[已解决]OOXX 抓妹子图片求助

Shyanne

代码如下，是对照着小甲鱼的代码来的 但是不知道出现了ValueError。。。

1. import urllib.request
   
2. import os
   
3. 
   
4. def url_open(url):
   
5.     req = urllib.request.Request(url)
   
6.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36')
   
7.     response = urllib.request.urlopen(url)
   
8.     html = response.read()
   
9.    
   
10.     return html
    
11.    
    
12. def get_page(url):  
    
13.     html = url_open(url).decode('utf-8')
    
14. 
    
15.     a= html.find('current-comment-page')+23
    
16.     b= html.find(']',a)
    
17. 
    
18.     return html[a:b]
    
19. 
    
20. def find_imgs(url):
    
21.     html = url_open(url).decode('utf-8')
    
22.     img_addrs = []
    
23. 
    
24. 
    
25.     a = html.find('img src=')
    
26. 
    
27.     while  a!= -1:
    
28.         b = html.find('.jpg',a,a+255)
    
29. 
    
30.         if b != -1:
    
31.             img_addrs.append(html[a+9:b+4])
    
32.    
    
33.         else:
    
34.             b=a+9
    
35. 
    
36.         a = html.find('img src=',b)
    
37.     return img_addrs
    
38. 
    
39.    
    
40. def save_imgs(folder,img_addrs):
    
41.     for each in img_addrs:
    
42.         filename = each.split('/')[-1]
    
43.         with open(filename,'wb') as f:
    
44.             img = url_open(each)
    
45.             f.write(img)
    
46. 
    
47. 
    
48. def download_mm(folder = 'OOXX',pages = 10):
    
49.     os.mkdir(folder)
    
50.     os.chdir(folder)
    
51. 
    
52.     url = 'http://jandan.net/ooxx/'
    
53.     page_num = int(get_page(url))
    
54. 
    
55.     for i in range(pages):
    
56.         page_num -= i
    
57.         page_url = url + 'page-' +str(page_num)+ '#comments'
    
58.         img_addrs = find_imgs(page_url)
    
59.         save_imgs(folder,img_addrs)
    
60. 
    
61. if __name__ == '__main__':
    
62.     download_mm()
    

复制代码

错误如下：

最佳答案

月排行榜 / 总排行榜

int2str

2017-3-5 14:28:17

1. import urllib.request
   
2. import os
   
3. 
   
4. def url_open(url):
   
5.     req = urllib.request.Request(url)
   
6.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36')
   
7.     response = urllib.request.urlopen(url)
   
8.     html = response.read()
   
9.    
   
10.     return html
    
11.    
    
12. def get_page(url):  
    
13.     html = url_open(url).decode('utf-8')
    
14. 
    
15.     a= html.find('current-comment-page')+23
    
16.     b= html.find(']',a)
    
17. 
    
18.     return html[a:b]
    
19. 
    
20. def find_imgs(url):
    
21.     html = url_open(url).decode('utf-8')
    
22.     img_addrs = []
    
23. 
    
24. 
    
25.     a = html.find('img src=')
    
26. 
    
27.     while  a!= -1:
    
28.         b = html.find('.jpg',a,a+255)
    
29. ################################################
    
30.         if b != -1:
    
31.             string = 'http:' + html[a+9:b+4] # 修改
    
32.             img_addrs.append(string) # 修改
    
33. ################################################   
    
34.         else:
    
35.             b=a+9
    
36. 
    
37.         a = html.find('img src=',b)
    
38.     return img_addrs
    
39. 
    
40.    
    
41. def save_imgs(folder,img_addrs):
    
42.     for each in img_addrs:
    
43.         filename = each.split('/')[-1]
    
44.         with open(filename,'wb') as f:
    
45.             img = url_open(each)
    
46.             f.write(img)
    
47. 
    
48. 
    
49. def download_mm(folder = 'OOXX',pages = 10):
    
50.     os.mkdir(folder)
    
51.     os.chdir(folder)
    
52. 
    
53.     url = 'http://jandan.net/ooxx/'
    
54.     page_num = int(get_page(url))
    
55. 
    
56.     for i in range(pages):
    
57.         page_num -= i
    
58.         page_url = url + 'page-' +str(page_num)+ '#comments'
    
59.         img_addrs = find_imgs(page_url)
    
60.         save_imgs(folder,img_addrs)
    
61. 
    
62. if __name__ == '__main__':
    
63.     download_mm()
    

复制代码

跳转到最佳答案楼层

int2str

url前面少了‘http:’

int2str

1. import urllib.request
   
2. import os
   
3. 
   
4. def url_open(url):
   
5.     req = urllib.request.Request(url)
   
6.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36')
   
7.     response = urllib.request.urlopen(url)
   
8.     html = response.read()
   
9.    
   
10.     return html
    
11.    
    
12. def get_page(url):  
    
13.     html = url_open(url).decode('utf-8')
    
14. 
    
15.     a= html.find('current-comment-page')+23
    
16.     b= html.find(']',a)
    
17. 
    
18.     return html[a:b]
    
19. 
    
20. def find_imgs(url):
    
21.     html = url_open(url).decode('utf-8')
    
22.     img_addrs = []
    
23. 
    
24. 
    
25.     a = html.find('img src=')
    
26. 
    
27.     while  a!= -1:
    
28.         b = html.find('.jpg',a,a+255)
    
29. ################################################
    
30.         if b != -1:
    
31.             string = 'http:' + html[a+9:b+4] # 修改
    
32.             img_addrs.append(string) # 修改
    
33. ################################################   
    
34.         else:
    
35.             b=a+9
    
36. 
    
37.         a = html.find('img src=',b)
    
38.     return img_addrs
    
39. 
    
40.    
    
41. def save_imgs(folder,img_addrs):
    
42.     for each in img_addrs:
    
43.         filename = each.split('/')[-1]
    
44.         with open(filename,'wb') as f:
    
45.             img = url_open(each)
    
46.             f.write(img)
    
47. 
    
48. 
    
49. def download_mm(folder = 'OOXX',pages = 10):
    
50.     os.mkdir(folder)
    
51.     os.chdir(folder)
    
52. 
    
53.     url = 'http://jandan.net/ooxx/'
    
54.     page_num = int(get_page(url))
    
55. 
    
56.     for i in range(pages):
    
57.         page_num -= i
    
58.         page_url = url + 'page-' +str(page_num)+ '#comments'
    
59.         img_addrs = find_imgs(page_url)
    
60.         save_imgs(folder,img_addrs)
    
61. 
    
62. if __name__ == '__main__':
    
63.     download_mm()
    

复制代码

Shyanne

int2str 发表于 2017-3-5 14:23
url前面少了‘http:’

啊 谢谢 运行成功了~~