用java解析html标签

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.Reader;
import java.io.StringReader;
import java.io.StringWriter;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.Set;

import com.hothouseobjects.tags.Inspector;
import com.hothouseobjects.tags.Tag;
import com.hothouseobjects.tags.TagTiller;
import com.hothouseobjects.tags.Text;

public class ParseHtml {

public static void main(String[] args) {
try {
File file = new File("d://ttt.htm");
int len = (int)file.length();
byte[] b;
b = new byte[len];
FileInputStream fis = new FileInputStream(file);
fis.read(b);
fis.close();
Reader read;
read = new StringReader(new String(b));

TagTiller tagtiller = new TagTiller(read);
tagtiller.runTiller();
Tag thePage = tagtiller.getTilledTags();
// search <a href=......
List theHref = Inspector.collectByType(thePage,"a");
int i = theHref.size();
while (i>0) {
//System.out.println(((Tag)theHref.get(i-1)).toHTML());
System.out.println(((Tag)theHref.get(i-1)).getAttributeValue("href"));
// System.out.println(((Tag)theHref.get(i-1)).getAttributeValue("target"));
// System.out.println(((Tag)theHref.get(i-1)).getItem(0).toHTML());
i -=1;
}
// search <img src=.....
List theImg = Inspector.collectByType(thePage,"img");
int j = 0;
while (j < theImg.size()) {
System.out.println(((Tag)theImg.get(j)).toHTML());
System.out.println(((Tag)theImg.get(j)).getAttributeValue("src"));
System.out.println(((Tag)theImg.get(j)).getAttributeValue("alt"));
j +=1;
}
// out put file of html
Tag big = new Tag ("H1");
Tag red = new Tag ("FONT");
Tag underlined = new Tag ("U");

red.setAttribute ("color", "#CCOOOO");
big.addItem (red);
red.addItem (underlined);
underlined.addItem (new Text ("Sorry, no addresses found."));
Tag title = Inspector.locateByType(thePage,"title");
title.addItem(big);

StringWriter writer = new StringWriter();
thePage.toHTML(writer);
File file1 = new File("test000.html");

FileOutputStream fos = new FileOutputStream(file1);

fos.write(writer.toString().getBytes());
fos.close();
// search of <table
List theTd = Inspector.collectByType(thePage,"td");
int k = 0;
while (k < theTd.size()) {
System.out.println(((Tag)theTd.get(k)).toHTML());
k +=1;
}
}
catch (Exception ex) {
ex.printStackTrace();
}
}

}