抓取百度Top500歌曲以及地址源码

在我整理完在线听歌(http://ting.faqee.com/)的模块后，剩下来的工作就是如何通过程序抓取最新的Baidu好听的歌曲，抓取的工作主要包括3个属性：歌名、歌曲在线播放地址和歌词内容（符合LRC歌词格式），目前完成歌曲和歌曲地址抓取，由于百度的歌曲地址很多通过js获取，所以歌曲地址获取我这里使用搜狗音乐搜索方便些，所有的源码如下：

package com.common.utils;

import java.io.BufferedReader;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.io.UnsupportedEncodingException;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;
import java.net.URLDecoder;
import java.net.URLEncoder;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;
import java.util.TreeSet;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.filters.OrFilter;
import org.htmlparser.nodes.TextNode;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;

import com.common.doc.FileOperUtils;


class Song{
	private String name;
	private String url;
	private String lrc;
	public Song(String name,String url){
		this.name = name;
		this.url = url;
		this.lrc = "";
	}
	public String getName() {
		return name;
	}
	public void setName(String name) {
		this.name = name;
	}
	public String getUrl() {
		return url;
	}
	public void setUrl(String url) {
		this.url = url;
	}
	public String getLrc() {
		return lrc;
	}
	public void setLrc(String lrc) {
		this.lrc = lrc;
	}
	
}

public class BaiduMp3 {
	
	public static String visitURL(String strUrl) {
		URL url = null;
		try {
			url = new URL(strUrl);
		} catch (MalformedURLException e) {
			e.printStackTrace();
		}
		URLConnection conn = null;
		try {
			conn = url.openConnection();
			conn.setDoOutput(true);
		} catch (IOException e) {
			System.out.println("e:"+e.getMessage());
		}
		OutputStreamWriter out;
		try {
			out = new OutputStreamWriter(conn.getOutputStream(), "GBK");
			out.flush();
			out.close();

		} catch (UnsupportedEncodingException e2) {

			e2.printStackTrace();
		} catch (IOException e2) {

			e2.printStackTrace();
		}

		// 接收返回信息
		BufferedReader rd = null;
		try {
			rd = new BufferedReader(
					new InputStreamReader(conn.getInputStream()));
			return rd.readLine();
		} catch (IOException e1) {
			e1.printStackTrace();
		}
		return "";
	}
	
	
	/**
	* 功能说明：访问指定的URL并检查返回结果。
	* @param strUrl
	* @param successFlag 请求成功的标识，比如包含“_SUCCESS”字。
	* @return
	*/
	public static String visitURL(String strUrl, String successFlag) {
	    
	    boolean rs = false;
	    HttpURLConnection jconn = null;
	    ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();

	    try {
	        URL url = new URL(strUrl);

	        jconn = (HttpURLConnection) url.openConnection();
	        jconn.setDoOutput(true);
	        jconn.setDoInput(true);
	        jconn.connect();
	        
	        InputStream in = jconn.getInputStream();
	        byte[] buf = new byte[4096];

	        int bytesRead;
	        while ((bytesRead = in.read(buf)) != -1) {
	            byteArrayOutputStream.write(buf, 0, bytesRead);
	        }

	        String strRead = new String(byteArrayOutputStream.toByteArray(),"GBK");
	        
	        
	        return strRead;
	        
	        
	    } catch (MalformedURLException e) {
	        e.printStackTrace();
	    } catch (IOException e) {
	        e.printStackTrace();
	    } finally {
	        jconn.disconnect();

	        try {
	            byteArrayOutputStream.close();
	        } catch (IOException e) {
	            e.printStackTrace();
	        }
	    }
	    
	    return "";
	}
	
	private static boolean isTrimEmptyOrBlank(String astr) {
		if ((null == astr) || (astr.length() == 0) || " ".equals(astr)) {
			return true;
		}
		astr = astr.trim();
		if ((null == astr) || (astr.length() == 0)) {
			return true;
		}
		return false;
	}

	private static String getFilteredContent(String htmlContent, String reg,int i) {
		String content = "";
		int k=1;
		Pattern pp = Pattern.compile(reg, Pattern.DOTALL);
		Matcher m = pp.matcher(htmlContent);
		while (m.find()) {
			content = m.group();
			if(k++==i)
				break;
		}
		return content;
	}	
	
	public static List<Song> getBaiduSongs(){
		List<Song> ss = new ArrayList();
		
