archive
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[ZingMp3] Add chart and user extractors (#3423)

Browse Source 
Authored by: hatienl0i261299
pull/3672/head
Ha Tien Loi 2 years ago committed by GitHub
parent 89f383c4ee
commit 54044decd0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 229 additions and 16 deletions
Show Stats Download Patch File Download Diff File

4
yt_dlp/extractor/extractors.py
Unescape Escape View File

@ -2162,6 +2162,10 @@ from .zhihu import ZhihuIE
from .zingmp3 import (
ZingMp3IE,
ZingMp3AlbumIE,
ZingMp3ChartHomeIE,
ZingMp3WeekChartIE,
ZingMp3ChartMusicVideoIE,
ZingMp3UserIE,
)
from .zoom import ZoomIE
from .zype import ZypeIE

241
yt_dlp/extractor/zingmp3.py
Unescape Escape View File

@ -1,11 +1,15 @@
import functools
import hashlib
import hmac
import json
import urllib.parse
from .common import InfoExtractor
from ..utils import (
OnDemandPagedList,
int_or_none,
traverse_obj,
urljoin,
)
@ -14,15 +18,26 @@ class ZingMp3BaseIE(InfoExtractor):
_GEO_COUNTRIES = ['VN']
_DOMAIN = 'https://zingmp3.vn'
_SLUG_API = {
# For audio/video
'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',
# For playlist
'playlist': '/api/v2/page/get/playlist',
'album': '/api/v2/page/get/playlist',
# For chart
'zing-chart': '/api/v2/page/get/chart-home',
'zing-chart-tuan': '/api/v2/page/get/week-chart',
'moi-phat-hanh': '/api/v2/page/get/newrelease-chart',
'the-loai-video': '/api/v2/video/get/list',
# For user
'info-artist': '/api/v2/page/get/artist',
'user-list-song': '/api/v2/song/get/list',
'user-list-video': '/api/v2/video/get/list',
}
_PER_PAGE = 50
_API_KEY = '88265e23d4284f25963e6eedac8fbfa3'
_SECRET_KEY = b'2aa2d1c561e809b267f3638c4a307aab'
@ -31,7 +46,12 @@ class ZingMp3BaseIE(InfoExtractor):
title = item.get('title') or item.get('alias')
if type_url == 'video-clip':
info = self._download_json(
'http://api.mp3.zing.vn/api/mobile/video/getvideoinfo', item_id,
query={'requestdata': json.dumps({'id': item_id})})
source = item.get('streaming')
if info.get('source'):
source['mp4'] = info.get('source')
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')
@ -52,8 +72,7 @@ class ZingMp3BaseIE(InfoExtractor):
formats.append({
'format_id': 'mp4-' + res,
'url': video_url,
'height': int_or_none(self._search_regex(
r'^(\d+)p', res, 'resolution', default=None)),
'height': int_or_none(res),
})
continue
elif v == 'VIP':
@ -120,6 +139,11 @@ class ZingMp3BaseIE(InfoExtractor):
}
return f'{self._DOMAIN}{name_api}?{urllib.parse.urlencode(data)}'
def _entries(self, items):
for item in items or []:
if item and item.get('link'):
yield self.url_result(urljoin(self._DOMAIN, item['link']))
class ZingMp3IE(ZingMp3BaseIE):
_VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'bai-hat|video-clip|embed'
@ -189,19 +213,17 @@ class ZingMp3AlbumIE(ZingMp3BaseIE):
_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,
'playlist_mincount': 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,
'playlist_mincount': 49,
}, {
'url': 'http://mp3.zing.vn/playlist/Duong-Hong-Loan-apollobee/IWCAACCB.html',
'only_matching': True,
@ -212,11 +234,198 @@ class ZingMp3AlbumIE(ZingMp3BaseIE):
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'),
items = traverse_obj(data, ('song', 'items')) or []
return self.playlist_result(self._entries(items), traverse_obj(data, 'id', 'encodeId'),
traverse_obj(data, 'name', 'title'))
class ZingMp3ChartHomeIE(ZingMp3BaseIE):
_VALID_URL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?P<id>(?:zing-chart|moi-phat-hanh))/?(?:[#?]|$)'
_TESTS = [{
'url': 'https://zingmp3.vn/zing-chart',
'info_dict': {
'id': 'zing-chart',
'title': 'zing-chart',
},
'playlist_mincount': 100,
}, {
'url': 'https://zingmp3.vn/moi-phat-hanh',
'info_dict': {
'id': 'moi-phat-hanh',
'title': 'moi-phat-hanh',
},
'playlist_mincount': 100,
}]
IE_NAME = 'zingmp3:chart-home'
def _real_extract(self, url):
type_url = self._match_id(url)
api = self.get_api_with_signature(name_api=self._SLUG_API[type_url], param={'id': type_url})
return self._process_data(self._download_json(api, type_url)['data'], type_url, type_url)
def _process_data(self, data, chart_id, type_url):
if type_url == 'zing-chart':
items = traverse_obj(data, ('RTChart', 'items'), default=[])
else:
items = data.get('items')
return self.playlist_result(self._entries(items), type_url, type_url)
class ZingMp3WeekChartIE(ZingMp3BaseIE):
_VALID_URL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?P<type>zing-chart-tuan)/[^/?#]+/(?P<id>\w+)'
IE_NAME = 'zingmp3:week-chart'
_TESTS = [{
