-# coding: utf-8
-from __future__ import unicode_literals
-
+import base64
import functools
import re
clean_html,
determine_ext,
float_or_none,
- HEADRequest,
- InAdvancePagedList,
int_or_none,
- join_nonempty,
+ make_archive_id,
+ mimetype2ext,
orderedSet,
+ parse_age_limit,
+ parse_iso8601,
remove_end,
- smuggle_url,
str_or_none,
strip_jsonp,
- unescapeHTML,
+ try_call,
unified_strdate,
- unsmuggle_url,
url_or_none,
)
+from ..utils.traversal import traverse_obj
+
+class ORFRadioIE(InfoExtractor):
+ IE_NAME = 'orf:radio'
+
+ STATION_INFO = {
+ 'fm4': ('fm4', 'fm4', 'orffm4'),
+ 'noe': ('noe', 'oe2n', 'orfnoe'),
+ 'wien': ('wie', 'oe2w', 'orfwie'),
+ 'burgenland': ('bgl', 'oe2b', 'orfbgl'),
+ 'ooe': ('ooe', 'oe2o', 'orfooe'),
+ 'steiermark': ('stm', 'oe2st', 'orfstm'),
+ 'kaernten': ('ktn', 'oe2k', 'orfktn'),
+ 'salzburg': ('sbg', 'oe2s', 'orfsbg'),
+ 'tirol': ('tir', 'oe2t', 'orftir'),
+ 'vorarlberg': ('vbg', 'oe2v', 'orfvbg'),
+ 'oe3': ('oe3', 'oe3', 'orfoe3'),
+ 'oe1': ('oe1', 'oe1', 'orfoe1'),
+ }
+ _STATION_RE = '|'.join(map(re.escape, STATION_INFO.keys()))
-class ORFTVthekIE(InfoExtractor):
- IE_NAME = 'orf:tvthek'
- IE_DESC = 'ORF TVthek'
- _VALID_URL = r'(?P<url>https?://tvthek\.orf\.at/(?:(?:[^/]+/){2}){1,2}(?P<id>\d+))(/[^/]+/(?P<vid>\d+))?(?:$|[?#])'
+ _VALID_URL = rf'''(?x)
+ https?://(?:
+ (?P<station>{_STATION_RE})\.orf\.at/player|
+ radiothek\.orf\.at/(?P<station2>{_STATION_RE})
+ )/(?P<date>[0-9]+)/(?P<show>\w+)'''
_TESTS = [{
- 'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079',
- 'info_dict': {
- 'id': '14121079',
- },
- 'playlist_count': 11,
- 'params': {'noplaylist': True}
- }, {
- 'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079/Umfrage-Welches-Tier-ist-Sebastian-Kurz/15083150',
+ 'url': 'https://radiothek.orf.at/ooe/20220801/OGMO',
'info_dict': {
- 'id': '14121079',
- },
- 'playlist_count': 1,
- 'params': {'playlist_items': '5'}
- }, {
- 'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079/Umfrage-Welches-Tier-ist-Sebastian-Kurz/15083150',
- 'info_dict': {
- 'id': '14121079',
- 'playlist_count': 1
+ 'id': 'OGMO',
+ 'title': 'Guten Morgen OÖ',
+ 'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
},
'playlist': [{
+ 'md5': 'f33147d954a326e338ea52572c2810e8',
'info_dict': {
- 'id': '15083150',
- 'ext': 'mp4',
- 'description': 'md5:7be1c485425f5f255a5e4e4815e77d04',
- 'thumbnail': 'https://api-tvthek.orf.at/uploads/media/segments/0130/59/824271ea35cd8931a0fb08ab316a5b0a1562342c.jpeg',
- 'title': 'Umfrage: Welches Tier ist Sebastian Kurz?',
- }
+ 'id': '2022-08-01_0459_tl_66_7DaysMon1_319062',
+ 'ext': 'mp3',
+ 'title': 'Guten Morgen OÖ',
+ 'upload_date': '20220801',
+ 'duration': 18000,
+ 'timestamp': 1659322789,
+ 'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
+ },
}],
- 'playlist_count': 1,
- 'params': {'noplaylist': True, 'skip_download': 'm3u8'}
}, {
- 'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
+ 'url': 'https://ooe.orf.at/player/20220801/OGMO',
+ 'info_dict': {
+ 'id': 'OGMO',
+ 'title': 'Guten Morgen OÖ',
+ 'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
+ },
'playlist': [{
- 'md5': '2942210346ed779588f428a92db88712',
+ 'md5': 'f33147d954a326e338ea52572c2810e8',
'info_dict': {
- 'id': '8896777',
- 'ext': 'mp4',
- 'title': 'Aufgetischt: Mit der Steirischen Tafelrunde',
- 'description': 'md5:c1272f0245537812d4e36419c207b67d',
