2 from functools
import partial
4 from .common
import InfoExtractor
21 from ..utils
.traversal
import traverse_obj
24 class ARDMediathekBaseIE(InfoExtractor
):
25 _GEO_COUNTRIES
= ['DE']
27 def _extract_media_info(self
, media_info_url
, webpage
, video_id
):
28 media_info
= self
._download
_json
(
29 media_info_url
, video_id
, 'Downloading media JSON')
30 return self
._parse
_media
_info
(media_info
, video_id
, '"fsk"' in webpage
)
32 def _parse_media_info(self
, media_info
, video_id
, fsk
):
33 formats
= self
._extract
_formats
(media_info
, video_id
)
37 self
.raise_no_formats(
38 'This video is only available after 20:00', expected
=True)
39 elif media_info
.get('_geoblocked'):
40 self
.raise_geo_restricted(
41 'This video is not available due to geoblocking',
42 countries
=self
._GEO
_COUNTRIES
, metadata_available
=True)
45 subtitle_url
= media_info
.get('_subtitleUrl')
52 'url': subtitle_url
.replace('/ebutt/', '/webvtt/') + '.vtt',
57 'duration': int_or_none(media_info
.get('_duration')),
58 'thumbnail': media_info
.get('_previewImage'),
59 'is_live': media_info
.get('_isLive') is True,
61 'subtitles': subtitles
,
64 def _extract_formats(self
, media_info
, video_id
):
65 type_
= media_info
.get('_type')
66 media_array
= media_info
.get('_mediaArray', [])
68 for num
, media
in enumerate(media_array
):
69 for stream
in media
.get('_mediaStreamArray', []):
70 stream_urls
= stream
.get('_stream')
73 if not isinstance(stream_urls
, list):
74 stream_urls
= [stream_urls
]
75 quality
= stream
.get('_quality')
76 server
= stream
.get('_server')
77 for stream_url
in stream_urls
:
78 if not url_or_none(stream_url
):
80 ext
= determine_ext(stream_url
)
81 if quality
!= 'auto' and ext
in ('f4m', 'm3u8'):
84 formats
.extend(self
._extract
_f
4m
_formats
(
85 update_url_query(stream_url
, {
87 'plugin': 'aasp-3.1.1.69.124'
88 }), video_id
, f4m_id
='hds', fatal
=False))
90 formats
.extend(self
._extract
_m
3u8_formats
(
91 stream_url
, video_id
, 'mp4', 'm3u8_native',
92 m3u8_id
='hls', fatal
=False))
94 if server
and server
.startswith('rtmp'):
97 'play_path': stream_url
,
98 'format_id': 'a%s-rtmp-%s' % (num
, quality
),
103 'format_id': 'a%s-%s-%s' % (num
, ext
, quality
)
106 r
'_(?P<width>\d+)x(?P<height>\d+)\.mp4$',
110 'width': int(m
.group('width')),
111 'height': int(m
.group('height')),
119 class ARDIE(InfoExtractor
):
120 _VALID_URL
= r
'(?P<mainurl>https?://(?:www\.)?daserste\.de/(?:[^/?#&]+/)+(?P<id>[^/?#&]+))\.html'
122 # available till 7.12.2023
123 'url': 'https://www.daserste.de/information/talk/maischberger/videos/maischberger-video-424.html',
124 'md5': '94812e6438488fb923c361a44469614b',
126 'id': 'maischberger-video-424',
127 'display_id': 'maischberger-video-424',
130 'title': 'maischberger am 07.12.2022',
131 'upload_date': '20221207',
132 'thumbnail': r
're:^https?://.*\.jpg$',
135 'url': 'https://www.daserste.de/information/politik-weltgeschehen/morgenmagazin/videosextern/dominik-kahun-aus-der-nhl-direkt-zur-weltmeisterschaft-100.html',
