java抓取网页源码的工具_java用程序抓取网页的源代码

packagecom.yjf.util;

importjava.io.BufferedReader;

importjava.io.IOException;

importjava.io.InputStream;

importjava.io.InputStreamReader;

http://www.doczj.com/doc/e3f5340b03d8ce2f00662380.html.HttpURLConnection;

import http://www.doczj.com/doc/e3f5340b03d8ce2f00662380.html.URL;

public class HttpWebUtil {

/**

*网页抓取方法

* @paramurlString要抓取的url地址

* @param charset 网页编码方式

* @param timeout 超时时间

* @paramautor http://www.doczj.com/doc/e3f5340b03d8ce2f00662380.html/

* @return 抓取的网页内容

* @throws IOException抓取异常

*/

public static String GetWebContent(String urlString, final String charset, int timeout) throws IOException {

if (urlString == null || urlString.length() == 0) {

return "";

}

urlString = (urlSt