- 'duration': 2668,
- 'upload_date': '20141208',
+ 'id': '2022-08-01_0459_tl_66_7DaysMon1_319062',
+ 'ext': 'mp3',
+ 'title': 'Guten Morgen OÖ',
+ 'upload_date': '20220801',
+ 'duration': 18000,
+ 'timestamp': 1659322789,
+ 'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
},
}],
- 'skip': 'Blocked outside of Austria / Germany',
- }, {
- 'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256',
- 'info_dict': {
- 'id': '7982259',
- 'ext': 'mp4',
- 'title': 'Best of Ingrid Thurnher',
- 'upload_date': '20140527',
- 'description': 'Viele Jahre war Ingrid Thurnher das "Gesicht" der ZIB 2. Vor ihrem Wechsel zur ZIB 2 im Jahr 1995 moderierte sie unter anderem "Land und Leute", "Österreich-Bild" und "Niederösterreich heute".',
- },
- 'params': {
- 'skip_download': True, # rtsp downloads
- },
- 'skip': 'Blocked outside of Austria / Germany',
}, {
- 'url': 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141',
- 'only_matching': True,
- }, {
- 'url': 'http://tvthek.orf.at/profile/Universum/35429',
- 'only_matching': True,
- }]
-
- def _pagefunc(self, url, data_jsb, n, *, image=None):
- sd = data_jsb[n]
- video_id, title = str(sd['id']), sd['title']
- formats = []
- for fd in sd['sources']:
- src = url_or_none(fd.get('src'))
- if not src:
- continue
- format_id = join_nonempty('delivery', 'quality', 'quality_string', from_dict=fd)
- ext = determine_ext(src)
- if ext == 'm3u8':
- m3u8_formats = self._extract_m3u8_formats(
- src, video_id, 'mp4', m3u8_id=format_id, fatal=False, note=f'Downloading {format_id} m3u8 manifest')
- if any('/geoprotection' in f['url'] for f in m3u8_formats):
- self.raise_geo_restricted()
- formats.extend(m3u8_formats)
- elif ext == 'f4m':
- formats.extend(self._extract_f4m_formats(
- src, video_id, f4m_id=format_id, fatal=False))
- elif ext == 'mpd':
- formats.extend(self._extract_mpd_formats(
- src, video_id, mpd_id=format_id, fatal=False, note=f'Downloading {format_id} mpd manifest'))
- else:
- formats.append({
- 'format_id': format_id,
- 'url': src,
- 'protocol': fd.get('protocol'),
- })
-
- # Check for geoblocking.
- # There is a property is_geoprotection, but that's always false
- geo_str = sd.get('geoprotection_string')
- http_url = next(
- (f['url'] for f in formats if re.match(r'^https?://.*\.mp4$', f['url'])),
- None) if geo_str else None
- if http_url:
- self._request_webpage(
- HEADRequest(http_url), video_id, fatal=False, note='Testing for geoblocking',
- errnote=f'This video seems to be blocked outside of {geo_str}. You may want to try the streaming-* formats')
-
- self._sort_formats(formats)
-
- subtitles = {}
- for sub in sd.get('subtitles', []):
- sub_src = sub.get('src')
- if not sub_src:
- continue
- subtitles.setdefault(sub.get('lang', 'de-AT'), []).append({
- 'url': sub_src,
- })
-
- upload_date = unified_strdate(sd.get('created_date'))
-
- thumbnails = []
- preview = sd.get('preview_image_url')
- if preview:
- thumbnails.append({
- 'id': 'preview',
- 'url': preview,
- 'preference': 0,
- })
- image = sd.get('image_full_url') or image
- if image:
- thumbnails.append({
- 'id': 'full',
- 'url': image,
- 'preference': 1,
- })
-
- yield {
- 'id': video_id,
- 'title': title,
- 'webpage_url': smuggle_url(f'{url}/part/{video_id}', {'force_noplaylist': True}),
- 'formats': formats,
- 'subtitles': subtitles,
- 'description': sd.get('description'),
