Java Code Examples for org.jsoup.select.NodeTraversor#traverse()

private static List<String> extractTextFromHTML(DocumentBuilder docBuilder, NodeList textNodes)
    throws ParserConfigurationException, TransformerConfigurationException,
    TransformerException, XPathExpressionException {
  List<String> allTextList = new ArrayList<>(0);
  if (textNodes != null) {
    for (int i = 0; i < textNodes.getLength(); i++) {
      Node n = textNodes.item(i);
                  /* This extremely around-the-horn approach to handling text content is due to the mix of HTML and
                   * XML in the patent body.  We use Jsoup to parse the HTML entities we find in the body, and use
                   * its extremely convenient NodeVisitor API to recursively traverse the document and extract the
                   * text content in reasonable chunks.
                   */
      Document contentsDoc = Util.nodeToDocument(docBuilder, "body", n);
      String docText = Util.documentToString(contentsDoc);
      // With help from http://stackoverflow.com/questions/832620/stripping-html-tags-in-java
      org.jsoup.nodes.Document htmlDoc = Jsoup.parse(docText);
      HtmlVisitor visitor = new HtmlVisitor();
      NodeTraversor traversor = new NodeTraversor(visitor);
      traversor.traverse(htmlDoc);
      List<String> textSegments = visitor.getTextContent();
      allTextList.addAll(textSegments);
    }
  }
  return allTextList;
}
 

/**
 * Format an Element to plain-text
 * @param element the root element to format
 * @return formatted text
 */
public String getPlainText(Element element) {
    FormattingVisitor formatter = new FormattingVisitor();
    NodeTraversor.traverse(formatter, element); // walk the DOM, and call .head() and .tail() for each node

    return formatter.toString();
}
 

/**
 * Format an Element to plain-text
 * @param element the root element to format
 * @return formatted text
 */
public String getPlainText(Element element) {
	FormattingVisitor formatter = new FormattingVisitor();
	NodeTraversor traversor = new NodeTraversor(formatter);
	traversor.traverse(element); // walk the DOM, and call .head() and .tail() for each node

	return formatter.toString();
}
 

/**
 * Format an Element to plain-text
 * @param element the root element to format
 * @return formatted text
 */
public String getPlainText(Element element) {
    FormattingVisitor formatter = new FormattingVisitor();
    NodeTraversor traversor = new NodeTraversor(formatter);
    traversor.traverse(element); // walk the DOM, and call .head() and .tail() for each node

    return formatter.toString();
}
 

/**
 * Format an Element to plain-text
 * @param element the root element to format
 * @return formatted text
 */
public String getPlainText(Element element) {
	FormattingVisitor formatter = new FormattingVisitor();
	NodeTraversor traversor = new NodeTraversor(formatter);
	traversor.traverse(element); // walk the DOM, and call .head() and .tail() for each node

	return formatter.toString();
}
 

/**
 * Perform a depth-first traversal through this node and its descendants.
 * @param nodeVisitor the visitor callbacks to perform on each node
 * @return this node, for chaining
 */
public Node traverse(NodeVisitor nodeVisitor) {
    Validate.notNull(nodeVisitor);
    NodeTraversor traversor = new NodeTraversor(nodeVisitor);
    traversor.traverse(this);
    return this;
}
 

/**
 * Format an Element to plain-text
 * @param element the root element to format
 * @return formatted text
 */
public String getPlainText(Element element) {
    FormattingVisitor formatter = new FormattingVisitor();
    NodeTraversor traversor = new NodeTraversor(formatter);
    traversor.traverse(element); // walk the DOM, and call .head() and .tail() for each node

    return formatter.toString();
}
 

/**
 * Converts a jsoup document into the provided W3C Document. If required, you can set options on the output document
 * before converting.
 * @param in jsoup doc
 * @param out w3c doc
 * @see org.jsoup.helper.W3CDom#fromJsoup(org.jsoup.nodes.Document)
 */
public void convert(org.jsoup.nodes.Document in, Document out) {
    if (!StringUtil.isBlank(in.location()))
        out.setDocumentURI(in.location());

    org.jsoup.nodes.Element rootEl = in.child(0); // skip the #root node
    NodeTraversor traversor = new NodeTraversor(new W3CBuilder(out));
    traversor.traverse(rootEl);
}
 

