python 爬虫系列07-天气爬虫

看天气

import requests
from bs4 import BeautifulSoup
ALL_DATA = []
def parse_page(url):
    headers = {
        'User-Agent': "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.84 Safari/537.36"
    }
    response = requests.get(url, headers=headers)
    text = response.content.decode('utf-8')
    soup = BeautifulSoup(text, 'html5lib')
    conMidtab = soup.find('div', class_='conMidtab')
    tables = conMidtab.find_all('table')
    for table in tables:
        trs = table.find_all('tr')[2:]
        for index,tr in enumerate(trs):
            tds = tr.find_all('td')
            city_td = tds[0]
            if index == 0:
                city_td = tds[1]
            city = list(city_td.stripped_strings)[0]
            temp_td = tds[-2]
            min_temp = list(temp_td.stripped_strings)[0]
            ALL_DATA.append({"城市 ":city,"温度 ":int(min_temp)})
          #  print("城市: %s ,温度%s℃ " % (city,int(min_temp)))

def main():
    urls = {
        'http://www.weather.com.cn/textFC/hb.shtml',
        'http://www.weather.com.cn/textFC/db.shtml',
        'http://www.weather.com.cn/textFC/hd.shtml',
        'http://www.weather.com.cn/textFC/hz.shtml',
        'http://www.weather.com.cn/textFC/hn.shtml',
        'http://www.weather.com.cn/textFC/xb.shtml',
        'http://www.weather.com.cn/textFC/xn.shtml',
        'http://www.weather.com.cn/textFC/gat.shtml'
    }
    for url in urls:
        parse_page(url)
    ALL_DATA.sort(key=lambda data:data['min_temp'])
    print(ALL_DATA)
if __name__ == "__main__":
    main()