X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/47d80ec0b18245caeb97018d4c1af18d0b5b972b..4af078afdfeb5a7f230d6e445b1d1e7eefd04704:/youtube_dl/extractor/ard.py?ds=sidebyside diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 35f3656..6bf8f61 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -14,66 +14,43 @@ from ..utils import ( unified_strdate, xpath_text, update_url_query, + url_or_none, ) from ..compat import compat_etree_fromstring class ARDMediathekIE(InfoExtractor): IE_NAME = 'ARD:mediathek' - _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de)/(?:.*/)(?P[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' + _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' _TESTS = [{ - 'url': 'http://www.ardmediathek.de/tv/Dokumentation-und-Reportage/Ich-liebe-das-Leben-trotzdem/rbb-Fernsehen/Video?documentId=29582122&bcastId=3822114', + # available till 26.07.2022 + 'url': 'http://www.ardmediathek.de/tv/S%C3%9CDLICHT/Was-ist-die-Kunst-der-Zukunft-liebe-Ann/BR-Fernsehen/Video?bcastId=34633636&documentId=44726822', 'info_dict': { - 'id': '29582122', + 'id': '44726822', 'ext': 'mp4', - 'title': 'Ich liebe das Leben trotzdem', - 'description': 'md5:45e4c225c72b27993314b31a84a5261c', - 'duration': 4557, + 'title': 'Was ist die Kunst der Zukunft, liebe Anna McCarthy?', + 'description': 'md5:4ada28b3e3b5df01647310e41f3a62f5', + 'duration': 1740, }, 'params': { # m3u8 download 'skip_download': True, - }, - 'skip': 'HTTP Error 404: Not Found', + } }, { - 'url': 'http://www.ardmediathek.de/tv/Tatort/Tatort-Scheinwelten-H%C3%B6rfassung-Video/Das-Erste/Video?documentId=29522730&bcastId=602916', - 'md5': 'f4d98b10759ac06c0072bbcd1f0b9e3e', - 'info_dict': { - 'id': '29522730', - 'ext': 'mp4', - 'title': 'Tatort: Scheinwelten - Hörfassung (Video tgl. ab 20 Uhr)', - 'description': 'md5:196392e79876d0ac94c94e8cdb2875f1', - 'duration': 5252, - }, - 'skip': 'HTTP Error 404: Not Found', + 'url': 'https://one.ard.de/tv/Mord-mit-Aussicht/Mord-mit-Aussicht-6-39-T%C3%B6dliche-Nach/ONE/Video?bcastId=46384294&documentId=55586872', + 'only_matching': True, }, { # audio 'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086', - 'md5': '219d94d8980b4f538c7fcb0865eb7f2c', - 'info_dict': { - 'id': '28488308', - 'ext': 'mp3', - 'title': 'Tod eines Fußballers', - 'description': 'md5:f6e39f3461f0e1f54bfa48c8875c86ef', - 'duration': 3240, - }, - 'skip': 'HTTP Error 404: Not Found', + 'only_matching': True, }, { 'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht', 'only_matching': True, }, { # audio 'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158', - 'md5': '4e8f00631aac0395fee17368ac0e9867', - 'info_dict': { - 'id': '30796318', - 'ext': 'mp3', - 'title': 'Vor dem Fest', - 'description': 'md5:c0c1c8048514deaed2a73b3a60eecacb', - 'duration': 3287, - }, - 'skip': 'Video is no longer available', + 'only_matching': True, }] def _extract_media_info(self, media_info_url, webpage, video_id): @@ -93,6 +70,7 @@ class ARDMediathekIE(InfoExtractor): duration = int_or_none(media_info.get('_duration')) thumbnail = media_info.get('_previewImage') + is_live = media_info.get('_isLive') is True subtitles = {} subtitle_url = media_info.get('_subtitleUrl') @@ -106,6 +84,7 @@ class ARDMediathekIE(InfoExtractor): 'id': video_id, 'duration': duration, 'thumbnail': thumbnail, + 'is_live': is_live, 'formats': formats, 'subtitles': subtitles, } @@ -124,6 +103,8 @@ class ARDMediathekIE(InfoExtractor): quality = stream.get('_quality') server = stream.get('_server') for stream_url in stream_urls: + if not url_or_none(stream_url): + continue ext = determine_ext(stream_url) if quality != 'auto' and ext in ('f4m', 'm3u8'): continue @@ -144,13 +125,11 @@ class ARDMediathekIE(InfoExtractor): 'play_path': stream_url, 'format_id': 'a%s-rtmp-%s' % (num, quality), } - elif stream_url.startswith('http'): + else: f = { 'url': stream_url, 'format_id': 'a%s-%s-%s' % (num, ext, quality) } - else: - continue m = re.search(r'_(?P\d+)x(?P\d+)\.mp4$', stream_url) if m: f.update({ @@ -166,9 +145,11 @@ class ARDMediathekIE(InfoExtractor): # determine video id from url m = re.match(self._VALID_URL, url) + document_id = None + numid = re.search(r'documentId=([0-9]+)', url) if numid: - video_id = numid.group(1) + document_id = video_id = numid.group(1) else: video_id = m.group('video_id') @@ -191,7 +172,7 @@ class ARDMediathekIE(InfoExtractor): title = self._html_search_regex( [r'(.*?)', - r'', + r'', r'

(.*?)