136 'only_matching': True,
138 'url': 'https://www.daserste.de/information/nachrichten-wetter/tagesthemen/videosextern/tagesthemen-17736.html',
139 'only_matching': True,
141 'url': 'https://www.daserste.de/unterhaltung/serie/in-aller-freundschaft-die-jungen-aerzte/videos/diversity-tag-sanam-afrashteh100.html',
142 'only_matching': True,
144 'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
145 'only_matching': True,
147 'url': 'https://www.daserste.de/unterhaltung/serie/in-aller-freundschaft-die-jungen-aerzte/Drehpause-100.html',
148 'only_matching': True,
150 'url': 'https://www.daserste.de/unterhaltung/film/filmmittwoch-im-ersten/videos/making-ofwendezeit-video-100.html',
151 'only_matching': True,
154 def _real_extract(self
, url
):
155 mobj
= self
._match
_valid
_url
(url
)
156 display_id
= mobj
.group('id')
158 player_url
= mobj
.group('mainurl') + '~playerXml.xml'
159 doc
= self
._download
_xml
(player_url
, display_id
)
160 video_node
= doc
.find('./video')
161 upload_date
= unified_strdate(xpath_text(
162 video_node
, './broadcastDate'))
163 thumbnail
= xpath_text(video_node
, './/teaserImage//variant/url')
166 for a
in video_node
.findall('.//asset'):
167 file_name
= xpath_text(a
, './fileName', default
=None)
170 format_type
= a
.attrib
.get('type')
171 format_url
= url_or_none(file_name
)
173 ext
= determine_ext(file_name
)
175 formats
.extend(self
._extract
_m
3u8_formats
(
176 format_url
, display_id
, 'mp4', entry_protocol
='m3u8_native',
177 m3u8_id
=format_type
or 'hls', fatal
=False))
180 formats
.extend(self
._extract
_f
4m
_formats
(
181 update_url_query(format_url
, {'hdcore': '3.7.0'}
),
182 display_id
, f4m_id
=format_type
or 'hds', fatal
=False))
185 'format_id': format_type
,
186 'width': int_or_none(xpath_text(a
, './frameWidth')),
187 'height': int_or_none(xpath_text(a
, './frameHeight')),
188 'vbr': int_or_none(xpath_text(a
, './bitrateVideo')),
189 'abr': int_or_none(xpath_text(a
, './bitrateAudio')),
190 'vcodec': xpath_text(a
, './codecVideo'),
191 'tbr': int_or_none(xpath_text(a
, './totalBitrate')),
193 server_prefix
= xpath_text(a
, './serverPrefix', default
=None)
196 'url': server_prefix
,
197 'playpath': file_name
,
202 f
['url'] = format_url
206 ('./dataTimedText', 'ttml'),
207 ('./dataTimedTextNoOffset', 'ttml'),
208 ('./dataTimedTextVtt', 'vtt'),
212 for subsel
, subext
in _SUB_FORMATS
:
213 for node
in video_node
.findall(subsel
):
214 subtitles
.setdefault('de', []).append({
215 'url': node
.attrib
['url'],
220 'id': xpath_text(video_node
, './videoId', default
=display_id
),
222 'subtitles': subtitles
,
223 'display_id': display_id
,
224 'title': video_node
.find('./title').text
,
225 'duration': parse_duration(video_node
.find('./duration').text
),
226 'upload_date': upload_date
,
227 'thumbnail': thumbnail
,
231 class ARDBetaMediathekIE(InfoExtractor
):
232 IE_NAME
= 'ARDMediathek'
233 _VALID_URL
