想要爬取任意页的图片代码该怎么加

hhad

import requests
import parsel
import os

filename = '壁纸\\'

if not os.path.exists(filename):
    os.mkdir(filename)


url = 'http://www.netbian.com/index.htm'
headers = {
    'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.82 Safari/537.36'
}
response = requests.get(url=url, headers=headers)
response.encoding = response.apparent_encoding
#print(response.text)
selector = parsel.Selector(response.text)
href = selector.css('.list li a::attr(href)').getall()
lis = selector.css('.list li')
#print(href)
for li in lis:
    title = li.css('b::text').get()
    if title:
        li_url = 'http://www.netbian.com/' + li.css('a::attr(href)').get()
        response_2 = requests.get(url=li_url, headers=headers)
        selector_2 = parsel.Selector(response_2.text)
        img_url = selector_2.css('.pic img::attr(src)').get()
        img_content = requests.get(url=img_url).content
        with open(filename + title +'.jpg', mode='wb') as f:
            f.write(img_content)
            print(title, img_url)

isdkz

1. import requests
   
2. import parsel
   
3. import os
   
4. 
   
5. filename = '壁纸\\'
   
6. 
   
7. if not os.path.exists(filename):
   
8.     os.mkdir(filename)
   
9. 
   
10. 
    
11. def main(page=1):
    
12.     if page == 1:
    
13.         url = 'http://www.netbian.com/index.htm'
    
14.     else:
    
15.         url = f'http://www.netbian.com/index_{page}.htm'
    
16.     headers = {
    
17.         'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.82 Safari/537.36'
    
18.     }
    
19.     response = requests.get(url=url, headers=headers)
    
20.     response.encoding = response.apparent_encoding
    
21.     # print(response.text)
    
22.     selector = parsel.Selector(response.text)
    
23.     href = selector.css('.list li a::attr(href)').getall()
    
24.     lis = selector.css('.list li')
    
25.     #print(href)
    
26.     for li in lis:
    
27.         title = li.css('b::text').get()
    
28.         if title:
    
29.             li_url = 'http://www.netbian.com/' + li.css('a::attr(href)').get()
    
30.             response_2 = requests.get(url=li_url, headers=headers)
    
31.             selector_2 = parsel.Selector(response_2.text)
    
32.             img_url = selector_2.css('.pic img::attr(src)').get()
    
33.             img_content = requests.get(url=img_url).content
    
34.             with open(filename + title +'.jpg', mode='wb') as f:
    
35.                 f.write(img_content)
    
36.                 print(title, img_url)
    
37. 
    
38. if __name__ == '__main__':
    
39.     main(2)                     # 爬取第二页

复制代码