Extract data from complex HTML tables to 2d array in Java

How to convert HTML tables with colspan and rowspan into 2d array (martix) in Java?

I have found nice solutions in Python and jQuery but not in Java (only very simple tables via jsoup). There is one pretty solution with XSLT but due malformed input HTML files it is not OK for me.

Input table example:

  <body>
    <table border="1">
        <tr><td>H1</td><td colspan="2">H2</td><tr>
        <tr><td></td><td>SubH2_1</td><td>SubH2_2</td><tr>
       <tr><td rowspan="3">A1</td><td>B1</td><td rowspan="2">C1</td></tr>
       <tr><td rowspan="2">B2</td></tr>
       <tr><td>C3</td></tr>
       <tr><td>C4</td><td>C5</td><td>C6</td></tr>
        <tr><td>D7</td><td colspan="2">D9</td></tr>
        <tr><td  colspan="3">Notes</td></tr>
   </table>
</body>

Desired output:

    [['H1', 'H2', 'H2'],
     ['', 'SubH2_1', 'SubH2_2'],
     ['A1', 'B1', 'C1'],
     ['A1', 'B2', 'C3'],
     ['C4', 'C5', 'C6'],
     ['D7', 'D9', 'D9'],
     ['Notes', 'Notes', 'Notes']]