python 爬取http://www.weather.com.cn/中国主要城市周边城市的天气

编程实现自动爬取中国气象网站 http://www.weather.com.cn/气象数据，将中国主要城市 （北京 、上海 、广州 、杭州 、武汉 、南京 、深圳 、苏州 、厦门 、合肥 和成都  ）周边地区当天的最高温度和低爬取并显示，如针对网页显示成都周边地区气候数据如下图：

# encoding=utf-8
import requests
from bs4 import BeautifulSoup

city_url = ['http://www.weather.com.cn/weather1d/101010100.shtml#search',
            'http://www.weather.com.cn/weather1d/101020100.shtml#search',
            'http://www.weather.com.cn/weather1d/101280101.shtml#search',
            'http://www.weather.com.cn/weather1d/101210101.shtml#search',
            'http://www.weather.com.cn/weather1d/101200101.shtml#search',
            'http://www.weather.com.cn/weather1d/101190101.shtml#search',
            'http://www.weather.com.cn/weather1d/101280601.shtml#search',
            'http://www.weather.com.cn/weather1d/101280601.shtml#search',
            'http://www.weather.com.cn/weather1d/101230201.shtml#search',
            'http://www.weather.com.cn/weather1d/101220101.shtml#search',
            'http://www.weather.com.cn/weather1d/101270101.shtml#search']

allfind = ['北京', '上海', '广州', '杭州', '武汉', '南京', '深圳', '苏州', '厦门', '合肥', '成都']

def getHTMLText(url):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = 'utf-8'
        return r.text
    except:
        return ""


def fillList(soup, num):
    allCity = []
    ul = soup.find('ul', {'class': 'clearfix city'})
    data = ul.find_all('li')
    for li in data:
        a = li.find('a')
        cityname = a.find('span')
        if len(cityname) == 0:
            continue
        temperature = a.find('i')
        temperature_str = temperature.string
        #分离温度
        str1 = temperature_str.split('/')
        temperature_l = str1[0] + '°C '
        temperature_h = str1[1]
        singleCity = []
        singleCity.append(allfind[num])
        singleCity.append(cityname.string)
        singleCity.append(temperature_l)
        singleCity.append(temperature_h)
        allCity.append(singleCity)
    return allCity

def printCityW(city):
    print("{1:^8}{2:{0}^6}{3:{0}^8}{4:{0}^6}".format(chr(12288), "城市名称", "周边地区", "最低温度", "最高温度"))
    for i in range(11):
        u = city[i]
        print("{1:^8}{2:{0}^8}{3:{0}^8}{4:{0}^8}".format(chr(12288), u[0], u[1], u[2], u[3]))

def main():
    for i in range(11):
        url = city_url[i]
        html = getHTMLText(url)
        soup = BeautifulSoup(html, "html.parser")
        City = fillList(soup, i)
        printCityW(City)
        if i != 10:
            print('-------------------**********---------------------')
main()

运行结果如下：