

In [23]:

    
# -*- coding:utf-8 -*-
import requests
from bs4 import BeautifulSoup

url = 'http://nthr.nantou.gov.tw/CustomerSet/032_population/u_population_v.asp'
id = "?id={8C3E3E30-CA6D-4819-87D7-CC6C52B1EA67}"

find_location = [
    u"光輝里",
    u"光華里",
    u"光榮里",
    u"光明里",
    u"營北里",
    u"營南里",
    u"內新里",
    u"內興里"
    ]

res = requests.get(url + id +"&yy=102&&mm=08")
# str type
print type(res.content)
# 需傳入content才會正確產生格式
soup = BeautifulSoup(res.content,"html.parser")
# utf-8
print type(soup.original_encoding)
# 印出內容
# print soup.contents
table = soup.find('table',attrs = {'class':'C-tableA0'})

for tr in table.select('tr'):
    for location in find_location:
        #比對此row是否有包含欲尋找的里名稱         
        if tr.find(string=location):
            # 取出 list td             
            td_list = tr.find_all('td')
            # 顯示名稱與總人口數             
            print td_list[0].text,td_list[-1].text
                
        

    # td.get_text() or text will not show unicode encode ,it will show real text









    



<type 'str'>
<type 'unicode'>
內新里 1,788
內興里 8,047
光明里 1,284
光華里 1,132
光榮里 1,402
光輝里 695
營北里 7,387
營南里 2,750