[已解决]程序报错，论坛的大佬的，复制了跑不出来

颂风侯

1. import requests
   
2. 
   
3. import re
   
4. 
   
5. import json
   
6. 
   
7. import os
   
8. 
   
9. 
   
10. 
    
11. 
    
12. 
    
13. 
    
14. 
    
15. def get_name(singer):
    
16. 
    
17.     url = 'https://c.y.qq.com/soso/fcgi-bin/client_search_cp'
    
18. 
    
19.     params = {
    
20. 
    
21.     'catZhida': '1',
    
22. 
    
23.     'w': singer,
    
24. 
    
25.     }
    
26. 
    
27.     headers = {
    
28. 
    
29.     'referer': 'https://y.qq.com/portal/search.html',
    
30. 
    
31.     'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36'
    
32. 
    
33.     }
    
34. 
    
35.     html = requests.get(url,headers=headers,params=params).text
    
36. 
    
37.     content = re.compile('callback\((.*)\)').findall(html)[0]
    
38. 
    
39.     content = json.loads(content)
    
40. 
    
41.     data = content.get('data')
    
42. 
    
43.     song = data.get('song')
    
44. 
    
45.     lists = song.get('list')
    
46. 
    
47.     name = []
    
48. 
    
49.     for list in lists:
    
50. 
    
51.         singer = list.get('singer')[0].get('mid')
    
52. 
    
53.         name.append(singer)
    
54. 
    
55.     name = name[0]
    
56. 
    
57.     return name
    
58. 
    
59. 
    
60. 
    
61. def get_html(name,singer):
    
62. 
    
63.     url = 'https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg'
    
64. 
    
65.     params = {
    
66. 
    
67.     'singermid': name,
    
68. 
    
69.     'order': 'listen',
    
70. 
    
71.     'begin': '0',
    
72. 
    
73.     'num': '30',
    
74. 
    
75.     }
    
76. 
    
77.     headers = {
    
78. 
    
79.     'referer': 'https://y.qq.com/n/yqq/singer/003aQYLo2x8izP.html',
    
80. 
    
81.     'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36'
    
82. 
    
83.     }
    
84. 
    
85.     html = requests.get(url,headers=headers,params=params).text
    
86. 
    
87.     return html
    
88. 
    
89. 
    
90. 
    
91. 
    
92. 
    
93. def get_music(vkey,songname,filename,singer):
    
94. 
    
95.     if vkey and songname:
    
96. 
    
97.         url3 = 'http://dl.stream.qqmusic.qq.com/' + filename + '?vkey=' + vkey + '&guid=7133372870&uin=0&fromtag=66'
    
98. 
    
99. 
    
100. 
     
101.         headers = {
     
102. 
     
103.         'referer': 'https://y.qq.com/n/yqq/singer/003aQYLo2x8izP.html',
     
104. 
     
105.         'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36'
     
106. 
     
107.         }
     
108. 
     
109.         music = requests.get(url3,headers=headers).content
     
110. 
     
111.         dir = singer
     
112. 
     
113.         if not os.path.exists(dir):
     
114. 
     
115.             os.mkdir(dir)
     
116. 
     
117.         with open(dir+'/'+songname+'.m4a','wb') as f:
     
118. 
     
119.             f.write(music)
     
120. 
     
121.         print(songname,'__',singer)
     
122. 
     
123. 
     
124. 
     
125. def get_vkey(strMediaMid,songmid,songname,singer):
     
126. 
     
127.     if strMediaMid and songmid and songname :
     
128. 
     
129.         url2 = 'https://c.y.qq.com/base/fcgi-bin/fcg_music_express_mobile3.fcg'
     
130. 
     
131.         params = {
     
132. 
     
133.         'g_tk': '5381',
     
134. 
     
135.         'jsonpCallback': 'MusicJsonCallback8571665793949388',
     
136. 
     
137.         'loginUin': '0',
     
138. 
     
139.         'hostUin': '0',
     
140. 
     
141.         'format': 'json',
     
142. 
     
