[已解决]python55讲，下载妹子图问题

ChenTaicheng

报错信息是什么意思？需要如何改？
先谢过各位了。

代码如下：

1. 
   
2. import urllib.request
   
3. import os
   
4. import random
   
5. 
   
6. def url_open(url):
   
7.     #隐藏：请求url并修改User-Agent
   
8.     req = urllib.request.Request(url)
   
9.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36')
   
10.     #生成代理
    
11.     proxies = ['61.191.41.130:80']
    
12.     proxy = random.choice(proxies)
    
13.     #生成ProxyHandler，创建opener，安装opener
    
14.     proxy_support = urllib.request.ProxyHandler({'http':proxy})
    
15.     opener = urllib.request.build_opener(proxy_support)
    
16.     urllib.request.install_opener(opener)
    
17.     #请求打开url
    
18.     response = urllib.request.urlopen(url)
    
19.     html = response.read()
    
20. 
    
21.     return html
    
22. 
    
23. 
    
24. def get_page(url):
    
25.     #得到请求页面的内容并解码
    
26.     html = url_open(url).decode('utf-8')
    
27. 
    
28.     a = html.find('current-comment-page') + 23
    
29.     b = html.find(']',a)
    
30.     #返回page的编号
    
31.     return html[a:b]
    
32. 
    
33. 
    
34. def find_imgs(url):
    
35.     html = url_open(url).decode('utf-8')
    
36.     img_addrs = []
    
37.     #找到图片的链接
    
38.     a = html.find('img src=')
    
39.     #无链接时为-1
    
40.     while a!=-1:
    
41.         b = html.find('.jpg',a,a+255)
    
42.         # 当链接不是以jpg结尾时b为-1
    
43.         if b!=-1:
    
44.             img_addrs.append(html[a+9:b+4])
    
45.         else:
    
46.             b = a + 9
    
47. 
    
48.         a = html.find('img src=',b)
    
49. 
    
50.     return img_addrs
    
51. 
    
52. 
    
53. def save_imgs(folder,img_addrs):
    
54.     for each in img_addrs:
    
55.         filename = each.split('/')[-1]#取得文件名字
    
56.         with open(filename,'wb') as f:
    
57.             img = url_open(each)
    
58.             f.write(img)
    
59. 
    
60. def download_mm(folder='OOXX',pages=10):
    
61.     #创建foler并进入folder
    
62.     os.mkdir(folder)
    
63.     os.chdir(folder)
    
64. 
    
65.     url = 'http://jandan.net/ooxx/'
    
66.     page_num = int(get_page(url))
    
67. 
    
68.     for i in range(pages):
    
69.         page_num = i
    
70.         page_url = url + 'page-' + str(page_num) + '#comments'
    
71.         img_addrs = find_imgs(page_url)
    
72.         save_imgs(folder,img_addrs)
    
73. 
    
74. if __name__ == '__main__':
    
75.     download_mm()

复制代码

报错如下：
C:\Users\c\AppData\Local\Programs\Python\Python35\python.exe D:/Python视频/test/test1.py
Traceback (most recent call last):
  File "D:/Python视频/test/test1.py", line 72, in <module>
    download_mm()
  File "D:/Python视频/test/test1.py", line 69, in download_mm
    save_imgs(folder, img_addrs)
  File "D:/Python视频/test/test1.py", line 54, in save_imgs
    img = url_open(each)
  File "D:/Python视频/test/test1.py", line 7, in url_open
    req = urllib.request.Request(url)
  File "C:\Users\c\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 269, in __init__
    self.full_url = url
  File "C:\Users\c\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 295, in full_url
    self._parse()
  File "C:\Users\c\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 324, in _parse
    raise ValueError("unknown url type: %r" % self.full_url)
ValueError: unknown url type: '//wx4.sinaimg.cn/mw600/0063qhYBgy1ffsu4e7ig7j30go0m8403.jpg'

Process finished with exit code 1

最佳答案

月排行榜 / 总排行榜

gaoke11240

2017-5-21 13:26:28

1. 
   
2. img_addrs.append(html[a+9:b+4])
   
3. 改成
   
4. img_addrs.append('http:'+html[a+9:b+4])
   
5. 地址就对了

复制代码

跳转到最佳答案楼层

gaoke11240

http://

gaoke11240

1. import urllib.request
   
2. import os
   
3. import re
   
4. 
   
5. def save_imgs(folder,img_addrs):
   
6.     for each in img_addrs:
   
7.         filename=each.split('/')[-1]
   
8.         with open(filename,'wb') as f:
   
9.             img =url_open(each)
   
10.             f.write(img)
    
11.         print(1)
    
12.     print(2)
    
13. 
    
14. 
    
15. def url_open(url):
    
16.     reg= urllib.request.Request(url)
    
17.     reg.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36')
    
18.     response = urllib.request.urlopen(url)
    
19.     html= response.read()
    
20.    
    
21.     return html
    
22. def get_page(url):
    
23.     html = url_open(url).decode('utf-8')
    
24.    
    
25.     #a = html.find('current-comment-page')+23
    
26.     a = re.search (r'\[\d{1,4}\]',html)
    
27.     a = a.group()
    
28.     b=len(a)
    
29.     a=a[1:b-1]
    
30.     return a   
    
31. def find_imgs(url):
    
32.     html =url_open(url).decode('utf-8')
    
33.     img_addrs= []
    
34.     a = html.find('img src=')
    
35.     while a != -1:
    
36.         b = html.find('.jpg',a,a+255)
    
37.         if b!= -1 :
    
38.             if 'lanya' in html[a+9:b+4]:
    
39.                 pass
    
40.             else:
    
41.                 img_addrs.append('http:'+html[a+9:b+4])
    
42.         else:
    
43.             b=a+9
    
44.         a = html.find('img src=',b)
    
45.     print(img_addrs)
    
46.     return img_addrs
    
47. 
    
48. 
    
49. 
    
50. def download_mm(folder='ooxx',pages=4,star=0):
    
51.     os.mkdir(folder)
    
52.     os.chdir(folder)
    
53.    
    
54.     url = 'http://jandan.net/ooxx/'  #妹子图地址
    
55.     #url = 'http://jandan.net/pic/' #无聊图地址
    
56.     if star!= 0 :
    
57.         page_num = star
    
58.     else:
    
59.         page_num=int(get_page(url))
    
60.     for i in  range(pages):
    
61.    
    
62.         page_num-=1
    
63.         page_url = url + 'page-'+str(page_num)+'#comments'
    
64.       
    
65.         img_addrs=find_imgs(page_url)
    
66.      
    
67.         save_imgs(folder,img_addrs)
    
68.         
    
69.         print(page_url)
    
70. if __name__=='__main__':
    
71.     download_mm()
    

复制代码

gaoke11240

1. 
   
2. img_addrs.append(html[a+9:b+4])
   
3. 改成
   
4. img_addrs.append('http:'+html[a+9:b+4])
   
5. 地址就对了

复制代码