用bs4爬中国天气网

你怕是在梦里哦

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. def parse_page(url):#解析url页面函数
   
4.     headers ={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:75.0) Gecko/20100101 Firefox/75.0'}
   
5.     response = requests.get(url,headers = headers)
   
6.     #print(response.content.decode('utf-8'))#当解码之后的页面有乱码说明用response.test()猜错了解码方式，则应该改成response.content.decode('utf-8')
   
7.     text = response.content.decode('utf-8')
   
8.     soup = BeautifulSoup(text,'lxml')
   
9.     conMidtab =soup.find('div',class_ = 'conMidtab')
   
10.     tables = conMidtab.find_all('table')
    
11.     for table in tables:
    
12.         trs = table.find_all('tr')[2:]
    
13.         for tr in trs:
    
14.             tds =tr.find_all('td')
    
15.             city_td = tds[0]
    
16.             city = list(city_td.stripped_strings)[0]
    
17.             temp_td = tds[-2]
    
18.             min_temp =list(temp_td.stripped_strings)[0]
    
19.             print({'city':city,'min_temp':min_temp})
    
20. def main():
    
21.     url = 'http://www.weather.com.cn/textFC/hb.shtml'
    
22.     parse_page(url)
    
23. 
    
24. if __name__ == '__main__':
    
25.     main()

复制代码