糗事百科数据下载到excel

mozzielx

写入excel数据前要保证：name、agre_num和comment_num的数目一致
欢迎大家指正

1. # -*- coding: utf-8 -*-
   
2. """
   
3. Created on Sun Jul 24 12:36:25 2016
   
4. 
   
5. @author: mozzielx
   
6. """
   
7. 
   
8. import re
   
9. from urllib.error import URLError
   
10. from urllib.request import  Request,urlopen
    
11. from openpyxl import Workbook
    
12. from openpyxl.compat import range
    
13. 
    
14. def get_content(url):
    
15.     req=Request(url)
    
16.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.84 Safari/537.36')
    
17.     temp=urlopen(req)
    
18.     html=temp.read().decode('utf-8')
    
19.     return html
    
20. 
    
21. def get_target(tar):
    
22.     name=re.findall(r'<a href="/users/[^"]+/" target="_blank" title="(.+)">',tar)
    
23.     agre_num=re.findall(r'<span class="stats-vote"><i class="number">(.+)</i> 好笑</span>',tar)
    
24.     comment_num=re.findall(r'<a href="/article/[^"]+" data-share="/article/[^"]+" id="[^"]+" class="qiushi_comments" target="_blank">\n<i class="number">(.+)</i> 评论\n</a>',tar)
    
25. #    print(len(name),len(agre_num),len(comment_num))
    
26. 
    
27.     for row in range(2,len(name)+2):#指定行数
    
28.             for col in range(1,2):#指定列数
    
29.                 _ = ws.cell(column=col, row=row, value="%s" % name[row-2])
    
30.     for row in range(2,len(agre_num)+2):
    
31.             for col in range(2,3):
    
32.                 _ = ws.cell(column=col, row=row, value="%s" % agre_num[row-2])  
    
33.     for row in range(2,len(comment_num)+2):
    
34.             for col in range(3,4):
    
35.                 _ = ws.cell(column=col, row=row, value="%s" % comment_num[row-2])
    
36. 
    
37. if __name__ == "__main__":
    
38.     url='http://www.qiushibaike.com/8hr/page/4/?s=4897779'
    
39.     wb=Workbook()#建立excel文件
    
40.     ws=wb.active
    
41.     ws['A1']='作者'
    
42.     ws['B1']='点赞数'
    
43.     ws['C1']='评论数'
    
44.     get_target(get_content(url))
    
45.     wb.save("糗事百科段子数据.xlsx")
    

复制代码