import re
import requests
from bs4 import BeautifulSoup

def get_page(url): #获取URL
  try:
    headers = {'user-agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36'}
    r = requests.get(url,headers)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    return r.text
  except:
    return '出现异常' #异常处理，防止出现错误

def parse_page(html, weather_list):
  soup = BeautifulSoup(html, 'html.parser')
  day_list = soup.find('ul', 't clearfix').find_all('li')
  for day in day_list:
    date = day.find('h1').get_text()
    wea = day.find('p', 'wea').get_text()
    if day.find('p', 'tem').find('span'): #判断标签'p','tem'下是否有标签'span'，以此判断是否有最高温
        tem_h = day.find('p', 'tem').find('span').get_text()
    else:
        tem_h = '' #最高温
    tem_l = day.find('p', 'tem').find('i').get_text() #最低温
    win1 = re.findall('(").*")', str(day.find('p','win').find('em')))
    win2 = '-'.join(win1) #风向，win1-win2
    level = day.find('p', 'win').find('i').get_text() #风力
    weather_list.append([date, wea, tem_l, tem_h, win2, level])


def print_wea(weather_list):
  s = ' \t' * 3
  print(s.join(('日期', '天气', '最低温', '最高温', '风向', '风力')))
  for i in weather_list:
    print(i[0], '\t',i[1],'\t\t\t',i[2],'\t\t\t',i[3],'\t\t',i[4],'\t\t',i[5]) #按格式输出

def main():
  url = 'http://www.weather.com.cn/weather/101200601.shtml'
  html = get_page(url)
  wea_list = []
  parse_page(html, wea_list)
  print("\t\t\t\t\t\t\t\t\t黄石市近7天天气预报")
  print_wea(wea_list)

if __name__ == '__main__':
  main()