5 from .common
import InfoExtractor
18 class SpotifyBaseIE(InfoExtractor
):
21 'Episode': '8276d4423d709ae9b68ec1b74cc047ba0f7479059a37820be730f125189ac2bf',
22 'MinimalShow': '13ee079672fad3f858ea45a55eb109553b4fb0969ed793185b2e34cbb6ee7cc0',
23 'ShowEpisodes': 'e0e5ce27bd7748d2c59b4d44ba245a8992a05be75d6fabc3b20753fc8857444d',
25 _VALID_URL_TEMPL
= r
'https?://open\.spotify\.com/(?:embed-podcast/|embed/|)%s/(?P<id>[^/?&#]+)'
26 _EMBED_REGEX
= [r
'<iframe[^>]+src="(?P<url>https?://open\.spotify.com/embed/[^"]+)"']
28 def _real_initialize(self
):
29 self
._ACCESS
_TOKEN
= self
._download
_json
(
30 'https://open.spotify.com/get_access_token', None)['accessToken']
32 def _call_api(self
, operation
, video_id
, variables
, **kwargs
):
33 return self
._download
_json
(
34 'https://api-partner.spotify.com/pathfinder/v1/query', video_id
, query
={
35 'operationName': 'query' + operation
,
36 'variables': json
.dumps(variables
),
37 'extensions': json
.dumps({
39 'sha256Hash': self
._OPERATION
_HASHES
[operation
],
42 }, headers
={'authorization': 'Bearer ' + self._ACCESS_TOKEN}
,
45 def _extract_episode(self
, episode
, series
):
46 episode_id
= episode
['id']
47 title
= episode
['name'].strip()
50 audio_preview
= episode
.get('audioPreview') or {}
51 audio_preview_url
= audio_preview
.get('url')
54 'url': audio_preview_url
.replace('://p.scdn.co/mp3-preview/', '://anon-podcast.scdn.co/'),
57 audio_preview_format
= audio_preview
.get('format')
58 if audio_preview_format
:
59 f
['format_id'] = audio_preview_format
60 mobj
= re
.match(r
'([0-9A-Z]{3})_(?:[A-Z]+_)?(\d+)', audio_preview_format
)
63 'abr': int(mobj
.group(2)),
64 'ext': mobj
.group(1).lower(),
68 for item
in (try_get(episode
, lambda x
: x
['audio']['items']) or []):
69 item_url
= item
.get('url')
70 if not (item_url
and item
.get('externallyHosted')):
73 'url': clean_podcast_url(item_url
),
78 for source
in (try_get(episode
, lambda x
: x
['coverArt']['sources']) or []):
79 source_url
= source
.get('url')
84 'width': int_or_none(source
.get('width')),
85 'height': int_or_none(source
.get('height')),
92 'thumbnails': thumbnails
,
93 'description': strip_or_none(episode
.get('description')),
94 'duration': float_or_none(try_get(
95 episode
, lambda x
: x
['duration']['totalMilliseconds']), 1000),
96 'release_date': unified_strdate(try_get(
97 episode
, lambda x
: x
['releaseDate']['isoString'])),
102 class SpotifyIE(SpotifyBaseIE
):
104 IE_DESC
= 'Spotify episodes'
105 _VALID_URL
= SpotifyBaseIE
._VALID
_URL
_TEMPL
% 'episode'
107 'url': 'https://open.spotify.com/episode/4Z7GAJ50bgctf6uclHlWKo',
108 'md5': '74010a1e3fa4d9e1ab3aa7ad14e42d3b',
110 'id': '4Z7GAJ50bgctf6uclHlWKo',
112 'title': 'From the archive: Why time management is ruining our lives',
113 'description': 'md5:b120d9c4ff4135b42aa9b6d9cde86935',
114 'duration': 2083.605,
115 'release_date': '20201217',
116 'series': "The Guardian's Audio Long Reads",
119 'url': 'https://open.spotify.com/embed/episode/4TvCsKKs2thXmarHigWvXE?si=7eatS8AbQb6RxqO2raIuWA',
120 'only_matching': True,
123 def _real_extract(self
, url
):
124 episode_id
= self
._match
_id
(url
)
125 episode
= self
._call
_api
('Episode', episode_id
, {
126 'uri': 'spotify:episode:' + episode_id
128 return self
._extract
_episode
(
129 episode
, try_get(episode
, lambda x
: x
['podcast']['name']))
132 class SpotifyShowIE(SpotifyBaseIE
):
133 IE_NAME
= 'spotify:show'
134 IE_DESC
= 'Spotify shows'
135 _VALID_URL
= SpotifyBaseIE
._VALID
_URL
_TEMPL
% 'show'
137 'url': 'https://open.spotify.com/show/4PM9Ke6l66IRNpottHKV9M',
139 'id': '4PM9Ke6l66IRNpottHKV9M',
140 'title': 'The Story from the Guardian',
141 'description': 'The Story podcast is dedicated to our finest audio documentaries, investigations and long form stories',
143 'playlist_mincount': 36,
147 def _fetch_page(self
, show_id
, page
=0):
148 return self
._call
_api
('ShowEpisodes', show_id
, {
150 'offset': page
* self
._PER
_PAGE
,
151 'uri': f
'spotify:show:{show_id}',
152 }, note
=f
'Downloading page {page + 1} JSON metadata')['podcast']
154 def _real_extract(self
, url
):
155 show_id
= self
._match
_id
(url
)
156 first_page
= self
._fetch
_page
(show_id
)
159 podcast
= self
._fetch
_page
(show_id
, page
) if page
else first_page
161 functools
.partial(self
._extract
_episode
, series
=podcast
.get('name')),
162 traverse_obj(podcast
, ('episodes', 'items', ..., 'episode')))
164 return self
.playlist_result(
165 OnDemandPagedList(_entries
, self
._PER
_PAGE
),
166 show_id
, first_page
.get('name'), first_page
.get('description'))