package cn.yq;

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.net.MalformedURLException;
import java.net.URL;

import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.filters.OrFilter;
import org.htmlparser.tags.ImageTag;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;

public class URLParse {
    public static void main(String[] args) {
        try {   
            Parser parser = new Parser("http://slide.sports.sina.com.cn/euro2012/slide_2_31402_29988.html");  
            parser.setEncoding("gb2312");
            //提取链接
            NodeFilter frameFilter = new NodeFilter() {
                public boolean accept(Node node) {
                    if (node.getText().startsWith("frame src=")) {
                        return true;
                    } else {
                        return false;
                    }
                }
            };
            //过滤出图片
            OrFilter orFilter = new OrFilter(new NodeClassFilter(LinkTag.class), new 
                    NodeClassFilter(ImageTag.class));
            OrFilter linkFilter = new OrFilter(orFilter, frameFilter);
            
            NodeList nodelist = parser.extractAllNodesThatMatch(linkFilter);
            //循环取得image标签
            for (int i = 0; i < nodelist.size(); i++) {
                Node tag = nodelist.elementAt(i);
                if (tag instanceof ImageTag)
                {
                    ImageTag image = (ImageTag) nodelist.elementAt(i);
                    String urlstr = image.getImageURL();
                    InputStream is;
                    OutputStream os;
                    int len;
                    if(urlstr.endsWith("jpg") || urlstr.endsWith("gif")){
                        System.out.println(urlstr);
                        //下载到本地目录
                        byte[] buf = new byte[102400];
                        try {
                            URL url = new URL(urlstr);
                            String suffix = urlstr.substring(urlstr.lastIndexOf("."),urlstr.length());

                            try {
                                is = url.openConnection().getInputStream();
                                os = new FileOutputStream("d:/downloadimage/" + i + suffix);
                                while((len = is.read(buf)) != -1){
                                    os.write(buf,0,len);
                                }
                                os.close();                            
                                is.close();
                            } catch (IOException e) {
                                e.printStackTrace();
                            }
    
                        } catch (MalformedURLException e) {
                            e.printStackTrace();
                        }