newsearch.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 Newsearch {

	/**
	 * @param args
	 */
	public static void main(String[] args) {
		// TODO Auto-generated method stub
		// String htmfile = "C:\\qq.txt";
		String searchUrl = "http://202.108.23.172/m?ct=134217728&tn=baidusg,今天你要嫁给我  &word=mp3,http://810115.homegz.cn/userblog/wy86892/Y2JjamZmaG9iZ2RmaWdqaGky.mp3,,[%BD%F1%CC%EC%C4%E3%D2%AA%BC%DE%B8%F8%CE%D2+%CC%D5%86%B4%2B%B2%CC%D2%C0%C1%D6]&si=%BD%F1%CC%EC%C4%E3%D2%AA%BC%DE%B8%F8%CE%D2;;%B2%CC%D2%C0%C1%D6+%CC%D5%86%B4;;0;;0&lm=16777216";
		// String strName;
		// String strLink;
		
		try {
			Parser parser = new Parser(searchUrl);
			parser.setEncoding("gb2312");
		    HasAttributeFilter fil = new HasAttributeFilter();
			fil.setAttributeName("style");
			fil.setAttributeValue("margin-right:10px;");
			
			NodeList items = parser.parse(fil);
			//NodeList items = parser.parse(null);
			System.out.println(items.size());
			
			for(int i = 0; i < items.size(); i++) {
				Node n = items.elementAt(i);
				System.out.println(n.toString());
				System.out.println(n.toHtml());
				Node n1 = n.getFirstChild();
				System.out.println(n1.getText());
				LinkTag linkTag = (LinkTag)n1;
				String strDownloadUrl = linkTag.getLink();
				System.out.println("下载地址：" + strDownloadUrl);
				System.out.println("本首/歌曲相关信息完毕");
				
				
				// System.out.println(((LinkTag)node).getLink());
				/*
				 * JoyoProduct p = new JoyoProduct(); p.setParent(node);
				 * p.update(); System.out.println(p.getStrName());
				 * System.out.println(p.getStrLink());
				 * System.out.println(p.getStrPublish());
				 * System.out.println(p.getStrAuthor());
				 * System.out.println(p.getStrPrice()); Parser ps = new
				 * Parser(p.getStrLink()); // NodeList nl = ps.parse(null);
				 * HasAttributeFilter f = new HasAttributeFilter();
				 * f.setAttributeName("class"); f.setAttributeValue("dark");
				 * NodeList items = ps.extractAllNodesThatMatch(f); for(int j =
				 * 0; j < items.size(); j++) { Node n = items.elementAt(j);
				 * NodeList nl = n.getParent().getChildren(); int idx =
				 * nl.indexOf(n); System.out.println("--" + nl.elementAt(idx +
				 * 1).toPlainTextString()); }
				 */
			}
			
			
		} catch (ParserException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		
		
	}	
	}