testhtmlparserlink.java

html 解析处理代码

package org.htmlparser.tests.mytest;

import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.StringFilter;
import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
import org.htmlparser.visitors.HtmlPage;

public class TestHTMLParserLink {

	/**
	 * @param args
	 */
	public static void main(String[] args) {
		try{
	        String sCurrentLine;
	        String sTotalString="";
        java.io.InputStream l_urlStream;
        java.net.URL l_url = new java.net.URL("http://www.chinahr66.com");
        java.net.HttpURLConnection l_connection = (java.net.HttpURLConnection) l_url.openConnection();
        l_connection.connect();
        l_urlStream = l_connection.getInputStream();
        java.io.BufferedReader l_reader = new java.io.BufferedReader(new java.io.InputStreamReader(l_urlStream));
        while ((sCurrentLine = l_reader.readLine()) != null) {
          sTotalString += sCurrentLine+"\r\n";
        }

		String htmlcode = sTotalString;
		Parser parser = Parser.createParser(htmlcode, "GBK");
		HtmlPage page = new HtmlPage(parser);
		try
		{ 
		parser.visitAllNodesWith(page);}
		catch (ParserException e1)
		{ e1 = null;}
		 
//			TableTag[] tt = page.getTables();
//			for (int i=0;i<tt.length;i++){
//				System.out.println(tt[0].getStringText());
//			}
		NodeList nodelist = page.getBody();
		NodeFilter filter = new StringFilter("a href=\"Apply_com_view.asp");
		
		nodelist = nodelist.extractAllNodesThatMatch(filter, true);
		for (int i = 0; i < nodelist.size(); i++)
		{
		LinkTag link=(LinkTag) nodelist.elementAt(i);
		System.out.println(link.getAttribute("href") + "\n");
		} 
		}catch(Exception e){
			e.printStackTrace();
		}
	}
	/**
	 * 获得链接
	 *
	 */
	public void getLink(){
		try{
	        String sCurrentLine;
	        String sTotalString="";
        java.io.InputStream l_urlStream;
        java.net.URL l_url = new java.net.URL("http://www.chinahr66.com");
        java.net.HttpURLConnection l_connection = (java.net.HttpURLConnection) l_url.openConnection();
        l_connection.connect();
        l_urlStream = l_connection.getInputStream();
        java.io.BufferedReader l_reader = new java.io.BufferedReader(new java.io.InputStreamReader(l_urlStream));
        while ((sCurrentLine = l_reader.readLine()) != null) {
          sTotalString += sCurrentLine+"\r\n";
        }

		String htmlcode = sTotalString;
		Parser parser = Parser.createParser(htmlcode, "GBK");
		HtmlPage page = new HtmlPage(parser);
		try
		{ 
		parser.visitAllNodesWith(page);}
		catch (ParserException e1)
		{ e1 = null;}
		NodeList nodelist = page.getBody();
		
		NodeFilter filter = new TagNameFilter("A");
		nodelist = nodelist.extractAllNodesThatMatch(filter, true);
		for (int i = 0; i < nodelist.size(); i++)
		{
		LinkTag link=(LinkTag) nodelist.elementAt(i);
		System.out.println(link.getAttribute("href") + "\n");
		} 
		}catch(Exception e){
			e.printStackTrace();
		}
	}
}