Package: javax.swing.text.* |
Product: JDK |
Release: 1.2 |
Related Links: |
General
JEditorPane
PlainDocument
|
Comment: |
** * Insert the method's description here. * Creation date: (11/23/00 10:39:44 PM) */ public void read() throws Exception { Reader in = new FileReader("index.html"); //HTMLReader.MyParser p = new HTMLReader.MyParser(DTD.getDTD("HTML")); //p.parse(in); //HTMLEditorkit contains HTML parser. Creates structured Document object that //models HTML: 'text storage model' HTMLEditorKit editorKit = new HTMLEditorKit(); HTMLDocument HTMLDoc = (HTMLDocument) editorKit.createDefaultDocument(); // The Document class does not yet handle character sets properly HTMLDoc.putProperty("IgnoreCharsetDirective", Boolean.TRUE); try { //Create a reader on the HTML content of inputted page Reader HTMLReader = in; //Parse the HTML using EditorKit's read() method. Inserts content from input //stream (above) into HTMLDoc editorKit.read(HTMLReader, HTMLDoc, 0); //Iterate through the elements of the HTML doc ElementIterator iterator = new ElementIterator(HTMLDoc); //Interface to describe structural piece of doc (token) javax.swing.text.Element elem; while ((elem = iterator.next()) != null) { SimpleAttributeSet sas = (SimpleAttributeSet) //StyleContext.NameAttribute attribute elem.getAttributes().getAttribute(HTML.Tag.A); if (sas != null) { System.out.println(sas.getAttribute(HTML.Attribute.HREF)); } } } catch (Exception e) { e.printStackTrace(); } System.exit(1); } |