java 吉时开奖网数据爬取中奖的数据

今天有个人要爬取这个网站的数据，地址为：

https://ig185.com/mkjw/html/PCEGG_180/index.html

然后我分析了这个网站的代码，发现这个网站是用structs来写的，然后分析网络连接发现，可以直接调用url：

https://ig185.com/kaijiangweb/getHistoryList.do?date=&lotCode=PCEGG_180

就可以获取到该网页的数据了，由于数据已经是json的数据，我们用fastjson封装编程类数据，我创建的是maven项目，依赖为：

<!-- https://mvnrepository.com/artifact/org.apache.httpcomponents/httpclient -->
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.5.3</version>
</dependency>
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.13</version>
</dependency>

创建javabean，首先是result.java

package bean;

import java.util.List;

public class Result {
private List<Lottery> result;
private int errorCode;
private String message;

public List<Lottery> getResult() {
return result;
}

public void setResult(List<Lottery> result) {
this.result = result;
}

public int getErrorCode() {
return errorCode;
}

public void setErrorCode(int errorCode) {
this.errorCode = errorCode;
}

public String getMessage() {
return message;
}

public void setMessage(String message) {
this.message = message;
}
}

lottery.java类

package bean;

import java.lang.reflect.Array;
import java.util.Arrays;

public class Lottery {
private int sumSingleDouble;
private int sumBigSmall;
private String preDrawIssue;
private String preDrawTime;
private int sumNum;
private int groupCode;
private int[] preDrawCode;

public int getSumSingleDouble() {
return sumSingleDouble;
}

public void setSumSingleDouble(int sumSingleDouble) {
this.sumSingleDouble = sumSingleDouble;
}

public int getSumBigSmall() {
return sumBigSmall;
}

public void setSumBigSmall(int sumBigSmall) {
this.sumBigSmall = sumBigSmall;
}

public String getPreDrawIssue() {
return preDrawIssue;
}

public void setPreDrawIssue(String preDrawIssue) {
this.preDrawIssue = preDrawIssue;
}

public String getPreDrawTime() {
return preDrawTime;
}

public void setPreDrawTime(String preDrawTime) {
this.preDrawTime = preDrawTime;
}

public int getSumNum() {
return sumNum;
}

public void setSumNum(int sumNum) {
this.sumNum = sumNum;
}

public int getGroupCode() {
return groupCode;
}

public void setGroupCode(int groupCode) {
this.groupCode = groupCode;
}

public int[] getPreDrawCode() {
return preDrawCode;
}

public void setPreDrawCode(int[] preDrawCode) {
this.preDrawCode = preDrawCode;
}

@Override
public String toString() {
return "Lottery{" +
"sumSingleDouble=" + sumSingleDouble +
", sumBigSmall=" + sumBigSmall +
", preDrawIssue='" + preDrawIssue + '\'' +
", preDrawTime='" + preDrawTime + '\'' +
", sumNum=" + sumNum +
", groupCode=" + groupCode +
", preDrawCode=" + Arrays.toString(preDrawCode) +
'}';
}
}

然后是LotteryPaser.java类

import bean.Lottery;
import bean.Result;
import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.TypeReference;
import org.apache.http.HttpEntity;
import org.apache.http.ParseException;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;

import java.io.IOException;
import java.util.List;

public class LotteryPaser {
public static void main(String args[]){
String url="https://ig185.com/kaijiangweb/getHistoryList.do?date=&lotCode=PCEGG_180";
String html=pickData(url);
System.out.println(html);
Result result = JSON.parseObject(html, new TypeReference<Result>() {});
System.out.println(result.getMessage());
System.out.println(result.getResult());
List<Lottery> lotteries=result.getResult();
for(Lottery lottery:lotteries){
System.out.println(lottery.toString());
System.out.println(lottery.getPreDrawTime());
}

}

/*
* 爬取网页信息
*/
private static String pickData(String url) {
CloseableHttpClient httpclient = HttpClients.createDefault();
try {
HttpGet httpget = new HttpGet(url);
CloseableHttpResponse response = httpclient.execute(httpget);
try {
// 获取响应实体
HttpEntity entity = response.getEntity();
// 打印响应状态
if (entity != null) {
return EntityUtils.toString(entity);
}
} finally {
response.close();
}
} catch (ClientProtocolException e) {
e.printStackTrace();
} catch (ParseException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} finally {
// 关闭连接,释放资源
try {
httpclient.close();
} catch (IOException e) {
e.printStackTrace();
}
}
return null;
}

}