searcher.java

实现从某个网站的全部遍历

package com.yinyueku;

import java.sql.*;
import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.HasAttributeFilter;
import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;

public class Searcher {

	/**
	 * @param args
	 */
	// String searchUrl = "http://www.yinyueku.com/gequ/45.htm";
	// String searchUrl;
	String strSongName;

	String strListenUrl;

	String strZhuanji;

	String strGeciUrl;

	// String strGeciUrl1;
	String strDownload;

	// String strDownload1;
	String strDownloadUrl;

	// String strLingsheng;

	// String strLink;
	// String strSingerClassName;
	// String strSingerClassUrl;
	// String strSingerName;
	// String strSingerUrl;
	// 打印一行用来检查程序执行状况
	// System.out.println("11111");
	public Searcher(String url) {
		try {
			Parser parser = new Parser(url);
			parser.setEncoding("gb2312");
			HasAttributeFilter fil = new HasAttributeFilter();
			fil.setAttributeName("align");
			fil.setAttributeValue("left");
			// 打印检查程序是否进入遍历指定网页
			// System.out.println("22222");
			// 将符合自定义属性的节点存取下来
			NodeList list = parser.parse(fil);
			System.out.println(list.size());

			// 对每一个符合标准的属性进行操作
			for (int i = 0; i < (list.size() - 1); i++) {
				System.out.println();

				Node node1 = list.elementAt((i + 1));
				// if ((node1.getText().substring(0, 2)) == "TD") {
				// i++;
				// System.out.println(node1.getText());
				// }else{
				// 音乐名称
				Node node11 = node1.getFirstChild().getFirstChild();
				strSongName = node11.toPlainTextString();
				System.out.println(strSongName);
				// 试听地址
				LinkTag linkTag1 = (LinkTag) node11;
				strListenUrl = linkTag1.getLink();
				System.out.println("试听地址：" + strListenUrl);
				// 专辑名称
				Node node2 = node1.getNextSibling().getNextSibling()
						.getNextSibling().getNextSibling();
				System.out.println(node2.getText());
				// System.out.println("33333");
				Node node21 = node2.getFirstChild();
				strZhuanji = node21.toPlainTextString();
				System.out.println("专辑名：" + strZhuanji);

				// 歌词地址
				Node node3 = node2.getNextSibling().getNextSibling();
				// System.out.println("33333");
				Node node31 = node3.getFirstChild();
				LinkTag LinkTag3 = (LinkTag) node31;
				// 还不是完整的地址,需要进一步进行字符串的处理
				strGeciUrl = LinkTag3.getLink();
				System.out.println(strGeciUrl);
				if (strGeciUrl.length() > 0)
					strGeciUrl = strGeciUrl.substring(strGeciUrl.indexOf("(")+1,strGeciUrl.indexOf(")"));
				System.out.println("歌词地址："
						+ "http://www.yinyueku.com/user/showgeci.asp?id="
						+ strGeciUrl);

				// 下载页面地址
				Node node4 = node3.getNextSibling().getNextSibling()
						.getNextSibling().getNextSibling();
				Node node41 = node4.getFirstChild();
				LinkTag linkTag4 = (LinkTag) node41;
				// 还不是完整的地址,需要进行字符串的处理
				strDownload = linkTag4.getLink();
				System.out.println(strDownload);
				if (strDownload.length() > 5)
					strDownload = strDownload.substring(strDownload.indexOf("(")+1,strDownload.indexOf(")"));
				strDownload = "http://www.yinyueku.com/user/qq570_down.asp?id="
						+ strDownload;
				System.out.println("下载页面：" + strDownload);
				System.out.println("本页歌曲相关信息搜索完毕");

				// 进一步遍历下载页面,得到音乐文件的真正地址
				/*
				Parser ps = new Parser("c:\\下载地址.txt");
				ps.setEncoding("gb2312");
				HasAttributeFilter f = new HasAttributeFilter();
				f.setAttributeName("height");
				f.setAttributeValue("9%");
				NodeList items = ps.parse(f);
				System.out.println(items.size());
				for (int j = 0; j < items.size(); j++) {
					Node n = items.elementAt(j);
					System.out.println(n.getText());
					Node n1 = n.getFirstChild();
					System.out.println(n1.getText());
					LinkTag linkTag = (LinkTag)n1;
					strDownloadUrl = linkTag.getLink();
					System.out.println("下载地址：" + strDownloadUrl);
					System.out.println("本首歌曲相关信息完毕");
				}*/

