The Java Developers Almanac 1.4

Home > List of Packages > javax.swing.text.html [2 examples]
e1018. Getting the Text in an HTML Document

    // This method takes a URI which can be either a filename (e.g. file://c:/dir/file.html)
    // or a URL (e.g. http://host.com/page.html) and returns all text in the document.
    public static String getText(String uriStr) {
        final StringBuffer buf = new StringBuffer(1000);
    
        try {
            // Create an HTML document that appends all text to buf
            HTMLDocument doc = new HTMLDocument() {
                public HTMLEditorKit.ParserCallback getReader(int pos) {
                    return new HTMLEditorKit.ParserCallback() {
                        // This method is whenever text is encountered in the HTML file
                        public void handleText(char[] data, int pos) {
                            buf.append(data);
                            buf.append('\n');
                        }
                    };
                }
            };
    
            // Create a reader on the HTML content
            URL url = new URI(uriStr).toURL();
            URLConnection conn = url.openConnection();
            Reader rd = new InputStreamReader(conn.getInputStream());
    
            // Parse the HTML
            EditorKit kit = new HTMLEditorKit();
            kit.read(rd, doc, 0);
        } catch (MalformedURLException e) {
        } catch (URISyntaxException e) {
        } catch (BadLocationException e) {
        } catch (IOException e) {
        }
    
        // Return the text
        return buf.toString();
    }