爬虫程序------天气

输入城市，爬取该城市在中国天气网的七天天气

代码如下：

# author:WN
# datetime:2019/10/27 11:03
import requests
import re
from bs4 import BeautifulSoup
from bs4 import UnicodeDammit


def find_city_num():
    """查找出城市所对应的编号"""
    city = input("请输入要查询的城市:").encode('utf8')
    city_name = str(city).replace(r'\x', '%')[1:]  # 编码后的城市名
    url = 'http://toy1.weather.com.cn/search?cityname=' + city_name
    # 设置请求头
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36',
    }

    response = requests.get(url, headers=headers)
    data = response.text
    try:
        city_num = re.search(r'\d+', data).group()
    except Exception:
        print('没有该城市!')
    else:
        city_weather(city_num, headers)


def city_weather(city_num, headers):
    """查询该城市的七天天气"""
    url = 'http://www.weather.com.cn/weather/%s.shtml' % city_num
    response = requests.get(url, headers=headers)
    # 解决网页的编码
    dammit = UnicodeDammit(response.content, ['gbk', 'utf8'])
    str_html = dammit.unicode_markup
    # 解析
    data = BeautifulSoup(str_html, 'lxml')
    weather_msg = data.select('ul[class="t clearfix"] li')
    for li in weather_msg:
        # 日期
        date = li.select('h1')[0].text
        # 天气
        weather = li.select('p')[0].text
        # 温度
        temp = li.select('p[class="tem"]')[0].text.strip('\n')
        # 风力
        windy = li.select('p[class="win"] i')[0].text
        print('{0}  {1}  {2}  {3}'.format(date, weather, temp, windy))


if __name__ == '__main__':
    find_city_num()