Python 如何使用bs4获取多个嵌套的div值并以json格式输出？

我想要刮取的Html数据如下所示。它由许多div标记组成

 <div id="hour3"> 
   <div id="day0" class="hour3"> 
     <div class="row first"> 
       <div class="label">Time</div> 
       <div style="font-size: 12px;">14:00</div> 
       <div style="font-size: 12px;">17:00</div> 
     </div> 
     <div class="row wd"> 
       <div class="label h3_wd">Temperature</div> 
       <div>27.5℃ </div> 
       <div>27.8℃ </div> 
     </div> 
   <div id="day1" class="hour3"> 
     <div class="row first"> 
       <div class="label">Time</div> 
       <div style="font-size: 12px;">8:00</div> 
       <div style="font-size: 12px;">11:00</div> 
     </div> 
     <div class="row wd"> 
       <div class="label h3_wd">Temperature</div> 
       <div>27.5℃ </div> 
       <div>27.8℃ </div> 
     </div>

在网站上，它看起来像一张桌子

              day0                day1

Time          14:00    17:00      08:00    11:00

Temperature   27.5℃   27.8℃     27.5℃   27.8℃ 

我有：

import time, re
import urllib2
from bs4 import BeautifulSoup

start_time = time.time()

url = 'some url'
html = urllib2.urlopen(url).read()
soup = BeautifulSoup(html,'html.parser')

for datas in soup.findAll('div', attrs = {'id':'hour3'}):
    for dates in datas('div',{'class':'row first'}):
        for temp in datas('div',{'class':'row wd'}):

            result = {
                'day0':[
                    {
                        'date' : dates.text.strip(),
                        'temperature' : temp.text.strip()
                    }
                ]
            }

print result

我得到：

{'day0': [{'date': u'Description 1\n       \n\n        14:00\n       \n\n        17:00\n       \n\n        08:00\n       \n\n        11:00\n, 'temperature': 27.5\u2103 \n       \n\n        27.8\u2103 \n       \n\n        27.5\u2103 \n       \n\n        27.8\u2103 \n       \n\n}]}

如何获取所需格式的数据？

html\u doc=''
html_doc='''<div id="hour3"> 
  <div id="day0" class="hour3"> 
    <div class="row first"> 
      <div class="label">Time</div> 
      <div style="font-size: 12px;">14:00</div> 
      <div style="font-size: 12px;">17:00</div> 
    </div> 
    <div class="row wd"> 
      <div class="label h3_wd">Temperature</div> 
      <div>27.5 </div> 
      <div>27.8 </div> 
    </div> 
  <div id="day1" class="hour3"> 
    <div class="row first"> 
      <div class="label">Time</div> 
      <div style="font-size: 12px;">8:00</div> 
      <div style="font-size: 12px;">11:00</div> 
    </div> 
    <div class="row wd"> 
      <div class="label h3_wd">Temperature</div> 
      <div>27.5 </div> 
      <div>27.8 </div> 
    </div>'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html_doc, 'html.parser')
result={}
days_conut=0
for datas in soup.findAll('div', attrs = {'id':'hour3'}):
    for dates in datas('div',{'class':'row first'}):

        for temp in datas('div',{'class':'row wd'}):
            lst_of_time=dates.text.split()[1:]
            lst_of_temp=temp.text.split()[1:]
            count=0
            result['day'+str(days_conut)]=[]
            for i in lst_of_temp:
              result['day'+str(days_conut)].append({'time':lst_of_time[count],'temperature':lst_of_temp[count]})
              count=count+1
        days_conut=days_conut+1


print result

时间
14:00 
17:00 
温度
27.5
27.8
时间
8:00 
11:00 
温度
27.5
27.8
'''
从bs4导入BeautifulSoup
soup=BeautifulSoup（html_doc，'html.parser'）
结果={}
天数=0
对于soup.findAll（'div'，attrs={id'：'hour3'}）中的数据：
对于数据中的日期（'div'，{'class'：'row first'}）：
对于数据中的临时（'div'，{'class'：'row wd'}）：
lst_of_time=dates.text.split（）[1:]
lst_of_temp=temp.text.split（）[1:]
计数=0
结果['day'+str（days_conut）]=[]
对于温度的第一个温度中的i：
结果['day'+str（days_conut）]。追加（{'time'：lst_of_time[count]，'temperature'：lst_of_temp[count]}）
计数=计数+1
天数=天数+1
打印结果

html_doc='''<div id="hour3"> 
  <div id="day0" class="hour3"> 
    <div class="row first"> 
      <div class="label">Time</div> 
      <div style="font-size: 12px;">14:00</div> 
      <div style="font-size: 12px;">17:00</div> 
    </div> 
    <div class="row wd"> 
      <div class="label h3_wd">Temperature</div> 
      <div>27.5 </div> 
      <div>27.8 </div> 
    </div> 
  <div id="day1" class="hour3"> 
    <div class="row first"> 
      <div class="label">Time</div> 
      <div style="font-size: 12px;">8:00</div> 
      <div style="font-size: 12px;">11:00</div> 
    </div> 
    <div class="row wd"> 
      <div class="label h3_wd">Temperature</div> 
      <div>27.5 </div> 
      <div>27.8 </div> 
    </div>'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html_doc, 'html.parser')
result={}
days_conut=0
for datas in soup.findAll('div', attrs = {'id':'hour3'}):
    for dates in datas('div',{'class':'row first'}):

        for temp in datas('div',{'class':'row wd'}):
            lst_of_time=dates.text.split()[1:]
            lst_of_temp=temp.text.split()[1:]
            count=0
            result['day'+str(days_conut)]=[]
            for i in lst_of_temp:
              result['day'+str(days_conut)].append({'time':lst_of_time[count],'temperature':lst_of_temp[count]})
              count=count+1
        days_conut=days_conut+1


print result

...
soup = BeautifulSoup(html, 'html.parser')

result = {}
for day in soup.find_all('div', attrs = {'class': 'hour3'}):
    times = day.find('div', {'class': 'row first'}).find_all('div')
    temps = day.find('div', {'class': 'row wd'}).find_all('div')
    result[day.get('id')] = [
        {'Time': t.text, 'Temperature': temp.text}
        for t, temp in zip(times[1:], temps[1:])
    ]
    # [1:] - to skip header column

print result