java 用xpath解析html,通过xpath获取html中的特定标签

package nekohtml;

import java.io.IOException;

import javax.xml.transform.TransformerException;

import org.apache.xpath.XPathAPI;

import org.cyberneko.html.parsers.DOMParser;

import org.w3c.dom.Document;

import org.w3c.dom.NodeList;

import org.xml.sax.SAXException;

public class NekoHtmlAndXPath {

// 通过url，将相应的html解析为DOM文档

public static Document getDocument(String url) {

DOMParser parser = new DOMParser();

try {

parser.parse(url);

} catch (SAXException e) {

e.printStackTrace();

} catch (IOException e) {

e.printStackTrace();

}

Document doc = parser.getDocument();

return doc;

}

// 通过XPath定位具体的节点

public static NodeList getExactNode(Document doc, String xp) {

NodeList list = null