java抓取网页内容--生成静态页面

private static String getStaticPage(String surl) {

  String htmlContent = "";

  try {

  java.io.InputStream inputStream;

  java.net.URL url = new java.net.URL(surl);

  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, "UTF-8");

  connection.disconnect();

  } catch (Exception ex) {

  ex.printStackTrace();

  }

  return htmlContent.trim();

  }

  String src= getStaticPage(“http://www.google.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();

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值