		String htmlContent = visitURL("http://list.mp3.baidu.com/topso/mp3topsong.html?id=1?top2","s");
		String encode = "GBK";
		
//		System.out.println("===========================================================================");
//		System.out.println(htmlContent);
//		System.out.println("===========================================================================");
		String reg = "<table width=\"100%\" align=\"center\" cellpadding=\"0\" cellspacing=\"0\" class=\"list\">(.*?)</table>";
		htmlContent = getFilteredContent(htmlContent,reg,0);
		//FileOperUtils.writeFile("c:\\1.html", htmlContent, false);
		
		String line = "",lineurl="";
		Node anode = null;
		TextNode textnode = null;
		try {
			Parser parser = Parser.createParser(htmlContent, encode);
			NodeClassFilter textFilter = new NodeClassFilter(LinkTag.class);
			
			OrFilter lastFilter = new OrFilter();
			lastFilter.setPredicates(new NodeFilter[] { textFilter });

			NodeList nodeList = parser.parse(lastFilter);

			Node[] nodes = nodeList.toNodeArray();
			for (int i = 0; i < nodes.length; i++) {
				anode = (Node) nodes[i];

				if(anode instanceof LinkTag){
					LinkTag txt = (LinkTag)anode;
					line = txt.getLinkText();
					if(txt.getPreviousSibling()!=null){
						if(txt.getPreviousSibling().toString().indexOf("(")>=0)
							continue;
					}
					line = txt.getLinkText();
					lineurl = txt.getAttribute("href");	
					
					//System.out.println(txt.getLink());
				}

				if (isTrimEmptyOrBlank(line)||isTrimEmptyOrBlank(lineurl))
					continue;

				ss.add(new Song(line,getSongURL(line)));
			}
		} catch (ParserException pe) {
			pe.printStackTrace();
		}
		return ss;
	}
	
	private static String getSongURL(String songname){
		try {
		String ss = URLEncoder.encode(songname,"GBK");
		String htmlContent = visitURL("http://so.mp3.qihoo.com/?type=0&src=s&kw="+ss,"s");
		String encode = "GBK";
		
		String reg = "<table width=\"100%\" border=\"0\" cellspacing=\"0\" cellpadding=\"0\">(.*?)</table>";
		htmlContent = getFilteredContent(htmlContent,reg,1);
		
		String line = "",lineurl="";
		Node anode = null;
		TextNode textnode = null;
		
			Parser parser = Parser.createParser(htmlContent, encode);
			NodeClassFilter textFilter = new NodeClassFilter(LinkTag.class);
			
			OrFilter lastFilter = new OrFilter();
			lastFilter.setPredicates(new NodeFilter[] { textFilter });

			NodeList nodeList = parser.parse(lastFilter);

			Node[] nodes = nodeList.toNodeArray();
			for (int i = 0; i < nodes.length; i++) {
				anode = (Node) nodes[i];

				if(anode instanceof LinkTag){
					LinkTag txt = (LinkTag)anode;
					line = txt.getLinkText();
					lineurl = txt.getAttribute("href");	
					if(!isTrimEmptyOrBlank(lineurl) && lineurl.startsWith("down.html")){
						String s = getFilteredContent(lineurl,"u=(.*?)\\&",0);
						if(!s.equals("")&&s.length()>5){
							s = Utils.replace(s, "u=", "");
							s = Utils.replace(s, "&", "");
							s = URLDecoder.decode(s,"GBK");
							return s;
						}
					}
				}
			}
		} catch (Exception pe) {
			pe.printStackTrace();
		}
		return "";		
	}
	
	public static void main(String[] args) throws Exception{
		List<Song> ss = getBaiduSongs();
		int idx = 0;
		for(Song s:ss){
			System.out.println((++idx)+":"+s.getName()+"->"+s.getUrl());
		}
//		String ss = getSongURL("国家");
//		System.out.println(ss);
		
//		String s = URLDecoder.decode("http%3A%2F%2Fwww.yuelin.net%2F%B9%FA%BC%D2.mp3","GBK");
//		System.out.println(s);
	}
}