Java爬取并下载酷狗TOP500歌曲（java爬取公众号文章并生成html）

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。

（完）

来源：my.oschina.net/gllfeixiang/blog/2995570?p=1