轉載【Java爬取某姐的小視頻】

import java.io.BufferedReader;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.util.HashMap;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
 
/**
 * 功能：爬取某姐的小視頻
 * @author cxd
 *
 */
public class WebSpiderDemo1 {
 
	public static void main(String[] args) throws Exception {
 
		String source = "http://www.budejie.com/video/";
		String destDir = "D:/rob/";
 
		Map<String, String&gt; urlMap = getUrlInSource(source);
 
		for (Map.Entry<String, String> entry : urlMap.entrySet()) {
			String title = entry.getKey();// 視頻名稱
			String url = entry.getValue();// 視頻url
			File destFile = new File(destDir + title + ".mp4");
			download(url, destFile);
		}
	}
 
	/**
	 * 經過視頻的URL下載該視頻並存入本地
	 * 
	 * @param url      視頻的URL
	 * @param destFile 視頻存入的位置
	 * @throws IOException
	 */
	public static void download(String url, File destFile) throws IOException {
		URL videoUrl = new URL(url);
 
		InputStream is = videoUrl.openStream();
		FileOutputStream fos = new FileOutputStream(destFile);
 
		int len = 0;
		byte[] buffer = new byte[1024];
		while ((-1) != (len = is.read(buffer))) {
			fos.write(buffer, 0, len);
		}
		fos.flush();
 
		if (null != fos) {
			fos.close();
		}
 
		if (null != is) {
			is.close();
		}
	}
 
	/**
	 * 獲取視頻的URL地址和視頻名稱存入hashMap
	 * 
	 * @param source
	 * @return
	 * @throws IOException
	 */
	public static Map<String, String> getUrlInSource(String source) throws IOException {
 
		Map<String, String> hashMap = new HashMap<>();
 
		for (int index = 1; index <= 1; index++) { // 頁數最大爲50，本身玩嘛，就只爬取了一頁。
			String pageUrl = source + index;
			URL url = new URL(pageUrl);
			InputStream is = url.openStream();
 
//			若遇到反爬機制則使用該方法將程序假裝爲瀏覽器進行訪問
//			HttpURLConnection conn = (HttpURLConnection) url.openConnection();
//			conn.setRequestMethod("GET");
//			conn.setRequestProperty("user-agent",
//					"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36");
//			BufferedReader br = new BufferedReader(new InputStreamReader(conn.getInputStream(), "UTF-8"));
 
			BufferedReader br = new BufferedReader(new InputStreamReader(is, "UTF-8"));
 
			String info = null;
			String title = null;
			// 此處不要用==null進行判斷，由於網頁中有不少行都是null，不然會報java.lang.NullPointerException。
			for (int i = 0; i < 10000; i++) {
				info = br.readLine();
 
				if (null != info) {
					String urlRegex = "href=\"(.*?\\.mp4)";
 
					if (info.contains("data-text")) {
						title = info;
					}
 
					Pattern pattern = Pattern.compile(urlRegex);
					Matcher matcher = pattern.matcher(info);
					if (matcher.find()) {
						for (int j = 0; j <= matcher.groupCount(); j++) {
							String tmp = matcher.group(j);
							if (!tmp.startsWith("href=")) {
								String videoTitle = getTitle(title.trim());
								hashMap.put(videoTitle, tmp);
							}
						}
					}
				}
			}
		}
		return hashMap;
	}
 
	/**
	 * 清洗整理titile字符串，
	 * 
	 * @param info
	 * @return
	 */
	private static String getTitle(String info) {
 
		int len = info.length();
		String title = info.substring(11, len - 2);
		return title;
	}
}