前几日受人之托,写了一个抓网页代码的小例子,通过一个JSP页面抓取某网站页面的HTML内容。
代码如下:
<%@ page language="java" contentType="text/html; charset=utf-8"
pageEncoding="utf-8" import="java.util.*,java.io.*,java.net.*"%>
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<title>抓取页面</title>
</head>
<body>
<%
String inputLine = "";
String urlvalue = "https://www.baidu.com";
try {
URL url = new URL(urlvalue);
URLConnection rulConnection = url.openConnection();
HttpURLConnection httpUrlConnection = (HttpURLConnection) rulConnection;
httpUrlConnection.setRequestProperty("User-Agent",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)");
httpUrlConnection.connect();
BufferedReader in = new BufferedReader(
new InputStreamReader(httpUrlConnection.getInputStream(), "UTF-8"));
inputLine = in.readLine().toString();
} catch (Exception e) {
e.printStackTrace();
}
%>
<textarea style="height: 500px; width: 500px">
<%
out.print(inputLine);
%>
</textarea>
</body>
</html>