Example usage for org.jsoup.select NodeTraversor NodeTraversor

Introduction

In this page you can find the example usage for org.jsoup.select NodeTraversor NodeTraversor.

Prototype

public NodeTraversor(NodeVisitor visitor) 

Source Link

Document

Create a new traversor.

Usage

From source file:com.trackplus.track.util.html.Html2LaTeX.java

/**
 * Format an Element to LaTeX/*from   w  w  w  .j  a v  a2 s.  c  o m*/
 *
 * @param element
 *            the root element to format
 * @return formatted text
 */
public static String getLatexText(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();
}

---

From source file:com.twentyn.patentExtractor.PatentDocument.java

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.
             *///w  ww  . j  ava 2s. c  om
            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;
}

---

From source file:no.kantega.publishing.admin.content.htmlfilter.RemoveNestedSpanTagsFilter.java

private void copySafeNodes(Element source, Element dest) {
    CleaningVisitor cleaningVisitor = new CleaningVisitor(dest);
    NodeTraversor traversor = new NodeTraversor(cleaningVisitor);
    traversor.traverse(source);//  w  ww .j  ava  2 s . c  o  m
}

---

From source file:org.apache.jmeter.protocol.http.parser.JsoupBasedHtmlParser.java

@Override
public Iterator<URL> getEmbeddedResourceURLs(String userAgent, byte[] html, URL baseUrl, URLCollection coll,
        String encoding) throws HTMLParseException {
    try {//from   w  w w  . j a v a  2s  .c  om
        // TODO Handle conditional comments for IE
        String contents = new String(html, encoding);
        Document doc = Jsoup.parse(contents);
        JMeterNodeVisitor nodeVisitor = new JMeterNodeVisitor(new URLPointer(baseUrl), coll);
        new NodeTraversor(nodeVisitor).traverse(doc);
        return coll.iterator();
    } catch (Exception e) {
        throw new HTMLParseException(e);
    }
}

---

From source file:org.jsweet.input.typescriptdef.visitor.DocFiller.java

@Override
public void visitTypeDeclaration(TypeDeclaration typeDeclaration) {
    if (typeDeclaration.getDocumentation() == null) {
        String moduleName = getCurrentModuleName();
        if (JSweetDefTranslatorConfig.LANG_PACKAGE.equals(moduleName)
                || JSweetDefTranslatorConfig.DOM_PACKAGE.equals(moduleName)) {
            this.currentModule = moduleName;

            String content = getTypeContent(context.cacheDir, "mdn", moduleName, typeDeclaration.getName());
            if (content != null) {
                try {
                    Document doc = Jsoup.parse(content, "UTF-8");
                    NodeTraversor traversor;
                    traversor = new NodeTraversor(new MdnTableFormatGrabber(this, typeDeclaration));
                    traversor.traverse(doc.body());
                    traversor = new NodeTraversor(new MdnDefinitionListFormatGrabber(this, typeDeclaration));
                    traversor.traverse(doc.body());
                    traversor = new NodeTraversor(new MdnMainDescriptionGrabber(this, typeDeclaration));
                    traversor.traverse(doc.body());
                } catch (Throwable t) {
                    context.reportError("cannot fill documentation for " + context.getTypeName(typeDeclaration),
                            typeDeclaration.getToken(), t);
                }//  w w  w  . j  a v  a 2  s.  c om
            }
        }
    }
}

---

From source file:org.jsweet.input.typescriptdef.visitor.DocFiller.java

public static String removeTags(String html, String[] tagsToBeRemoved) {
    StringBuilder sb = new StringBuilder();
    NodeTraversor traversor = new NodeTraversor(new TagRemover(sb, tagsToBeRemoved));
    traversor.traverse(Jsoup.parse(html).body());
    return sb.toString().replace("<p></p>", "");
}

---