java爬取猫咪上的图片

首先是对知识点归纳

1.用到获取网页源代码，分析图片地址，发现图片的地址都是按编号排列的，所以想到用循环获取

2.保存图片要用到流操作和文件操作，对两部分知识进行了复习巩固

3.保存后的图片有一部分是广告文字，所以我又看了一下如何截取图片

下面上代码：

网页源代码不粘贴了

对网页源代码分析之后进行循环提取图片链接并下载：

 package 文件操作;
 
 import java.io.ByteArrayOutputStream;
 import java.io.File;
 import java.io.FileOutputStream;
 import java.io.IOException;
 import java.io.InputStream;
 import java.net.HttpURLConnection;
 import java.net.MalformedURLException;
 import java.net.URL;
 
 public class Pic696 {
 
     public static void main(String[] args) {
     for(int i =1;i<72;i++) {
         for (int j =1; j < 50; j++) {
 
             if(i<10&&j<10) {
                 String strUrl ="https://mmslt1.com/tp/girl/FEILIN/A-00"+i+"/0"+j+".jpg";
 //                System.out.println(i+" "+j);
                 System.out.println(strUrl);
                 URL url;
                 try {
                     url = new URL(strUrl);
                     try {
                         Pig(url, i, j);
                     } catch (IOException e) {
                         System.out.println("404");
                     }
                 } catch (MalformedURLException e) {
 
                 }
 
             }
             if(i<10&&j>=10) {
                 String strUrl ="https://mmslt1.com/tp/girl/FEILIN/A-00"+i+"/"+j+".jpg";
 //                System.out.println(i+" "+j);
                 System.out.println(strUrl);
                 URL url;
                 try {
                     url = new URL(strUrl);
                     try {
                         Pig(url, i, j);
                     } catch (IOException e) {
                         System.out.println("404");
                     }
                 } catch (MalformedURLException e) {
                     // TODO Auto-generated catch block
                     e.printStackTrace();
                 }
 
             }
             if(i>=10&&j<10) {
                 String strUrl ="https://mmslt1.com/tp/girl/FEILIN/A-0"+i+"/0"+j+".jpg";
 //                System.out.println(i+" "+j);
                 System.out.println(strUrl);
                 URL url;
                 try {
                     url = new URL(strUrl);
                     try {
                     Pig(url, i, j);
                 } catch (IOException e) {
                     System.out.println("404");
                 }
                 } catch (MalformedURLException e) {
                     // TODO Auto-generated catch block
                     e.printStackTrace();
                 }
 
             }
             if(i>=10&&j>=10) {
             String strUrl ="https://mmslt1.com/tp/girl/FEILIN/A-0"+i+"/"+j+".jpg";
 //            System.out.println(i+" "+j);
             System.out.println(strUrl);
             URL url;
             try {
                 url = new URL(strUrl);
                 try {
                 Pig(url, i, j);
             } catch (IOException e) {
                 System.out.println("404");
             }
             } catch (MalformedURLException e) {
                 // TODO Auto-generated catch block
                 e.printStackTrace();
             }
 
             }
         }
     }
 
 }
 
     static void Pig(URL urlStr,int i,int j) throws IOException {
         //构造连接
         HttpURLConnection conn = (HttpURLConnection)urlStr.openConnection();
         conn.setRequestMethod("GET");
         //这个网站要模拟浏览器才行
         conn.setRequestProperty("User-Agent","Mozilla/5.0 (Windows NT 10.0; WOW64; rv:46.0) Gecko/20100101 Firefox/46.0");
         //打开连接
         conn.connect();
 
         //打开这个网站的输入流
         InputStream inStream = conn.getInputStream();
         //用这个做中转站 ，把图片数据都放在了这里，再调用toByteArray()即可获得数据的byte数组
         ByteArrayOutputStream outStream = new ByteArrayOutputStream();
         //用这个是很好的，不用一次就把图片读到了文件中
         //要是需要把图片用作其他用途呢？所以直接把图片的数据弄成一个变量，十分有用
         //相当于操作这个变量就能操作图片了
 
         byte [] buf = new byte[1024];
         //为什么是1024？
         //1024Byte=1KB，分配1KB的缓存
 
         int len = 0;
 
         //读取图片数据
         while((len=inStream.read(buf))!=-1){
 //        System.out.println(len);
         outStream.write(buf,0,len);
         }
         inStream.close();
         outStream.close();
 
         //把图片数据填入文件中
 //        File files = new File("E://Pic696");
 //        files.mkdirs();
         File file = new File("E://Pic696/Pic"+i+"_"+j+".jpg");
 
         FileOutputStream op = new FileOutputStream(file);
 
         op.write(outStream.toByteArray());
 
         op.close();
      }
 }

对下载下来的图片进行截取（获取原来的尺寸，减掉一部分）

 package 文件操作;
 
 import java.awt.Rectangle;
 import java.awt.image.BufferedImage;
 import java.io.BufferedReader;
 import java.io.File;
 import java.io.FileInputStream;
 import java.io.IOException;
 import java.io.InputStream;
 import java.io.InputStreamReader;
 import java.net.MalformedURLException;
 import java.net.URL;
 import java.util.Iterator;
 
 import javax.imageio.ImageIO;
 import javax.imageio.ImageReadParam;
 import javax.imageio.ImageReader;
 import javax.imageio.stream.ImageInputStream;
 import javax.swing.ImageIcon;
 
 public class cityScore {
 
     public static void main(String[] args) {
         for (int i = 1; i < 10; i++) {
             for (int j = 1; j < 40; j++) {
                 String OldPic ="E:/Pic696/Pic"+i+"_"+j+".jpg";
                 String NewPic ="E:/Pic696/new/Pic"+i+"_"+j+".jpg";
                 ImageIcon imageIcon = new ImageIcon(OldPic);
                 int iconWidth = imageIcon.getIconWidth();
                 int iconHeight =imageIcon.getIconHeight();
                 cutImage(OldPic, NewPic,iconWidth, iconHeight-70);
             }
         }
 
     }
 
     /**
      * 图片裁剪
      * @param srcImageFile 图片裁剪地址
      * @param result 图片输出文件夹
      * @param destWidth 图片裁剪宽度
      * @param destHeight 图片裁剪高度
      */
     public final static void cutImage(String srcImageFile, String result,
             int destWidth, int destHeight) {
         try {
             Iterator iterator = ImageIO.getImageReadersByFormatName("JPEG");/*PNG,BMP*/
             ImageReader reader = (ImageReader)iterator.next();/*获取图片尺寸*/
             InputStream inputStream = new FileInputStream(srcImageFile);
             ImageInputStream iis = ImageIO.createImageInputStream(inputStream);
             reader.setInput(iis, true);
             ImageReadParam param = reader.getDefaultReadParam();
             Rectangle rectangle = new Rectangle(0,0, destWidth, destHeight);/*指定截取范围*/
             param.setSourceRegion(rectangle);
             BufferedImage bi = reader.read(0,param);
             ImageIO.write(bi, "JPEG", new File(result));
         } catch (Exception e) {
             System.out.println(e);
         }
     }
 }