				// 插入数据库
				/*
				 * try { //建立连接
				 * Class.forName("com.microsoft.jdbc.sqlserver.SQLServerDriver");
				 * 
				 * Connection con = DriverManager.getConnection(
				 * "jdbc:microsoft:sqlserver://localhost:1433;DatabaseName=chenlei",
				 * "sa", "12345"); Statement stmt = con.createStatement();
				 * //stmt.executeUpdate("CREATE TABLE SINGERS "+ "(SINGER_NAME
				 * VARCHAR(32), SINGER_URL VARCHAR(64))"); String sql="Insert
				 * into SINGERS003
				 * values('"+strSingerName+"','"+strSingerUrl+"')";
				 * System.out.println(sql); stmt.executeUpdate(sql);
				 * 
				 * System.out.println("Insert into table ok!"); } catch
				 * (Exception e) { e.printStackTrace(); } }
				 */

			}
			// }

		} catch (ParserException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		try{
			Parser ps = new Parser(url);
			ps.setEncoding("gb2312");
			HasAttributeFilter fil = new HasAttributeFilter();
			fil.setAttributeName("color");
			fil.setAttributeValue("#000000");
			// 打印检查程序是否进入遍历指定网页
			// System.out.println("22222");
			// 将符合自定义属性的节点存取下来
			//NodeList list = ps.parse (new TagNameFilter("td"));
			NodeList list = ps.parse(fil);
			System.out.println(list.size());
			Node nodecenter=list.elementAt(0);
			System.out.println(nodecenter.toHtml());
			Node nodecenter1=nodecenter.getNextSibling();
			System.out.println(nodecenter1.toHtml());
			Node nodecenter2=nodecenter1.getNextSibling();
			System.out.println(nodecenter2.toHtml());
			Node nodecenter3=nodecenter2.getNextSibling();
			System.out.println(nodecenter3.toHtml());
			boolean b=nodecenter3.toHtml().endsWith("[后一页]  [尾 页]");
			System.out.println(b);
			if(!b)
			{	Node nodecenter4=nodecenter3.getNextSibling();
			System.out.println(nodecenter4.toHtml());
			LinkTag a=(LinkTag)nodecenter4;
			System.out.println(a.getLink());
			
			//Searcher search1 = new Searcher(a.getLink());
			Searcher search1 = new Searcher(a.getLink());
			System.out.println("c");
			}
			System.out.println("本歌手所有歌曲搜索完毕");
			}catch(Exception e){
				e.printStackTrace();
			}


	}


	public static void main(String[] args) {
		// TODO Auto-generated method stub
		// String htmfile = "C:\\search.htm";
		// String searchUrl = "c:\\45歌曲.txt";
		String searchUrl = "http://www.yinyueku.com/gequ/1.htm";
		Searcher search = new Searcher(searchUrl);
		//String searchUrl2 = "c:\\45_2.htm";
		//Searcher search2 = new Searcher(searchUrl);
		/*try{
		Parser ps = new Parser(searchUrl);
		ps.setEncoding("gb2312");
		HasAttributeFilter fil = new HasAttributeFilter();
		fil.setAttributeName("color");
		fil.setAttributeValue("#000000");
		// 打印检查程序是否进入遍历指定网页
		// System.out.println("22222");
		// 将符合自定义属性的节点存取下来
		//NodeList list = ps.parse (new TagNameFilter("td"));
		NodeList list = ps.parse(fil);
		System.out.println(list.size());
		Node nodecenter=list.elementAt(0);
		System.out.println(nodecenter.toHtml());
		Node nodecenter1=nodecenter.getNextSibling();
		System.out.println(nodecenter1.toHtml());
		Node nodecenter2=nodecenter1.getNextSibling();
		System.out.println(nodecenter2.toHtml());
		Node nodecenter3=nodecenter2.getNextSibling();
		System.out.println(nodecenter3.toHtml());
		boolean b=nodecenter3.toHtml().endsWith("[后一页]  [尾 页]");
		System.out.println(b);
		if(!b)
		{	Node nodecenter4=nodecenter3.getNextSibling();
		System.out.println(nodecenter4.toHtml());
		LinkTag a=(LinkTag)nodecenter4;
		System.out.println(a.getLink());
		
		//Searcher search1 = new Searcher(a.getLink());
		Searcher search1 = new Searcher(a.getLink());
		System.out.println("c");}
        
		//Node nodecenter1=nodecenter.getLastChild();
		//System.out.println(nodecenter1.toHtml());
	    //Node nodecenter2=nodecenter1.getNextSibling().getNextSibling().getNextSibling().getNextSibling();
		System.out.println("完毕");
		}catch(Exception e){
			e.printStackTrace();
		}*/

	}

}