= r
'''(?x)https://
234 (?:(?:beta|www)\.)?ardmediathek\.de/
236 (?:player|live|video)/
240 _GEO_COUNTRIES
= ['DE']
243 'url': 'https://www.ardmediathek.de/video/filme-im-mdr/liebe-auf-vier-pfoten/mdr-fernsehen/Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MjIwOTEtNDAyNTM0',
244 'md5': 'b6e8ab03f2bcc6e1f9e6cef25fcc03c4',
246 'display_id': 'Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MjIwOTEtNDAyNTM0',
248 'title': 'Liebe auf vier Pfoten',
249 'description': r
're:^Claudia Schmitt, Anwältin in Salzburg',
251 'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:aee7cbf8f06de976?w=960&ch=ae4d0f2ee47d8b9b',
252 'timestamp': 1701343800,
253 'upload_date': '20231130',
255 'episode': 'Liebe auf vier Pfoten',
256 'series': 'Filme im MDR',
259 '_old_archive_ids': ['ardbetamediathek Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MjIwOTEtNDAyNTM0'],
262 'url': 'https://www.ardmediathek.de/mdr/video/die-robuste-roswita/Y3JpZDovL21kci5kZS9iZWl0cmFnL2Ntcy84MWMxN2MzZC0wMjkxLTRmMzUtODk4ZS0wYzhlOWQxODE2NGI/',
263 'md5': 'a1dc75a39c61601b980648f7c9f9f71d',
265 'display_id': 'die-robuste-roswita',
267 'title': 'Die robuste Roswita',
268 'description': r
're:^Der Mord.*totgeglaubte Ehefrau Roswita',
270 'thumbnail': 'https://img.ardmediathek.de/standard/00/78/56/67/84/575672121/16x9/960?mandant=ard',
271 'timestamp': 1596658200,
272 'upload_date': '20200805',
277 'url': 'https://www.ardmediathek.de/video/tagesschau-oder-tagesschau-20-00-uhr/das-erste/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhZ2Vzc2NoYXUvZmM4ZDUxMjgtOTE0ZC00Y2MzLTgzNzAtNDZkNGNiZWJkOTll',
278 'md5': '1e73ded21cb79bac065117e80c81dc88',
282 'title': 'tagesschau, 20:00 Uhr',
283 'timestamp': 1636398000,
284 'description': 'md5:39578c7b96c9fe50afdf5674ad985e6b',
285 'upload_date': '20211108',
286 'display_id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhZ2Vzc2NoYXUvZmM4ZDUxMjgtOTE0ZC00Y2MzLTgzNzAtNDZkNGNiZWJkOTll',
288 'episode': 'tagesschau, 20:00 Uhr',
289 'series': 'tagesschau',
290 'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:fbb21142783b0a49?w=960&ch=ee69108ae344f678',
291 'channel': 'ARD-Aktuell',
292 '_old_archive_ids': ['ardbetamediathek Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhZ2Vzc2NoYXUvZmM4ZDUxMjgtOTE0ZC00Y2MzLTgzNzAtNDZkNGNiZWJkOTll'],
295 'url': 'https://www.ardmediathek.de/video/7-tage/7-tage-unter-harten-jungs/hr-fernsehen/N2I2YmM5MzgtNWFlOS00ZGFlLTg2NzMtYzNjM2JlNjk4MDg3',
296 'md5': 'c428b9effff18ff624d4f903bda26315',
301 'episode': '7 Tage ... unter harten Jungs',
302 'description': 'md5:0f215470dcd2b02f59f4bd10c963f072',
303 'upload_date': '20231005',
304 'timestamp': 1696491171,
305 'display_id': 'N2I2YmM5MzgtNWFlOS00ZGFlLTg2NzMtYzNjM2JlNjk4MDg3',
306 'series': '7 Tage ...',
308 'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:f6e6d5ffac41925c?w=960&ch=fa32ba69bc87989a',
309 'title': '7 Tage ... unter harten Jungs',
310 '_old_archive_ids': ['ardbetamediathek N2I2YmM5MzgtNWFlOS00ZGFlLTg2NzMtYzNjM2JlNjk4MDg3'],
