使用Jsoup爬取網站圖片

package com.test.pic.crawler;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.net.URL;
import java.net.URLConnection;
import java.util.Arrays;
import java.util.HashSet;
import java.util.List;
import java.util.Set;
import java.util.concurrent.BlockingQueue;
import java.util.concurrent.LinkedBlockingDeque;
import java.util.concurrent.ScheduledExecutorService;
import java.util.concurrent.ScheduledThreadPoolExecutor;
import org.apache.commons.lang3.concurrent.BasicThreadFactory;
import org.jsoup.Jsoup;
import org.jsoup.nodes.*;
import org.jsoup.select.Elements;




/**   
 * @Title: PicCrawler.java 
 *
 * @Package com.test.pic.crawler 
 *
 * @Description: 爬取指定網站的指定Tag下的圖片或者全部Tag圖片 
 *
 * @author CoderZZ   
 *
 * @date 2018年1月12日 下午11:22:41 
 *
 * @version V1.0   
 *
 */
public class PicCrawler implements Runnable{
    private static String pathString = "G:/test/pic/";//存儲目錄
    //存儲真正的爬取頁面
    static BlockingQueue<String> urlBlockingQueue = new LinkedBlockingDeque<String>(1000);
    static int threadNum = 10;
//    public PicCrawler(String url){
//        this.url = url;
//    }

    /** 
     * @Title: main 
     *
     * @Description: TODO(這里用一句話描述這個方法的作用) 
     *
     * @param @param args    設定文件 
     *
     * @return void    返回類型 
     *
     * @throws 
     *
     */
    public static void main(String[] args) {
        String homeurlString = "https://www.xxxx.com";//爬取頁面的基本地址
        String tagPageUrl = "https://www.xxxx.com/tag/";//tag分頁地址
        //Tag標簽的完整路徑
        Set<String> tagFullHrefSet = new HashSet<String>(16);
        //想要爬取哪些tag，如果為空，則全部爬取;否則只配置對應的tag
        String[] crawlerTagArray = {"風景"};
        List<String> crawlerTagList = Arrays.asList(crawlerTagArray);
        try {
            //1.獲取想要的tag完整的url
            Document tagListDocument = Jsoup.connect(tagPageUrl).get();
            Elements tagsListDivElements = tagListDocument.getElementsByClass("tags_list");
            for(Element element:tagsListDivElements){
                Elements aElements = element.getElementsByTag("a");
                for(Element a:aElements){
                    if(crawlerTagList.size() == 0 || crawlerTagList.contains(a.text())){
                        String tagUrlString = homeurlString+a.attr("href");
                        //https://www.xxxx.com/tag/fengjing.html
                        tagUrlString = tagUrlString.substring(0, tagUrlString.lastIndexOf("."))+"/1.html";
                        tagFullHrefSet.add(tagUrlString);
                    }
                }
            }
            //2.獲取圖片鏈接頁面地址，分頁爬取
            for(String tagUrl:tagFullHrefSet){
                String tempTagUrlString = tagUrl;
                int currentPageNum = 1;
                while(true){
                    try{
                        Document imagePageDocument = Jsoup.connect(tempTagUrlString).get();
                        Elements imageListElements = imagePageDocument.getElementsByClass("Pli-litpic");
                        if(imageListElements.size() == 0){
                            break;
                        }
                        for(Element image:imageListElements){
                            urlBlockingQueue.offer(homeurlString+image.attr("href"));
                        }
                        //https://www.xxxx.com/tag/fengjing/1.html
                        tempTagUrlString = tempTagUrlString.substring(0, tempTagUrlString.lastIndexOf("/")+1)+(++currentPageNum)+".html";
                    }catch(Exception e){
                        break;
                    }
                }
            }
            ScheduledExecutorService excutor = new ScheduledThreadPoolExecutor(threadNum,new BasicThreadFactory.Builder().namingPattern("my-crawler-thread-%d").daemon(false).build());
            for(int i=0;i<threadNum;i++){
//                excutor.schedule(new PicCrawler(urlArray[i]), 1, TimeUnit.SECONDS);
//                excutor.execute(new PicCrawler(urlArray[i]));
                excutor.submit(new PicCrawler());
            }
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }
    @Override
    public void run() {
        while (true) {
            try {
                long begin = System.currentTimeMillis();
                String url = urlBlockingQueue.poll();
                if(null != url){
                    Document doc = Jsoup.connect(url).get();
                    Elements titleElements =doc.select("#photos > h1");
                    if(null != titleElements && null != titleElements.get(0)){
                        Set<String> imgSrcSet = new HashSet<String>(16);
                        Element titleElement = titleElements.get(0);
                        String foldNameString = titleElement.text();
                        String[] nameArray = foldNameString.split("\\(");
                        foldNameString = nameArray[0];
                        nameArray = nameArray[1].split("/");
                        int totalPaggs = Integer.parseInt(nameArray[1].replace(")", ""));
                        for(int i=1;i<=totalPaggs;i++){
                            String urlTemp = url.replace(".html", "_"+i+".html");
                            Document docTemp = Jsoup.connect(urlTemp).get();
                            Element element = docTemp.getElementById("big-pic");
                            Elements imgElements = element.getElementsByTag("img");
                            for(Element imgElement:imgElements){
                                imgSrcSet.add(imgElement.attr("src"));
                            }
                        }
                        if(imgSrcSet.size()>0){
                            for(String imgSrc:imgSrcSet){
                                // 構造URL    
                                URL imgurl = new URL(imgSrc);    
                                // 打開連接    
                                URLConnection con = imgurl.openConnection();    
                                //設置請求超時為10s    
                                con.setConnectTimeout(10*1000);    
                                // 輸入流    
                                InputStream is = con.getInputStream();    
                                // 500k的數據緩沖    
                                byte[] bs = new byte[1024*500];    
                                // 讀取到的數據長度    
                                int len;    
                                // 輸出的文件流    
                                File sf=new File(pathString+"\\"+foldNameString);    
                                if(!sf.exists()){    
                                    sf.mkdirs();    
                                }
                                String filename = imgSrc.split("/")[imgSrc.split("/").length-1];
                                OutputStream os = new FileOutputStream(sf.getPath()+"\\"+filename);    
                                // 開始讀取    
                                while ((len = is.read(bs)) != -1) {    
                                    os.write(bs, 0, len);    
                                }    
                                // 完畢，關閉所有鏈接    
                                os.close();    
                                is.close();  
                                System.out.println(imgSrc+"下載完成!!!");
                            }
                        }
                        long end = System.currentTimeMillis();
                        System.out.println("================================================================");
                        System.out.println(Thread.currentThread().getName()+"******************已全部下載完成，用時："+((end-begin)/1000)+"S");
                    }
                }else{
                    System.out.println("========================BlockingQueue已空，已全部抓取完成!=======================");
                }
            } catch (Exception e) {
                System.out.println("========================抓取異常=======================");
            }
        }
    }
}