- 'duration': int_or_none(sd.get('duration_in_seconds')),
- 'upload_date': upload_date,
- 'thumbnails': thumbnails,
- }
-
- def _real_extract(self, url):
- url, smuggled_data = unsmuggle_url(url)
- playlist_id, video_id, base_url = self._match_valid_url(url).group('id', 'vid', 'url')
- webpage = self._download_webpage(url, playlist_id)
-
- data_jsb = self._parse_json(
- self._search_regex(
- r'<div[^>]+class=(["\']).*?VideoPlaylist.*?\1[^>]+data-jsb=(["\'])(?P<json>.+?)\2',
- webpage, 'playlist', group='json'),
- playlist_id, transform_source=unescapeHTML)['playlist']['videos']
-
- if not self._yes_playlist(playlist_id, video_id, smuggled_data):
- data_jsb = [sd for sd in data_jsb if str(sd.get('id')) == video_id]
-
- playlist_count = len(data_jsb)
- image = self._og_search_thumbnail(webpage) if playlist_count == 1 else None
-
- page_func = functools.partial(self._pagefunc, base_url, data_jsb, image=image)
- return {
- '_type': 'playlist',
- 'entries': InAdvancePagedList(page_func, playlist_count, 1),
- 'id': playlist_id,
- }
-
-
-class ORFRadioIE(InfoExtractor):
- def _real_extract(self, url):
- mobj = self._match_valid_url(url)
- show_date = mobj.group('date')
- show_id = mobj.group('show')
-
- data = self._download_json(
- 'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s'
- % (self._API_STATION, show_id, show_date), show_id)
-
- entries = []
- for info in data['streams']:
- loop_stream_id = str_or_none(info.get('loopStreamId'))
- if not loop_stream_id:
- continue
- title = str_or_none(data.get('title'))
- if not title:
- continue
- start = int_or_none(info.get('start'), scale=1000)
- end = int_or_none(info.get('end'), scale=1000)
- duration = end - start if end and start else None
- entries.append({
- 'id': loop_stream_id.replace('.mp3', ''),
- 'url': 'https://loopstream01.apa.at/?channel=%s&id=%s' % (self._LOOP_STATION, loop_stream_id),
- 'title': title,
- 'description': clean_html(data.get('subtitle')),
- 'duration': duration,
- 'timestamp': start,
- 'ext': 'mp3',
- 'series': data.get('programTitle'),
- })
-
- return {
- '_type': 'playlist',
- 'id': show_id,
- 'title': data.get('title'),
- 'description': clean_html(data.get('subtitle')),
- 'entries': entries,
- }
-
-
-class ORFFM4IE(ORFRadioIE):
- IE_NAME = 'orf:fm4'
- IE_DESC = 'radio FM4'
- _VALID_URL = r'https?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>4\w+)'
- _API_STATION = 'fm4'
- _LOOP_STATION = 'fm4'
-
- _TEST = {
'url': 'http://fm4.orf.at/player/20170107/4CC',
- 'md5': '2b0be47375432a7ef104453432a19212',
- 'info_dict': {
- 'id': '2017-01-07_2100_tl_54_7DaysSat18_31295',
- 'ext': 'mp3',
- 'title': 'Solid Steel Radioshow',
- 'description': 'Die Mixshow von Coldcut und Ninja Tune.',
- 'duration': 3599,
- 'timestamp': 1483819257,
- 'upload_date': '20170107',
- },
- 'skip': 'Shows from ORF radios are only available for 7 days.',
'only_matching': True,
- }
-
-
-class ORFNOEIE(ORFRadioIE):
- IE_NAME = 'orf:noe'
- IE_DESC = 'Radio Niederösterreich'
- _VALID_URL = r'https?://(?P<station>noe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
- _API_STATION = 'noe'
- _LOOP_STATION = 'oe2n'
-
- _TEST = {
+ }, {
'url': 'https://noe.orf.at/player/20200423/NGM',
'only_matching': True,
- }
-
-
-class ORFWIEIE(ORFRadioIE):
- IE_NAME = 'orf:wien'
- IE_DESC = 'Radio Wien'
- _VALID_URL = r'https?://(?P<station>wien)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
