为什么 会出现 错误 帮忙看一下 谢谢

caiheng2019

这是代码

1. import requests
   
2. import re
   
3. from lxml import etree
   
4. import os
   
5. 
   
6. def download_pics(url):
   
7.         response = requests.get(url,headers=headers)
   
8.         base_link = etree.HTML(response.text).xpath('//div[@class="main-image"]//img/@src')[0][0:-6]
   
9.         page_info = etree.HTML(response.text).xpath('//div[@class="pagenavi"]//span/text()')
   
10.         max_page = int(page_info[-2])
    
11.         for i in range(1,max_page+1):
    
12.                 page = str(i).zfill(2)
    
13.                 download_link = base_link+str(page)+'.jpg'
    
14.                 response = requests.get(download_link)
    
15.                 pic_name = download_link[-9:-4]
    
16.                 print('目前第{}套妹子,共{}张  正在下载第{} 张图片......'.format (list_cnt,max_page,i))
    
17.                 with open(save_path+'\\'+pic_name+'.jpg','wb') as f:
    
18.                         f.write(response.content)
    
19. 
    
20. def get_list(url):
    
21.         global list_cnt,save_path
    
22.         list_cnt = 1
    
23.         response = requests.get(url,headers=headers)
    
24.         p = r'<a href="(https://www.mzitu.com/\d+)" target="_blank">'
    
25.         list_pool = re.findall(p,response.text)
    
26.         for li in list_pool:
    
27.                 save_path = '美女图\\EP'+str(list_cnt).zfill(3)
    
28.                 if not os.path.exists(save_path):
    
29.                         os.mkdir(save_path)
    
30.                 download_pics(url)
    
31.                 list_cnt+=1
    
32. 
    
33. def main():
    
34.         if not os.path.exists('美女图'):
    
35.                 os.mkdir('美女图')
    
36.         os.startfile('美女图')
    
37.         get_list(url)
    
38. 
    
39. if __name__=="__main__":
    
40.         url = 'https://www.mzitu.com/'
    
41.         headers = {'user-agent': 'Mozilla/5.0'}
    
42.         main()
    

复制代码

出现错误  Traceback (most recent call last):
  File "C:\Users\Administrator\Desktop\新建文本文档 (3).py", line 42, in <module>
    main()
  File "C:\Users\Administrator\Desktop\新建文本文档 (3).py", line 37, in main
    get_list(url)
  File "C:\Users\Administrator\Desktop\新建文本文档 (3).py", line 30, in get_list
    download_pics(url)
  File "C:\Users\Administrator\Desktop\新建文本文档 (3).py", line 8, in download_pics
    base_link = etree.HTML(response.text).xpath('//div[@class="main-image"]//img/@src')[0][0:-6]
IndexError: list index out of range
[Finished in 1.6s]

傻纸

你看你这两句类名是不是写错了

1. 
   
2. base_link = etree.HTML(response.text).xpath('//div[@class="main-image"]//img/@src')[0][0:-6]
   
3. page_info = etree.HTML(response.text).xpath('//div[@class="pagenavi"]//span/text()')
   

复制代码

用print(response.text)可以查看网页的html，这里面找不到你指定的main-image和pagenavi这两个类
lxml库没怎么用过，不知道对不对

Stubborn

1. base_link = etree.HTML(response.text).xpath('//div[@class="main-image"]//img/@src')[0][0:-6]
   
2. base_link = etree.HTML(response.text).xpath('//div[@class="main-image"]//img/@src')
   
3. print(base_link)
   
4. print(type(base_link ))

复制代码

去掉后面的截取，和[0],先确认获得的是什么对象