python3 爬取qq音乐作者所有单曲 并且下载歌曲

  1 import requests
  2 import re
  3 import json
  4 import os
  5 
  6  
  7  
  8 # 便于存放作者的姓名
  9 zuozhe = []
 10 
 11 headers = {‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36‘}
 12 
 13 
 14 def get_singermid():
 15     name = input(‘请输入你要下载歌曲的作者:‘)
 16     zuozhe.append(name)
 17     if not os.path.exists(name):
 18         os.mkdir(name)
 19     url = ‘https://c.y.qq.com/soso/fcgi-bin/client_search_cp‘
 20     headers = {‘user-agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36‘}
 21     data = {
 22             ‘w‘: name,
 23             ‘jsonpCallback‘: ‘MusicJsonCallback885332333726736‘,}
 24     response = requests.get(url,headers=headers,params=data).text
 25     patt = re.compile(‘MusicJsonCallback\d+\((.*?)\}\)‘)
 26     singermid = re.findall(patt,response)[0]
 27     singermid = singermid+‘}‘
 28     dic = json.loads(singermid)
 29     return dic[‘data‘][‘song‘][‘list‘][0][‘singer‘][0][‘mid‘]
 30 
 31 
 32 def get_page_html(singermid):
 33     url = ‘https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg‘
 34     params = {
 35         ‘g_tk‘: 5381,
 36         ‘jsonpCallback‘: ‘MusicJsonCallbacksinger_track‘,
 37         ‘loginUin‘: 0,
 38         ‘hostUin‘: 0,
 39         ‘format‘: ‘jsonp‘,
 40         ‘inCharset‘: ‘utf8‘,
 41         ‘outCharset‘: ‘utf-8‘,
 42         ‘notice‘: 0,
 43         ‘platform‘: ‘yqq‘,
 44         ‘needNewCode‘: 0,
 45         ‘singermid‘: singermid,
 46         ‘order‘: ‘listen‘,
 47         ‘begin‘: 0,# 页数  0 30  60
 48         ‘num‘: 30,
 49         ‘songstatus‘: 1,
 50     }
 51     response = requests.get(url,headers=headers,params=params)
 52     return response.text
 53 
 54 
 55 def get_vkey_data(songmid,strMediaMid,name):
 56     url = ‘https://c.y.qq.com/base/fcgi-bin/fcg_music_express_mobile3.fcg‘
 57     strMediaMid1 = ‘C400‘+strMediaMid+‘.m4a‘
 58     data = {
 59         ‘g_tk‘: 5381,
 60         ‘jsonpCallback‘: "MusicJsonCallback4327043425715609",
 61         ‘loginUin‘: 0,
 62         ‘hostUin‘: 0,
 63         ‘format‘: ‘json‘,
 64         ‘inCharset‘: ‘utf8‘,
 65         ‘outCharset‘: ‘utf-8‘,
 66         ‘notice‘: 0,
 67         ‘platform‘: ‘yqq‘,
 68         ‘needNewCode‘: 0,
 69         ‘cid‘: 205361747,
 70         ‘callback‘: ‘MusicJsonCallback4327043425715609‘,
 71         ‘uin‘: 0,
 72         ‘songmid‘: songmid,
 73         ‘filename‘: strMediaMid1,
 74         ‘guid‘: 4428680404,
 75     }
 76     response = requests.get(url,headers=headers,params=data).text
 77     try:
 78         patt = re.compile(‘\"vkey\":\"(.*?)\"‘)
 79         vkey = re.findall(patt,response)[0]
 80         patt = re.compile(‘\"filename\":\"(.*?)\"‘)
 81         filename = re.findall(patt, response)[0]
 82         url1 = ‘http://dl.stream.qqmusic.qq.com/‘ + filename + ‘?vkey=‘ + vkey + ‘&guid=4428680404&uin=0&fromtag=66‘
 83         yingyue = requests.get(url1,headers=headers).content
 84         with open(zuozhe[0]+‘/‘+name+‘.m4a‘,‘wb‘) as f:
 85             f.write(yingyue)
 86             f.close()
 87             print(‘下载完成《‘+name+‘》‘)
 88     except Exception as e:
 89         print(e)
 90         pass
 91 
 92 
 93 def get_detail_html(html):
 94     if html:
 95         patt = re.compile(‘data\":{\"list\":(.*?),\"singer_id‘,re.S)
 96         json_html = re.findall(patt,html)[0]
 97         data_html = json.loads(json_html)
 98         for data in data_html:
 99             name = data[‘musicData‘][‘songname‘]
100             songmid = data[‘musicData‘][‘songmid‘]
101             strMediaMid = data[‘musicData‘][‘strMediaMid‘]
102             print(‘正在下载《‘ + name + ‘》......‘)
103             get_vkey_data(songmid,strMediaMid,name)
104 
105 def main():
106     # 获取 singermid 
107     singermid = get_singermid()
108     html = get_page_html(singermid)
109     get_detail_html(html)
110 
111 
112 if __name__ == ‘__main__‘:
113     main()