1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
|
# coding: utf-8
from __future__ import unicode_literals
import hashlib
import hmac
import urllib.parse
from .common import InfoExtractor
from ..utils import (
int_or_none,
traverse_obj,
)
class ZingMp3BaseIE(InfoExtractor):
_VALID_URL_TMPL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?P<type>(?:%s))/[^/]+/(?P<id>\w+)(?:\.html|\?)'
_GEO_COUNTRIES = ['VN']
_DOMAIN = 'https://zingmp3.vn'
_SLUG_API = {
'bai-hat': '/api/v2/page/get/song',
'embed': '/api/v2/page/get/song',
'video-clip': '/api/v2/page/get/video',
'playlist': '/api/v2/page/get/playlist',
'album': '/api/v2/page/get/playlist',
'lyric': '/api/v2/lyric/get/lyric',
'song_streaming': '/api/v2/song/get/streaming',
}
_API_KEY = '88265e23d4284f25963e6eedac8fbfa3'
_SECRET_KEY = b'2aa2d1c561e809b267f3638c4a307aab'
def _extract_item(self, item, song_id, type_url, fatal):
item_id = item.get('encodeId') or song_id
title = item.get('title') or item.get('alias')
if type_url == 'video-clip':
source = item.get('streaming')
else:
api = self.get_api_with_signature(name_api=self._SLUG_API.get('song_streaming'), param={'id': item_id})
source = self._download_json(api, video_id=item_id).get('data')
formats = []
for k, v in (source or {}).items():
if not v:
continue
if k in ('mp4', 'hls'):
for res, video_url in v.items():
if not video_url:
continue
if k == 'hls':
formats.extend(self._extract_m3u8_formats(
video_url, item_id, 'mp4',
'm3u8_native', m3u8_id=k, fatal=False))
elif k == 'mp4':
formats.append({
'format_id': 'mp4-' + res,
'url': video_url,
'height': int_or_none(self._search_regex(
r'^(\d+)p', res, 'resolution', default=None)),
})
continue
elif v == 'VIP':
continue
formats.append({
'ext': 'mp3',
'format_id': k,
'tbr': int_or_none(k),
'url': self._proto_relative_url(v),
'vcodec': 'none',
})
if not formats:
if not fatal:
return
msg = item.get('msg')
if msg == 'Sorry, this content is not available in your country.':
self.raise_geo_restricted(countries=self._GEO_COUNTRIES, metadata_available=True)
self.raise_no_formats(msg, expected=True)
self._sort_formats(formats)
lyric = item.get('lyric')
if not lyric:
api = self.get_api_with_signature(name_api=self._SLUG_API.get("lyric"), param={'id': item_id})
info_lyric = self._download_json(api, video_id=item_id)
lyric = traverse_obj(info_lyric, ('data', 'file'))
subtitles = {
'origin': [{
'url': lyric,
}],
} if lyric else None
album = item.get('album') or {}
return {
'id': item_id,
'title': title,
'formats': formats,
'thumbnail': traverse_obj(item, 'thumbnail', 'thumbnailM'),
'subtitles': subtitles,
'duration': int_or_none(item.get('duration')),
'track': title,
'artist': traverse_obj(item, 'artistsNames', 'artists_names'),
'album': traverse_obj(album, 'name', 'title'),
'album_artist': traverse_obj(album, 'artistsNames', 'artists_names'),
}
def _real_initialize(self):
if not self.get_param('cookiefile') and not self.get_param('cookiesfrombrowser'):
self._request_webpage(self.get_api_with_signature(name_api=self._SLUG_API['bai-hat'], param={'id': ''}),
None, note='Updating cookies')
def _real_extract(self, url):
song_id, type_url = self._match_valid_url(url).group('id', 'type')
api = self.get_api_with_signature(name_api=self._SLUG_API[type_url], param={'id': song_id})
