From 9ee984fc760c9a3f4818055ff28ea886aadc58cb Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 29 Dec 2020 16:13:36 +0100 Subject: [PATCH] [aenetworks] add support for biography.com (closes #3863) --- youtube_dl/extractor/aenetworks.py | 97 ++++++++++++++++++++++-------- youtube_dl/extractor/extractors.py | 2 + 2 files changed, 73 insertions(+), 26 deletions(-) diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py index 3d0cf1208..237012978 100644 --- a/youtube_dl/extractor/aenetworks.py +++ b/youtube_dl/extractor/aenetworks.py @@ -6,6 +6,7 @@ import re from .theplatform import ThePlatformIE from ..utils import ( ExtractorError, + GeoRestrictedError, int_or_none, update_url_query, urlencode_postdata, @@ -28,6 +29,7 @@ class AENetworksBaseIE(ThePlatformIE): 'lifetimemovieclub.com': ('LIFETIMEMOVIECLUB', 'lmc'), 'fyi.tv': ('FYI', 'fyi'), 'historyvault.com': (None, 'historyvault'), + 'biography.com': (None, 'biography'), } def _extract_aen_smil(self, smil_url, video_id, auth=None): @@ -54,6 +56,8 @@ class AENetworksBaseIE(ThePlatformIE): tp_formats, tp_subtitles = self._extract_theplatform_smil( m_url, video_id, 'Downloading %s SMIL data' % (q.get('switch') or q['assetTypes'])) except ExtractorError as e: + if isinstance(e, GeoRestrictedError): + raise last_e = e continue formats.extend(tp_formats) @@ -67,6 +71,34 @@ class AENetworksBaseIE(ThePlatformIE): 'subtitles': subtitles, } + def _extract_aetn_info(self, domain, filter_key, filter_value, url): + requestor_id, brand = self._DOMAIN_MAP[domain] + result = self._download_json( + 'https://feeds.video.aetnd.com/api/v2/%s/videos' % brand, + filter_value, query={'filter[%s]' % filter_key: filter_value})['results'][0] + title = result['title'] + video_id = result['id'] + media_url = result['publicUrl'] + theplatform_metadata = self._download_theplatform_metadata(self._search_regex( + r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id) + info = self._parse_theplatform_metadata(theplatform_metadata) + auth = None + if theplatform_metadata.get('AETN$isBehindWall'): + resource = self._get_mvpd_resource( + requestor_id, theplatform_metadata['title'], + theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'), + theplatform_metadata['ratings'][0]['rating']) + auth = self._extract_mvpd_auth( + url, video_id, requestor_id, resource) + info.update(self._extract_aen_smil(media_url, video_id, auth)) + info.update({ + 'title': title, + 'series': result.get('seriesName'), + 'season_number': int_or_none(result.get('tvSeasonNumber')), + 'episode_number': int_or_none(result.get('tvSeasonEpisodeNumber')), + }) + return info + class AENetworksIE(AENetworksBaseIE): IE_NAME = 'aenetworks' @@ -139,32 +171,7 @@ class AENetworksIE(AENetworksBaseIE): def _real_extract(self, url): domain, canonical = re.match(self._VALID_URL, url).groups() - requestor_id, brand = self._DOMAIN_MAP[domain] - result = self._download_json( - 'https://feeds.video.aetnd.com/api/v2/%s/videos' % brand, - canonical, query={'filter[canonical]': '/' + canonical})['results'][0] - title = result['title'] - video_id = result['id'] - media_url = result['publicUrl'] - theplatform_metadata = self._download_theplatform_metadata(self._search_regex( - r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id) - info = self._parse_theplatform_metadata(theplatform_metadata) - auth = None - if theplatform_metadata.get('AETN$isBehindWall'): - resource = self._get_mvpd_resource( - requestor_id, theplatform_metadata['title'], - theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'), - theplatform_metadata['ratings'][0]['rating']) - auth = self._extract_mvpd_auth( - url, video_id, requestor_id, resource) - info.update(self._extract_aen_smil(media_url, video_id, auth)) - info.update({ - 'title': title, - 'series': result.get('seriesName'), - 'season_number': int_or_none(result.get('tvSeasonNumber')), - 'episode_number': int_or_none(result.get('tvSeasonEpisodeNumber')), - }) - return info + return self._extract_aetn_info(domain, 'canonical', '/' + canonical, url) class AENetworksListBaseIE(AENetworksBaseIE): @@ -294,3 +301,41 @@ class HistoryTopicIE(AENetworksBaseIE): return self.url_result( 'http://www.history.com/videos/' + display_id, AENetworksIE.ie_key()) + + +class HistoryPlayerIE(AENetworksBaseIE): + IE_NAME = 'history:player' + _VALID_URL = r'https?://(?:www\.)?(?P(?:history|biography)\.com)/player/(?P\d+)' + + def _real_extract(self, url): + domain, video_id = re.match(self._VALID_URL, url).groups() + return self._extract_aetn_info(domain, 'id', video_id, url) + + +class BiographyIE(AENetworksBaseIE): + _VALID_URL = r'https?://(?:www\.)?biography\.com/video/(?P[^/?#&]+)' + _TESTS = [{ + 'url': 'https://www.biography.com/video/vincent-van-gogh-full-episode-2075049808', + 'info_dict': { + 'id': '30322987', + 'ext': 'mp4', + 'title': 'Vincent Van Gogh - Full Episode', + 'description': 'A full biography about the most influential 20th century painter, Vincent Van Gogh.', + 'timestamp': 1311970571, + 'upload_date': '20110729', + 'uploader': 'AENE-NEW', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + 'add_ie': ['ThePlatform'], + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + player_url = self._search_regex( + r']+src="(%s)' % HistoryPlayerIE._VALID_URL, + webpage, 'player URL') + return self.url_result(player_url, HistoryPlayerIE.ie_key()) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index cf50b897b..20472f2f7 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -33,6 +33,8 @@ from .aenetworks import ( AENetworksCollectionIE, AENetworksShowIE, HistoryTopicIE, + HistoryPlayerIE, + BiographyIE, ) from .afreecatv import AfreecaTVIE from .airmozilla import AirMozillaIE