java 抓取页面信息

最新推荐文章于 2023-02-15 13:56:16 发布

wwwww222221

最新推荐文章于 2023-02-15 13:56:16 发布

阅读量76

点赞数

分类专栏： JAVA 文章标签： Java .net HTML

本文链接：https://blog.csdn.net/wwwww222221/article/details/83872056

版权

JAVA 专栏收录该内容

12 篇文章 0 订阅

订阅专栏

public String CreateCrawlWebData(String myurl){

  String htmlContent = "";
try {

     java.io.InputStream inputStream;
     java.net.URL url = new java.net.URL(myurl);
     java.net.HttpURLConnection connection = (java.net.HttpURLConnection) url.openConnection();
     connection.connect();
     inputStream = connection.getInputStream();
     byte bytes[] = new byte[1024 * 2000];
     int index = 0;
     int count = inputStream.read(bytes, index, 1024 * 2000);
     while (count != -1) {
     index += count;
     count = inputStream.read(bytes, index, 1);

     htmlContent = new String(bytes, "gb2312");
     connection.disconnect();
     }
  }catch (Exception ex)
     {
      ex.printStackTrace();
     }
      return htmlContent.trim();
}

public static void main(String[] args) throws IOException {

String _src= getStaticPage(cwd.CreateCrawlWebData("http://www.baidu.com"));
     //System.out.println(cwd.CreateCrawlWebData("http://www.baidu.com"));
  File file = new File("d:\\aa.html");
  FileWriter resultFile = new FileWriter(file);
  PrintWriter myFile = new PrintWriter(resultFile);
   //写文件
    myFile.println(_src);
   resultFile.close();
   myFile.close();

}