python3网络爬虫：爬虫正则表达式下载图片（六）

  

   

    

     

    
    

     

      import urllib.request
     
    
   

    

     

    
    

     

      import re
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      def open_url(url):
     
    
   

    

     

    
    

     

          req = urllib.request.Request(url)
     
    
   

    

     

    
    

     

          req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36')
     
    
   

    

     

    
    

     

          page = urllib.request.urlopen(req)
     
    
   

    

     

    
    

     

          html = page.read().decode('utf-8')
     
    
   

    

     

    
    

     
    #print(html)
     
    
   

    

     

    
    

     
    return html
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      def get_img(html):
     
    
   

    

     

    
    

     

          p = r'<img class="BDE_Image" src="([^"]+\.jpg)"'    #正则匹配图片url的路径，https://imgsa.baidu.com/forum/w%3D580/sign=aa042893d558ccbf1bbcb53229d9bcd4/82e96d600c338744f222ae5d550fd9f9d62aa07d.jpg
     
    
   

    

     

    
    

     

          imglist = re.findall(p,html)
     
    
   

    

     

    
    

     
    print(imglist)
     
    
   

    

     

    
    

     
    # for each in imglist: #遍历出所有的图片完整的链接
     
    
   

    

     

    
    

     
    # print(each)
     
    
   

    

     

    
    

     
    for each in imglist:
     
    
   

    

     

    
    

     

              filename = each.split("/")[-1]
     
    
   

    

     

    
    

     

              urllib.request.urlretrieve(each,filename,None)  # urlretrieve(each,filename,None) 下载图片
     
    
   

    

     

    
    

     

      if __name__=='__main__':
     
    
   

    

     

    
    

     

          url = "https://tieba.baidu.com/p/3563409202?red_tag=3526577411"
     
    
   

    

     

    
    

     

          get_img(open_url(url))
     
    
   

    

     

    
    

     
    #open_url(url)
     
    
  
 

文章来源: brucelong.blog.csdn.net，作者：Bruce小鬼，版权归原作者所有，如需转载，请联系作者。

原文链接：brucelong.blog.csdn.net/article/details/80505041