from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
+ clean_html,
determine_ext,
float_or_none,
HEADRequest,
int_or_none,
orderedSet,
remove_end,
+ str_or_none,
strip_jsonp,
unescapeHTML,
unified_strdate,
+ url_or_none,
)
webpage, 'playlist', group='json'),
playlist_id, transform_source=unescapeHTML)['playlist']['videos']
- def quality_to_int(s):
- m = re.search('([0-9]+)', s)
- if m is None:
- return -1
- return int(m.group(1))
-
entries = []
for sd in data_jsb:
video_id, title = sd.get('id'), sd.get('title')
video_id = compat_str(video_id)
formats = []
for fd in sd['sources']:
- format_id = '%s-%s-%s' % (
- fd['delivery'], fd['quality'], fd['quality_string'])
- if determine_ext(fd['src']) == 'm3u8':
- formats.extend(self._extract_m3u8_formats(
- fd['src'], video_id, 'mp4', m3u8_id=format_id))
- elif determine_ext(fd['src']) == 'f4m':
+ 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(
- fd['src'], video_id, f4m_id=format_id))
+ src, video_id, f4m_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
class ORFRadioIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- station = mobj.group('station')
show_date = mobj.group('date')
show_id = mobj.group('show')
- if station == 'fm4':
- show_id = '4%s' % show_id
-
data = self._download_json(
- 'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s' % (station, show_id, show_date),
- show_id
- )
-
- def extract_entry_dict(info, title, subtitle):
- return {
- 'id': info['loopStreamId'].replace('.mp3', ''),
- 'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, info['loopStreamId']),
- 'title': title,
- 'description': subtitle,
- 'duration': (info['end'] - info['start']) / 1000,
- 'timestamp': info['start'] / 1000,
- 'ext': 'mp3'
- }
+ 'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s'
+ % (self._API_STATION, show_id, show_date), show_id)
- entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']]
+ 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': 'http://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['title'],
- 'description': data['subtitle'],
- 'entries': entries
+ '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>\w+)'
+ _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/CC',
+ 'url': 'http://fm4.orf.at/player/20170107/4CC',
'md5': '2b0be47375432a7ef104453432a19212',
'info_dict': {
'id': '2017-01-07_2100_tl_54_7DaysSat18_31295',
'timestamp': 1483819257,
'upload_date': '20170107',
},
- 'skip': 'Shows from ORF radios are only available for 7 days.'
+ '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,
}
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',
projects / youtube-dl / blobdiff