get the header content from some website, in java

最新推荐文章于 2024-09-04 17:08:26 发布

tlcd

最新推荐文章于 2024-09-04 17:08:26 发布

阅读量456

点赞数

文章标签： website header url string equals class

本文链接：https://blog.youkuaiyun.com/tlcd/article/details/3231902

版权

just help one friend for writing some java code to access the meta data of the header of some website's response:

=====================================

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;

public class ReadWebsite {

/**
* @param args
*/
public static void main(String[] args) {
  int READ_BUFFER_SIZE = 1024;

  try
  {
   //make change to a different website, please edit here!
      //URL url = new URL("http://www.google.com/");
   URL url = new URL("http://java.sun.com/j2se/1.4.2/docs/api/java/lang/String.html");

      URLConnection urlConnection = url.openConnection();
      InputStream ins = urlConnection.getInputStream();
      InputStreamReader i = new InputStreamReader(ins);

      BufferedReader b = new BufferedReader(new InputStreamReader(ins));
      String oneLine = "", content = "", oneField;

      while ((oneLine = b.readLine()) != null)
      {
      content += oneLine;
      }

      int start = -1, end = -1;

      content = content.toUpperCase();

      start = content.indexOf("<META");

      while (start != -1)
      {
      content = content.substring(start);

      end = content.indexOf(">");
      if (end != -1)
      {
        oneField = content.substring(0, end + 1);
        System.out.println("/n");
        System.out.println(oneField);

        content = content.substring(end + 1);
      }

      start = content.indexOf("<META");
      }
  }
  catch (IOException e)
  {
   System.err.println("Error: " + e);
  }

}

}

======== output is as follows: