Java爬蟲——B站彈幕爬取

如何通過B站視頻AV號找到彈幕對應的xml文件號

首先爬取視頻網頁，將對應視頻網頁源碼獲得

 

 

 就可以找到該視頻的av號aid=8678034

 還有彈幕序號，cid=14295428

 彈幕存放位置為  http://comment.bilibili.com/14295428.xml

 獲得該鏈接內容即可。

package BiliBili彈幕爬取;

import org.apache.http.HttpEntity; 
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.util.regex.Matcher;
import java.util.regex.Pattern;

public class getBiliBiliBofqi {
    public static void getBofqi(String aid) throws Exception{
        CloseableHttpClient closeableHttpClient = HttpClients.createDefault() ;
        HttpGet httpGet = new HttpGet("https://www.bilibili.com/video/av"+aid+"/") ;
        CloseableHttpResponse httpResponse = closeableHttpClient.execute(httpGet) ;
        HttpEntity httpEntity = httpResponse.getEntity() ;
        String en= EntityUtils.toString(httpEntity) ;
//"cid=16496518&aid=9979006&pre_ad="
        String con = "cid=(.*)?&aid=" ;
        Pattern ah = Pattern.compile(con);
        Matcher mr = ah.matcher(en);
        while(mr.find()) {
            String id = mr.group() ;
            String newUrl = id.replace("cid=","") ;
            String x = newUrl.replace("&aid=","") ;
            HttpGet httpGet1 = new HttpGet("http://comment.bilibili.com/"+x+".xml");
            CloseableHttpResponse httpResponse1 = closeableHttpClient.execute(httpGet1) ;
            HttpEntity httpEntity1 = httpResponse1.getEntity() ;
            String en1 = EntityUtils.toString(httpEntity1) ;
            String c = "\">(.*?)<" ;
            Pattern a = Pattern.compile(c);
            Matcher m = a.matcher(en1);
            while(m.find()){
                String speak = m.group().replace("\">","") ;
                speak = speak.replace("<","") ;
                System.out.println(speak);
            }
        }
    }
    public static void main(String[] args) throws Exception{
        getBofqi("8678034");
    }
}

 運行結果：