'], webpage, 'title') description = self._html_search_meta( @@ -228,12 +209,16 @@ class ARDMediathekIE(InfoExtractor): 'formats': formats, } else: # request JSON file + if not document_id: + video_id = self._search_regex( + r'/play/(?:config|media)/(\d+)', webpage, 'media id') info = self._extract_media_info( - 'http://www.ardmediathek.de/play/media/%s' % video_id, webpage, video_id) + 'http://www.ardmediathek.de/play/media/%s' % video_id, + webpage, video_id) info.update({ 'id': video_id, - 'title': title, + 'title': self._live_title(title) if info.get('is_live') else title, 'description': description, 'thumbnail': thumbnail, }) @@ -243,20 +228,23 @@ class ARDMediathekIE(InfoExtractor): class ARDIE(InfoExtractor): _VALID_URL = r'(?Phttps?://(www\.)?daserste\.de/[^?#]+/videos/(?P[^/?#]+)-(?P[0-9]+))\.html' - _TEST = { - 'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html', - 'md5': 'd216c3a86493f9322545e045ddc3eb35', + _TESTS = [{ + # available till 14.02.2019 + 'url': 'http://www.daserste.de/information/talk/maischberger/videos/das-groko-drama-zerlegen-sich-die-volksparteien-video-102.html', + 'md5': '8e4ec85f31be7c7fc08a26cdbc5a1f49', 'info_dict': { - 'display_id': 'die-story-im-ersten-mission-unter-falscher-flagge', - 'id': '100', + 'display_id': 'das-groko-drama-zerlegen-sich-die-volksparteien-video', + 'id': '102', 'ext': 'mp4', - 'duration': 2600, - 'title': 'Die Story im Ersten: Mission unter falscher Flagge', - 'upload_date': '20140804', - 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 4435.0, + 'title': 'Das GroKo-Drama: Zerlegen sich die Volksparteien?', + 'upload_date': '20180214', + 'thumbnail': r're:^https?://.*\.jpg$', }, - 'skip': 'HTTP Error 404: Not Found', - } + }, { + 'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -297,3 +285,76 @@ class ARDIE(InfoExtractor): 'upload_date': upload_date, 'thumbnail': thumbnail, } + + +class ARDBetaMediathekIE(InfoExtractor): + _VALID_URL = r'https://beta\.ardmediathek\.de/[a-z]+/player/(?P[a-zA-Z0-9]+)/(?P[^/?#]+)' + _TESTS = [{ + 'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita', + 'md5': '2d02d996156ea3c397cfc5036b5d7f8f', + 'info_dict': { + 'display_id': 'die-robuste-roswita', + 'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE', + 'title': 'Tatort: Die robuste Roswita', + 'description': r're:^Der Mord.*trüber ist als die Ilm.', + 'duration': 5316, + 'thumbnail': 'https://img.ardmediathek.de/standard/00/55/43/59/34/-1774185891/16x9/960?mandant=ard', + 'upload_date': '20180826', + 'ext': 'mp4', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('video_id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);\n', webpage, 'json') + data = self._parse_json(data_json, display_id) + + res = { + 'id': video_id, + 'display_id': display_id, + } + formats = [] + for widget in data.values(): + if widget.get('_geoblocked'): + raise ExtractorError('This video is not available due to geoblocking', expected=True) + + if '_duration' in widget: + res['duration'] = widget['_duration'] + if 'clipTitle' in widget: + res['title'] = widget['clipTitle'] + if '_previewImage' in widget: + res['thumbnail'] = widget['_previewImage'] + if 'broadcastedOn' in widget: + res['upload_date'] = unified_strdate(widget['broadcastedOn']) + if 'synopsis' in widget: + res['description'] = widget['synopsis'] + if '_subtitleUrl' in widget: + res['subtitles'] = {'de': [{ + 'ext': 'ttml', + 'url': widget['_subtitleUrl'], + }]} + if '_quality' in widget: + format_url = widget['_stream']['json'][0] + + if format_url.endswith('.f4m'): + formats.extend(self._extract_f4m_formats( + format_url + '?hdcore=3.11.0', + video_id, f4m_id='hds', fatal=False)) + elif format_url.endswith('m3u8'): + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + else: + formats.append({ + 'format_id': 'http-' + widget['_quality'], + 'url': format_url, + 'preference': 10, # Plain HTTP, that's nice + }) + + self._sort_formats(formats) + res['formats'] = formats + + return res