[已解决]爬妹子图

huangdongdong

1. import urllib.request
   
2. import os
   
3. import base64
   
4. 
   
5. def url_open(url):
   
6.     req = urllib.request.Request(url)
   
7.     req.add_header('User-Agent','Mozilla / 5.0（Windows NT 10.0; WOW64）AppleWebKit / 537.36（KHTML，like Gecko）Chrome / 86.0.4240.198 Safari / 537.36')
   
8.     response = urllib.request.urlopen(req)
   
9.     html = response.read()
   
10.     return html
    
11. 
    
12. def get_page(url):
    
13.     html = url_open(url).decode('UTF-8')
    
14.     a = html.find('current-comment-page') + 23
    
15.     b = html.find(']',a)
    
16.    
    
17.     return html[a:b]
    
18. 
    
19. def find_addrs(url):
    
20.     html = url_open(url).decode('UTF-8')
    
21.     img_addrs = []
    
22. 
    
23.     a = html.find('img src =')
    
24. 
    
25.     while a != -1:
    
26.         b = html.find('.jpg',a,a+255)
    
27.         if b != -1:
    
28.             img_addrs.append(html[a+9:b+4])
    
29.         else:
    
30.             b = a+9
    
31. 
    
32.         a = html.find('img src =',b)
    
33. 
    
34.     return img_addrs
    
35. 
    
36. 
    
37. def save_imgs(folder,img_addrs):
    
38.     for each in img_addrs:
    
39.         filename = each.split('/')[-1]
    
40.         with open(filename,'wb') as f:
    
41.             img = url_open(each)
    
42.             f.write(img)
    
43. 
    
44. def download_num(folder = 'ooxx',pages = 10):
    
45.     os.mkdir(folder)
    
46.     os.chdir(folder)
    
47. 
    
48.     url = 'http://jandan.net/ooxx/'
    
49.     page_num = int(get_page(url))
    
50. 
    
51.     for i in range(pages):
    
52.         page_num  -= 1
    
53.         target_num = '20210114' + str(page_num)
    
54.         target_num = base64.b64encode(target_num.encode('UTF-8'))
    
55. 
    
56.         page_url = url + '/' + str(target_num,'UTF -8') + '#comment'
    
57.         img_addrs = find_imgs(page_url)
    
58.         save_imgs(folder,img_addrs)
    
59.         
    
60. if __name__ == '__main__':
    
61.     download_num()
    

复制代码

UnicodeEncodeError: 'latin-1' codec can't encode character '\uff08' in position 13: ordinal not in range(256)
>>>
如何解决？？？

最佳答案

月排行榜 / 总排行榜

路神

2021-5-26 15:30:52

'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 '
                  'Safari/537.36'

跳转到最佳答案楼层

路神

'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 '
                  'Safari/537.36'

huangdongdong

路神 发表于 2021-5-26 22:00
'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 '
...

ValueError: unknown url type: '//wx3.sinaimg.cn/mw600/0089jzyPly1gqwwi3t18vj30u01hcx6q.jpg'

路神

huangdongdong 发表于 2021-5-27 14:32
ValueError: unknown url type: '//wx3.sinaimg.cn/mw600/0089jzyPly1gqwwi3t18vj30u01hcx6q.jpg'

https:

huangdongdong

路神 发表于 2021-5-27 16:54
https:

程序走完但文件夹为空

路神

huangdongdong 发表于 2021-5-27 17:06
程序走完但文件夹为空

a = html.find('img src =')这句全是-1当然没文件，这是你自己写的？还有这爬的也不是妹图

huangdongdong

路神 发表于 2021-5-27 19:35
a = html.find('img src =')这句全是-1当然没文件，这是你自己写的？还有这爬的也不是妹图

找到解决办法了。只要在with ....of下加一句each  = 'http'+ each即可