Java NodeTraversor类代码示例

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
@Override
public _Object deserialize(Reader reader, Config config) {
	StringBuilder sb = new StringBuilder();
	char[] buff = new char[100];
	int len;
	try {
		while ((len = reader.read(buff)) > 0)
			sb.append(buff, 0, len);
	} catch (Exception e) {
		throw new RuntimeException(e);
	}

	Document doc = Jsoup.parse(sb.toString());
	JSoupHtmlNodeVisitor visitor = new JSoupHtmlNodeVisitor();
	NodeTraversor traversor = new NodeTraversor(visitor);
	traversor.traverse(doc);
	return visitor.getObject();
}
 

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
/**
 * Format an Element to plain-text
 * @param element the root element to format
 * @return formatted text
 */
private static 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();
}
 

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
/**
 * removes HTML tags from a google calendar event's description
 * @param description  an event description possibly containing HTML tags
 * @return an event description free of HTML tags
 */
public static String cleanDescription(String description)
{
    FormattingVisitor formatter = new FormattingVisitor();
    new NodeTraversor(formatter).traverse(Jsoup.parse(description));
    return formatter.toString();
}
 

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
/**
 * 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();
}
 

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
/**
 * 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);
}
 

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
/**
 * 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();
}
 

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
/**
 * 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;
}
 

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
@Override
public Iterator<URL> getEmbeddedResourceURLs(String userAgent, byte[] html, URL baseUrl,
        URLCollection coll, String encoding) throws HTMLParseException {
    try {
        // 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);
    }
}
 

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
/**
 * 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();
}
 

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
/**
 * Format an Element to LaTeX
 *
 * @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();
}
 

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
/**
 * 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);
}
 

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
/**
 * 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();
}
 

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
@Override
public Iterator<URL> getEmbeddedResourceURLs(byte[] html, URL baseUrl,
        URLCollection coll, String encoding) throws HTMLParseException {
    try {
        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);
    }
}
 

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
protected static String convertNodeToText(Node node) {
	if (node == null)
		return "";
	StringBuilder buffer = new StringBuilder();
	new NodeTraversor(new ToTextNodeVisitor(buffer)).traverse(node);
	return buffer.toString().trim();
}
 

import org.jsoup.select.NodeTraversor; //导入依赖的package包/类
protected static String convertElementsToText(Elements elements) {
	if (elements == null || elements.isEmpty())
		return "";
	StringBuilder buffer = new StringBuilder();
	NodeTraversor nt = new NodeTraversor(new ToTextNodeVisitor(buffer));
	for (Element element : elements) {
		nt.traverse(element);
	}
	return buffer.toString().trim();
}