/**
 * Format an Element to plain-text
 * @param element the root element to format
 * @return formatted text
 */
public String getPlainText(Element element) {
    FormattingVisitor formatter = new FormattingVisitor();
    NodeTraversor traversor = new NodeTraversor(formatter);
    traversor.traverse(element); // walk the DOM, and call .head() and .tail() for each node

    return formatter.toString();
}
 

/**
 * Format an Element to plain-text
 * @param element the root element to format
 * @return formatted text
 */
public String getPlainText(Element element) {
    FormattingVisitor formatter = new FormattingVisitor();
    NodeTraversor.traverse(formatter, element); // walk the DOM, and call .head() and .tail() for each node

    return formatter.toString();
}
 

/**
 * Converts a jsoup document into the provided W3C Document. If required, you can set options on the output document
 * before converting.
 * @param in jsoup doc
 * @param out w3c doc
 * @see org.jsoup.helper.W3CDom#fromJsoup(org.jsoup.nodes.Document)
 */
public void convert(org.jsoup.nodes.Document in, Document out) {
    if (!StringUtil.isBlank(in.location()))
        out.setDocumentURI(in.location());

    org.jsoup.nodes.Element rootEl = in.child(0); // skip the #root node
    NodeTraversor.traverse(new W3CBuilder(out), rootEl);
}
 

/**
 * Converts a jsoup document into the provided W3C Document. If required, you can set options on the output document
 * before converting.
 * @param in jsoup doc
 * @param out w3c doc
 * @see org.jsoup.helper.W3CDom#fromJsoup(org.jsoup.nodes.Document)
 */
public void convert(org.jsoup.nodes.Document in, Document out) {
    if (!StringUtil.isBlank(in.location()))
        out.setDocumentURI(in.location());

    org.jsoup.nodes.Element rootEl = in.child(0); // skip the #root node
    NodeTraversor.traverse(new W3CBuilder(out), rootEl);
}
 

/**
 * Format an Element to plain-text
 * @param element the root element to format
 * @return formatted text
 */
public String getPlainText(Element element) {
    FormattingVisitor formatter = new FormattingVisitor();
    NodeTraversor.traverse(formatter, element); // walk the DOM, and call .head() and .tail() for each node

    return formatter.toString();
}
 

public static DocumentFragment fromJsoup(
        org.jsoup.nodes.Document jsoupDocument) {
    HTMLDocumentImpl htmlDoc = new HTMLDocumentImpl();
    htmlDoc.setErrorChecking(false);
    DocumentFragment fragment = htmlDoc.createDocumentFragment();
    org.jsoup.nodes.Element rootEl = jsoupDocument.child(0); // skip the
                                                             // #root node
    NodeTraversor.traverse(new W3CBuilder(htmlDoc, fragment), rootEl);
    return fragment;
}
 

protected void outerHtml(Appendable accum) {
    NodeTraversor.traverse(new OuterHtmlVisitor(accum, getOutputSettings()), this);
}
 

private int copySafeNodes(Element source, Element dest) {
    CleaningVisitor cleaningVisitor = new CleaningVisitor(source, dest);
    NodeTraversor.traverse(cleaningVisitor, source);
    return cleaningVisitor.numDiscarded;
}
 

protected void outerHtml(Appendable accum) {
    NodeTraversor.traverse(new OuterHtmlVisitor(accum, getOutputSettings()), this);
}
 

private int copySafeNodes(Element source, Element dest) {
    CleaningVisitor cleaningVisitor = new CleaningVisitor(source, dest);
    NodeTraversor.traverse(cleaningVisitor, source);
    return cleaningVisitor.numDiscarded;
}
 

private int copySafeNodes(Element source, Element dest) {
    CleaningVisitor cleaningVisitor = new CleaningVisitor(source, dest);
    NodeTraversor traversor = new NodeTraversor(cleaningVisitor);
    traversor.traverse(source);
    return cleaningVisitor.numDiscarded;
}
 

private static String text(Element element) {
	FormattingVisitor formatter = new FormattingVisitor();
	NodeTraversor.traverse(formatter, element);
	return formatter.toString();
}