mirror/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-05-22 18:05:46 -05:00
Code Activity

[ie/jiosaavn:show] Add extractor (#12803)

Browse source 
Closes #12766

Authored by: subrat-lima
This commit is contained in:
Subrat Lima 2025-05-11 00:39:35 -05:00 committed by bashonly
parent cbcfe6378d
commit 6839276496
2 changed files with 155 additions and 38 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
yt_dlp/extractor/_extractors.py
View file

@ -929,6 +929,7 @@
from .jiosaavn import (
JioSaavnAlbumIE,
JioSaavnPlaylistIE,
JioSaavnShowIE,
JioSaavnSongIE,
)
from .joj import JojIE

192
yt_dlp/extractor/jiosaavn.py
View file

@ -5,19 +5,24 @@
from .common import InfoExtractor
from ..utils import (
InAdvancePagedList,
ISO639Utils,
clean_html,
int_or_none,
make_archive_id,
smuggle_url,
unified_strdate,
unified_timestamp,
unsmuggle_url,
url_basename,
url_or_none,
urlencode_postdata,
urljoin,
)
from ..utils.traversal import traverse_obj
class JioSaavnBaseIE(InfoExtractor):
_URL_BASE_RE = r'https?://(?:www\.)?(?:jio)?saavn\.com'
_API_URL = 'https://www.jiosaavn.com/api.php'
_VALID_BITRATES = {'16', '32', '64', '128', '320'}
@ -30,16 +35,20 @@ def requested_bitrates(self):
f'Valid bitrates are: {", ".join(sorted(self._VALID_BITRATES, key=int))}')
return requested_bitrates
def _extract_formats(self, song_data):
def _extract_formats(self, item_data):
# Show/episode JSON data has a slightly different structure than song JSON data
if media_url := traverse_obj(item_data, ('more_info', 'encrypted_media_url', {str})):
item_data.setdefault('encrypted_media_url', media_url)
for bitrate in self.requested_bitrates:
media_data = self._download_json(
self._API_URL, song_data['id'],
self._API_URL, item_data['id'],
f'Downloading format info for {bitrate}',
fatal=False, data=urlencode_postdata({
'__call': 'song.generateAuthToken',
'_format': 'json',
'bitrate': bitrate,
'url': song_data['encrypted_media_url'],
'url': item_data['encrypted_media_url'],
}))
if not traverse_obj(media_data, ('auth_url', {url_or_none})):
self.report_warning(f'Unable to extract format info for {bitrate}')
@ -53,24 +62,6 @@ def _extract_formats(self, song_data):
'vcodec': 'none',
}
def _extract_song(self, song_data, url=None):
info = traverse_obj(song_data, {
'id': ('id', {str}),
'title': ('song', {clean_html}),
'album': ('album', {clean_html}),
'thumbnail': ('image', {url_or_none}, {lambda x: re.sub(r'-\d+x\d+\.', '-500x500.', x)}),
'duration': ('duration', {int_or_none}),
'view_count': ('play_count', {int_or_none}),
'release_year': ('year', {int_or_none}),
'artists': ('primary_artists', {lambda x: x.split(', ') if x else None}),
'webpage_url': ('perma_url', {url_or_none}),
})
if webpage_url := info.get('webpage_url') or url:
info['display_id'] = url_basename(webpage_url)
info['_old_archive_ids'] = [make_archive_id(JioSaavnSongIE, info['display_id'])]
return info
def _call_api(self, type_, token, note='API', params={}):
return self._download_json(
self._API_URL, token, f'Downloading {note} JSON', f'Unable to download {note} JSON',
@ -84,6 +75,81 @@ def _call_api(self, type_, token, note='API', params={}):
**params,
})
@staticmethod
def _extract_common_info(data):
return traverse_obj(data, {
'id': ('id', {str}),
'thumbnail': ('image', {url_or_none}, {lambda x: re.sub(r'-\d+x\d+\.', '-500x500.', x)}),
'view_count': ('play_count', {int_or_none}),
'release_year': ('year', {int_or_none}),
'language': ('language', {lambda x: ISO639Utils.short2long(x.casefold()) or 'und'}),
'webpage_url': ('perma_url', {url_or_none}),
})