- _API_STATION = 'wie'
- _LOOP_STATION = 'oe2w'
-
- _TEST = {
+ }, {
'url': 'https://wien.orf.at/player/20200423/WGUM',
'only_matching': True,
- }
-
-
-class ORFBGLIE(ORFRadioIE):
- IE_NAME = 'orf:burgenland'
- IE_DESC = 'Radio Burgenland'
- _VALID_URL = r'https?://(?P<station>burgenland)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
- _API_STATION = 'bgl'
- _LOOP_STATION = 'oe2b'
-
- _TEST = {
+ }, {
'url': 'https://burgenland.orf.at/player/20200423/BGM',
'only_matching': True,
- }
-
-
-class ORFOOEIE(ORFRadioIE):
- IE_NAME = 'orf:oberoesterreich'
- IE_DESC = 'Radio Oberösterreich'
- _VALID_URL = r'https?://(?P<station>ooe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
- _API_STATION = 'ooe'
- _LOOP_STATION = 'oe2o'
-
- _TEST = {
- 'url': 'https://ooe.orf.at/player/20200423/OGMO',
- 'only_matching': True,
- }
-
-
-class ORFSTMIE(ORFRadioIE):
- IE_NAME = 'orf:steiermark'
- IE_DESC = 'Radio Steiermark'
- _VALID_URL = r'https?://(?P<station>steiermark)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
- _API_STATION = 'stm'
- _LOOP_STATION = 'oe2st'
-
- _TEST = {
+ }, {
'url': 'https://steiermark.orf.at/player/20200423/STGMS',
'only_matching': True,
- }
-
-
-class ORFKTNIE(ORFRadioIE):
- IE_NAME = 'orf:kaernten'
- IE_DESC = 'Radio Kärnten'
- _VALID_URL = r'https?://(?P<station>kaernten)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
- _API_STATION = 'ktn'
- _LOOP_STATION = 'oe2k'
-
- _TEST = {
+ }, {
'url': 'https://kaernten.orf.at/player/20200423/KGUMO',
'only_matching': True,
- }
-
-
-class ORFSBGIE(ORFRadioIE):
- IE_NAME = 'orf:salzburg'
- IE_DESC = 'Radio Salzburg'
- _VALID_URL = r'https?://(?P<station>salzburg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
- _API_STATION = 'sbg'
- _LOOP_STATION = 'oe2s'
-
- _TEST = {
+ }, {
'url': 'https://salzburg.orf.at/player/20200423/SGUM',
'only_matching': True,
- }
-
-
-class ORFTIRIE(ORFRadioIE):
- IE_NAME = 'orf:tirol'
- IE_DESC = 'Radio Tirol'
- _VALID_URL = r'https?://(?P<station>tirol)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
- _API_STATION = 'tir'
- _LOOP_STATION = 'oe2t'
-
- _TEST = {
+ }, {
'url': 'https://tirol.orf.at/player/20200423/TGUMO',
'only_matching': True,
- }
-
-
-class ORFVBGIE(ORFRadioIE):
- IE_NAME = 'orf:vorarlberg'
- IE_DESC = 'Radio Vorarlberg'
- _VALID_URL = r'https?://(?P<station>vorarlberg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
- _API_STATION = 'vbg'
- _LOOP_STATION = 'oe2v'
-
- _TEST = {
+ }, {
'url': 'https://vorarlberg.orf.at/player/20200423/VGUM',
'only_matching': True,
- }
-
-
-class ORFOE3IE(ORFRadioIE):
- IE_NAME = 'orf:oe3'
- IE_DESC = 'Radio Österreich 3'
- _VALID_URL = r'https?://(?P<station>oe3)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
- _API_STATION = 'oe3'
- _LOOP_STATION = 'oe3'
-
- _TEST = {
+ }, {
'url': 'https://oe3.orf.at/player/20200424/3WEK',
'only_matching': True,
- }
-
-
-class ORFOE1IE(ORFRadioIE):
- IE_NAME = 'orf:oe1'
- IE_DESC = 'Radio Österreich 1'
- _VALID_URL = r'https?://(?P<station>oe1)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
- _API_STATION = 'oe1'
- _LOOP_STATION = 'oe1'
-
- _TEST = {
+ }, {
'url': 'http://oe1.orf.at/player/20170108/456544',
'md5': '34d8a6e67ea888293741c86a099b745b',
'info_dict': {
'timestamp': 1483858796,
'upload_date': '20170108',
},
- 'skip': 'Shows from ORF radios are only available for 7 days.'
