爬京客隆PDF代码

赵乾舟

1. 
   
2. import requests
   
3. import os
   
4. from lxml import etree
   
5. if not os.path.exists('c:/c'):
   
6.     os.mkdir('c:/c')
   
7. url = 'https://www.jkl.com.cn/cn/invest.aspx'
   
8. listpdf = []
   
9. listname = []
   
10. for page in range(1,4):
    
11. 
    
12.     fanye = {'__EVENTTARGET': 'AspNetPager1',
    
13.             '__EVENTARGUMENT': page}
    
14. 
    
15.     UA = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'}
    
16.     respon = requests.get( url = url,params=fanye,headers=UA).text
    
17.     jiexi = etree.HTML(respon)
    
18.     pdflist = jiexi.xpath('//div[@class="newsLis"]//li//@href')
    
19.     name = jiexi.xpath('//div[@class="newsLis"]//li/a/text()')
    
20.     for i in pdflist:
    
21. 
    
22.         i = 'https://www.jkl.com.cn' + i
    
23.         listpdf.append(i)
    
24.         #print(i)
    
25.     for j in name:
    
26.         j= j.strip()
    
27.         listname.append(j)
    
28. 
    
29. zidian = dict(zip(listname,listpdf))
    
30. 
    
31. for a,b in zidian.items():
    
32.     houzhui = b.split('.')[-1]
    
33.     pdfshuju = requests.get(url=b,headers=UA).content
    
34.     add = 'c:/c/' + a +'.'+houzhui
    
35.     with open(add,'wb') as u:
    
36.         u.write(pdfshuju)
    
37.         print(a,'下载成功')

复制代码