143.         'inCharset': 'utf8',
     
144. 
     
145.         'outCharset': 'utf-8',
     
146. 
     
147.         'notice': '0',
     
148. 
     
149.         'platform': 'yqq',
     
150. 
     
151.         'needNewCode': '0',
     
152. 
     
153.         'cid': '205361747',
     
154. 
     
155.         'callback': 'MusicJsonCallback8571665793949388',
     
156. 
     
157.         'uin': '0',
     
158. 
     
159.         'songmid': songmid,
     
160. 
     
161.         'filename': 'C400'+ strMediaMid + '.m4a',
     
162. 
     
163.         'guid': '7133372870'
     
164. 
     
165.         }
     
166. 
     
167.         headers = {
     
168. 
     
169.         'referer': 'https://y.qq.com/portal/player.html',
     
170. 
     
171.         'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36'
     
172. 
     
173.         }
     
174. 
     
175.         detail_html = requests.get(url2,headers=headers,params=params).text
     
176. 
     
177.         vkey_disc = re.compile('MusicJsonCallback8571665793949388\((.*?)\)').findall(detail_html)[0]
     
178. 
     
179.         vkey_disc = json.loads(vkey_disc)
     
180. 
     
181. 
     
182. 
     
183.         data = vkey_disc['data']
     
184. 
     
185.         items = data.get('items')[0]
     
186. 
     
187.         vkey = items.get('vkey')
     
188. 
     
189.         get_music(vkey,songname,'C400'+ strMediaMid + '.m4a',singer)
     
190. 
     
191. 
     
192. 
     
193. 
     
194. 
     
195. def get_list(detail_html,singer):
     
196. 
     
197.     if detail_html:
     
198. 
     
199.         lists = re.compile('data":{"list":(.*?),"singer_id',re.S).findall(detail_html)[0]
     
200. 
     
201.         datas = json.loads(lists)
     
202. 
     
203.         for data in datas:
     
204. 
     
205.             musicData = data.get('musicData')
     
206. 
     
207.             strMediaMid = musicData.get('strMediaMid')
     
208. 
     
209.             songmid = musicData.get('songmid')
     
210. 
     
211.             songname = musicData.get('songname')
     
212. 
     
213.             get_vkey(strMediaMid,songmid,songname,singer)
     
214. 
     
215. 
     
216. 
     
217. 
     
218. 
     
219. 
     
220. 
     
221. def main():
     
222. 
     
223.     singer = input('请输入您想要下载的歌手：')
     
224. 
     
225.     name = get_name(singer)
     
226. 
     
227.     detail_html = get_html(name,singer)
     
228. 
     
229.     get_list(detail_html,singer)
     
230. 
     
231. 
     
232. 
     
233. if __name__ == '__main__':
     
234. 
     
235.     main()

复制代码

复制的论坛大神的，跑不出来
报错如下
D:\PYTHON_NEW\pack20240926\pythonProject1\.venv\Scripts\python.exe D:\PYTHON_NEW\pack20240926\pythonProject1\tkinter练习\爬虫测试\测试qq音乐爬虫.py
D:\PYTHON_NEW\pack20240926\pythonProject1\tkinter练习\爬虫测试\测试qq音乐爬虫.py:37: SyntaxWarning: invalid escape sequence '′content=re.compile(′callback\((.∗)
').findall(html)[zxsq-anti-bbcode-0]
D:\PYTHON_NEW\pack20240926\pythonProject1\tkinter练习\爬虫测试\测试qq音乐爬虫.py:177: SyntaxWarning: invalid escape sequence '′vkeydisc=re.compile(′MusicJsonCallback8571665793949388\((.∗?)
').findall(detail_html)[zxsq-anti-bbcode-0]

最佳答案

月排行榜 / 总排行榜

Stubborn

2024-10-14 18:01:24

爬虫有时效性的， 这报错，一般就是网站请求给的数据不对头，后续清洗数据报错

跳转到最佳答案楼层

Stubborn

爬虫有时效性的， 这报错，一般就是网站请求给的数据不对头，后续清洗数据报错