[yt-dlp.git] / yt_dlp / extractor / zingmp3.py

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'))
Commit	Line	Data
ecca4519 HTL	1	import hashlib
	2	import hmac
	3	import urllib.parse
	4
c66bdc48	5	from .common import InfoExtractor
3d47ee0a	6	from ..utils import (
3d47ee0a	7	int_or_none,
ecca4519	8	traverse_obj,
3d47ee0a	9	)
c66bdc48 DHS	10
c66bdc48 DHS	11
1418a043	12	class ZingMp3BaseIE(InfoExtractor):
ecca4519	13	_VALID_URL_TMPL = r'https?://(?:mp3\.zing\|zingmp3)\.vn/(?P<type>(?:%s))/[^/]+/(?P<id>\w+)(?:\.html\|\?)'
1418a043	14	_GEO_COUNTRIES = ['VN']
ecca4519 HTL	15	_DOMAIN = 'https://zingmp3.vn'
	16	_SLUG_API = {
	17	'bai-hat': '/api/v2/page/get/song',
	18	'embed': '/api/v2/page/get/song',
	19	'video-clip': '/api/v2/page/get/video',
	20	'playlist': '/api/v2/page/get/playlist',
	21	'album': '/api/v2/page/get/playlist',
	22	'lyric': '/api/v2/lyric/get/lyric',
	23	'song_streaming': '/api/v2/song/get/streaming',
	24	}
	25
	26	_API_KEY = '88265e23d4284f25963e6eedac8fbfa3'
	27	_SECRET_KEY = b'2aa2d1c561e809b267f3638c4a307aab'
c66bdc48	28
ecca4519 HTL	29	def _extract_item(self, item, song_id, type_url, fatal):
	30	item_id = item.get('encodeId') or song_id
	31	title = item.get('title') or item.get('alias')
	32
	33	if type_url == 'video-clip':
	34	source = item.get('streaming')
	35	else:
	36	api = self.get_api_with_signature(name_api=self._SLUG_API.get('song_streaming'), param={'id': item_id})
	37	source = self._download_json(api, video_id=item_id).get('data')
51156528	38
3d47ee0a	39	formats = []
ecca4519	40	for k, v in (source or {}).items():
1418a043	41	if not v:
3d47ee0a	42	continue
1418a043	43	if k in ('mp4', 'hls'):
	44	for res, video_url in v.items():
	45	if not video_url:
	46	continue
	47	if k == 'hls':
	48	formats.extend(self._extract_m3u8_formats(
	49	video_url, item_id, 'mp4',
	50	'm3u8_native', m3u8_id=k, fatal=False))
	51	elif k == 'mp4':
	52	formats.append({
	53	'format_id': 'mp4-' + res,
	54	'url': video_url,
	55	'height': int_or_none(self._search_regex(
	56	r'^(\d+)p', res, 'resolution', default=None)),
	57	})
ecca4519 HTL	58	continue
	59	elif v == 'VIP':
	60	continue
	61	formats.append({
	62	'ext': 'mp3',
	63	'format_id': k,
	64	'tbr': int_or_none(k),
	65	'url': self._proto_relative_url(v),
	66	'vcodec': 'none',
	67	})
1418a043	68	if not formats:
	69	if not fatal:
	70	return
ecca4519	71	msg = item.get('msg')
1418a043	72	if msg == 'Sorry, this content is not available in your country.':
b7da73eb	73	self.raise_geo_restricted(countries=self._GEO_COUNTRIES, metadata_available=True)
b7da73eb	74	self.raise_no_formats(msg, expected=True)
1418a043	75	self._sort_formats(formats)
1418a043	76
1418a043	77	lyric = item.get('lyric')
ecca4519 HTL	78	if not lyric:
	79	api = self.get_api_with_signature(name_api=self._SLUG_API.get("lyric"), param={'id': item_id})
