java中根据url抓取html页面内容的方法

最新推荐文章于 2021-05-31 07:35:23 发布

siye1982

最新推荐文章于 2021-05-31 07:35:23 发布

阅读量183

点赞数

分类专栏： JAVA积累文章标签： Java HTML .net

JAVA积累专栏收录该内容

32 篇文章 0 订阅

订阅专栏

import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;

public class URLUtil {

  public static String getHtml(String urlString) {
    try {
      StringBuffer html = new StringBuffer();
      URL url = new URL(urlString);
      HttpURLConnection conn = (HttpURLConnection) url.openConnection();
      InputStreamReader isr = new InputStreamReader(conn.getInputStream());
      BufferedReader br = new BufferedReader(isr);
      String temp;
      while ((temp = br.readLine()) != null) {
        html.append(temp).append("\n");
      }
      br.close();
      isr.close();
      return html.toString();
    } catch (Exception e) {
      e.printStackTrace();
      return null;
    }
  }

  public static void main(String[] args) {
    System.out.println(URLUtil.getHtml("http://www.163.com"));
  }
}