如何使用Jericho HTML Parser解析XML

时间:2011-11-21 16:23:50

标签: java xml servlets jericho-html-parser

我是java和servlet的新手,目前正在尝试使用Jericho XML Parser解析XML。 例如,我想从每个链接标签获取链接,但它不显示任何内容,总数显示为27(只能获得没有字符串的正确总数)。 知道怎么做的人,请教我。

import java.io.IOException;
import java.io.PrintWriter;
import javax.servlet.ServletException;
import javax.servlet.annotation.WebServlet;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.*;

import net.htmlparser.jericho.Element;
import net.htmlparser.jericho.Source;

@WebServlet(urlPatterns = { "/HelloServlet"})

public class HelloServlet extends HttpServlet {
private static final long serialVersionUID = 1L;

@Override
protected void doGet(HttpServletRequest req, HttpServletResponse resp) throws ServletException, IOException,MalformedURLException{

    resp.setContentType("text/html; charset=UTF-8");
    PrintWriter out = resp.getWriter();
    out.println("<html>");
    out.println("<head><meta http-equiv='content-type' content='text/html; charset=UTF-8'></head>");
    out.println("<body>");
    Source source = new Source(new URL("http://news.yahoo.com/rss/"));
    source.fullSequentialParse();


    List<Element> Linklist = source.getAllElements("link");


    if(Linklist!=null){
        out.println("<p>total:"+Linklist.size()+"</p>");
        for(Element link: Linklist){
            out.println("<p>"+link.getContent().toString()+"</p>");
        }
    }


    out.println("</body>");
    out.println("</html>");
}


}

1 个答案:

答案 0 :(得分:1)

根据Jericho HTML Parser主页,Jericho用于处理HTML文档。但来自Yahoo的RSS是XML,您可以使用Java的标准XML来解析此文档并提取链接标记。 这是一个例子:

import java.io.IOException;
import java.net.URL;
import java.util.LinkedList;
import java.util.List;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.NodeList;
import org.xml.sax.SAXException;

// ...

private List<String> getRssLinks() throws ParserConfigurationException,
    SAXException, IOException 
{
  final List<String> rssLinks = new LinkedList<String>();
  final URL url = new URL("http://news.yahoo.com/rss/");
  final Document doc = DocumentBuilderFactory.newInstance().newDocumentBuilder()
                       .parse(url.openStream());
  final NodeList linkNodes = doc.getElementsByTagName("link");
  for(int i = 0; i < linkNodes.getLength(); i++) {
    final Element linkElement = (Element) linkNodes.item(i);
    rssLinks.add(linkElement.getTextContent());
  }

  return rssLinks;
}