	80	info_lyric = self._download_json(api, video_id=item_id)
	81	lyric = traverse_obj(info_lyric, ('data', 'file'))
	82	subtitles = {
	83	'origin': [{
	84	'url': lyric,
	85	}],
	86	} if lyric else None
3d47ee0a	87
1418a043	88	album = item.get('album') or {}
c66bdc48 DHS	89
c66bdc48 DHS	90	return {
1418a043	91	'id': item_id,
1418a043	92	'title': title,
3d47ee0a	93	'formats': formats,
ecca4519	94	'thumbnail': traverse_obj(item, 'thumbnail', 'thumbnailM'),
1418a043	95	'subtitles': subtitles,
	96	'duration': int_or_none(item.get('duration')),
	97	'track': title,
ecca4519 HTL	98	'artist': traverse_obj(item, 'artistsNames', 'artists_names'),
	99	'album': traverse_obj(album, 'name', 'title'),
	100	'album_artist': traverse_obj(album, 'artistsNames', 'artists_names'),
c66bdc48 DHS	101	}
c66bdc48 DHS	102
ecca4519 HTL	103	def _real_initialize(self):
ecca4519 HTL	104	if not self.get_param('cookiefile') and not self.get_param('cookiesfrombrowser'):
63b2f88b HTL	105	self._request_webpage(self.get_api_with_signature(name_api=self._SLUG_API['bai-hat'], param={'id': ''}),
63b2f88b HTL	106	None, note='Updating cookies')
ecca4519	107
1418a043	108	def _real_extract(self, url):
ecca4519	109	song_id, type_url = self._match_valid_url(url).group('id', 'type')
ecca4519	110	api = self.get_api_with_signature(name_api=self._SLUG_API[type_url], param={'id': song_id})
ecca4519 HTL	111	return self._process_data(self._download_json(api, song_id)['data'], song_id, type_url)
	112
	113	def get_api_with_signature(self, name_api, param):
63b2f88b HTL	114	param.update({'ctime': '1'})
63b2f88b HTL	115	sha256 = hashlib.sha256(''.join(f'{i}={param[i]}' for i in sorted(param)).encode('utf-8')).hexdigest()
ecca4519 HTL	116	data = {
	117	'apiKey': self._API_KEY,
	118	'sig': hmac.new(self._SECRET_KEY, f'{name_api}{sha256}'.encode('utf-8'), hashlib.sha512).hexdigest(),
	119	**param,
	120	}
	121	return f'{self._DOMAIN}{name_api}?{urllib.parse.urlencode(data)}'
c66bdc48 DHS	122
c66bdc48 DHS	123
1418a043	124	class ZingMp3IE(ZingMp3BaseIE):
ecca4519	125	_VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'bai-hat\|video-clip\|embed'
c66bdc48	126	_TESTS = [{
ecca4519	127	'url': 'https://mp3.zing.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
4ffc3103	128	'md5': 'ead7ae13693b3205cbc89536a077daed',
c66bdc48 DHS	129	'info_dict': {
c66bdc48 DHS	130	'id': 'ZWZB9WAB',
4ffc3103	131	'title': 'Xa Mãi Xa',
c66bdc48	132	'ext': 'mp3',
1418a043	133	'thumbnail': r're:^https?://.+\.jpg',
	134	'subtitles': {
	135	'origin': [{
	136	'ext': 'lrc',
	137	}]
	138	},
	139	'duration': 255,
	140	'track': 'Xa Mãi Xa',
	141	'artist': 'Bảo Thy',
	142	'album': 'Special Album',
	143	'album_artist': 'Bảo Thy',
c66bdc48	144	},
3d47ee0a	145	}, {
ecca4519	146	'url': 'https://zingmp3.vn/video-clip/Suong-Hoa-Dua-Loi-K-ICM-RYO/ZO8ZF7C7.html',
