通过文本或url扫描下载文件

package com.xxxx;

import java.io.BufferedInputStream; 
import java.io.BufferedReader; 
import java.io.File; 
import java.io.FileNotFoundException; 
import java.io.FileOutputStream; 
import java.io.IOException; 
import java.io.InputStreamReader; 
import java.net.MalformedURLException; 
import java.net.URL; 
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher; 
import java.util.regex.Pattern; 
 
public class GetImage { 
    
    public int getCharacterPosition(String string,int numb){
        //这里是获取"#"符号的位置
        Matcher slashMatcher = Pattern.compile("/").matcher(string);
        int mIdx = 0;
        while(slashMatcher.find()) {
           mIdx++;
           //当"#"符号第二次出现的位置
           if(mIdx == numb){
              break;
           }
        }
        return slashMatcher.start();
    }
    
    
    
    
    
    /**
     * 下载文件(图片、压缩包等文件都可以下载)
     * @param httpUrl
     * eg:http://www.xxxx.com/uploadfiles/123.rar
     */
    public void getHtmlFile(String httpUrl) { 
    URL url; 
    BufferedInputStream in; 
    FileOutputStream file; 
    try { 
       System.out.println("取网络文件"); 
       //获取子目录
       String unitPath = httpUrl.substring(getCharacterPosition(httpUrl,3) ,httpUrl.lastIndexOf("/"));
       String fileName = httpUrl.substring(httpUrl.lastIndexOf("/")); 
       String filePath = "F:\\FocuSimple"+unitPath+"\\";
       File up = new File(filePath);
        if(!up.exists()){    //判断文件夹是否不存在
            up.mkdirs();
        }
       
       url = new URL(httpUrl); 
      
       in = new BufferedInputStream(url.openStream()); 
      
       file = new FileOutputStream(new File(filePath+fileName)); 
       int t; 
       while ((t = in.read()) != -1) { 
       file.write(t); 
       } 
       file.close(); 
       in.close(); 
      System.out.println("文件获取成功"); 
    } catch (MalformedURLException e) { 
       e.printStackTrace(); 
    } catch (FileNotFoundException e) { 
      e.printStackTrace(); 
    } catch (IOException e) { 
       e.printStackTrace(); 
    } 
    } 
      
    public String getHtmlCode(String httpUrl) throws IOException { 
    String content =""; 
    URL uu = new URL(httpUrl); // 创建URL类对象 
    BufferedReader ii = new BufferedReader(new InputStreamReader(uu 
        .openStream())); // //使用openStream得到一输入流并由此构造一个BufferedReader对象 
    String input; 
    while ((input = ii.readLine()) != null) { // 建立读取循环，并判断是否有读取值 
       content += input; 
    } 
    ii.close(); 
    return content; 
    } 
    public static List<String> getImageSrc(String htmlCode) {
        List<String> imageSrcList = new ArrayList<String>();
//        Pattern p = Pattern.compile("<img\\b[^>]*\\bsrc\\b\\s*=\\s*('|\")?([^'\"\n\r\f>]+(\\.jpg|\\.bmp|\\.eps|\\.gif|\\.mif|\\.miff|\\.png|\\.tif|\\.tiff|\\.svg|\\.wmf|\\.jpe|\\.jpeg|\\.dib|\\.ico|\\.tga|\\.cut|\\.pic)\\b)[^>]*>", Pattern.CASE_INSENSITIVE);
        Pattern p = Pattern.compile("src\\b\\s*=\\s*('|\")?([^'\"\n\r\f>]+(\\.jpg|\\.bmp|\\.eps|\\.gif|\\.mif|\\.miff|\\.png|\\.tif|\\.tiff|\\.svg|\\.wmf|\\.jpe|\\.jpeg|\\.dib|\\.ico|\\.tga|\\.cut|\\.pic)\\b)[^>]*", Pattern.CASE_INSENSITIVE);
        Matcher m = p.matcher(htmlCode);
        String quote = null;
        String src = null;
        while (m.find()) {
            quote = m.group(1);
            src = (quote == null || quote.trim().length() == 0) ? m.group(2).split("\\s+")[0] : m.group(2);
            imageSrcList.add(src);
            System.out.println("src"+src);
        }
        return imageSrcList;
    }
    
    public void get(String url,String text) throws IOException { 
      
    String searchImgReg = "(?x)(src|SRC|background|BACKGROUND)=('|\")/?(([\\w-]+/)*([\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))('|\")"; 
    String searchImgReg2 = "(?x)(src|SRC|background|BACKGROUND)=('|\")(http://([\\w-]+\\.)+[\\w-]+(:[0-9]+)*(/[\\w-]+)*(/[\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))('|\")"; 
    String content  = "";
    if(text == null){
        content = this.getHtmlCode(url);
    }else{
        content = text;
    }
    System.out.println("内容："+content); 
    
    Pattern p = Pattern.compile("src\\b\\s*=\\s*('|\")?([^'\"\n\r\f>]+(\\.jpg|\\.bmp|\\.eps|\\.gif|\\.mif|\\.miff|\\.png|\\.tif|\\.tiff|\\.svg|\\.wmf|\\.jpe|\\.jpeg|\\.dib|\\.ico|\\.tga|\\.cut|\\.pic)\\b)[^>]*", Pattern.CASE_INSENSITIVE);
    Matcher m = p.matcher(content);
    String quote = null;
    String src = null;
    while (m.find()) {
        quote = m.group(1);
        src = (quote == null || quote.trim().length() == 0) ? m.group(2).split("\\s+")[0] : m.group(2);
        this.getHtmlFile(url+src); 
    }
    
    Pattern pattern = Pattern.compile(searchImgReg); 
    Matcher matcher = pattern.matcher(content); 
    while (matcher.find()) { 
       System.out.println("图片路径1："+matcher.group(3)); 
      this.getHtmlFile(url+matcher.group(3)); 
         
    } 
      
    pattern = Pattern.compile(searchImgReg2); 
    matcher = pattern.matcher(content); 
    while (matcher.find()) { 
       System.out.println("图片路径1："+matcher.group(3)); 
      this.getHtmlFile(matcher.group(3)); 
          
    } 
    // searchImgReg = 
    // "(?x)(src|SRC|background|BACKGROUND)=('|\")/?(([\\w-]+/)*([\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))('|\")"; 
    } 
    public static void main(String[] args) throws IOException { 
        GetImage gcp = new GetImage(); 
        gcp.get("http://www.123rf.com.cn/#baidu01",null); 
        gcp.get(null,"<img src=\"/images/ico/logo.png\">"); 
        gcp.getHtmlFile("http://www.xxxx.com/uploadfiles/123.rar");
    } 
}