编程语言
首页 > 编程语言> > Java爬取并下载酷狗音乐

Java爬取并下载酷狗音乐

作者:互联网

本文方法及代码仅供学习,仅供学习。

案例:

  下载酷狗TOP500歌曲,代码用到的代码库包含:Jsoup、HttpClient、fastJson等。

正文:

  1、分析是否可以获取到TOP500歌单

打开酷狗首页,查看TOP500,发现存在分页,每页显示22条歌曲,

发现酷狗的链接如下:

https://www.kugou.com/yy/rank/home/1-8888.html?from=homepage

通过更改链接中的1可以进行分页,所以我们可以通过更改链接地址获取其余的歌曲。

2、分析找到正真的mp3下载地址

 点一个歌曲进入播放页面,使用谷歌浏览器的控制台的Elements,搜一下mp3,很轻松就定位到了MP3的位置。

但是使用java访问的时候爬取的html里却没有该mp3的文件地址,那么这肯定是在该页面的位置使用了js来加载mp3,那么刷新下网页,看网页加载了哪些东西,加载的东西有点多,着重看一下js、php的请求,主要是看里面有没有mp3的地址。

最终在列表中找到:

https://wwwapi.kugou.com/yy/index.php?r=play/getdata&callback=jQuery191044492686523157987_1559446927765&hash=458E9B9F362277AC37E9EEF1CB80B535&album_id=18712576&dfid=1ZxQbe0MiP8J09j5tR0Np9IA&mid=9393340fecff864a4d6c4e95099b2be1&platid=4&_=1559446927766

这个请求结果中发现了mp3的完整地址:

那这个js是怎么判断是哪首歌的呢,那么只可能是hash这个参数来决定歌曲的,然后到播放页面里找到这个hash的位置,是在下面的js里:

var dataFromSmarty = [{"hash":"667939C6E784265D541DEEE65AE4F2F8","timelength":"237051","audio_name":"\u767d\u5c0f\u767d - \u6700\u7f8e\u5a5a\u793c","author_name":"\u767d\u5c0f\u767d","song_name":"\u6700\u7f8e\u5a5a\u793c","album_id":0}],//当前页面歌曲信息
            playType = "search_single";//当前播放
    </script>

在去java爬取该网页,查看能否爬到这个hash,果然,爬取的html里有这段js,到现在mp3的地址也找到了,歌单也找到了,那么下一步就用程序实现就可以了。

3、代码实现

SpiderKugou.java
package com.billy.test;

import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONObject;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import java.io.IOException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * 爬取并下载酷狗的歌曲
 */
public class SpiderKugou {

    private static String filePath;

    //酷狗地址
    private static String LINK;

    //mp3地址
    private static String mp3;

    static {
        filePath = "F:/music/";
        LINK = "https://www.kugou.com/yy/rank/home/PAGE-8888.html?from=rank";
        mp3 = "https://wwwapi.kugou.com/yy/index.php?r=play/getdata&callback=jQuery19103632090130122796_1558800325111&"
                + "hash=HASH&_=TIME";
    }


    public static void main(String[] args) throws Exception {

        for(int i = 5 ; i < 23 ; i++){

            String url = LINK.replace("PAGE", i + "");
            downSong(url);
        }
    }

    /**
     * 下载歌曲
     * @param url
     * @throws Exception
     */
    private static void downSong(String url) throws Exception{

        HttpGetConnect connect = new HttpGetConnect();
        String content = connect.connect(url, "utf-8");
        HtmlManage html = new HtmlManage();
        Document doc = html.manage(content);
        Element ele = doc.getElementsByClass("pc_temp_songlist").get(0);
        Elements elements = ele.getElementsByTag("li");
        for(int i = 0 ; i < elements.size() ; i++){

            Element item = elements.get(i);
            String title = item.attr("title").trim();
            String link = item.getElementsByTag("a").first().attr("href");
            downLoad(link,title);
            Thread.sleep(1000);
        }
    }

    /**
     * 下载
     * @param url
     * @param name
     * @throws IOException
     */
    private static void downLoad(String url,String name) throws IOException{

        String hash = "";
        HttpGetConnect connect = new HttpGetConnect();
        String content = connect.connect(url, "utf-8");

        String regEx = "\"hash\":\"[0-9A-Z]+\"";
        // 编译正则表达式
        Pattern pattern = Pattern.compile(regEx);
        Matcher matcher = pattern.matcher(content);
        if (matcher.find()) {
            hash = matcher.group();
            hash = hash.replace("\"hash\":\"", "");
            hash = hash.replace("\"", "");
        }

        String item = mp3.replace("HASH", hash);
        item = item.replace("TIME", System.currentTimeMillis() + "");
        System.out.println("item:" + item);

        String mp = connect.connect(item, "utf-8");
        mp = mp.substring(mp.indexOf("(") + 1, mp.length() - 3);

        JSONObject json = JSON.parseObject(mp);
        if(Integer.parseInt(json.get("status") + "") != 0){

            String playUrl = json.getJSONObject("data").getString("play_url");
            FileDownload down = new FileDownload();
            down.download(playUrl, filePath + name + ".mp3");
        }

    }

}
View Code
HttpGetConnect.java
package com.billy.test;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.http.HttpEntity;
import org.apache.http.client.config.RequestConfig;
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.impl.conn.BasicHttpClientConnectionManager;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;