return self._process_data(self._download_json(api, song_id)['data'], song_id, type_url)
def get_api_with_signature(self, name_api, param):
param.update({'ctime': '1'})
sha256 = hashlib.sha256(''.join(f'{i}={param[i]}' for i in sorted(param)).encode('utf-8')).hexdigest()
data = {
'apiKey': self._API_KEY,
'sig': hmac.new(self._SECRET_KEY, f'{name_api}{sha256}'.encode('utf-8'), hashlib.sha512).hexdigest(),
**param,
}
return f'{self._DOMAIN}{name_api}?{urllib.parse.urlencode(data)}'
class ZingMp3IE(ZingMp3BaseIE):
_VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'bai-hat|video-clip|embed'
_TESTS = [{
'url': 'https://mp3.zing.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
'md5': 'ead7ae13693b3205cbc89536a077daed',
'info_dict': {
'id': 'ZWZB9WAB',
'title': 'Xa Mãi Xa',
'ext': 'mp3',
'thumbnail': r're:^https?://.+\.jpg',
'subtitles': {
'origin': [{
'ext': 'lrc',
}]
},
'duration': 255,
'track': 'Xa Mãi Xa',
'artist': 'Bảo Thy',
'album': 'Special Album',
'album_artist': 'Bảo Thy',
},
}, {
'url': 'https://zingmp3.vn/video-clip/Suong-Hoa-Dua-Loi-K-ICM-RYO/ZO8ZF7C7.html',
'md5': 'c7f23d971ac1a4f675456ed13c9b9612',
'info_dict': {
'id': 'ZO8ZF7C7',
'title': 'Sương Hoa Đưa Lối',
'ext': 'mp4',
'thumbnail': r're:^https?://.+\.jpg',
'duration': 207,
'track': 'Sương Hoa Đưa Lối',
'artist': 'K-ICM, RYO',
'album': 'Sương Hoa Đưa Lối (Single)',
'album_artist': 'K-ICM, RYO',
},
}, {
'url': 'https://zingmp3.vn/bai-hat/Nguoi-Yeu-Toi-Lanh-Lung-Sat-Da-Mr-Siro/ZZ6IW7OU.html',
'md5': '3e9f7a9bd0d965573dbff8d7c68b629d',
'info_dict': {
'id': 'ZZ6IW7OU',
'title': 'Người Yêu Tôi Lạnh Lùng Sắt Đá',
'ext': 'mp3',
'thumbnail': r're:^https?://.+\.jpg',
'duration': 303,
'track': 'Người Yêu Tôi Lạnh Lùng Sắt Đá',
'artist': 'Mr. Siro',
'album': 'Người Yêu Tôi Lạnh Lùng Sắt Đá (Single)',
'album_artist': 'Mr. Siro',
},
}, {
'url': 'https://zingmp3.vn/embed/song/ZWZEI76B?start=false',
'only_matching': True,
}, {
'url': 'https://zingmp3.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
'only_matching': True,
}]
IE_NAME = 'zingmp3'
IE_DESC = 'zingmp3.vn'
def _process_data(self, data, song_id, type_url):
return self._extract_item(data, song_id, type_url, True)
class ZingMp3AlbumIE(ZingMp3BaseIE):
_VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'album|playlist'
_TESTS = [{
'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
'info_dict': {
'_type': 'playlist',
'id': 'ZWZBWDAF',
'title': 'Lâu Đài Tình Ái',
},
'playlist_count': 9,
}, {
'url': 'https://zingmp3.vn/album/Nhung-Bai-Hat-Hay-Nhat-Cua-Mr-Siro-Mr-Siro/ZWZAEZZD.html',
'info_dict': {
'_type': 'playlist',
'id': 'ZWZAEZZD',
'title': 'Những Bài Hát Hay Nhất Của Mr. Siro',
},
'playlist_count': 49,
}, {
'url': 'http://mp3.zing.vn/playlist/Duong-Hong-Loan-apollobee/IWCAACCB.html',
'only_matching': True,
}, {
'url': 'https://zingmp3.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
'only_matching': True,
}]
IE_NAME = 'zingmp3:album'
def _process_data(self, data, song_id, type_url):
def entries():
for item in traverse_obj(data, ('song', 'items')) or []:
entry = self._extract_item(item, song_id, type_url, False)
if entry:
yield entry
return self.playlist_result(entries(), traverse_obj(data, 'id', 'encodeId'),
traverse_obj(data, 'name', 'title'))
|
