X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/03342304420e5daeb428ffdcc7bbd2bbfecfa61a..a7fd25993be110e616bb9bf6d602949b54df1a7d:/youtube_dl/extractor/acast.py diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py index 92eee81..c4362be 100644 --- a/youtube_dl/extractor/acast.py +++ b/youtube_dl/extractor/acast.py @@ -2,71 +2,124 @@ from __future__ import unicode_literals import re +import functools from .common import InfoExtractor from ..compat import compat_str -from ..utils import int_or_none +from ..utils import ( + float_or_none, + int_or_none, + try_get, + unified_timestamp, + OnDemandPagedList, +) class ACastIE(InfoExtractor): IE_NAME = 'acast' - _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P[^/]+)/(?P[^/#?]+)' - _TEST = { - 'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan', - 'md5': 'ada3de5a1e3a2a381327d749854788bb', + _VALID_URL = r'''(?x) + https?:// + (?: + (?:(?:embed|www)\.)?acast\.com/| + play\.acast\.com/s/ + ) + (?P[^/]+)/(?P[^/#?]+) + ''' + _TESTS = [{ + 'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna', + 'md5': 'a02393c74f3bdb1801c3ec2695577ce0', 'info_dict': { - 'id': '57de3baa-4bb0-487e-9418-2692c1277a34', + 'id': '2a92b283-1a75-4ad8-8396-499c641de0d9', 'ext': 'mp3', - 'title': '"Where Are You?": Taipei 101, Taiwan', - 'timestamp': 1196172000000, - 'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e', - 'duration': 211, + 'title': '2. Raggarmordet - Röster ur det förflutna', + 'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4', + 'timestamp': 1477346700, + 'upload_date': '20161024', + 'duration': 2766.602563, + 'creator': 'Anton Berg & Martin Johnson', + 'series': 'Spår', + 'episode': '2. Raggarmordet - Röster ur det förflutna', } - } + }, { + 'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015', + 'only_matching': True, + }, { + 'url': 'https://play.acast.com/s/rattegangspodden/s04e09-styckmordet-i-helenelund-del-22', + 'only_matching': True, + }] def _real_extract(self, url): channel, display_id = re.match(self._VALID_URL, url).groups() - - embed_page = self._download_webpage( - re.sub('(?:www\.)?acast\.com', 'embedcdn.acast.com', url), display_id) - cast_data = self._parse_json(self._search_regex( - r'window\[\'acast/queries\'\]\s*=\s*([^;]+);', embed_page, 'acast data'), - display_id)['GetAcast/%s/%s' % (channel, display_id)] - + s = self._download_json( + 'https://play-api.acast.com/stitch/%s/%s' % (channel, display_id), + display_id)['result'] + media_url = s['url'] + cast_data = self._download_json( + 'https://play-api.acast.com/splash/%s/%s' % (channel, display_id), + display_id)['result'] + e = cast_data['episode'] + title = e['name'] return { - 'id': compat_str(cast_data['id']), + 'id': compat_str(e['id']), 'display_id': display_id, - 'url': cast_data['blings'][0]['audio'], - 'title': cast_data['name'], - 'description': cast_data.get('description'), - 'thumbnail': cast_data.get('image'), - 'timestamp': int_or_none(cast_data.get('publishingDate')), - 'duration': int_or_none(cast_data.get('duration')), + 'url': media_url, + 'title': title, + 'description': e.get('description') or e.get('summary'), + 'thumbnail': e.get('image'), + 'timestamp': unified_timestamp(e.get('publishingDate')), + 'duration': float_or_none(s.get('duration') or e.get('duration')), + 'filesize': int_or_none(e.get('contentLength')), + 'creator': try_get(cast_data, lambda x: x['show']['author'], compat_str), + 'series': try_get(cast_data, lambda x: x['show']['name'], compat_str), + 'season_number': int_or_none(e.get('seasonNumber')), + 'episode': title, + 'episode_number': int_or_none(e.get('episodeNumber')), } class ACastChannelIE(InfoExtractor): IE_NAME = 'acast:channel' - _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P[^/#?]+)' - _TEST = { - 'url': 'https://www.acast.com/condenasttraveler', + _VALID_URL = r'''(?x) + https?:// + (?: + (?:www\.)?acast\.com/| + play\.acast\.com/s/ + ) + (?P[^/#?]+) + ''' + _TESTS = [{ + 'url': 'https://www.acast.com/todayinfocus', 'info_dict': { - 'id': '50544219-29bb-499e-a083-6087f4cb7797', - 'title': 'Condé Nast Traveler Podcast', - 'description': 'md5:98646dee22a5b386626ae31866638fbd', + 'id': '4efc5294-5385-4847-98bd-519799ce5786', + 'title': 'Today in Focus', + 'description': 'md5:9ba5564de5ce897faeb12963f4537a64', }, - 'playlist_mincount': 20, - } - _API_BASE_URL = 'https://www.acast.com/api/' + 'playlist_mincount': 35, + }, { + 'url': 'http://play.acast.com/s/ft-banking-weekly', + 'only_matching': True, + }] + _API_BASE_URL = 'https://play.acast.com/api/' + _PAGE_SIZE = 10 @classmethod def suitable(cls, url): return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url) - def _real_extract(self, url): - display_id = self._match_id(url) - channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id) - casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id) - entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts] + def _fetch_page(self, channel_slug, page): + casts = self._download_json( + self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page), + channel_slug, note='Download page %d of channel data' % page) + for cast in casts: + yield self.url_result( + 'https://play.acast.com/s/%s/%s' % (channel_slug, cast['url']), + 'ACast', cast['id']) - return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description')) + def _real_extract(self, url): + channel_slug = self._match_id(url) + channel_data = self._download_json( + self._API_BASE_URL + 'channels/%s' % channel_slug, channel_slug) + entries = OnDemandPagedList(functools.partial( + self._fetch_page, channel_slug), self._PAGE_SIZE) + return self.playlist_result(entries, compat_str( + channel_data['id']), channel_data['name'], channel_data.get('description'))