@staticmethod
def _extract_song(song_data, url=None):
info = JioSaavnBaseIE._extract_common_info(song_data)
info.update(traverse_obj(song_data, {
'title': ('song', {clean_html}),
'album': ('album', {clean_html}),
'duration': ('duration', {int_or_none}),
'release_date': ('release_date', {unified_strdate}),
'channel': ('label', {str}),
'channel_id': ('label_id', {str}),
'channel_url': ('label_url', {urljoin('https://www.jiosaavn.com/')}),
'artists': ('primary_artists', {lambda x: x.split(', ') if x else None}),
}))
if webpage_url := info.get('webpage_url') or url:
info['display_id'] = url_basename(webpage_url)
info['_old_archive_ids'] = [make_archive_id(JioSaavnSongIE, info['display_id'])]
return info
@staticmethod
def _extract_episode(episode_data, url=None):
info = JioSaavnBaseIE._extract_common_info(episode_data)
info.update(traverse_obj(episode_data, {
'title': ('title', {clean_html}),
'description': ('more_info', 'description', {str}),
'duration': ('more_info', 'duration', {int_or_none}),
'timestamp': ('more_info', 'release_time', {unified_timestamp}),
'channel': ('more_info', 'label', {str}),
'channel_id': ('more_info', 'label_id', {str}),
'channel_url': ('more_info', 'label_url', {urljoin('https://www.jiosaavn.com/')}),
'series': ('more_info', 'show_title', {str}),
'series_id': ('more_info', 'show_id', {str}),
'season': ('more_info', 'season_title', {str}),
'season_number': ('more_info', 'season_no', {int_or_none}),
'season_id': ('more_info', 'season_id', {str}),
'episode_number': ('more_info', 'episode_number', {int_or_none}),
'cast': ('starring', {lambda x: x.split(', ') if x else None}),
'artists': ('more_info', 'artistMap', 'primary_artists', ..., 'name', {str}),
}))
if webpage_url := info.get('webpage_url') or url:
info['display_id'] = url_basename(webpage_url)
if featured_artists := traverse_obj(episode_data, ('featured_artists', {str})):
info.setdefault('artists', []).extend(featured_artists.split(', '))
return info
def _extract_jiosaavn_result(self, url, endpoint, response_key, parse_func):
url, smuggled_data = unsmuggle_url(url)
data = traverse_obj(smuggled_data, ({
'id': ('id', {str}),
'encrypted_media_url': ('encrypted_media_url', {str}),
}))
if 'id' in data and 'encrypted_media_url' in data:
result = {'id': data['id']}
else:
# only extract metadata if this is not a url_transparent result
data = self._call_api(endpoint, self._match_id(url))[response_key][0]
result = parse_func(data, url)
result['formats'] = list(self._extract_formats(data))
return result
def _yield_songs(self, playlist_data):
for song_data in traverse_obj(playlist_data, ('songs', lambda _, v: v['id'] and v['perma_url'])):
song_info = self._extract_song(song_data)
@ -96,7 +162,7 @@ def _yield_songs(self, playlist_data):
class JioSaavnSongIE(JioSaavnBaseIE):
IE_NAME = 'jiosaavn:song'
_VALID_URL = r'https?://(?:www\.)?(?:jiosaavn\.com/song/[^/?#]+/|saavn\.com/s/song/(?:[^/?#]+/){3})(?P<id>[^/?#]+)'
_VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'(?:/song/[^/?#]+/|/s/song/(?:[^/?#]+/){3})(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.jiosaavn.com/song/leja-re/OQsEfQFVUXk',
'md5': '3b84396d15ed9e083c3106f1fa589c04',
@ -106,12 +172,38 @@ class JioSaavnSongIE(JioSaavnBaseIE):
'ext': 'm4a',
'title': 'Leja Re',
'album': 'Leja Re',
'thumbnail': r're:https?://c.saavncdn.com/258/Leja-Re-Hindi-2018-20181124024539-500x500.jpg',
'thumbnail': r're:https?://.+/.+\.jpg',
'duration': 205,
'view_count': int,
'release_year': 2018,
'artists': ['Sandesh Shandilya', 'Dhvani Bhanushali', 'Tanishk Bagchi'],
