已解决

micrchaoo

已解决

yakczh_cu

1. 
   
2. import lxml.html
   
3. 
   
4. url='http://www.icbc.com.cn/ICBCDynamicSite2/other/rmbdeposit.aspx'
   
5. 
   
6. doc = lxml.html.parse(url)
   
7. table = doc.xpath('//table[@frame="border"]')
   
8. if table[0]:
   
9.         for row in table[0].xpath('.//tr'):
   
10.                 cells = row.xpath('.//th') + row.xpath('.//td')
    
11.                 print()
    
12.                 for cell in cells:
    
13.                         # The individual cell's content
    
14.                         content = cell.text_content() #.encode("utf8")
    
15.                         print(content,end="\t")

复制代码

micrchaoo

十分感谢
这个网址我也找到了办法
但我从工行官网上点人个金融的存贷款利率表网页，你这个不一样，里面连日期列表都没有，感觉无从下手

majiayang2012

回复 3# micrchaoo

1. #-*-conding=utf-8 -*-
   
2. import urllib2
   
3. import urllib
   
4. import lxml.html
   
5. import re
   
6. import json
   
7. import sys
   
8. 
   
9. reload(sys)
   
10. sys.setdefaultencoding( "utf-8" )
    
11. 
    
12. results={}
    
13. url ="http://www.yinhang.com/rate/saving/3_1"
    
14. request=urllib2.Request(url)
    
15. response=urllib2.urlopen(request).read()
    
16. for option in lxml.html.fromstring(response).xpath('//*[@id="begin_time"]/option/@value'):
    
17.         values={'begin_time':option}
    
18.         if len(values['begin_time'])>2:
    
19.                 data=urllib.urlencode(values)
    
20.                 request_=urllib2.Request(url,data)
    
21.                 response_=urllib2.urlopen(request_).read()
    
22.                 results[values['begin_time']]=lxml.html.fromstring(response_).xpath("//div[@class='xiangmu mg_top10']/ul/li/text()")
    
23. with open('resutls.json','wb') as f:
    
24.         f.write(json.dumps(results, ensure_ascii = False,encoding='ascii',indent = 4,separators = (',',':')))

复制代码