爬取百度贴吧某一网页图片

Chysial

爬取百度贴吧的妹子图，没有加网页page，save哪个地方可以自己用urlretrieve，以及名字部分有更好的方法。

1. import re
   
2. import os
   
3. import urllib.request
   
4. 
   
5. def open_url(url):
   
6.     req = urllib.request.Request(url)
   
7.     req.add_header("user-agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36")
   
8. 
   
9.     response = urllib.request.urlopen(req)
   
10.     html = response.read()
    
11.     return html
    
12. 
    
13. def get_img(url):
    
14.     p = r'src="http:([^"]+\.jpg)"'
    
15.     html = open_url(url).decode("utf-8")
    
16.     imglist = re.findall(p,html)
    
17.     img_list = []
    
18.     for each in imglist:
    
19.         img_list.append("http:" + each)
    
20.     return img_list
    
21. 
    
22. def save_img(img_list):
    
23.     for each in img_list:
    
24.         num = each.rfind("/")
    
25.         each_name = each[num+1:]
    
26.         with open(each_name,"wb") as f:
    
27.             print(each)
    
28.             img = open_url(each)
    
29.             f.write(img)
    
30.    
    
31. def download_img(folder="baidu_girls"):
    
32.     os.chdir("C:\\Users\\Chysial\\Desktop")
    
33.     os.mkdir(folder)
    
34.     os.chdir(folder)
    
35.     url = "https://tieba.baidu.com/p/6526349637"
    
36.     img_list = get_img(url)
    
37.     save_img(img_list)
    
38. 
    
39. 
    
40. 
    
41. if __name__ == "__main__":
    
42.     download_img()
    

复制代码