python爬虫系列-爬取音频

知识点：
1.request库的使用
2.re正则表达式
3.json字符串
4.搜索歌曲爬取对应的音频文件

简介：
我这边使用的是QQ音乐的网址爬取的音频

1.首先选择网址
2.选择后F12查看headers的请求头和 接口对应的关系
3.配置body体
4.循环的方式下载mp3
5.读写拿到的mp3

具体代码如下：

点击(此处)折叠或打开

1. #-*- coding: UTF-8 -*-
   
2. 
   
3. 
   
4. import requests
   
5. import re
   
6. 
   
7. 
   
8. 
   
9. headers = {
   
10.     "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36",
    
11. }
    
12. keyword = input('请输入你想下载的歌曲名：')
    
13. url = 'https://c.y.qq.com/soso/fcgi-bin/client_search_cp'
    
14. params = {
    
15.     "ct": " 24",
    
16.     "qqmusic_ver": " 1298",
    
17.     "new_json": " 1",
    
18.     "remoteplace": " txt.yqq.song",
    
19.     "searchid": " 66595602585102401",
    
20.     "t": " 0",
    
21.     "aggr": " 1",
    
22.     "cr": " 1",
    
23.     "catZhida": " 1",
    
24.     "lossless": " 0",
    
25.     "flag_qc": " 0",
    
26.     "p": " 1",
    
27.     "n": " 10",
    
28.     "w": keyword,
    
29.     "g_tk_new_20200303": " 1390029147",
    
30.     "g_tk": " 1390029147",
    
31.     "loginUin": " 1164153961",
    
32.     "hostUin": " 0",
    
33.     "format": " json",
    
34.     "inCharset": " utf8",
    
35.     "outCharset": " utf-8",
    
36.     "notice": " 0",
    
37.     "platform": " yqq.json",
    
38.     "needNewCode": " 0"
    
39. }
    
40. response = requests.get(url, params=params, headers=headers)
    
41. search_result = eval(re.findall('callback\((.*)\)', response.text)[0])
    
42. song_info = search_result['data']['song']['list']
    
43. songname = []
    
44. songmid = []
    
45. singer = []
    
46. for i in song_info:
    
47.     songname.append(i['songname'])
    
48.     songmid.append(i['songmid'])
    
49.     singer.append(i['singer'][0]['name'])
    
50. tplt = "{0:
    
51. print(tplt.format("序号", "歌手", "歌名"))
    
52. for i in range(len(songname)):
    
53.     print(tplt.format(i, singer[i], songname[i]))
    
54. songid = songmid[int(input('请输入序号选择你要下载的歌曲：'))]
    
55. url1 = 'https://u.y.qq.com/cgi-bin/musicu.fcg'
    
56. params1 = {
    
57.     "-": "getplaysongvkey8636402145203543",
    
58.     "g_tk": "1390029147",
    
59.     "loginUin": "1164153961",
    
60.     "hostUin": "0",
    
61.     "format": "json",
    
62.     "inCharset": "utf8",
    
63.     "outCharset": "utf-8",
    
64.     "notice": "0",
    
65.     "platform": "yqq.json",
    
66.     "needNewCode": "0",
    
67.     "data": '{"req":{"module":"CDN.SrfCdnDispatchServer","method":"GetCdnDispatch","param":{"guid":"7469768631","calltype":0,"userip":""}},"req_0":{"module":"vkey.GetVkeyServer","method":"CgiGetVkey","param":{"guid":"7469768631","songmid":["' + songid + '"],"songtype":[0],"uin":"1164153961","loginflag":1,"platform":"20"}},"comm":{"uin":1164153961,"format":"json","ct":24,"cv":0}}'
    
68. }
    
69. response = requests.get(url1, params=params1, headers=headers)
    
70. songlink = response.json()['req_0']['data']['midurlinfo'][0]['purl']
    
71. if songlink == '':
    
72.     print('这首歌是付费歌曲无法下载。')
    
73. else:
    
74.     with open(keyword + '.mp3', mode='wb') as f:
    
75.         f.write(requests.get('https://isure.stream.qqmusic.qq.com/' + songlink, headers=headers).content)
    
76.         print('歌曲下载成功')