怎么把解析网站的电影信息添加到自己的数据库

Question

怎么把解析网站的电影信息添加到自己的数据库

Answer 1

java抓取优酷[url]http://movie.youku.com/[/url]中强档专区的简单例子，你参考一下。
[code="java"]
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Test {
private static final String regex = "

\s*\s*.*?\s*\s*\s*(.*?)\s*
\s*.*?\s*\s*";

public static void main(String[] args) {
    try {
        HttpURLConnection urlconn = (HttpURLConnection) new URL(
                "http://movie.youku.com/").openConnection();

        BufferedReader rd = new BufferedReader(new InputStreamReader(
                urlconn.getInputStream(), "utf-8"));

        String temp = null;
        StringBuffer sb = new StringBuffer();
        temp = rd.readLine();
        while (temp != null) {
            sb.append(temp);
            temp = rd.readLine();
        }
        rd.close();
        urlconn.disconnect();

        String content = sb.toString();

        System.out.println(content);
        System.out.println(content);
        System.out.println(content);
        System.out.println(content);
        System.out.println(content);

        Pattern p = Pattern.compile(regex);
        Matcher ma = p.matcher(content);

        System.out.println("强档专区的电影：");
        while (ma.find()) {
            System.out.println(ma.group(1));
        }

    } catch (MalformedURLException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    } catch (IOException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }

}

}

[/code]