这是个好网站

此人

1. import requests
   
2. from lxml import etree
   
3. import os
   
4. 
   
5. 
   
6. class ManhuaSpider:
   
7.     def __init__(self):
   
8.         self.url='http://www.ccnn88.com'
   
9.         self.start_url='http://www.ccnn88.com/htm/Pic4/15608.htm'
   
10.         self.headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36'}
    
11.         
    
12.     def parse_url(self, url):
    
13.         r = requests.get(url, headers=self.headers)
    
14.         return r
    
15.         
    
16.     def save_img(self, imgs, title):
    
17.         os.mkdir(title)
    
18.         os.chdir(title)
    
19.         for i in imgs:
    
20.             with open(i.url.split('_')[-1], 'wb') as f:
    
21.                 f.write(i.content)
    
22.         os.chdir('..')
    
23.         
    
24.     def get_content_list(self,url):
    
25.         html = etree.HTML(url.content.decode())
    
26.         title = html.xpath("/html/head/title/text()")[0]
    
27.         print(title)
    
28.         next_url = self.url + html.xpath("//li/a[contains(text(),'下一篇')]/@href")[0] if html.xpath("//li/a[contains(text(),'下一篇')]/@href") else None
    
29.         if os.path.isdir(title):
    
30.             return next_url
    
31.         imgs = [self.parse_url(u) for u in html.xpath("//div[@class='details-content text-justify']//img/@src")]
    
32.         self.save_img(imgs,title)
    
33.         return next_url
    
34.         
    
35.     def run(self):
    
36.         next_url = self.start_url
    
37.         while next_url is not None:
    
38.             res = self.parse_url(next_url)
    
39.             next_url = self.get_content_list(res)
    
40.       
    
41.       
    
42. if __name__ == "__main__":
    
43.     manhua = ManhuaSpider()
    
44.     manhua.run()

复制代码

g403290116

Traceback (most recent call last):
  File "D:\AA\1.py", line 44, in <module>
    manhua.run()
  File "D:\AA\1.py", line 39, in run
    next_url = self.get_content_list(res)
  File "D:\AA\1.py", line 32, in get_content_list
    self.save_img(imgs,title)
  File "D:\AA\1.py", line 17, in save_img
    os.mkdir(title)
OSError: [WinError 123] 文件名、目录名或卷标语法不正确。