'url': 'https://zingmp3.vn/zing-chart-tuan/Bai-hat-Viet-Nam/IWZ9Z08I.html',
'info_dict': {
'id': 'IWZ9Z08I',
'title': 'zing-chart-vn',
},
'playlist_mincount': 10,
}, {
'url': 'https://zingmp3.vn/zing-chart-tuan/Bai-hat-US-UK/IWZ9Z0BW.html',
'info_dict': {
'id': 'IWZ9Z0BW',
'title': 'zing-chart-us',
},
'playlist_mincount': 10,
}, {
'url': 'https://zingmp3.vn/zing-chart-tuan/Bai-hat-KPop/IWZ9Z0BO.html',
'info_dict': {
'id': 'IWZ9Z0BO',
'title': 'zing-chart-korea',
},
'playlist_mincount': 10,
}]
def _process_data(self, data, chart_id, type_url):
return self.playlist_result(self._entries(data['items']), chart_id, f'zing-chart-{data.get("country", "")}')
class ZingMp3ChartMusicVideoIE(ZingMp3BaseIE):
_VALID_URL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?P<type>the-loai-video)/(?P<regions>[^/]+)/(?P<id>[^\.]+)'
IE_NAME = 'zingmp3:chart-music-video'
_TESTS = [{
'url': 'https://zingmp3.vn/the-loai-video/Viet-Nam/IWZ9Z08I.html',
'info_dict': {
'id': 'IWZ9Z08I',
'title': 'the-loai-video_Viet-Nam',
},
'playlist_mincount': 400,
}, {
'url': 'https://zingmp3.vn/the-loai-video/Au-My/IWZ9Z08O.html',
'info_dict': {
'id': 'IWZ9Z08O',
'title': 'the-loai-video_Au-My',
},
'playlist_mincount': 40,
}, {
'url': 'https://zingmp3.vn/the-loai-video/Han-Quoc/IWZ9Z08W.html',
'info_dict': {
'id': 'IWZ9Z08W',
'title': 'the-loai-video_Han-Quoc',
},
'playlist_mincount': 30,
}, {
'url': 'https://zingmp3.vn/the-loai-video/Khong-Loi/IWZ9Z086.html',
'info_dict': {
'id': 'IWZ9Z086',
'title': 'the-loai-video_Khong-Loi',
},
'playlist_mincount': 10,
}]
def _fetch_page(self, song_id, type_url, page):
page += 1
api = self.get_api_with_signature(name_api=self._SLUG_API[type_url], param={
'id': song_id,
'type': 'genre',
'page': page,
'count': self._PER_PAGE
})
data = self._download_json(api, song_id)['data']
return self._entries(data.get('items'))
def _real_extract(self, url):
song_id, regions, type_url = self._match_valid_url(url).group('id', 'regions', 'type')
entries = OnDemandPagedList(functools.partial(self._fetch_page, song_id, type_url), self._PER_PAGE)
return self.playlist_result(entries, song_id, f'{type_url}_{regions}')
class ZingMp3UserIE(ZingMp3BaseIE):
_VALID_URL = r'''(?x)
https?://
(?:mp3\.zing|zingmp3)\.vn/
(?P<user>[^/]+)
(?:
/(?P<type>bai-hat|single|album|video)
)
/?(?:[?#]|$)
'''
IE_NAME = 'zingmp3:user'
_TESTS = [{
'url': 'https://zingmp3.vn/Mr-Siro/bai-hat',
'info_dict': {
'id': 'IWZ98609',
'title': 'Mr. Siro - bai-hat',
'description': 'md5:85ab29bd7b21725c12bf76fd1d6922e5',
},
'playlist_mincount': 91,
}, {
'url': 'https://zingmp3.vn/Mr-Siro/album',
'info_dict': {
'id': 'IWZ98609',
'title': 'Mr. Siro - album',
'description': 'md5:85ab29bd7b21725c12bf76fd1d6922e5',
},
'playlist_mincount': 3,
}, {
'url': 'https://zingmp3.vn/Mr-Siro/single',
'info_dict': {
'id': 'IWZ98609',
'title': 'Mr. Siro - single',
'description': 'md5:85ab29bd7b21725c12bf76fd1d6922e5',
},
'playlist_mincount': 20,
}, {
'url': 'https://zingmp3.vn/Mr-Siro/video',
'info_dict': {
'id': 'IWZ98609',
'title': 'Mr. Siro - video',
'description': 'md5:85ab29bd7b21725c12bf76fd1d6922e5',
},
'playlist_mincount': 15,
}]
def _fetch_page(self, user_id, type_url, page):
page += 1
name_api = self._SLUG_API['user-list-song'] if type_url == 'bai-hat' else self._SLUG_API['user-list-video']
api = self.get_api_with_signature(name_api=name_api, param={
'id': user_id,
'type': 'artist',
'page': page,
'count': self._PER_PAGE
})
data = self._download_json(api, user_id, query={'sort': 'new', 'sectionId': 'aSong'})['data']
return self._entries(data.get('items'))
def _real_extract(self, url):
user_alias, type_url = self._match_valid_url(url).group('user', 'type')
if not type_url:
type_url = 'bai-hat'
user_info = self._download_json(
self.get_api_with_signature(name_api=self._SLUG_API['info-artist'], param={}),
video_id=user_alias, query={'alias': user_alias})['data']
user_id = user_info.get('id')
biography = user_info.get('biography')
if type_url == 'bai-hat' or type_url == 'video':
entries = OnDemandPagedList(functools.partial(self._fetch_page, user_id, type_url), self._PER_PAGE)
return self.playlist_result(entries, user_id, f'{user_info.get("name")} - {type_url}', biography)
else:
entries = []
for section in user_info.get('sections', {}):
if section.get('link') == f'/{user_alias}/{type_url}':
items = section.get('items')
for item in items:
entries.append(self.url_result(urljoin(self._DOMAIN, item.get('link'))))
break
return self.playlist_result(entries, user_id, f'{user_info.get("name")} - {type_url}', biography)

Write Preview
Loading…
Cancel
Save