com.quiotix.html.parser
Class HtmlStripper

java.lang.Object
  com.quiotix.html.parser.HtmlVisitor
      com.quiotix.html.parser.HtmlDumper
          com.quiotix.html.parser.HtmlStripper

public class HtmlStripper
extends HtmlDumper

A runnable class intended to produce readable, sparse html from formatted pages.

Author:

timp

Field Summary

protected static Set	html1BlockTags
protected static String[]	html1BlockTagStrings
protected static Set	html1EmptyTags
protected static String[]	html1EmptyTagStrings
protected static Set	html1Tags
protected static String[]	html4BlockTagStrings

Fields inherited from class com.quiotix.html.parser.HtmlDumper

out

Constructor Summary

HtmlStripper(OutputStream os)

HtmlStripper(OutputStream os, String encoding)

Method Summary

static void	main(String[] args) Runnable.
void	visit(HtmlDocument.Comment comment) Visit a Comment.
void	visit(HtmlDocument.Tag t) Visit a Tag.
void	visit(HtmlDocument.TagBlock tagBlock) Visit a TagBlock.

Methods inherited from class com.quiotix.html.parser.HtmlDumper

finish, visit, visit, visit, visit

Methods inherited from class com.quiotix.html.parser.HtmlVisitor

start, visit, visit

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

html1BlockTags

protected static Set html1BlockTags

html1EmptyTags

protected static Set html1EmptyTags

html1Tags

protected static Set html1Tags

html1EmptyTagStrings

protected static String[] html1EmptyTagStrings

html1BlockTagStrings

protected static String[] html1BlockTagStrings

html4BlockTagStrings

protected static String[] html4BlockTagStrings

Constructor Detail

HtmlStripper

public HtmlStripper(OutputStream os)

Parameters:

os -

HtmlStripper

public HtmlStripper(OutputStream os,
                    String encoding)
             throws UnsupportedEncodingException

Parameters:

os -

encoding -

Throws:

UnsupportedEncodingException

Method Detail

visit

public void visit(HtmlDocument.TagBlock tagBlock)

Description copied from class: HtmlVisitor

Visit a TagBlock.

Overrides:

visit in class HtmlVisitor

visit

public void visit(HtmlDocument.Tag t)

Description copied from class: HtmlVisitor

Visit a Tag.

Overrides:

visit in class HtmlDumper

visit

public void visit(HtmlDocument.Comment comment)

Description copied from class: HtmlVisitor

Visit a Comment.

Overrides:

visit in class HtmlDumper

main

public static void main(String[] args)
                 throws Exception

Runnable.

Throws:

Exception