目标网站： http://www.kuwo.cn/
    爬取需求
    1、爬取任意一个歌单页面的html代码
    2、用正则解析数据，拿到歌名和歌曲链接

    2. import requests
    3. import re
    4. from fake_useragent import UserAgent
    5. import os
    6. import xlsxwriter
    7. class KuwoMusic:
    9.     def __init__(self,cate_id):
    10.         self.cate_id = cate_id
    11.         self.base_url = 'https://www.kuwo.cn'
    12.         self.url = self.base_url + '/playlist_detail/' + cate_id
    13.         self.headers = {
    14.             'User-Agent':UserAgent().random,
    15.             'Cookie':'Hm_lvt_cdb524f42f0ce19b169a8071123a4797=1642227195; _ga=GA1.2.1122063446.1642227195; _gid=GA1.2.280619156.1642227195; gtoken=j8VE8ybEY8ot; gid=085db92c-1032-4576-a03c-a8fca605c0c0; Hm_lpvt_cdb524f42f0ce19b169a8071123a4797=1642231516; kw_token=29VMFISUU6K',
    16.         }
    18.     # 保存酷我音乐页面
    19.     def saveMusicHtml(self):
    20.         self.headers['Referer'] = self.url
    21.         if not os.path.exists(f'{self.cate_id}-music.html'):
    22.             response = requests.get(self.url, headers=self.headers)
    23.             if response.status_code == 200:
    24.                 with open(f'{self.cate_id}-music.html', 'w', encoding='utf-8') as file:
    25.                     file.write(response.content.decode('utf-8'))
    26.             else:
    27.                 print(response.reason)
    28.             self.getMusicInfo()
    29.         else:
    30.             self.getMusicInfo()
    32.     # 获取音乐信息
    33.     def getMusicInfo(self):
    34.         with open(f'{self.cate_id}-music.html','r',encoding='utf-8') as file:
    35.             html = file.read()
    36.             allLi = re.findall('<li class="song_item flex_c" data-v-1344465b>.*?</li>',html)
    37.             songTitles = []
    38.             songArtistes = []
    39.             times = []
    40.             links = []
    41.             songLyrices = []
    42.             for li in allLi:
    43.                 songName = re.findall('<div class="song_name flex_c" .*?<a title="(.*?)" href="(.*?)".*?data-v-1344465b>(.*?)</a>.*?</div>',li)[0]
    44.                 songArtist = re.findall('<div class="song_artist" .*?<span title="(.*?)" data-v-1344465b>(.*?)</span></div>',li)[0]
    45.                 time = re.findall('<div class="song_time" data-v-1344465b.*?<span data-v-1344465b>(.*?)</span></div>',li)[0]
    46.                 #print(f'音乐名称为:【{songName[0]}】,歌手:{songArtist[0]},时长为:{time},链接为:{self.base_url + songName[1]}')
    47.                 songLyric = self.getMusicDetail(songName[0],self.base_url + songName[1])
    48.                 #print('歌词为:',songLyric)
    49.                 songTitles.append(songName[0])
    50.                 songArtistes.append(songArtist[0])
    51.                 times.append(time)
    52.                 links.append(self.base_url + songName[1])
    53.                 songLyrices.append(songLyric)
    55.             fileName = f'{cate_id}-歌词.xlsx'
    56.             workbook = xlsxwriter.Workbook(fileName)
    57.             # 创建一个sheet
    58.             worksheet = workbook.add_worksheet()
    59.             bold = workbook.add_format({'bold': 1})
    60.             # # --------1、准备数据并写入excel---------------
    61.             # # 向excel中写入数据，建立图标时要用到
    62.             headings = ['序号', '歌名', '歌手','时长','链接','歌词']
    63.             data = [
    64.                 [i for i in range(0,len(songTitles))],
    65.                 songTitles,
    66.                 songArtistes,
    67.                 times,
    68.                 links,
    69.                 songLyrices,
    70.             ]
    71.             # 写入表头
    72.             worksheet.write_row('A1', headings, bold)
    73.             # 写入数据
    74.             worksheet.write_column('A2', data[0])
    75.             worksheet.write_column('B2', data[1])
    76.             worksheet.write_column('C2', data[2])
    77.             worksheet.write_column('D2', data[3])
    78.             worksheet.write_column('E2', data[4])
    79.             worksheet.write_column('F2', data[5])
    80.             workbook.close()
    82.     # 获取歌曲-歌词
    83.     def getMusicDetail(self,songName,link):
    84.         self.headers['Referer'] = link
    85.         response = requests.get(link,headers=self.headers)
    86.         if response.status_code == 200:
    87.             if os.path.exists(f'detail/{songName}-歌词.html'):
    88.                 with open(f'detail/{songName}-歌词.html', 'r', encoding='utf-8') as file:
    89.                     html = file.read()
    90.             else:
    91.                 html = response.content.decode('utf-8')
    92.                 with open(f'detail/{songName}-歌词.html', 'w', encoding='utf-8') as file:
    93.                     file.write(html)
    94.             allP = re.findall('<div id="lyric" class="lyric" .*? data-v-34783d0c>.*?<div data-v-34783d0c>(.*?)</div></div>',html)
    95.             for p in allP:
    96.                 songLyrics = re.findall('<p data-v-34783d0c.*?>(.*?)</p>',p)
    97.                 songLyrics = ','.join(songLyrics)
    98.                 return songLyrics
    99.         else:
    100.             print(response.reason)
    104. #cate_id = input('请输入歌曲分类id')
    105. cate_id = '1191296579'
    106. music = KuwoMusic(cate_id)
    107. music.saveMusicHtml()