Java爬虫抓取视频网站下载链接

package action;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;
import java.sql.Connection;
import java.sql.PreparedStatement;
import java.sql.SQLException;
import java.util.LinkedHashMap;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
 
public class VideoLinkGrab {
 
  public static void main(String[] args) {
    VideoLinkGrab videoLinkGrab = new VideoLinkGrab();
    videoLinkGrab.saveData("http://www.80s.la/movie/list/-2015----p");
  }
 
  /**
   * 将获取到的数据保存在数据库中
   * 
   * @param baseUrl
   *      爬虫起点
   * @return null
   * */
  public void saveData(String baseUrl) {
    Map oldMap = new LinkedHashMap(); // 存储链接-是否被遍历
 
    Map videoLinkMap = new LinkedHashMap(); // 视频下载链接
    String oldLinkHost = ""; // host
 
    Pattern p = Pattern.compile("(https?://)?[^/\\s]*"); // 比如：http://www.zifangsky.cn
    Matcher m = p.matcher(baseUrl);
    if (m.find()) {
      oldLinkHost = m.group();
    }
 
    oldMap.put(baseUrl, false);
    videoLinkMap = crawlLinks(oldLinkHost, oldMap);
    // 遍历，然后将数据保存在数据库中
    try {
      Connection connection = JDBCDemo.getConnection();
      for (Map.Entry mapping : videoLinkMap.entrySet()) {
        PreparedStatement pStatement = connection
            .prepareStatement("insert into movie(MovieName,MovieLink) values(?,?)");
        pStatement.setString(1, mapping.getKey());
        pStatement.setString(2, mapping.getValue());
        pStatement.executeUpdate();
        pStatement.close();
//       System.out.println(mapping.getKey() + " : " + mapping.getValue());
      }
      connection.close();
    } catch (SQLException e) {
      e.printStackTrace();
    }
  }
 
  /**
   * 抓取一个网站所有可以抓取的网页链接，在思路上使用了广度优先算法 对未遍历过的新链接不断发起GET请求， 一直到遍历完整个集合都没能发现新的链接
   * 则表示不能发现新的链接了，任务结束
   * 
   * 对一个链接发起请求时，对该网页用正则查找我们所需要的视频链接，找到后存入集合videoLinkMap
   * 
   * @param oldLinkHost
   *      域名，如：http://www.zifangsky.cn
   * @param oldMap
   *      待遍历的链接集合
   * 
   * @return 返回所有抓取到的视频下载链接集合
   * */
  private Map crawlLinks(String oldLinkHost,
      Map oldMap) {
    Map newMap = new LinkedHashMap(); // 每次循环获取到的新链接
    Map videoLinkMap = new LinkedHashMap(); // 视频下载链接
    String oldLink = "";
 
    for (Map.Entry mapping : oldMap.entrySet()) {
      // System.out.println("link:" + mapping.getKey() + "--------check:"
      // + mapping.getValue());
      // 如果没有被遍历过
      if (!mapping.getValue()) {
        oldLink = mapping.getKey();
        // 发起GET请求
        try {
          URL url = new URL(oldLink);
          HttpURLConnection connection = (HttpURLConnection) url
              .openConnection();
          connection.setRequestMethod("GET");
          connection.setConnectTimeout(2500);
          connection.setReadTimeout(2500);
 
          if (connection.getResponseCode() == 200) {
            InputStream inputStream = connection.getInputStream();
            BufferedReader reader = new BufferedReader(
                new InputStreamReader(inputStream, "UTF-8"));
            String line = "";
            Pattern pattern = null;
            Matcher matcher = null;
            //电影详情页面，取出其中的视频下载链接，不继续深入抓取其他页面
            if(isMoviePage(oldLink)){
              boolean checkTitle = false;
              String title = "";
              while ((line = reader.readLine()) != null) {
                //取出页面中的视频标题
                if(!checkTitle){
                  pattern = Pattern.compile("([^\\s]+).*?");
                  matcher = pattern.matcher(line);
                  if(matcher.find()){
                    title = matcher.group(1);
                    checkTitle = true;
                    continue;
                  }
                }
                // 取出页面中的视频下载链接
                pattern = Pattern
                    .compile("(thunder:[^\"]+).*thunder[rR]es[tT]itle=\"[^\"]*\"");
                matcher = pattern.matcher(line);
                if (matcher.find()) {
                  videoLinkMap.put(title,matcher.group(1));
                  System.out.println("视频名称： "
                      + title + " ------ 视频链接："
                      + matcher.group(1));
                  break; //当前页面已经检测完毕
                }
              } 
            }
            //电影列表页面
            else if(checkUrl(oldLink)){
              while ((line = reader.readLine()) != null) {
 
                pattern = Pattern
                    .compile("