How to read content from ms word files using Jakarta POI

Question

I\'ve included jakarta-poi-1.5.1-final-20020615.jar file to read content from ms word.

I am unable to do this ...can anyone help me?

Answer 1

Use this code with apache-poi

XWPFDocument doc = new XWPFDocument(new FileInputStream(fileName));
    List table = doc.getTables();
    for (XWPFTable xwpfTable : table) {
        List row = xwpfTable.getRows();
        for (XWPFTableRow xwpfTableRow : row) {
            List cell = xwpfTableRow.getTableCells();
            for (XWPFTableCell xwpfTableCell : cell) {
                if (xwpfTableCell != null) {
                    System.out.println(xwpfTableCell.getText());
                    String s = xwpfTableCell.getText();
                    for (XWPFParagraph p : xwpfTableCell.getParagraphs()) {
                        for (XWPFRun run : p.getRuns()) {
                            for (XWPFPicture pic : run.getEmbeddedPictures()) {
                                byte[] pictureData = pic.getPictureData().getData();
                                System.out.println("picture : " + pictureData);
                            }
                        }
                    }
                }
            }
        }
    }