- }
+ 'skip': 'Shows from ORF radios are only available for 7 days.',
+ }]
+
+ def _entries(self, data, station):
+ _, loop_station, old_ie = self.STATION_INFO[station]
+ for info in data['streams']:
+ item_id = info.get('loopStreamId')
+ if not item_id:
+ continue
+ video_id = item_id.replace('.mp3', '')
+ yield {
+ 'id': video_id,
+ 'ext': 'mp3',
+ 'url': f'https://loopstream01.apa.at/?channel={loop_station}&id={item_id}',
+ '_old_archive_ids': [make_archive_id(old_ie, video_id)],
+ 'title': data.get('title'),
+ 'description': clean_html(data.get('subtitle')),
+ 'duration': try_call(lambda: (info['end'] - info['start']) / 1000),
+ 'timestamp': int_or_none(info.get('start'), scale=1000),
+ 'series': data.get('programTitle'),
+ }
+
+ def _real_extract(self, url):
+ station, station2, show_date, show_id = self._match_valid_url(url).group('station', 'station2', 'date', 'show')
+ api_station, _, _ = self.STATION_INFO[station or station2]
+ data = self._download_json(
+ f'http://audioapi.orf.at/{api_station}/api/json/current/broadcast/{show_id}/{show_date}', show_id)
+
+ return self.playlist_result(
+ self._entries(data, station or station2), show_id, data.get('title'), clean_html(data.get('subtitle')))
+
+
+class ORFPodcastIE(InfoExtractor):
+ IE_NAME = 'orf:podcast'
+ _STATION_RE = '|'.join(map(re.escape, (
+ 'bgl', 'fm4', 'ktn', 'noe', 'oe1', 'oe3',
+ 'ooe', 'sbg', 'stm', 'tir', 'tv', 'vbg', 'wie')))
+ _VALID_URL = rf'https?://sound\.orf\.at/podcast/(?P<station>{_STATION_RE})/(?P<show>[\w-]+)/(?P<id>[\w-]+)'
+ _TESTS = [{
+ 'url': 'https://sound.orf.at/podcast/oe3/fruehstueck-bei-mir/nicolas-stockhammer-15102023',
+ 'md5': '526a5700e03d271a1505386a8721ab9b',
+ 'info_dict': {
+ 'id': 'nicolas-stockhammer-15102023',
+ 'ext': 'mp3',
+ 'title': 'Nicolas Stockhammer (15.10.2023)',
+ 'duration': 3396.0,
+ 'series': 'Frühstück bei mir',
+ },
+ 'skip': 'ORF podcasts are only available for a limited time',
+ }]
+
+ def _real_extract(self, url):
+ station, show, show_id = self._match_valid_url(url).group('station', 'show', 'id')
+ data = self._download_json(
+ f'https://audioapi.orf.at/radiothek/api/2.0/podcast/{station}/{show}/{show_id}', show_id)
+
+ return {
+ 'id': show_id,
+ 'ext': 'mp3',
+ 'vcodec': 'none',
+ **traverse_obj(data, ('payload', {
+ 'url': ('enclosures', 0, 'url'),
+ 'ext': ('enclosures', 0, 'type', {mimetype2ext}),
+ 'title': 'title',
+ 'description': ('description', {clean_html}),
+ 'duration': ('duration', {functools.partial(float_or_none, scale=1000)}),
+ 'series': ('podcast', 'title'),
+ })),
+ }
class ORFIPTVIE(InfoExtractor):
story_id = self._match_id(url)
webpage = self._download_webpage(
- 'http://iptv.orf.at/stories/%s' % story_id, story_id)
+ f'http://iptv.orf.at/stories/{story_id}', story_id)
video_id = self._search_regex(
r'data-video(?:id)?="(\d+)"', webpage, 'video id')
data = self._download_json(
- 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
+ f'http://bits.orf.at/filehandler/static-api/json/current/data.json?file={video_id}',
video_id)[0]
duration = float_or_none(data['duration'], 1000)
format_url, video_id, 'mp4', m3u8_id=format_id))
else:
continue
- self._sort_formats(formats)
title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at')
description = self._og_search_description(webpage)
all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d+)"', webpage))
for idx, video_id in enumerate(all_ids):
data = self._download_json(
- 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
+ f'http://bits.orf.at/filehandler/static-api/json/current/data.json?file={video_id}',
video_id)[0]
duration = float_or_none(data['duration'], 1000)
format_url, video_id, 'mp4', m3u8_id=format_id))
else:
continue
- self._sort_formats(formats)
title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at')
if idx >= 1:
})
return self.playlist_result(entries)
+
+
+class ORFONIE(InfoExtractor):
+ IE_NAME = 'orf:on'
+ _VALID_URL = r'https?://on\.orf\.at/video/(?P<id>\d+)(?:/(?P<segment>\d+))?'
