youtube-dl

commit: ac61f2e0581ad15727870e8dd9a80ddacf01636e
parent 8487e8b98afd1b469c2b9d29ee53bd173ff9a7e0
Author: Remita Amine <remitamine@gmail.com>
Date:   Mon,  4 Jan 2021 01:09:11 +0100

[applepodcasts] Add new extractor(#25918)

Diffstat:
A
youtube_dl/extractor/applepodcasts.py
61
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
M
youtube_dl/extractor/extractors.py
1
+

2 files changed, 62 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/applepodcasts.py b/youtube_dl/extractor/applepodcasts.py
@@ -0,0 +1,61 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_podcast_url,
+    int_or_none,
+    parse_iso8601,
+    try_get,
+)
+
+
+class ApplePodcastsIE(InfoExtractor):
+    _VALID_URL = r'https?://podcasts\.apple\.com/(?:[^/]+/)?podcast(?:/[^/]+){1,2}.*?\bi=(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://podcasts.apple.com/us/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
+        'md5': 'df02e6acb11c10e844946a39e7222b08',
+        'info_dict': {
+            'id': '1000482637777',
+            'ext': 'mp3',
+            'title': '207 - Whitney Webb Returns',
+            'description': 'md5:13a73bade02d2e43737751e3987e1399',
+            'upload_date': '20200705',
+            'timestamp': 1593921600,
+            'duration': 6425,
+            'series': 'The Tim Dillon Show',
+        }
+    }, {
+        'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
+        'only_matching': True,
+    }, {
+        'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns?i=1000482637777',
+        'only_matching': True,
+    }, {
+        'url': 'https://podcasts.apple.com/podcast/id1135137367?i=1000482637777',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        episode_id = self._match_id(url)
+        webpage = self._download_webpage(url, episode_id)
+        ember_data = self._parse_json(self._search_regex(
+            r'id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
+            webpage, 'ember data'), episode_id)
+        episode = ember_data['data']['attributes']
+        description = episode.get('description') or {}
+
+        series = None
+        for inc in (ember_data.get('included') or []):
+            if inc.get('type') == 'media/podcast':
+                series = try_get(inc, lambda x: x['attributes']['name'])
+
+        return {
+            'id': episode_id,
+            'title': episode['name'],
+            'url': clean_podcast_url(episode['assetUrl']),
+            'description': description.get('standard') or description.get('short'),
+            'timestamp': parse_iso8601(episode.get('releaseDateTime')),
+            'duration': int_or_none(episode.get('durationInMilliseconds'), 1000),
+            'series': series,
+        }
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -55,6 +55,7 @@ from .appletrailers import (
     AppleTrailersIE,
     AppleTrailersSectionIE,
 )
+from .applepodcasts import ApplePodcastsIE
 from .archiveorg import ArchiveOrgIE
 from .arcpublishing import ArcPublishingIE
 from .arkena import ArkenaIE