private String getListHtml(String listUrl) throws IOException {
        String sHtml = "";
        URLConnection uc = null;
        BufferedReader br = null;
        try {
            java.net.URL url = new URL(listUrl);
            uc = url.openConnection();

            //设置模拟浏览器浏览参数，防止部分网站阻止
            uc.setRequestProperty("User-Agent",
                    "Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; DigExt)");
            uc.connect();

            boolean bgCatch = false;
            boolean edCatch = false;
            String line = "";

            br = new BufferedReader(new InputStreamReader(new DataInputStream(
                    uc.getInputStream()), "UTF8"));//编码视具体情况而定

            while ((line = br.readLine()) != null) {
                System.out.println(line);//自己处理获得的每行HTML内容
                sHtml += line + "\r\n";
            }
        } catch (MalformedURLException e) {
            e.printStackTrace();
            throw new IOException("该地址格式不正确！");
        } catch (ConnectException e) {
            e.printStackTrace();
            throw new IOException("该地址不可到达！");
        } finally {
            try {
                if (br != null)
                    br.close();
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
        return sHtml;
    }

------解决方案--------------------
楼主也可以考虑下用httpClient.jar