/**
 * httpclient 工具类
 */
public class HttpGetConnect {

    /**
     *  获取html内容
     * @param url
     * @param charsetName  UTF-8、GB2312
     * @return
     * @throws IOException
     */
    public static String connect(String url,String charsetName) throws IOException{
        BasicHttpClientConnectionManager connManager = new BasicHttpClientConnectionManager();

        CloseableHttpClient httpclient = HttpClients.custom()
                .setConnectionManager(connManager)
                .build();
        String content = "";

        try{
            HttpGet httpget = new HttpGet(url);

            RequestConfig requestConfig = RequestConfig.custom()
                    .setSocketTimeout(5000)
                    .setConnectTimeout(50000)
                    .setConnectionRequestTimeout(50000)
                    .build();
            httpget.setConfig(requestConfig);
            httpget.setHeader("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8");
            httpget.setHeader("Accept-Encoding", "gzip,deflate,sdch");
            httpget.setHeader("Accept-Language", "zh-CN,zh;q=0.8");
            httpget.setHeader("Connection", "keep-alive");
            httpget.setHeader("Upgrade-Insecure-Requests", "1");
            httpget.setHeader("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36");
            httpget.setHeader("cache-control", "max-age=0");

            httpget.setHeader("Referer","https://www.kugou.com/song/");

            //设置cookie
            httpget.setHeader("Cookie", "kg_mid=9393340fecff864a4d6c4e95099b2be1;");



            CloseableHttpResponse response = httpclient.execute(httpget);

            int status = response.getStatusLine().getStatusCode();
            if (status >= 200 && status < 300) {

                HttpEntity entity = response.getEntity();
                InputStream instream = entity.getContent();
                BufferedReader br = new BufferedReader(new InputStreamReader(instream,charsetName));
                StringBuffer sbf = new StringBuffer();
                String line = null;
                while ((line = br.readLine()) != null){
                    sbf.append(line + "\n");
                }

                br.close();
                content = sbf.toString();
            } else {
                content = "";
            }

        }catch(Exception e){
            e.printStackTrace();
        }finally{
            httpclient.close();
        }
        log.info("content is " + content);
        return content;
    }

    private static Log log = LogFactory.getLog(HttpGetConnect.class);
}
View Code
HtmlManage.java
package com.billy.test;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;

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


/**
 * html manage 工具类
 */
public class HtmlManage {

    public Document manage(String html) {
        Document doc = Jsoup.parse(html);
        return doc;
    }

    public Document manageDirect(String url) throws IOException {
        Document doc = Jsoup.connect(url).get();
        return doc;
    }

    public List<String> manageHtmlTag(Document doc, String tag) {
        List<String> list = new ArrayList<String>();

        Elements elements = doc.getElementsByTag(tag);
        for (int i = 0; i < elements.size(); i++) {
            String str = elements.get(i).html();
            list.add(str);
        }
        return list;
    }

    public List<String> manageHtmlClass(Document doc, String clas) {
        List<String> list = new ArrayList<String>();

        Elements elements = doc.getElementsByClass(clas);
        for (int i = 0; i < elements.size(); i++) {
            String str = elements.get(i).html();
            list.add(str);
        }
        return list;
    }

    public List<String> manageHtmlKey(Document doc, String key, String value) {
        List<String> list = new ArrayList<String>();

        Elements elements = doc.getElementsByAttributeValue(key, value);
        for (int i = 0; i < elements.size(); i++) {
            String str = elements.get(i).html();
            list.add(str);
        }
        return list;
    }

    private static Log log = LogFactory.getLog(HtmlManage.class);
}
View Code
FileDownload.java
package com.billy.test;

import java.io.BufferedInputStream;
import java.io.BufferedOutputStream;
import java.io.File;
import java.io.FileOutputStream;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.http.client.config.RequestConfig;
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;

/**
 * 文件下载工具类
 */
public class FileDownload {

    /**
     * 文件下载
     *
     * @param url  链接地址
     * @param path 要保存的路径及文件名
     * @return
     */
    public static boolean download(String url, String path) {

        boolean flag = false;

        CloseableHttpClient httpclient = HttpClients.createDefault();
        RequestConfig requestConfig = RequestConfig.custom().setSocketTimeout(2000)
                .setConnectTimeout(2000).build();

        HttpGet get = new HttpGet(url);
        get.setConfig(requestConfig);

        BufferedInputStream in = null;
        BufferedOutputStream out = null;
        try {
            for (int i = 0; i < 3; i++) {
                CloseableHttpResponse result = httpclient.execute(get);
                System.out.println(result.getStatusLine());
                if (result.getStatusLine().getStatusCode() == 200) {
                    in = new BufferedInputStream(result.getEntity().getContent());
                    File file = new File(path);
                    out = new BufferedOutputStream(new FileOutputStream(file));
                    byte[] buffer = new byte[1024];
                    int len = -1;
                    while ((len = in.read(buffer, 0, 1024)) > -1) {
                        out.write(buffer, 0, len);
                    }
                    flag = true;
                    break;
                } else if (result.getStatusLine().getStatusCode() == 500) {
                    continue;
                }
            }

        } catch (Exception e) {
            e.printStackTrace();
            flag = false;
        } finally {
            get.releaseConnection();
            try {
                if (in != null) {
                    in.close();
                }
                if (out != null) {
                    out.close();
                }
            } catch (Exception e) {
                e.printStackTrace();
                flag = false;
            }
        }
        return flag;
    }

    private static Log log = LogFactory.getLog(FileDownload.class);
}
View Code

 

 
 
 
 

 

标签:酷狗,Java,String,java,new,爬取,import,apache,org
来源: https://www.cnblogs.com/BillyYoung/p/10962441.html