HtmlParseUtil

package com.hszc.commons.utils;

import java.net.HttpURLConnection;
import java.net.URL;
import org.apache.log4j.Logger;
import org.htmlparser.Node;
import org.htmlparser.Parser;
import org.htmlparser.util.NodeIterator;

/**
* 解析HTML
* @author admin
*
*/
public class HtmlParseUtil {
private static Logger logger = Logger.getLogger(HtmlParseUtil.class);

public static StringBuffer toHtml(String url) {
StringBuffer sBuffer = new StringBuffer();
try {
Parser parser = new Parser(
(HttpURLConnection) (new URL(url)).openConnection());

for (NodeIterator i = parser.elements(); i.hasMoreNodes();) {
Node node = i.nextNode();
sBuffer.append(node.toHtml());
}
} catch (Exception e) {
logger.error("解析HTML异常", e);
}

return sBuffer;
}

public static void main(String[] args) {
　　System.out.println(toHtml("http://www.baidu.com/"));
}

}