python 爬虫 老是出错，快来帮我看看

箜白

1. import urllib.request
   
2. import os
   
3. 
   
4. def get_page(url):
   
5.     req = urllib.request.Request(url)
   
6.     req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36')
   
7.     response = urllib.request.urlopen(url)
   
8.     html = response.read().decode('utf-8')
   
9. 
   
10.     a = html.find('current-comment-page') + 23
    
11.     b = html.find(']', a)
    
12.     print(html[a:b])
    
13.    
    
14. def find_imgs(url):
    
15.     pass
    
16. 
    
17. def save_imgs(folder, img_addrs):
    
18.     pass
    
19. 
    
20. def download_mm(folder = 'OOXX', pages = 10):
    
21. ##    os.mkdir(folder)
    
22.     os.chdir(folder)
    
23. 
    
24.     url = 'http://jandan.net/ooxx'
    
25.     page_num = int(get_page(url))
    
26. 
    
27.     for i in range(pages):
    
28.         page_num -= i
    
29.         page_url = url + 'page-' + str(page_num) + '#comments'
    
30.         img_addrs = find_img(page_url)
    
31.         save_imgs(folder, img_addrs)
    
32. 
    
33. if __name__ == '__main__':
    
34.     download_mm()
    
35. 
    

复制代码

老王他师父

这是证书出错，加上以下代码：
import ssl

ssl._create_default_https_context = ssl._create_unverified_context

望采纳

老王他师父

我也是刚看到这里，调了半天才找到的解决方法

不是酥鱼

这里的response = urllib.request.urlopen(url)，改为response = urllib.request.urlopen(req)