1. import csv
    2. import re
    3. import requests
    5. url = 'https://www.kugou.com/yy/html/rank.html'
    6. headers = {
    7.     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36'
    8. }
    10. res = requests.get(url, headers)
    11. html = res.text
    12. result = re.match(r'.*?(<div class="pc_temp_songlist  pc_rank_songlist_short">(.*?)</div>)', html, re.S)
    13. ul = result.group(1)
    14. li = re.findall(r'<li.*?>.*?</li>', ul, re.S)
    15. pattern = re.compile(r'<li .*?title="(.*?)-(.*?)".*?>.*?<a.*?href="(.*?)".*?</a>.*?</li>', re.S)
    17. lst = []
    18. for i in li:
    19.     li = pattern.match(i)
    20.     tu = (li.group(1), li.group(2), li.group(3))
    21.     print(tu)
    22.     lst.append(tu)
    24. # 写入
    25. with open('酷狗音乐飙升榜.csv', 'w', encoding='utf-8-sig', newline='') as f:
    26.     writer = csv.writer(f)
    27.     writer.writerow(['歌名', '歌手', '详情网页'])
    28.     writer.writerows(lst)