313 'url': 'https://beta.ardmediathek.de/ard/video/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
314 'only_matching': True,
316 'url': 'https://ardmediathek.de/ard/video/saartalk/saartalk-gesellschaftsgift-haltung-gegen-hass/sr-fernsehen/Y3JpZDovL3NyLW9ubGluZS5kZS9TVF84MTY4MA/',
317 'only_matching': True,
319 'url': 'https://www.ardmediathek.de/ard/video/trailer/private-eyes-s01-e01/one/Y3JpZDovL3dkci5kZS9CZWl0cmFnLTE1MTgwYzczLWNiMTEtNGNkMS1iMjUyLTg5MGYzOWQxZmQ1YQ/',
320 'only_matching': True,
322 'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3N3ci5kZS9hZXgvbzEwNzE5MTU/',
323 'only_matching': True,
325 'url': 'https://www.ardmediathek.de/swr/live/Y3JpZDovL3N3ci5kZS8xMzQ4MTA0Mg',
326 'only_matching': True,
328 'url': 'https://www.ardmediathek.de/video/coronavirus-update-ndr-info/astrazeneca-kurz-lockdown-und-pims-syndrom-81/ndr/Y3JpZDovL25kci5kZS84NzE0M2FjNi0wMWEwLTQ5ODEtOTE5NS1mOGZhNzdhOTFmOTI/',
329 'only_matching': True,
332 def _extract_episode_info(self
, title
):
334 # Pattern for title like "Homo sapiens (S06/E07) - Originalversion"
335 # from: https://www.ardmediathek.de/one/sendung/doctor-who/Y3JpZDovL3dkci5kZS9vbmUvZG9jdG9yIHdobw
336 r
'.*(?P<ep_info> \(S(?P<season_number>\d+)/E(?P<episode_number>\d+)\)).*',
337 # E.g.: title="Fritjof aus Norwegen (2) (AD)"
338 # from: https://www.ardmediathek.de/ard/sammlung/der-krieg-und-ich/68cMkqJdllm639Skj4c7sS/
339 r
'.*(?P<ep_info> \((?:Folge |Teil )?(?P<episode_number>\d+)(?:/\d+)?\)).*',
340 r
'.*(?P<ep_info>Folge (?P<episode_number>\d+)(?:\:| -|) )\"(?P<episode>.+)\".*',
341 # E.g.: title="Folge 25/42: Symmetrie"
342 # from: https://www.ardmediathek.de/ard/video/grips-mathe/folge-25-42-symmetrie/ard-alpha/Y3JpZDovL2JyLmRlL3ZpZGVvLzMyYzI0ZjczLWQ1N2MtNDAxNC05ZmZhLTFjYzRkZDA5NDU5OQ/
343 # E.g.: title="Folge 1063 - Vertrauen"
344 # from: https://www.ardmediathek.de/ard/sendung/die-fallers/Y3JpZDovL3N3ci5kZS8yMzAyMDQ4/
345 r
'.*(?P<ep_info>Folge (?P<episode_number>\d+)(?:/\d+)?(?:\:| -|) ).*',
346 # As a fallback use the full title
350 return traverse_obj(patterns
, (..., {partial(re.match, string=title)}
, {
351 'season_number': ('season_number', {int_or_none}
),
352 'episode_number': ('episode_number', {int_or_none}
),
354 ('episode', {str_or_none}
),
355 ('ep_info', {lambda x: title.replace(x, '')}
),
360 def _real_extract(self
, url
):
361 display_id
= self
._match
_id
(url
)
363 page_data
= self
._download
_json
(
364 f
'https://api.ardmediathek.de/page-gateway/pages/ard/item/{display_id}', display_id
, query
={
369 # For user convenience we use the old contentId instead of the longer crid
370 # Ref: https://github.com/yt-dlp/yt-dlp/issues/8731#issuecomment-1874398283
371 old_id
= traverse_obj(page_data
, ('tracking', 'atiCustomVars', 'contentId', {int}
))
372 if old_id
is not None:
373 video_id
= str(old_id
)
374 archive_ids
= [make_archive_id(ARDBetaMediathekIE
, display_id
)]
376 self
