Java-爬取页面数据

Java-爬取页面数据

public class HttpReptilianUtil {
	public static String getHtml(String url){
		BufferedReader in = null;
		//定义字符缓冲区
		StringBuffer stringBuffer = new StringBuffer();
		try {
			//创建URL地址
			URL net = new URL(url);
			//打开URL
			URLConnection connection = net.openConnection();
			//开启输入/输出。注意：请求网络需要传参必须开启
			//connection.setDoOutput(true);
			//connection.setDoInput(true);
			//实例化字符缓冲输入流来读取数据
			in = new BufferedReader(
					new InputStreamReader(connection.getInputStream())
					);
			String line = null;
			while ((line = in.readLine())!=null) {
				//用stringBuffer拼接数据
				stringBuffer.append(line);
			}
		} catch (Exception e) {
			e.printStackTrace();
			System.out.println("网络超时");
		} finally {
			try {
				in.close();
			} catch (IOException e) {
				e.printStackTrace();
			}
		}
		return stringBuffer.toString();
	}
	public static void main(String[] args) {
		String content = getHtml("https://www.baidu.com");
		System.out.println(content);
	}
}