java htmlparser 下载_JAVA HtmlParser 提取照片下载到本地

package sometry;

import java.io.BufferedInputStream;

import java.io.File;

import java.io.FileOutputStream;

import java.io.IOException;

import java.io.OutputStream;

import java.net.HttpURLConnection;

import java.net.URL;

import org.htmlparser.Node;

import org.htmlparser.NodeFilter;

import org.htmlparser.Parser;

import org.htmlparser.filters.NodeClassFilter;

import org.htmlparser.tags.ImageTag;

import org.htmlparser.util.NodeList;

public class ExtractPicture {

private static HttpURLConnection con = null;

private static BufferedInputStream bis = null;

private static OutputStream out = null;

public static void extractLinks(String url) {

try {

Parser parser = new Parser(url);

parser.setEncoding("UTF-8");

// image filter;

NodeFilter imageFilter = new NodeClassFilter(ImageTag.class);

NodeList nodeList = parser.extractAllNodesThatMatch(imageFilter);

for (int i = 0; i < nodeList.size(); i++) {

Node tag = nodeList.elementAt(i);

ImageTag image = (ImageTag)tag;

String imageURL = image.getImageURL();

String imageText = image.getText();

System.out.println("imageURL:"+imageURL);

System.out.println("imageText:"+imageText);

con = (HttpURLConnection)(new URL(imageURL).openConnection());

con.connect();

bis = new BufferedInputStream(con.getInputStream());

out = new FileOutputStream(new File("D:\\360Downloads\\" + i + "_" +System.currentTimeMillis() +imageURL.substring(imageURL.lastIndexOf("."))));

byte[] buf = new byte[1024];

int size = 0;

while((size = bis.read(buf)) != -1){

out.write(buf, 0, size);

}

}

} catch (Exception e) {

System.err.println(e.getStackTrace());

} finally {

try {

out.close();

bis.close();

con.disconnect();

} catch (IOException e) {

e.printStackTrace();

}

}

}

public static void main(String[] args) {

ExtractPicture.extractLinks("http://www.cb.cityu.edu.hk/staff/issliao/");

}

}