.report_warning(f
'Could not extract contentId{bug_reports_message()}')
377 video_id
= display_id
380 player_data
= traverse_obj(
381 page_data
, ('widgets', lambda _
, v
: v
['type'] in ('player_ondemand', 'player_live'), {dict}
), get_all
=False)
382 is_live
= player_data
.get('type') == 'player_live'
383 media_data
= traverse_obj(player_data
, ('mediaCollection', 'embedded', {dict}
))
385 if player_data
.get('blockedByFsk'):
386 self
.raise_no_formats('This video is only available after 22:00', expected
=True)
390 for stream
in traverse_obj(media_data
, ('streams', ..., {dict}
)):
391 kind
= stream
.get('kind')
392 # Prioritize main stream over sign language and others
393 preference
= 1 if kind
== 'main' else None
394 for media
in traverse_obj(stream
, ('media', lambda _
, v
: url_or_none(v
['url']))):
395 media_url
= media
['url']
397 audio_kind
= traverse_obj(media
, (
398 'audios', 0, 'kind', {str}
), default
='').replace('standard', '')
399 lang_code
= traverse_obj(media
, ('audios', 0, 'languageCode', {str}
)) or 'deu'
400 lang
= join_nonempty(lang_code
, audio_kind
)
401 language_preference
= 10 if lang
== 'deu' else -10
403 if determine_ext(media_url
) == 'm3u8':
404 fmts
, subs
= self
._extract
_m
3u8_formats
_and
_subtitles
(
405 media_url
, video_id
, m3u8_id
=f
'hls-{kind}', preference
=preference
, fatal
=False, live
=is_live
)
408 f
['language_preference'] = language_preference
410 self
._merge
_subtitles
(subs
, target
=subtitles
)
414 'format_id': f
'http-{kind}',
415 'preference': preference
,
417 'language_preference': language_preference
,
418 **traverse_obj(media
, {
419 'format_note': ('forcedLabel', {str}
),
420 'width': ('maxHResolutionPx', {int_or_none}
),
421 'height': ('maxVResolutionPx', {int_or_none}
),
422 'vcodec': ('videoCodec', {str}
),
426 for sub
in traverse_obj(media_data
, ('subtitles', ..., {dict}
)):
427 for sources
in traverse_obj(sub
, ('sources', lambda _
, v
: url_or_none(v
['url']))):
428 subtitles
.setdefault(sub
.get('languageCode') or 'deu', []).append({
429 'url': sources
['url'],
430 'ext': {'webvtt': 'vtt', 'ebutt': 'ttml'}
.get(sources
.get('kind')),
433 age_limit
= traverse_obj(page_data
, ('fskRating', {lambda x: remove_start(x, 'FSK')}
, {int_or_none}
))
436 'display_id': display_id
,
438 'subtitles': subtitles
,
440 'age_limit': age_limit
,
441 **traverse_obj(media_data
, ('meta', {
443 'description': 'synopsis',
444 'timestamp': ('broadcastedOnDateTime', {parse_iso8601}
),
445 'series': 'seriesTitle',
446 'thumbnail': ('images', 0, 'url', {url_or_none}
),
447 'duration': ('durationSeconds', {int_or_none}
),
448 'channel': 'clipSourceName',
450 **self
._extract
_episode
_info
(page_data
.get('title')),
451 '_old_archive_ids': archive_ids
,
455 class ARDMediathekCollectionIE(InfoExtractor
):
456 _VALID_URL
= r
'''(?x)https://
457 (?:(?:beta|www)\.)?ardmediathek\.de/
459 (?P<playlist>sendung|serie|sammlung)/
460 (?:(?P<display_id>[^?#]+?)/)?
