爬取一页内容的多列数据

赵乾舟

1. import requests
   
2. from pyquery import PyQuery as pq
   
3. from openpyxl import Workbook
   
4. wb = Workbook()
   
5. sheet = wb.active
   
6. sheet['a1'] = '标题'
   
7. sheet['b1'] = '作者'
   
8. url ='http://suixian666.com/forum.php?mod=forumdisplay&fid=54'
   
9. spon = requests.get(url=url).text
   
10. 
    
11. d = pq(spon)
    
12. 
    
13. for item in d('#threadlisttableid tbody'):
    
14.     sub_b = pq(item)
    
15.     print(sub_b('.xst').text(),end=' ')
    
16.     print(sub_b('.by a').text().split(' ')[0])
    
17.     sheet.append([sub_b('.xst').text(),sub_b('.by a').text().split(' ')[0]])
    
18. 
    
19. wb.save('mine.xlsx')
    

复制代码

赵乾舟

赵乾舟

发现个怪事，我抄代码的时候，把pq换成其他内容，也可以正常访问抓取