python 爬取中国天气网+数据可视化

需要安装的库：requests,bs4,pyecharts[版本0.1.9.4],lxml,html5lib

代码复制粘贴即可用，2019年8月9日测试通过

爬取全国城市的最高温度，以及导出张柱状图：

import requests
from bs4 import BeautifulSoup
from pyecharts import Bar

DATA = []

def parse_page(url):
    headers={
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 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 :
            city = tr.find_all('td')[-8]
            city_name = list(city.stripped_strings)[0]
            temp = tr.find_all('td')[-5]
            max_temp=list(temp.stripped_strings)[0]
            DATA.append({"city":city_name,"temp":int(max_temp)})

def main():
    baseurl = "http://www.weather.com.cn/textFC/{}.shtml"
    areas = ['hb','db','hz','hd','hn','xb','xn','gat']
    for area in areas:
        url = baseurl.format(area)
        parse_page(url)

    # 分析数据
    # 排序
    DATA.sort(key=lambda DATA:DATA['temp'],reverse=True)
    print(DATA)
    data = DATA[:10]

    chart = Bar("中国城市最高气温排行榜")
    chart.add("温度",
              list(map(lambda data:data['city'],data)),
              list(map(lambda data:data['temp'],data))
              )
    chart.render('temperature.html')

if __name__=='__main__':
    main()

运行截图：

自动导出可视化数据：