462 (?:/(?P<season>\d+)(?:/(?P<version>OV|AD))?)?/?(?:[?#]|$)'''
463 _GEO_COUNTRIES
= ['DE']
466 'url': 'https://www.ardmediathek.de/serie/quiz/staffel-1-originalversion/Y3JpZDovL3dkci5kZS9vbmUvcXVpeg/1/OV',
468 'id': 'Y3JpZDovL3dkci5kZS9vbmUvcXVpeg_1_OV',
469 'display_id': 'quiz/staffel-1-originalversion',
470 'title': 'Staffel 1 Originalversion',
474 'url': 'https://www.ardmediathek.de/serie/babylon-berlin/staffel-4-mit-audiodeskription/Y3JpZDovL2Rhc2Vyc3RlLmRlL2JhYnlsb24tYmVybGlu/4/AD',
476 'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL2JhYnlsb24tYmVybGlu_4_AD',
477 'display_id': 'babylon-berlin/staffel-4-mit-audiodeskription',
478 'title': 'Staffel 4 mit Audiodeskription',
480 'playlist_count': 12,
482 'url': 'https://www.ardmediathek.de/serie/babylon-berlin/staffel-1/Y3JpZDovL2Rhc2Vyc3RlLmRlL2JhYnlsb24tYmVybGlu/1/',
484 'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL2JhYnlsb24tYmVybGlu_1',
485 'display_id': 'babylon-berlin/staffel-1',
486 'title': 'Staffel 1',
490 'url': 'https://www.ardmediathek.de/sendung/tatort/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydA',
492 'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydA',
493 'display_id': 'tatort',
496 'playlist_mincount': 500,
498 'url': 'https://www.ardmediathek.de/sammlung/die-kirche-bleibt-im-dorf/5eOHzt8XB2sqeFXbIoJlg2',
500 'id': '5eOHzt8XB2sqeFXbIoJlg2',
501 'display_id': 'die-kirche-bleibt-im-dorf',
502 'title': 'Die Kirche bleibt im Dorf',
503 'description': 'Die Kirche bleibt im Dorf',
507 # playlist of type 'sendung'
508 'url': 'https://www.ardmediathek.de/ard/sendung/doctor-who/Y3JpZDovL3dkci5kZS9vbmUvZG9jdG9yIHdobw/',
509 'only_matching': True,
511 # playlist of type 'serie'
512 'url': 'https://www.ardmediathek.de/serie/nachtstreife/staffel-1/Y3JpZDovL3N3ci5kZS9zZGIvc3RJZC8xMjQy/1',
513 'only_matching': True,
515 # playlist of type 'sammlung'
516 'url': 'https://www.ardmediathek.de/ard/sammlung/team-muenster/5JpTzLSbWUAK8184IOvEir/',
517 'only_matching': True,
522 def _real_extract(self
, url
):
523 playlist_id
, display_id
, playlist_type
, season_number
, version
= self
._match
_valid
_url
(url
).group(
524 'id', 'display_id', 'playlist', 'season', 'version')
526 def call_api(page_num
):
527 api_path
= 'compilations/ard' if playlist_type
== 'sammlung' else 'widgets/ard/asset'
528 return self
._download
_json
(
529 f
'https://api.ardmediathek.de/page-gateway/{api_path}/{playlist_id}', playlist_id
,
530 f
'Downloading playlist page {page_num}', query
={
531 'pageNumber': page_num
,
532 'pageSize': self
._PAGE
_SIZE
,
535 'seasonNumber': season_number
,
536 'withOriginalversion': 'true' if version
== 'OV' else 'false',
537 'withAudiodescription': 'true' if version
== 'AD' else 'false',
538 } if season_number
else {}),
541 def fetch_page(page_num
):
542 for item
in traverse_obj(call_api(page_num
), ('teasers', ..., {dict}
)):
543 item_id
= traverse_obj(item
, ('links', 'target', ('urlId', 'id')), 'id', get_all
=False)
544 if not item_id
or item_id
== playlist_id
:
546 item_mode
= 'sammlung' if item
.get('type') == 'compilation' else 'video'
547 yield self
.url_result(
548 f
'https://www.ardmediathek.de/{item_mode}/{item_id}',
549 ie
=(ARDMediathekCollectionIE
if item_mode
== 'sammlung' else ARDBetaMediathekIE
),
550 **traverse_obj(item
, {
552 'title': ('longTitle', {str}
),
553 'duration': ('duration', {int_or_none}
),
554 'timestamp': ('broadcastedOn', {parse_iso8601}
),
557 page_data
= call_api(0)
558 full_id
= join_nonempty(playlist_id
, season_number
, version
, delim
='_')
560 return self
.playlist_result(
561 OnDemandPagedList(fetch_page
, self
._PAGE
_SIZE
), full_id
, display_id
=display_id
,
562 title
=page_data
.get('title'), description
=page_data
.get('synopsis'))