java 抓取网页内容

最新推荐文章于 2023-12-13 15:45:08 发布

gzchenbing

最新推荐文章于 2023-12-13 15:45:08 发布

阅读量593

点赞数

分类专栏： IT java 抓取网页内容 Javascript 文章标签： java string exception null url

本文链接：https://blog.csdn.net/gzchenbing/article/details/6253722

版权

IT 同时被 3 个专栏收录

3 篇文章 0 订阅

订阅专栏

Javascript

2 篇文章 0 订阅

订阅专栏

java 抓取网页内容

1 篇文章 0 订阅

订阅专栏

public static void main(String[] args) {
  try {
   URL url = new URL("http://www.google.com");
   URLConnection conn = url.openConnection();
   conn.setDoOutput(true);
   InputStream in = null;
   in = url.openStream();
   String content = pipe(in, "utf-8");
   System.out.println(content);
  } catch (Exception e) {
   e.printStackTrace();
  }
}

static String pipe(InputStream in, String charset) throws IOException {
  StringBuffer s = new StringBuffer();
  if (charset == null || "".equals(charset)) {
   charset = "utf-8";
  }
  String rLine = null;
  BufferedReader bReader = new BufferedReader(new InputStreamReader(in,
    charset));
  PrintWriter pw = null;
  FileOutputStream fo = new FileOutputStream("../index.html");
  OutputStreamWriter writer = new OutputStreamWriter(fo, "utf-8");
  pw = new PrintWriter(writer);
  while ((rLine = bReader.readLine()) != null) {
   String tmp_rLine = rLine;
   int str_len = tmp_rLine.length();
   if (str_len > 0) {
    s.append(tmp_rLine);
    pw.println(tmp_rLine);
    pw.flush();
   }
   tmp_rLine = null;
  }
  in.close();
  pw.close();
  return s.toString();
}