【爬虫练手】爬中国天气网

import requests
from bs4 import BeautifulSoup
from pyecharts.charts import Bar

ALL_DATA = []

def parser_page(url):
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 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 tr in trs:
            tds = tr.find_all('td')
            city_td = tds[0]
            city = list(city_td.stripped_strings)[0]
            temperature = list(tds[-2].stripped_strings)[0]
            ALL_DATA.append({'city':city,'temperature':int(temperature)})
            # print({'city':city,'temperature':temperature})

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/hb.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/hb.shtml#',
        'http://www.weather.com.cn/textFC/xn.shtml#',
        'http://www.weather.com.cn/textFC/gat.shtml#',
    ]
    for url in urls:
        parser_page(url)
    ALL_DATA.sort(key=lambda data:data['temperature'])
    data = ALL_DATA[:10]
    citys = list(map(lambda x:x['city'],data))
    temps = list(map(lambda x:x['temperature'],data))
    # print(citys,temps)
    bar = Bar()
    bar.add_xaxis(citys)
    bar.add_yaxis("最低气温",temps)
    bar.render('temperature.html')

if __name__ == '__main__':
    main()

2020年3月17日跟着视频加了一条可视化的操作。