[已解决]老师请帮我看看这个错误如何解决

redaiconglin

import urllib.request
import os
def get_page(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36')
    response = urllib.request.urlopen(req)
    html = response.read().decode('utf-8')
    a = html.find('thisclass __web-inspector-hide-shortcut__')+42
    b = html.find('<',a)
    print(html[a:b])                                         想要看一下图片页面的地址是否正确，但是显示编码错误。请老师帮我看看如何解决谢谢了
def find_img (url):
    pass
def save_img(name,img_addrs):
    pass
def download_mm(name='tupian',pages = 10):
    os.mkdir(name)
    os.chdir(name)
    url = 'https://www.tupianzj.com/meinv/xinggan'
    page_num = int(get_page(url))
    for i in range(pages):
        page_num -= i
        page_url = url +'list_176_'+str(page_num)+'.html'
        img_addrs = find_img (page_url)
        save_img(name,img_addrs)
if __name__ == '__main__':
    download_mm()
目前代码还未写完只是想先看一下图片页面的数字提取的是不是正确。但显示编码错误。

最佳答案

月排行榜 / 总排行榜

ba21

2022-4-10 21:54:43

import cchardet

1. import cchardet
   
2. import urllib.request
   
3. import os
   
4. 
   
5. def get_page(url):
   
6.     req = urllib.request.Request(url)
   
7.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36')
   
8.     response = urllib.request.urlopen(req)
   
9.     html = response.read()
   
10.    
    
11.     enc = cchardet.detect(html)
    
12.     enc = enc['encoding']
    
13.     html = html.decode(enc)
    
14.     print(html)
    
15. 
    
16.     a = html.find('thisclass __web-inspector-hide-shortcut__')
    
17.     b = html.find('<',a)
    
18.     print(html[a:b])                                         
    
19. def find_img (url):
    
20.     pass
    
21. def save_img(name,img_addrs):
    
22.     pass
    
23. def download_mm(name='tupian',pages = 10):
    
24.     os.mkdir(name)
    
25.     os.chdir(name)
    
26.     url = 'https://www.tupianzj.com/meinv/xinggan'
    
27.     page_num = int(get_page(url))
    
28.     for i in range(pages):
    
29.         page_num -= i
    
30.         page_url = url +'list_176_'+str(page_num)+'.html'
    
31.         img_addrs = find_img (page_url)
    
32.         save_img(name,img_addrs)
    
33. if __name__ == '__main__':
    
34.     download_mm()
    

复制代码

跳转到最佳答案楼层

ba21

import cchardet

1. import cchardet
   
2. import urllib.request
   
3. import os
   
4. 
   
5. def get_page(url):
   
6.     req = urllib.request.Request(url)
   
7.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36')
   
8.     response = urllib.request.urlopen(req)
   
9.     html = response.read()
   
10.    
    
11.     enc = cchardet.detect(html)
    
12.     enc = enc['encoding']
    
13.     html = html.decode(enc)
    
14.     print(html)
    
15. 
    
16.     a = html.find('thisclass __web-inspector-hide-shortcut__')
    
17.     b = html.find('<',a)
    
18.     print(html[a:b])                                         
    
19. def find_img (url):
    
20.     pass
    
21. def save_img(name,img_addrs):
    
22.     pass
    
23. def download_mm(name='tupian',pages = 10):
    
24.     os.mkdir(name)
    
25.     os.chdir(name)
    
26.     url = 'https://www.tupianzj.com/meinv/xinggan'
    
27.     page_num = int(get_page(url))
    
28.     for i in range(pages):
    
29.         page_num -= i
    
30.         page_url = url +'list_176_'+str(page_num)+'.html'
    
31.         img_addrs = find_img (page_url)
    
32.         save_img(name,img_addrs)
    
33. if __name__ == '__main__':
    
34.     download_mm()
    

复制代码

redaiconglin

ba21 发表于 2022-4-10 21:54
import cchardet

感谢老师