conversion of html to txt problem
hi everybody,
import java.io.*;
import javax.swing.*;
import javax.swing.text.*;
import javax.swing.text.html.*;
import javax.swing.text.html.parser.*;
public class TextFromHtml extends HTMLEditorKit.ParserCallback{
private PrintWriter pw;
private boolean furtherCalls = false;
public TextFromHtml(File outputFile) throws IOException {
pw = new PrintWriter(new BufferedWriter(new FileWriter(outputFile, false)));
}
public void handleText(char[] data, int pos){
//place ' ' between calls to handlText
if (furtherCalls) {
pw.write(' ');
}
furtherCalls = true;
boolean printSpace = false;
for(int i=0; i<data.length; ++i) {
char ch = data;
boolean notSpace = !Character.isSpaceChar(ch);
if (notSpace || printSpace) {
pw.write(ch);
}
printSpace = notSpace;
}
}
public void flush() {
pw.close();
}
public static void main(String args[]) throws IOException {
ParserDelegator parser = new ParserDelegator();
TextFromHtml app = new TextFromHtml(new File("2.txt"));
parser.parse(new FileReader("MyApplet.html"), app, true);
app.flush();
}
}
i am trying to use the above given code to convert html document to pure text....
but i hv a problem...
><style type="text/css">
.petstore {
font-family: Helvetica, Arial, sans-serif;
font-size: small;
}
.petstore_title {
font-family: Helvetica, Arial, sans-serif;
font-weight: bold;
}
.petstore_footer {
font-family: Helvetica, Arial, sans-serif;
font-size: x-small;
}
.petstore_listing {
font-family: Helvetica, Arial, sans-serif;
font-size: x-small;
}
.petstore_form {
font-family: Helvetica, Arial, sans-serif;
font-size: x-small;
}
</style>
the text between <style> and </style> is not getting removed ...but i want it also to be eliminated....anybody help me.....