+ _TESTS = [{
+ 'url': 'https://on.orf.at/video/14210000/school-of-champions-48',
+ 'info_dict': {
+ 'id': '14210000',
+ 'ext': 'mp4',
+ 'duration': 2651.08,
+ 'thumbnail': 'https://api-tvthek.orf.at/assets/segments/0167/98/thumb_16697671_segments_highlight_teaser.jpeg',
+ 'title': 'School of Champions (4/8)',
+ 'description': 'md5:d09ad279fc2e8502611e7648484b6afd',
+ 'media_type': 'episode',
+ 'timestamp': 1706558922,
+ 'upload_date': '20240129',
+ 'release_timestamp': 1706472362,
+ 'release_date': '20240128',
+ 'modified_timestamp': 1712756663,
+ 'modified_date': '20240410',
+ '_old_archive_ids': ['orftvthek 14210000'],
+ },
+ }, {
+ 'url': 'https://on.orf.at/video/3220355',
+ 'md5': 'f94d98e667cf9a3851317efb4e136662',
+ 'info_dict': {
+ 'id': '3220355',
+ 'ext': 'mp4',
+ 'duration': 445.04,
+ 'thumbnail': 'https://api-tvthek.orf.at/assets/segments/0002/60/thumb_159573_segments_highlight_teaser.png',
+ 'title': '50 Jahre Burgenland: Der Festumzug',
+ 'description': 'md5:1560bf855119544ee8c4fa5376a2a6b0',
+ 'media_type': 'episode',
+ 'timestamp': 52916400,
+ 'upload_date': '19710905',
+ 'release_timestamp': 52916400,
+ 'release_date': '19710905',
+ 'modified_timestamp': 1498536049,
+ 'modified_date': '20170627',
+ '_old_archive_ids': ['orftvthek 3220355'],
+ },
+ }, {
+ # Video with multiple segments selecting the second segment
+ 'url': 'https://on.orf.at/video/14226549/15639808/jugendbande-einbrueche-aus-langeweile',
+ 'md5': '90f4ebff86b4580837b8a361d0232a9e',
+ 'info_dict': {
+ 'id': '15639808',
+ 'ext': 'mp4',
+ 'duration': 97.707,
+ 'thumbnail': 'https://api-tvthek.orf.at/assets/segments/0175/43/thumb_17442704_segments_highlight_teaser.jpg',
+ 'title': 'Jugendbande: Einbrüche aus Langeweile',
+ 'description': 'md5:193df0bf0d91cf16830c211078097120',
+ 'media_type': 'segment',
+ 'timestamp': 1715792400,
+ 'upload_date': '20240515',
+ 'modified_timestamp': 1715794394,
+ 'modified_date': '20240515',
+ '_old_archive_ids': ['orftvthek 15639808'],
+ },
+ 'params': {'noplaylist': True},
+ }, {
+ # Video with multiple segments and no combined version
+ 'url': 'https://on.orf.at/video/14227864/formel-1-grosser-preis-von-monaco-2024',
+ 'info_dict': {
+ '_type': 'multi_video',
+ 'id': '14227864',
+ 'duration': 18410.52,
+ 'thumbnail': 'https://api-tvthek.orf.at/assets/segments/0176/04/thumb_17503881_segments_highlight_teaser.jpg',
+ 'title': 'Formel 1: Großer Preis von Monaco 2024',
+ 'description': 'md5:aeeb010710ccf70ce28ccb4482243d4f',
+ 'media_type': 'episode',
+ 'timestamp': 1716721200,
+ 'upload_date': '20240526',
+ 'release_timestamp': 1716721802,
+ 'release_date': '20240526',
+ 'modified_timestamp': 1716967501,
+ 'modified_date': '20240529',
+ },
+ 'playlist_count': 42,
+ }, {
+ # Video with multiple segments, but with combined version
+ 'url': 'https://on.orf.at/video/14228172',
+ 'info_dict': {
+ 'id': '14228172',
+ 'ext': 'mp4',
+ 'duration': 3294.878,
+ 'thumbnail': 'https://api-tvthek.orf.at/assets/segments/0176/17/thumb_17516455_segments_highlight_teaser.jpg',
+ 'title': 'Willkommen Österreich mit Stermann & Grissemann',
+ 'description': 'md5:5de034d033a9c27f989343be3bbd4839',
+ 'media_type': 'episode',
+ 'timestamp': 1716926584,
+ 'upload_date': '20240528',