'_old_archive_ids': ['jiosaavnsong OQsEfQFVUXk'],
'channel': 'T-Series',
'language': 'hin',
'channel_id': '34297',
'channel_url': 'https://www.jiosaavn.com/label/t-series-albums/6DLuXO3VoTo_',
'release_date': '20181124',
},
}, {
'url': 'https://www.jiosaavn.com/song/chuttamalle/P1FfWjZkQ0Q',
'md5': '96296c58d6ce488a417ef0728fd2d680',
'info_dict': {
'id': 'O94kBTtw',
'display_id': 'P1FfWjZkQ0Q',
'ext': 'm4a',
'title': 'Chuttamalle',
'album': 'Devara Part 1 - Telugu',
'thumbnail': r're:https?://.+/.+\.jpg',
'duration': 222,
'view_count': int,
'release_year': 2024,
'artists': 'count:3',
'_old_archive_ids': ['jiosaavnsong P1FfWjZkQ0Q'],
'channel': 'T-Series',
'language': 'tel',
'channel_id': '34297',
'channel_url': 'https://www.jiosaavn.com/label/t-series-albums/6DLuXO3VoTo_',
'release_date': '20240926',
},
}, {
'url': 'https://www.saavn.com/s/song/hindi/Saathiya/O-Humdum-Suniyo-Re/KAMiazoCblU',
@ -119,26 +211,50 @@ class JioSaavnSongIE(JioSaavnBaseIE):
}]
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url)
song_data = traverse_obj(smuggled_data, ({
'id': ('id', {str}),
'encrypted_media_url': ('encrypted_media_url', {str}),
}))
return self._extract_jiosaavn_result(url, 'song', 'songs', self._extract_song)
if 'id' in song_data and 'encrypted_media_url' in song_data:
result = {'id': song_data['id']}
else:
# only extract metadata if this is not a url_transparent result
song_data = self._call_api('song', self._match_id(url))['songs'][0]
result = self._extract_song(song_data, url)
result['formats'] = list(self._extract_formats(song_data))
return result
class JioSaavnShowIE(JioSaavnBaseIE):
IE_NAME = 'jiosaavn:show'
_VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'/shows/[^/?#]+/(?P<id>[^/?#]{11,})/?(?:$|[?#])'
_TESTS = [{
'url': 'https://www.jiosaavn.com/shows/non-food-ways-to-boost-your-energy/XFMcKICOCgc_',
'md5': '0733cd254cfe74ef88bea1eaedcf1f4f',
'info_dict': {
'id': 'qqzh3RKZ',
'display_id': 'XFMcKICOCgc_',
'ext': 'mp3',
'title': 'Non-Food Ways To Boost Your Energy',
'description': 'md5:26e7129644b5c6aada32b8851c3997c8',
'episode': 'Episode 1',
'timestamp': 1640563200,
'series': 'Holistic Lifestyle With Neha Ranglani',
'series_id': '52397',
'season': 'Holistic Lifestyle With Neha Ranglani',
'season_number': 1,
'season_id': '61273',
'thumbnail': r're:https?://.+/.+\.jpg',
'duration': 311,
'view_count': int,
'release_year': 2021,
'language': 'eng',
'channel': 'Saavn OG',
'channel_id': '1953876',
'episode_number': 1,
'upload_date': '20211227',
},
}, {
'url': 'https://www.jiosaavn.com/shows/himesh-reshammiya/Kr8fmfSN4vo_',
'only_matching': True,
}]
def _real_extract(self, url):
return self._extract_jiosaavn_result(url, 'episode', 'episodes', self._extract_episode)
class JioSaavnAlbumIE(JioSaavnBaseIE):
IE_NAME = 'jiosaavn:album'
_VALID_URL = r'https?://(?:www\.)?(?:jio)?saavn\.com/album/[^/?#]+/(?P<id>[^/?#]+)'
_VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'/album/[^/?#]+/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.jiosaavn.com/album/96/buIOjYZDrNA_',
'info_dict': {
@ -158,7 +274,7 @@ def _real_extract(self, url):
class JioSaavnPlaylistIE(JioSaavnBaseIE):
IE_NAME = 'jiosaavn:playlist'
_VALID_URL = r'https?://(?:www\.)?(?:jio)?saavn\.com/(?:s/playlist/(?:[^/?#]+/){2}|featured/[^/?#]+/)(?P<id>[^/?#]+)'
_VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'/(?:s/playlist/(?:[^/?#]+/){2}|featured/[^/?#]+/)(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.jiosaavn.com/s/playlist/2279fbe391defa793ad7076929a2f5c9/mood-english/LlJ8ZWT1ibN5084vKHRj2Q__',
'info_dict': {