爬虫 天气

爬取上海临沂两地天气和污染指数

import urllib.request
from pyquery import PyQuery as pq
import re

city= ['上海','临沂']
city_num = ['101020100','101120901']

def find_weather(country):
     url = 'http://www.weather.com.cn/weather/' + country + '.shtml'
     html = urllib.request.urlopen(url).read().decode('utf-8')
     parse = re.compile('class="sky skyid.*?<h1>(.*?)</h1>.*?<span>(.*?)</span>.*?<i>(.*?)</i>'
                   +'.*?<p class="win">.*?<i>(.*?)</i>',re.S)
     doc = pq(html)
     polute = list(doc('.li6 span').text())
     item = re.findall(parse,html)
     print(polute)
     for each in item:
          yield{
               '日期': each[0],
               '温度': each[1]+'/' + each[2],
               '风级': each[3],
          }

def main():
     for i in range(2):
          weater =[]
          print(city[i]+'\n')
          for each in find_weather(city_num[i]):
               weater.append(each)
          for i in range(7):
               print(weater[i])
          print('\n')
               
if __name__ == '__main__':
     main()