网页去燥

一种基于标签属性的网页去噪方法
http://wenku.baidu.com/link?url=5A1-yUkoNYDwKTEyMWXZBb5L3drtTD6Hjg-w9EGfpMVLPPsatMX71zHZbAmyExsNbBOUIZshPU31GqU6Zpiwd07aaNGDDEB_Purp4fZDnNS
论文 http://www.cqvip.com/read/read.aspx?id=1005358363#
西安交通大学的论文 http://www.taodocs.com/p-41624911.html

一种基于内容规则的网页去噪算法
http://wenku.baidu.com/link?url=pWisCo4IfVeOiq0q6LhpbbDUoysCItjChi5mKGSpM_NzwbD9EDc8HlFQ0I1Lpzt-3uKUTqscoHcyyaLfVRJYcGOe35YEQlIDqyg11gVjTKm

一个网友提供的接口
http://www.weixinxi.wang/open/extract.html

public class Parser
{
  private static String verifyurl(String url)
  {
    String vurl = null;
    if ((url == null) || (url.equals("")))
    {
      vurl = "http://www.weixinxi.wang/service/parser?url=http://www.weixinxi.wang/blog/aitrcle.html?id=68";
    }
    else {
      vurl = "http://www.weixinxi.wang/service/parser?url=" + url;
    }

    return vurl;
  }
  public static String getjson(String urls) {
    String jsonstr = null;
    String urlStr = urls;
    try {
      urlStr = verifyurl(urls);
      URL url = new URL(urlStr);
      HttpURLConnection httpConn = (HttpURLConnection)url.openConnection();
      httpConn.setConnectTimeout(3000);

      httpConn.setRequestMethod("GET");
      httpConn.setRequestProperty("User-agent", "Mozilla/4.0");
      int respCode = httpConn.getResponseCode();
      ByteArrayOutputStream out = null;
      InputStream inputStream = null;
      byte[] buffer = (byte[])null;
      int len = 0;
      if (respCode == 200)
      {
        buffer = new byte[1024];
        inputStream = httpConn.getInputStream();
        out = new ByteArrayOutputStream();
        try {
          while ((len = inputStream.read(buffer, 0, buffer.length)) != -1) {
            out.write(buffer, 0, len);
          }

          jsonstr = new String(out.toByteArray());
        }
        catch (Exception localException)
        {
        }
      }
    }
    catch (Exception localException1)
    {
    }
    return jsonstr;
  }

  public static void main(String[] args)
  {
    System.out.println(getjson("http://news.xinhuanet.com/legal/2015-07/30/c_1116096002.htm"));
  }
}