Searching the HTML Stream

Question

I need to search NOT WELL FORMATTED HTML for data extraction. Are there any stream searching library in java.

Answer 1

Hi,
Anil_Pathak wrote:
I need to search NOT WELL FORMATTED HTML for data extraction. Are there any stream searching library in java.If the "NOT WELL FORMATTED" is not too bad, one could extend HTMLDocument and overwrite HTMLDocument.HTMLReader. There the parser callback is involved an so one can overwrite the handleXY methods to get the tags and the text out of the HTML.
Example
import java.io.*;
import javax.swing.text.*;
import javax.swing.text.html.*;
import javax.swing.text.html.parser.*;
class ParseHTML {
  ParseHTML(String myHTML) {
    HTMLEditorKit kit = new HTMLEditorKit();
    try {
      kit.read(new StringReader(myHTML), new MyHTMLDocument(), 0);
    } catch(IOException e) {
      e.printStackTrace();
    } catch(BadLocationException e) {
      e.printStackTrace();
  public static void main(String[] args){
    String myHTML = "<TITLE>Test</TITLE>" +
                               "<P>Paragraph <B>test</B> with bold" +
                               "<TABLE border=1>" +
                               "<TR><TD>Tablecell1.1</TD>" +
                               "<TD>Tablecell1.2</TD>" +
                               "<HR>" +
                               "<IMG src=\"duke.gif\">" +
                               "<P>End";
    ParseHTML phtml = new ParseHTML(myHTML);
  class MyHTMLDocument extends HTMLDocument {
    MyHTMLDocument() {
      super();
    public HTMLEditorKit.ParserCallback getReader(int pos) {
      return new HTMLReader(pos);
    public HTMLEditorKit.ParserCallback getReader(int pos, int popDepth, int pushDepth, HTML.Tag insertTag) {
      return new HTMLReader(pos, popDepth, pushDepth, insertTag);
    class HTMLReader extends HTMLDocument.HTMLReader {
      HTMLReader(int pos) {
        super(pos);
      HTMLReader(int pos, int popDepth, int pushDepth, HTML.Tag insertTag) {
        super(pos, popDepth, pushDepth, insertTag);
      public void handleText(char[] data, int pos) {
        System.out.println("text: " + new String(data));
        super.handleText(data, pos);
      public void handleSimpleTag(HTML.Tag t, MutableAttributeSet a, int pos) {
        System.out.println("simple tag: " + t + " Attributes: " + a);
        super.handleSimpleTag(t, a, pos);
      public void handleStartTag(HTML.Tag t, MutableAttributeSet a, int pos) {
        System.out.println("start tag: " + t + " Attributes: " + a);
        super.handleStartTag(t, a, pos);
      public void handleEndTag(HTML.Tag t, int pos) {
        System.out.println("end tag: " + t);
        super.handleEndTag(t, pos);
}greetings
Axel