08d30158	147	'md5': 'c7f23d971ac1a4f675456ed13c9b9612',
3d47ee0a	148	'info_dict': {
1418a043	149	'id': 'ZO8ZF7C7',
1418a043	150	'title': 'Sương Hoa Đưa Lối',
3d47ee0a	151	'ext': 'mp4',
1418a043	152	'thumbnail': r're:^https?://.+\.jpg',
	153	'duration': 207,
	154	'track': 'Sương Hoa Đưa Lối',
	155	'artist': 'K-ICM, RYO',
08d30158	156	'album': 'Sương Hoa Đưa Lối (Single)',
08d30158	157	'album_artist': 'K-ICM, RYO',
3d47ee0a	158	},
63b2f88b HTL	159	}, {
	160	'url': 'https://zingmp3.vn/bai-hat/Nguoi-Yeu-Toi-Lanh-Lung-Sat-Da-Mr-Siro/ZZ6IW7OU.html',
	161	'md5': '3e9f7a9bd0d965573dbff8d7c68b629d',
	162	'info_dict': {
	163	'id': 'ZZ6IW7OU',
	164	'title': 'Người Yêu Tôi Lạnh Lùng Sắt Đá',
	165	'ext': 'mp3',
	166	'thumbnail': r're:^https?://.+\.jpg',
	167	'duration': 303,
	168	'track': 'Người Yêu Tôi Lạnh Lùng Sắt Đá',
	169	'artist': 'Mr. Siro',
	170	'album': 'Người Yêu Tôi Lạnh Lùng Sắt Đá (Single)',
	171	'album_artist': 'Mr. Siro',
	172	},
ecca4519 HTL	173	}, {
	174	'url': 'https://zingmp3.vn/embed/song/ZWZEI76B?start=false',
	175	'only_matching': True,
3d47ee0a	176	}, {
1418a043	177	'url': 'https://zingmp3.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
	178	'only_matching': True,
	179	}]
	180	IE_NAME = 'zingmp3'
ecca4519	181	IE_DESC = 'zingmp3.vn'
1418a043	182
ecca4519 HTL	183	def _process_data(self, data, song_id, type_url):
ecca4519 HTL	184	return self._extract_item(data, song_id, type_url, True)
1418a043	185
	186
	187	class ZingMp3AlbumIE(ZingMp3BaseIE):
	188	_VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'album\|playlist'
	189	_TESTS = [{
43abd799 S	190	'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
	191	'info_dict': {
	192	'_type': 'playlist',
	193	'id': 'ZWZBWDAF',
1418a043	194	'title': 'Lâu Đài Tình Ái',
c66bdc48	195	},
ecca4519	196	'playlist_count': 9,
63b2f88b HTL	197	}, {
	198	'url': 'https://zingmp3.vn/album/Nhung-Bai-Hat-Hay-Nhat-Cua-Mr-Siro-Mr-Siro/ZWZAEZZD.html',
	199	'info_dict': {
	200	'_type': 'playlist',
	201	'id': 'ZWZAEZZD',
	202	'title': 'Những Bài Hát Hay Nhất Của Mr. Siro',
	203	},
	204	'playlist_count': 49,
43abd799 S	205	}, {
	206	'url': 'http://mp3.zing.vn/playlist/Duong-Hong-Loan-apollobee/IWCAACCB.html',
	207	'only_matching': True,
1418a043	208	}, {
	209	'url': 'https://zingmp3.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
	210	'only_matching': True,
43abd799	211	}]
1418a043	212	IE_NAME = 'zingmp3:album'
1418a043	213
ecca4519	214	def _process_data(self, data, song_id, type_url):
1418a043	215	def entries():
ecca4519 HTL	216	for item in traverse_obj(data, ('song', 'items')) or []:
ecca4519 HTL	217	entry = self._extract_item(item, song_id, type_url, False)
1418a043	218	if entry:
1418a043	219	yield entry
ecca4519 HTL	220
	221	return self.playlist_result(entries(), traverse_obj(data, 'id', 'encodeId'),
	222	traverse_obj(data, 'name', 'title'))