Examples with Parser org.htmlparser.Parser used on opensource projects

Example 1 with Parser

use of org.htmlparser.Parser in project lucida by claritylab.

the class HTMLConverter method file2text.

/**
	 * Reads an HTML document from a file and converts it into plain text.
	 * 
	 * @param filename name of file containing HTML documents
	 * @return plain text or <code>null</code> if the reading or conversion failed
	 */
public static synchronized String file2text(String filename) {
    // read from file and convert HTML document
    StringBean sb = new StringBean();
    // no links
    sb.setLinks(false);
    // replace non-breaking spaces
    sb.setReplaceNonBreakingSpaces(true);
    // replace sequences of whitespaces
    sb.setCollapse(true);
    Parser parser = new Parser();
    try {
        parser.setResource(filename);
        parser.visitAllNodesWith(sb);
    } catch (ParserException e) {
        return null;
    }
    String docText = sb.getStrings();
    return docText;
}

Example 2 with Parser

use of org.htmlparser.Parser in project lucida by claritylab.

the class HTMLConverter method html2text.

/**
	 * Converts an HTML document into plain text.
	 * 
	 * @param html HTML document
	 * @return plain text or <code>null</code> if the conversion failed
	 */
public static synchronized String html2text(String html) {
    // convert HTML document
    StringBean sb = new StringBean();
    // no links
    sb.setLinks(false);
    // replace non-breaking spaces
    sb.setReplaceNonBreakingSpaces(true);
    // replace sequences of whitespaces
    sb.setCollapse(true);
    Parser parser = new Parser();
    try {
        parser.setInputHTML(html);
        parser.visitAllNodesWith(sb);
    } catch (ParserException e) {
        return null;
    }
    String docText = sb.getStrings();
    // no content
    if (docText == null)
        docText = "";
    return docText;
}

Example 3 with Parser

use of org.htmlparser.Parser in project dhis2-core by dhis2.

the class GridUtils method fromHtml.

/**
     * Creates a list of Grids based on the given HTML string. This works only
     * for table-based HTML documents.
     *
     * @param html the HTML string.
     * @param title the title to use for the grids.
     * @return a list of Grids.
     */
public static List<Grid> fromHtml(String html, String title) throws Exception {
    if (html == null || html.trim().isEmpty()) {
        return null;
    }
    List<Grid> grids = new ArrayList<>();
    Parser parser = Parser.createParser(html, "UTF-8");
    Node[] tables = parser.extractAllNodesThatMatch(new TagNameFilter("table")).toNodeArray();
    for (Node t : tables) {
        Grid grid = new ListGrid();
        grid.setTitle(title);
        TableTag table = (TableTag) t;
        TableRow[] rows = table.getRows();
        Integer firstColumnCount = null;
        for (TableRow row : rows) {
            if (// Ignore if no cells
            getColumnCount(row) == 0) {
                log.warn("Ignoring row with no columns");
                continue;
            }
            Node[] cells = row.getChildren().extractAllNodesThatMatch(HTML_ROW_FILTER).toNodeArray();
            if (// First row becomes header
            firstColumnCount == null) {
                firstColumnCount = getColumnCount(row);
                for (Node c : cells) {
                    TagNode cell = (TagNode) c;
                    grid.addHeader(new GridHeader(getValue(cell), false, false));
                    Integer colSpan = MathUtils.parseInt(cell.getAttribute("colspan"));
                    if (colSpan != null && colSpan > 1) {
                        grid.addEmptyHeaders((colSpan - 1));
                    }
                }
            } else // Rest becomes rows
            {
                if (// Ignore
                firstColumnCount != getColumnCount(row)) {
                    log.warn("Ignoring row which has " + row.getColumnCount() + " columns since table has " + firstColumnCount + " columns");
                    continue;
                }
                grid.addRow();
                for (Node c : cells) {
                    // TODO row span
                    TagNode cell = (TagNode) c;
                    grid.addValue(getValue(cell));
                    Integer colSpan = MathUtils.parseInt(cell.getAttribute("colspan"));
                    if (colSpan != null && colSpan > 1) {
                        grid.addEmptyValues((colSpan - 1));
                    }
                }
            }
        }
        grids.add(grid);
    }
    return grids;
}