1. import requests
    2. import csv
    3. import re
    5. url = 'http://www.weather.com.cn/weather/101070301.shtml'
    6. headers = {
    7.     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.82 Safari/537.36'
    8. }
    9. response = requests.get(url, headers=headers)
    10. response.encoding = 'utf-8'
    11. html = response.text
    12. result = re.match(r'.*(<ul class="t clearfix">.*?</ul>).*', html, re.S)   # 匹配多行数据
    13. ul = result.group(1)
    14. # print(ul)
    15. lis = re.findall(r'<li.*?>.*?</li>', ul, re.S)
    16. print(lis)
    17. pattern = re.compile(r'<li.*?>.*?<h1>(.*?)</h1>.*?<p.*?>(.*?)</p>.*?<span>(.*?)</span>.*?<i>(.*?)</i>.*?<i>(.*?)</i>.*?</li>', re.S)
    18. lst = []
    19. for i in lis:
    20.     r = pattern.match(i)
    21.     tu = (r.group(1), r.group(2), r.group(3), r.group(4), r.group(5))
    22.     lst.append(tu)
    23. # print(lst)
    24. with open('weather.csv', 'w', encoding='utf-8-sig', newline='') as f:
    25.     writer = csv.writer(f)
    26.     writer.writerow(['日期', '天气', '最高气温', '最低气温', '风力'])
    27.     writer.writerows(lst)