Example usage for javax.swing.text EditorKit createDefaultDocument

Introduction

In this page you can find the example usage for javax.swing.text EditorKit createDefaultDocument.

Prototype

public abstract Document createDefaultDocument();

Source Link

Document

Creates an uninitialized text storage model that is appropriate for this type of editor.

Usage

From source file:Main.java

public static void main(String[] argv) throws Exception {
    URL url = new URI("http://www.google.com").toURL();
    URLConnection conn = url.openConnection();
    Reader rd = new InputStreamReader(conn.getInputStream());

    EditorKit kit = new HTMLEditorKit();
    HTMLDocument doc = (HTMLDocument) kit.createDefaultDocument();
    kit.read(rd, doc, 0);/*  w  ww .  j av  a2  s  . c om*/

    HTMLDocument.Iterator it = doc.getIterator(HTML.Tag.A);
    while (it.isValid()) {
        SimpleAttributeSet s = (SimpleAttributeSet) it.getAttributes();

        String link = (String) s.getAttribute(HTML.Attribute.HREF);
        if (link != null) {
            System.out.println(link);
        }
        it.next();
    }
}

---

From source file:HTML.java

/**
 * Utility method to convert HTML to text.
 * @param html The string containing HTML.
 * @return a String containing the derived text .
 *//*from   w  w  w.ja v  a  2  s  .  c  o m*/
public static final String html2text(String html) {
    EditorKit kit = new HTMLEditorKit();
    Document doc = kit.createDefaultDocument();
    doc.putProperty("IgnoreCharsetDirective", Boolean.TRUE);
    try {
        Reader reader = new StringReader(html);
        kit.read(reader, doc, 0);
        return doc.getText(0, doc.getLength());
    } catch (Exception e) {

        return "";
    }
}

---

From source file:org.python.pydev.core.docutils.StringUtils.java

/**
 * Given some html, extracts its text.//from   w  w w.j  av  a  2 s .c om
 */
public static String extractTextFromHTML(String html) {
    try {
        EditorKit kit = new HTMLEditorKit();
        Document doc = kit.createDefaultDocument();

        // The Document class does not yet handle charset's properly.
        doc.putProperty("IgnoreCharsetDirective", Boolean.TRUE);

        // Create a reader on the HTML content.
        Reader rd = new StringReader(html);

        // Parse the HTML.
        kit.read(rd, doc, 0);

        //  The HTML text is now stored in the document
        return doc.getText(0, doc.getLength());
    } catch (Exception e) {
    }
    return "";
}

---