爬取酷我音乐热歌榜

  1. import requests
  2. import re
  3. import csv
  5. # 分析页面url
  6. '''
  7. 第一页：http://www.kuwo.cn/api/www/bang/bang/musicList?bangId=93&pn=1&rn=30&httpsStatus=1&reqId=82dbed60-74fa-11ec-b1c4-eb380bf2a161
  8. 第二页：http://www.kuwo.cn/api/www/bang/bang/musicList?bangId=93&pn=2&rn=30&httpsStatus=1&reqId=82dbed60-74fa-11ec-b1c4-eb380bf2a161
  10. referer反爬
  11. csrf和cookie
  12. '''
  15. class KuWOSpider:
  16.     def __init__(self):
  17.         self.headers = {
  18.             'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36',
  19.             'referer': 'http://www.kuwo.cn/rankList',
  20.             'csrf': 'FB96B28A1J',
  21.             'cookie': 'Hm_lvt_cdb524f42f0ce19b169a8071123a4797=1642136341; _ga=GA1.2.905152829.1642136341; _gid=GA1.2.1336775727.1642136341; Hm_lpvt_cdb524f42f0ce19b169a8071123a4797=1642137803; _gat=1; kw_token=FB96B28A1J'
  23.         }
  25.     def read_url(self, url):
  26.         res = requests.get(url, headers=self.headers)
  27.         html = res.content.decode('utf-8')
  28.         return html
  31.     def pare_url(self, html, li):
  32.         for i in range(30):
  33.             item = {}
  34.             item['singers'] = re.findall(r'"artist":"(.*?)"', html)[i]
  35.             item['name'] = re.findall(r'"album":"(.*?)"', html)[i]
  36.             # 歌曲链接为：'http://www.kuwo.cn/play_detail/206079303'，可以取出id与 前面的url链接
  37.             item['link'] = 'http://www.kuwo.cn/play_detail/' + re.findall(r'"rid":(.*?),', html)[i]
  38.             li.append(item)
  41.     def write_html(self, header, li):
  42.         with open('酷我音乐top300.csv', 'w', encoding='utf-8') as f:
  43.             w = csv.DictWriter(f, header)
  44.             w.writeheader()
  45.             w.writerows(li)
  46.             print("写入成功！")
  48.     def main(self):
  49.         header = ['singers', 'name', 'link']
  50.         li = []
  51.         for i in range(1, 11):
  52.             html = self.read_url(
  53.                 f'http://www.kuwo.cn/api/www/bang/bang/musicList?bangId=93&pn={i}&rn=30&httpsStatus=1&reqId=82dbed60-74fa-11ec-b1c4-eb380bf2a161')
  54.             self.pare_url(html, li)
  55.         # print(li)
  56.         self.write_html(header, li)
  59. if __name__ == '__main__':
  60.     k = KuWOSpider()
  61.     k.main()

结果展示

image.png