = "update test2 set diyvma ='"+acode+"',biaozhundiyv = '"+diyv+"' where  wanchengdanwei ='"+wanchengdanwei+"'";
        Connection conn = DBUtil.getConn();
        Statement state = null;
        try {
            state = conn.createStatement();
            state.executeUpdate(sql);
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            DBUtil.close(state, conn);
        }
    }
    public static void main(String[] args) {
        YiDao yindao=new YiDao();
        yindao.select_city();
    }
}

部分结果图

 到这里就结束了，当然代码也并非全部如作者编写，有借鉴网上的模板，毕竟第一次接触调用百度地图API，有想过像爬取网页一样实现，但还是感觉不正规，虽然也可以实现，然后由于数据问题，有些地点搜索不到或过长等，我们要跳过这些信息，这也没有办法，明天我会继续完成第二部分，就这么多了，再见。