1. 必應今日美圖

當使用bing搜索時，每天都會出現一副美圖。

搜索找到bing今日美圖??http://bing.plmeizi.com/?(這里收集了一年多的今日美圖) 收集者：?http://leil.plmeizi.com/?

目前共47頁

url格式按?http://bing.plmeizi.com/?page=*

?

?點進去就是我們要的名稱和名稱

2. 開始編碼

使用簡單的Jsoup進行爬蟲，很簡單，很好理解。

HtmlUtil

1 package util; 2 3 import java.io.IOException; 4 5 import org.jsoup.Jsoup; 6 import org.jsoup.nodes.Document; 7 8 public class HtmlUtil { 9 // 根據url從網絡獲取網頁文本 10 public Document getHtmlTextByUrl(String url) { 11 Document doc = null; 12 try { 13 // doc = Jsoup.connect(url).timeout(5000000).get(); 14 int i = (int) (Math.random() * 1000); // 做一個隨機延時，防止網站屏蔽 15 while (i != 0) { 16 i--; 17 } 18 doc = Jsoup.connect(url).data("query", "Java").userAgent("Mozilla").cookie("auth", "token").timeout(300000) 19 .post(); 20 } catch (IOException e) { 21 e.printStackTrace(); 22 try { 23 doc = Jsoup.connect(url).timeout(5000000).get(); 24 } catch (IOException e1) { 25 // TODO Auto-generated catch block 26 e1.printStackTrace(); 27 } 28 } 29 return doc; 30 } 31 }

GetPhoto

這個編碼主要需要先分析html屬性，按照屬性取到我們需要的元素，元素值。

我是先拿到每個圖的page頁面url

然后到詳情頁面拿到圖的url，圖的名字截取。

然后將圖保存到本地。

1 package bing; 2 3 import java.io.DataInputStream; 4 import java.io.File; 5 import java.io.FileOutputStream; 6 import java.io.IOException; 7 import java.net.URL; 8 9 import org.jsoup.nodes.Document; 10 import org.jsoup.nodes.Element; 11 import org.jsoup.select.Elements; 12 13 import util.HtmlUtil; 14 15 /** 16 * 17 * @author loveincode 18 * @data Sep 29, 2017 1:15:00 PM 19 */ 20 public class GetPhoto { 21 22 public static void go(int startpage, int endpage) throws IOException { 23 24 HtmlUtil htmlutil = new HtmlUtil(); 25 // 獲取圖片的絕對路徑 26 String url = "http://bing.plmeizi.com/?page="; 27 for (int i = startpage; i <= endpage; i++) { 28 String gourl = url + i + ""; 29 Document dochtml = htmlutil.getHtmlTextByUrl(gourl); 30 Elements elements_a = dochtml.getElementsByClass("item"); 31 for (int x = 0; x < elements_a.size(); x++) { 32 String pyotopage = elements_a.get(x).attr("href"); 33 Document dochtml_photo = htmlutil.getHtmlTextByUrl(pyotopage); 34 Element elements_picurl = dochtml_photo.getElementById("picurl"); 35 String picurl = elements_picurl.attr("href"); 36 Element elements_searchlink = dochtml_photo.getElementById("searchlink"); 37 String name = elements_searchlink.getElementsByTag("span").get(0).html(); 38 name = name.split("\\(")[0]; 39 40 if (picurl.contains("jpg")) { 41 // 下載圖片 42 URL url_pic = new URL(picurl); 43 DataInputStream dataInputStream = new DataInputStream(url_pic.openStream()); 44 String imageName = name + ".jpg"; 45 FileOutputStream fileOutputStream = new FileOutputStream(new File("bing_pic/" + imageName)); 46 byte[] buffer = new byte[1024]; 47 int length; 48 while ((length = dataInputStream.read(buffer)) > 0) { 49 fileOutputStream.write(buffer, 0, length); 50 } 51 dataInputStream.close(); 52 fileOutputStream.close(); 53 } 54 } 55 } 56 57 } 58 59 public static void main(String[] args) throws IOException { 60 System.out.println("test"); 61 go(1, 1); 62 } 63 64 }

Mythread

1 package bing; 2 3 import java.io.IOException; 4 5 public class Mythread extends Thread { 6 7 private int startpage; 8 9 private int endpage; 10 11 public Mythread(int startpage, int endpage) { 12 this.startpage = startpage; 13 this.endpage = endpage; 14 } 15 16 @SuppressWarnings("static-access") 17 @Override 18 public void run() { 19 GetPhoto getPhoto = new GetPhoto(); 20 try { 21 getPhoto.go(startpage, endpage); 22 } catch (IOException e) { 23 // TODO Auto-generated catch block 24 e.printStackTrace(); 25 } 26 } 27 }RUN

RUN

采用多線程，開啟多個線程同時爬取圖片

1 package bing; 2 3 import java.io.IOException; 4 5 /** 6 * 7 * @author loveincode 8 * @data Sep 29, 2017 1:55:57 PM 9 */ 10 public class RUN { 11 12 public static void main(String[] args) throws IOException { 13 14 long startTime = System.currentTimeMillis(); // 獲取開始時間 15 16 Mythread a1 = new Mythread(1, 5); 17 Mythread a2 = new Mythread(6, 10); 18 Mythread a3 = new Mythread(11, 15); 19 Mythread a4 = new Mythread(16, 20); 20 Mythread a5 = new Mythread(21, 25); 21 Mythread a6 = new Mythread(26, 30); 22 Mythread a7 = new Mythread(31, 35); 23 Mythread a8 = new Mythread(36, 40); 24 Mythread a9 = new Mythread(41, 45); 25 Mythread a10 = new Mythread(46, 47); 26 27 a1.start(); 28 a2.start(); 29 a3.start(); 30 a4.start(); 31 a5.start(); 32 a6.start(); 33 a7.start(); 34 a8.start(); 35 a9.start(); 36 a10.start(); 37 38 while (true) { 39 if (a1.isAlive() == false && a2.isAlive() == false && a3.isAlive() == false && a4.isAlive() == false 40 && a5.isAlive() == false && a6.isAlive() == false && a7.isAlive() == false && a8.isAlive() == false 41 && a9.isAlive() == false && a10.isAlive() == false) { 42 long endTime = System.currentTimeMillis(); // 獲取結束時間 43 System.out.println("程序運行時間： " + (endTime - startTime) / 1000.0 + "s"); 44 break; 45 } 46 } 47 } 48 49 }

執行 RUN?

耗時76.962s 完成圖片下載到本地。

成功

效果：

很高清吧

?

轉載于:https://www.cnblogs.com/loveincode/p/jsoup_bingpic.html

總結

以上是生活随笔為你收集整理的一个简单粗暴的爬虫 - 必应今日美图的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。