使用BeautifulSoup解析HTML，保存为excel。使用xlwt模块，想到了两种保存方式：一种是将全国的地区和区号放在一个sheet里面，另一种是把每个地区的单独放在一个sheet里。而且保存的excel单元格使用的全部是默认样式，xlwt模块支持给单元格设置样式，设置字体等操作，这次只是简单获取数据，如果下次还有兴趣，再继续完善。

python

# -*- coding:utf-8 -*-

import xlwt, urllib
from bs4 import BeautifulSoup

w =  xlwt.Workbook(encoding = 'utf-8')
sheet = w.add_sheet('sheet 1')
sheet.write(0, 0, 'num')
sheet.write(0, 1, 'name')
sheet.write(0, 2, 'code')

url = 'http://dianhua.mapbar.com/'
index = urllib.urlopen(url)
soup = BeautifulSoup(index,"html.parser")
result = soup.find_all('div', {'class':'phonenum clr'})

n = 1

for each_div in result:
    city_title = each_div.find('h2').get_text()
    city_content = each_div.find_all('dl')
    sheet.write(n, 0, city_title)
    n = n + 1

    for each_content in city_content:
        city_name = each_content.find('dt').get_text()
        city_code = each_content.find('dd').get_text()
        sheet.write(n, 0, n - 1)
        sheet.write(n, 1, city_name)
        sheet.write(n, 2, city_code)
        n = n + 1

w.save('D:/img/mimi.xls')

预览结果

excel内容

python 

# -*- coding:utf-8 -*-

import xlwt, urllib
from bs4 import BeautifulSoup

w =  xlwt.Workbook(encoding = 'utf-8')

url = 'http://dianhua.mapbar.com/'
index = urllib.urlopen(url)
soup = BeautifulSoup(index,"html.parser")
result = soup.find_all('div', {'class':'phonenum clr'})

for each_div in result:
    n = 1
    city_title = each_div.find('h2').get_text()
    city_content = each_div.find_all('dl')
    sheet = w.add_sheet(city_title)
    sheet.write(0, 0, 'num')
    sheet.write(0, 1, 'name')
    sheet.write(0, 2, 'code')

    for each_content in city_content:
        city_name = each_content.find('dt').get_text()
        city_code = each_content.find('dd').get_text()
        sheet.write(n, 0, n)
        sheet.write(n, 1, city_name)
        sheet.write(n, 2, city_code)
        n = n + 1

w.save('D:/img/mini.xls')

预览结果

excel内容