+ 'release_timestamp': 1716919202,
+ 'release_date': '20240528',
+ 'modified_timestamp': 1716968045,
+ 'modified_date': '20240529',
+ '_old_archive_ids': ['orftvthek 14228172'],
+ },
+ }]
+
+ @staticmethod
+ def _parse_metadata(api_json):
+ return traverse_obj(api_json, {
+ 'id': ('id', {int}, {str_or_none}),
+ 'age_limit': ('age_classification', {parse_age_limit}),
+ 'duration': ('exact_duration', {functools.partial(float_or_none, scale=1000)}),
+ 'title': (('title', 'headline'), {str}),
+ 'description': (('description', 'teaser_text'), {str}),
+ 'media_type': ('video_type', {str}),
+ 'thumbnail': ('_embedded', 'image', 'public_urls', 'highlight_teaser', 'url', {url_or_none}),
+ 'timestamp': (('date', 'episode_date'), {parse_iso8601}),
+ 'release_timestamp': ('release_date', {parse_iso8601}),
+ 'modified_timestamp': ('updated_at', {parse_iso8601}),
+ }, get_all=False)
+
+ def _extract_video_info(self, video_id, api_json):
+ formats, subtitles = [], {}
+ for manifest_type in traverse_obj(api_json, ('sources', {dict.keys}, ...)):
+ for manifest_url in traverse_obj(api_json, ('sources', manifest_type, ..., 'src', {url_or_none})):
+ if manifest_type == 'hls':
+ fmts, subs = self._extract_m3u8_formats_and_subtitles(
+ manifest_url, video_id, fatal=False, m3u8_id='hls')
+ elif manifest_type == 'dash':
+ fmts, subs = self._extract_mpd_formats_and_subtitles(
+ manifest_url, video_id, fatal=False, mpd_id='dash')
+ else:
+ continue
+ formats.extend(fmts)
+ self._merge_subtitles(subs, target=subtitles)
+
+ for sub_url in traverse_obj(api_json, (
+ '_embedded', 'subtitle',
+ ('xml_url', 'sami_url', 'stl_url', 'ttml_url', 'srt_url', 'vtt_url'), {url_or_none})):
+ self._merge_subtitles({'de': [{'url': sub_url}]}, target=subtitles)
+
+ return {
+ 'id': video_id,
+ 'formats': formats,
+ 'subtitles': subtitles,
+ '_old_archive_ids': [make_archive_id('ORFTVthek', video_id)],
+ **self._parse_metadata(api_json),
+ }
+
+ def _real_extract(self, url):
+ video_id, segment_id = self._match_valid_url(url).group('id', 'segment')
+
+ encrypted_id = base64.b64encode(f'3dSlfek03nsLKdj4Jsd{video_id}'.encode()).decode()
+ api_json = self._download_json(
+ f'https://api-tvthek.orf.at/api/v4.3/public/episode/encrypted/{encrypted_id}', video_id)
+
+ if traverse_obj(api_json, 'is_drm_protected'):
+ self.report_drm(video_id)
+
+ segments = traverse_obj(api_json, ('_embedded', 'segments', lambda _, v: v['id']))
+ selected_segment = traverse_obj(segments, (lambda _, v: str(v['id']) == segment_id, any))
+
+ # selected_segment will be falsy if input URL did not include a valid segment_id
+ if selected_segment and not self._yes_playlist(video_id, segment_id, playlist_label='episode', video_label='segment'):
+ return self._extract_video_info(segment_id, selected_segment)
+
+ # Even some segmented videos have an unsegmented version available in API response root
+ if not traverse_obj(api_json, ('sources', ..., ..., 'src', {url_or_none})):
+ return self.playlist_result(
+ (self._extract_video_info(str(segment['id']), segment) for segment in segments),
+ video_id, **self._parse_metadata(api_json), multi_video=True)
+
+ return self._extract_video_info(video_id, api_json)
projects / yt-dlp.git / blobdiff