java爬取并下载酷狗TOP500歌曲的方法

是这样的，之前买车送的垃圾记录仪不能用了，这两天狠心买了好点的记录仪，带导航、音乐、蓝牙、4g等功能，寻思，既然有这些功能就利用起来，用4g听歌有点奢侈，就准备去酷狗下点歌听，居然都是需要办会员才能下载，而且vip一月只能下载300首，我这么穷又这么抠怎么可能冲会员，于是百度搜了下怎么免费下载，都是python爬取，虽然也会一点，但是电脑上没安装python，再安装再研究感觉有点费劲，于是就花了半小时做了这个爬虫，技术一般，只记录分析实现过程，大牛请绕行。其中用到了一些库，包括：jsoup、httpclient、net.sf.json大家可以自行去下载jar包

1、分析是否能获得top500歌单

首先，打开酷狗首页查看酷狗top500，说好的500首，怎么就只有22首呢，

是真的只让看这些还是能找到其余的呢，于是我就看了下这top500的链接

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

可以看的出home后边有个1，难道这是代表第一页的意思？于是我就把1改成2，进入，果然进入了第二页，至此可以知道我们可以在网页里获取这500首的歌单。

2.分析找到真正的mp3下载地址（这个有点绕）

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，分析细节就不用说了，

最终我在列表的

https://wwwapi.kugou.com/yy/index.php?r=play/getdata&callback=jquery191027067069941080546_1546235744250&hash=667939c6e784265d541deee65ae4f2f8&album_id=0&_=1546235744251

这个请求里发现了mp3的完整地址，

"play_url": "http:\/\/fs.w.kugou.com\/201812311325\/dcf5b6449160903c6ee48035e11434bb\/g128\/m08\/02\/09\/iicbafrzqf2anoadadn94ubomau995.mp3",

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.java实现爬取酷狗mp3

先看一下爬取结果

找到了资源，程序实现就好说了，其中使用到了自己写的几个工具类，自己整理点自己的工具类还是有好处的，以后遇到什么问题就没必要重新写了，直接拿来用就可以了。没什么好说的了，下面直接贴出源码

spiderkugou.java

package com.bing.spider;

import java.io.ioexception;
import java.util.regex.matcher;
import java.util.regex.pattern;

import org.jsoup.nodes.document;
import org.jsoup.nodes.element;
import org.jsoup.select.elements;

import com.bing.download.filedownload;
import com.bing.html.htmlmanage;
import com.bing.http.httpgetconnect;

import net.sf.json.jsonobject;

public class spiderkugou {

	public static string filepath = "f:/music/";
	public static string mp3 = "https://wwwapi.kugou.com/yy/index.php?r=play/getdata&callback=jquery191027067069941080546_1546235744250&"
			+ "hash=hash&album_id=0&_=time";
	
	public static string link = "https://www.kugou.com/yy/rank/home/page-8888.html?from=rank";
	//"https://www.kugou.com/yy/rank/home/page-23784.html?from=rank";
	
	
	public static void main(string[] args) throws ioexception {
		
		for(int i = 1 ; i < 23 ; i++){
			string url = link.replace("page", i + "");
			gettitle(url);
			//download("https://www.kugou.com/song/mfy6je5.html");
		}
	}
	
	public static string gettitle(string url) throws ioexception{
		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 eles = ele.getelementsbytag("li");
		for(int i = 0 ; i < eles.size() ; i++){
			element item = eles.get(i);
			string title = item.attr("title").trim();
			string link = item.getelementsbytag("a").first().attr("href");
			
			download(link,title);
		}
		return null;
	}
	
	public static string download(string url,string name) throws ioexception{
		string hash = "";
		httpgetconnect connect = new httpgetconnect();
		string content = connect.connect(url, "utf-8");
		htmlmanage html = new htmlmanage();
		
		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);
		string mp = connect.connect(item, "utf-8");
		
		mp = mp.substring(mp.indexof("(") + 1, mp.length() - 3);
		
		jsonobject json = jsonobject.fromobject(mp);
		string playurl = json.getjsonobject("data").getstring("play_url");
		

		system.out.print(playurl + " == ");
		filedownload down = new filedownload();
		down.download(playurl, filepath + name + ".mp3");
		
		system.out.println(name + "下载完成");
		return playurl;
	}

}

httpgetconnect.java

package com.bing.http;

import java.io.bufferedreader;
import java.io.ioexception;
import java.io.inputstream;
import java.io.inputstreamreader;
import java.security.nosuchalgorithmexception;
import java.security.cert.certificateexception;
import java.security.cert.x509certificate;

import javax.net.ssl.sslcontext;
import javax.net.ssl.trustmanager;
import javax.net.ssl.x509trustmanager;

import org.apache.commons.logging.log;
import org.apache.commons.logging.logfactory;
import org.apache.http.httpentity;
import org.apache.http.client.clientprotocolexception;
import org.apache.http.client.httpclient;
import org.apache.http.client.responsehandler;
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.conn.clientconnectionmanager;
import org.apache.http.conn.scheme.scheme;
import org.apache.http.conn.scheme.schemeregistry;
import org.apache.http.conn.ssl.sslsocketfactory;
import org.apache.http.impl.client.basicresponsehandler;
import org.apache.http.impl.client.closeablehttpclient;
import org.apache.http.impl.client.defaulthttpclient;
import org.apache.http.impl.client.httpclients;
import org.apache.http.impl.conn.basichttpclientconnectionmanager;
import org.apache.http.params.httpparams; 
/**
 * @说明：
 * @author: gaoll
 * @createtime:2014-11-13
 * @modifytime:2014-11-13
 */
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("hosts", "www.oschina.net");
	    httpget.setheader("cache-control", "max-age=0"); 
		  
			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);
}

htmlmanage.java

package com.bing.html;

import java.io.ioexception;
import java.util.arraylist;
import java.util.list;

import org.apache.commons.logging.log;
import org.apache.commons.logging.logfactory;
import org.jsoup.jsoup;
import org.jsoup.nodes.document;
import org.jsoup.nodes.element;
import org.jsoup.select.elements;

import com.bing.http.httpgetconnect;

/**
 * @说明：
 * @author: gaoll
 * @createtime:2014-11-13
 * @modifytime:2014-11-13
 */
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);
}

filedownload.java

package com.bing.download;

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;

/**
 * @说明：
 * @author: gaoll
 * @createtime:2014-11-20
 * @modifytime:2014-11-20
 */
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);
}

到这就结束了，有可能有些代码没贴全，主要代码已经差不多，应该可以跑起来，多多指教。

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。