[已解决]怎么都跑不出来啊

JKmorgan

import urllib.request
import os

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36')
    response = urllib.request.urlopen(url)
    html = response.read()
   

    return html

def get_page(url):
    html = url_open(url).decode('utf-8')

    a = html.find('current-comment-page') + 23
    b = html.find(']',a)
    print(html[a:b])
    return html[a:b]

def find_imgs(url):
    html = url_open(url).decode('utf-8')
    img_addrs = []

    a = html.find('img src=')

    while a != -1:
        b = html.find('.jpg', a, a+255)
        if b != -1:
            img_addrs.append(html[a+9:b+4])
        else:
            b = a + 9
        a = html.find('img src=',b)

   
    return img_addrs

def save_imgs(folder,img_addrs):
    for each in img_addrs:
        filename = each.split('/')[-1]
        with open(filename,'wb') as f:
            img = url_open(each)
            f.write(img)
   

def download_mm(folder='ooxx',page=10):
    os.mkdir(folder)
    os.chdir(folder)

    url = 'http://jandan.net/ooxx/'
    page_num = int(get_page(url))

    for i in range(page):
        page_num -= i
        page_url = url + 'page-'+ str(page_num) + '#comments'
        img_addrs = find_imgs(page_url)
        save_imgs(folder, img_addrs)

if __name__ == '__main__':
    download_mm()
        

报错
Traceback (most recent call last):
  File "C:\Users\Administrator\Desktop\pc1.py", line 60, in <module>
    download_mm()
  File "C:\Users\Administrator\Desktop\pc1.py", line 57, in download_mm
    save_imgs(folder, img_addrs)
  File "C:\Users\Administrator\Desktop\pc1.py", line 42, in save_imgs
    img = url_open(each)
  File "C:\Users\Administrator\Desktop\pc1.py", line 5, in url_open
    req = urllib.request.Request(url)
  File "F:\Internet\python3.6.2\lib\urllib\request.py", line 329, in __init__
    self.full_url = url
  File "F:\Internet\python3.6.2\lib\urllib\request.py", line 355, in full_url
    self._parse()
  File "F:\Internet\python3.6.2\lib\urllib\request.py", line 384, in _parse
    raise ValueError("unknown url type: %r" % self.full_url)
ValueError: unknown url type: '//wx4.sinaimg.cn/mw600/942a2e4agy1fj6sn0gvs2j20dw0afjtd.jpg'

最佳答案

月排行榜 / 总排行榜

ba21

2017-9-4 09:10:48

1. import urllib.request
   
2. import sys
   
3. import os
   
4. 
   
5. 
   
6. def url_open(url):
   
7.     req = urllib.request.Request(url)
   
8.     req.add_header('User-Agent',
   
9.                    'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36')
   
10.     resp = urllib.request.urlopen(url)
    
11.     html = resp.read()
    
12.     # print(html)
    
13.     return html
    
14. 
    
15. 
    
16. def get_page(url):  # 获取图片页码
    
17.     html = url_open(url).decode('utf-8')  # 解码，之后查找图片页码做准备
    
18.     a = html.find('current-comment-page') + 23  # 返回页码数的首位置
    
19.     b = html.find(']', a)  # 返回页码数的末位置
    
20.     # print(html[a:b])
    
21.     return html[a:b]  # 拼接返回页码
    
22. 
    
23. 
    
24. def find_imgs(url):  # 在当前URL查找图片
    
25.     html = url_open(url).decode('utf-8')
    
26.     img_addrs = []
    
27. 
    
28.     a = html.find('img src=')  # 图片真实地址
    
29. 
    
30.     while a != -1:
    
31.         b = html.find('.jpg', a, a + 200)
    
32.         if b != -1:
    
33.             img_addrs.append(html[a + 9:b + 4])
    
34.         else:
    
35.             b = a + 9
    
36. 
    
37.         a = html.find('img src=', b)
    
38.     return img_addrs
    
39. 
    
40. 
    
41. def save_imgs(img_addrs):
    
42.     for each in img_addrs:
    
43.         filename = each.split('/')[-1]
    
44.         with open(filename, 'wb') as f:
    
45.             img = url_open("http:"+each)
    
46.             f.write(img)
    
47. 
    
48. 
    
49. def download(folder='Girls', pages=20):
    
50.     os.mkdir(folder)  # 创建文件夹
    
51.     os.chdir(folder)  # 切换到文件夹目录
    
52. 
    
53.     url = 'http://jandan.net/ooxx'
    
54.     page_num = int(get_page(url))  # 获取当前该图片页码
    
55. 
    
56.     for i in range(pages):  # 依次下载指定页数的图片
    
57.         page_num -= 1
    
58.         page_url = url + '/page-' + str(page_num) + '#comments'  # 图片的URL
    
59.         # print(page_url)
    
60.         img_addrs = find_imgs(page_url)
    
61.         save_imgs(img_addrs)
    
62. 
    
63. 
    
64. if __name__ == '__main__':
    
65.     download()
    

复制代码

跳转到最佳答案楼层

左手十字

url错误，前面少了http

ba21

1. import urllib.request
   
2. import sys
   
3. import os
   
4. 
   
5. 
   
6. def url_open(url):
   
7.     req = urllib.request.Request(url)
   
8.     req.add_header('User-Agent',
   
9.                    'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36')
   
10.     resp = urllib.request.urlopen(url)
    
11.     html = resp.read()
    
12.     # print(html)
    
13.     return html
    
14. 
    
15. 
    
16. def get_page(url):  # 获取图片页码
    
17.     html = url_open(url).decode('utf-8')  # 解码，之后查找图片页码做准备
    
18.     a = html.find('current-comment-page') + 23  # 返回页码数的首位置
    
19.     b = html.find(']', a)  # 返回页码数的末位置
    
20.     # print(html[a:b])
    
21.     return html[a:b]  # 拼接返回页码
    
22. 
    
23. 
    
24. def find_imgs(url):  # 在当前URL查找图片
    
25.     html = url_open(url).decode('utf-8')
    
26.     img_addrs = []
    
27. 
    
28.     a = html.find('img src=')  # 图片真实地址
    
29. 
    
30.     while a != -1:
    
31.         b = html.find('.jpg', a, a + 200)
    
32.         if b != -1:
    
33.             img_addrs.append(html[a + 9:b + 4])
    
34.         else:
    
35.             b = a + 9
    
36. 
    
37.         a = html.find('img src=', b)
    
38.     return img_addrs
    
39. 
    
40. 
    
41. def save_imgs(img_addrs):
    
42.     for each in img_addrs:
    
43.         filename = each.split('/')[-1]
    
44.         with open(filename, 'wb') as f:
    
45.             img = url_open("http:"+each)
    
46.             f.write(img)
    
47. 
    
48. 
    
49. def download(folder='Girls', pages=20):
    
50.     os.mkdir(folder)  # 创建文件夹
    
51.     os.chdir(folder)  # 切换到文件夹目录
    
52. 
    
53.     url = 'http://jandan.net/ooxx'
    
54.     page_num = int(get_page(url))  # 获取当前该图片页码
    
55. 
    
56.     for i in range(pages):  # 依次下载指定页数的图片
    
57.         page_num -= 1
    
58.         page_url = url + '/page-' + str(page_num) + '#comments'  # 图片的URL
    
59.         # print(page_url)
    
60.         img_addrs = find_imgs(page_url)
    
61.         save_imgs(img_addrs)
    
62. 
    
63. 
    
64. if __name__ == '__main__':
    
65.     download()
    

复制代码