Element to string in HTMLDocument

前端 未结 1 1086
执笔经年
执笔经年 2020-12-04 03:01

i have a Element object its a HTMLDocument object and i want to string value of this element.

i want this result

Christina Toth, Pharm. D.

===============

1条回答
  •  温柔的废话
    2020-12-04 03:29

    Try this instead.

    Edited to use the read() method of HTMLEditorKit.

    import java.io.StringReader;
    import javax.swing.text.AttributeSet;
    import javax.swing.text.Element;
    import javax.swing.text.ElementIterator;
    import javax.swing.text.StyleConstants;
    import javax.swing.text.html.HTML;
    import javax.swing.text.html.HTMLDocument;
    import javax.swing.text.html.HTMLEditorKit;
    
    public class NewMain {
    
        public static void main(String args[]) throws Exception {
            HTMLEditorKit htmlKit = new HTMLEditorKit();
            HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
            htmlKit.read(new StringReader(text), htmlDoc, 0);
            // Parse
            ElementIterator iterator = new ElementIterator(htmlDoc);
            Element element;
            while ((element = iterator.next()) != null) {
                AttributeSet as = element.getAttributes();
                Object name = as.getAttribute(StyleConstants.NameAttribute);
                if (name == HTML.Tag.DIV) {
                    StringBuffer sb = new StringBuffer();
                    sb.append(name).append(": ");
                    int count = element.getElementCount();
                    for (int i = 0; i < count; i++) {
                        Element child = element.getElement(i);
                        int startOffset = child.getStartOffset();
                        int endOffset = child.getEndOffset();
                        int length = endOffset - startOffset;
                        sb.append(htmlDoc.getText(startOffset, length));
                    }
                    System.out.println(sb);
                }
            }
        }
        private static String text
            = "\n"
            + "\n"
            + "pg_0001\n"
            + "\n"
            + "\n"
            + "\n"
            + "\n"
            + "\n"
            + "\n"
            + "
    Christina Toth, Pharm. D.
    \n" + "\n" + "\n" + "\n" + ""; }

    Console:

    div: Christina Toth, Pharm. D.

    0 讨论(0)
提交回复
热议问题