package com.csu.test;

import java.io.File;
import java.io.IOException;
import java.util.HashSet;
import java.util.Iterator;
import java.util.Set;

import org.apache.commons.io.FilenameUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

/**
 * 
 * @author CSU-Max
 * 抓取指定网页的图片保存在指定文件夹
 *
 */
public class Main {

	public static void main(String[] args) {
	
		//抓取的图片存放的文件夹
		String filePath = "D:/CSU-Max-temp";
		//要抓取图片的网页地址
		String webUrl = "http://xiangce.baidu.com/picture/album/list/85062425ab359f0760819f33a14ec718884ce667";
		
		File file = new File(filePath);
	
		if(file.exists()){
			System.out.println("文件夹已经存在");
		}else{
			file.mkdir();
			System.out.println("自动创建文件夹");
		}

		try {
		
			Document doc = Jsoup.connect(webUrl).userAgent("Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.31 (KHTML, like Gecko) Chrome/26.0.1410.64 Safari/537.31").get();
			Elements imgElements = doc.getElementsByTag("img");
			
			Set<String> imgSrcSet = new HashSet<String>();
			for (Element img : imgElements) {
				String imgSrc = img.attr("abs:src");
				imgSrcSet.add(imgSrc);
			}
			System.out.println("图片总数："+imgSrcSet.size());
			
			Iterator<String> i = imgSrcSet.iterator();
			while(i.hasNext()){
				
				String imgSrc = (String)i.next();
				String imgName = FilenameUtils.getName(imgSrc);
				
				if (imgName.indexOf(".") != -1) {
					if (imgName.indexOf("?") > -1) {
						imgName = imgName.substring(0, imgName.indexOf("?"));
					}
					
					Util util = new Util();
					String saveImagePath = filePath+"/"+imgName;
					System.out.println("图片抓取开始：");
					util.download(imgSrc,saveImagePath);
					System.out.println("图片抓取结束："+imgSrc+" 保存路径："+saveImagePath);
					
				}
			}  

		} catch (IOException e) {
			e.printStackTrace();
		} 
	}
}