-# coding: utf-8
-from __future__ import unicode_literals
-
+import functools
import re
from .common import InfoExtractor
-from ..compat import compat_str
from ..utils import (
clean_html,
determine_ext,
float_or_none,
HEADRequest,
+ InAdvancePagedList,
int_or_none,
+ join_nonempty,
orderedSet,
remove_end,
- str_or_none,
+ make_archive_id,
+ smuggle_url,
strip_jsonp,
+ try_call,
unescapeHTML,
unified_strdate,
+ unsmuggle_url,
url_or_none,
)
class ORFTVthekIE(InfoExtractor):
IE_NAME = 'orf:tvthek'
IE_DESC = 'ORF TVthek'
- _VALID_URL = r'https?://tvthek\.orf\.at/(?:[^/]+/)+(?P<id>\d+)'
+ _VALID_URL = r'(?P<url>https?://tvthek\.orf\.at/(?:(?:[^/]+/){2}){1,2}(?P<id>\d+))(/[^/]+/(?P<vid>\d+))?(?:$|[?#])'
_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',
+ '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
+ },
+ 'playlist': [{
+ '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?',
+ }
+ }],
+ 'playlist_count': 1,
+ 'params': {'noplaylist': True, 'skip_download': 'm3u8'}
+ }, {
'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
'playlist': [{
'md5': '2942210346ed779588f428a92db88712',
'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):
- playlist_id = self._match_id(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(
webpage, 'playlist', group='json'),
playlist_id, transform_source=unescapeHTML)['playlist']['videos']
- entries = []
- for sd in data_jsb:
- video_id, title = sd.get('id'), sd.get('title')
- if not video_id or not title:
- continue
- video_id = compat_str(video_id)
- formats = []
- for fd in sd['sources']:
- src = url_or_none(fd.get('src'))
- if not src:
- continue
- format_id_list = []
- for key in ('delivery', 'quality', 'quality_string'):
- value = fd.get(key)
- if value:
- format_id_list.append(value)
- format_id = '-'.join(format_id_list)
- ext = determine_ext(src)
- if ext == 'm3u8':
- m3u8_formats = self._extract_m3u8_formats(
- src, video_id, 'mp4', m3u8_id=format_id, fatal=False)
- 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))
- 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')
- if geo_str:
- try:
- http_url = next(
- f['url']
- for f in formats
- if re.match(r'^https?://.*\.mp4$', f['url']))
- except StopIteration:
- pass
- else:
- req = HEADRequest(http_url)
- self._request_webpage(
- req, video_id,
- note='Testing for geoblocking',
- errnote=((
- 'This video seems to be blocked outside of %s. '
- 'You may want to try the streaming-* formats.')
- % geo_str),
- fatal=False)
-
- self._check_formats(formats, video_id)
- 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')
- if not image and len(data_jsb) == 1:
- image = self._og_search_thumbnail(webpage)
- if image:
- thumbnails.append({
- 'id': 'full',
- 'url': image,
- 'preference': 1,
- })
+ 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]
- entries.append({
- '_type': 'video',
- 'id': video_id,
- 'title': title,
- 'formats': formats,
- 'subtitles': subtitles,
- 'description': sd.get('description'),
- 'duration': int_or_none(sd.get('duration_in_seconds')),
- 'upload_date': upload_date,
- 'thumbnails': thumbnails,
- })
+ 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': entries,
+ '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')
+ 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()))
- data = self._download_json(
- 'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s'
- % (self._API_STATION, show_id, show_date), show_id)
+ _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+)'''
- 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,
+ _TESTS = [{
+ 'url': 'https://radiothek.orf.at/ooe/20220801/OGMO',
+ 'info_dict': {
+ 'id': 'OGMO',
+ 'title': 'Guten Morgen OÖ',
+ 'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
+ },
+ 'playlist': [{
+ 'md5': 'f33147d954a326e338ea52572c2810e8',
+ 'info_dict': {
+ 'id': '2022-08-01_0459_tl_66_7DaysMon1_319062',
'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',
+ 'title': 'Guten Morgen OÖ',
+ 'upload_date': '20220801',
+ 'duration': 18000,
+ 'timestamp': 1659322789,
+ 'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
+ }
+ }]
+ }, {
+ 'url': 'https://ooe.orf.at/player/20220801/OGMO',
'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',
+ 'id': 'OGMO',
+ 'title': 'Guten Morgen OÖ',
+ 'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
},
- 'skip': 'Shows from ORF radios are only available for 7 days.',
+ 'playlist': [{
+ 'md5': 'f33147d954a326e338ea52572c2810e8',
+ 'info_dict': {
+ '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',
+ }
+ }]
+ }, {
+ 'url': 'http://fm4.orf.at/player/20170107/4CC',
'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': {
'upload_date': '20170108',
},
'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 ORFIPTVIE(InfoExtractor):