music/clips[/#]|
radio/player/
)
- (?P<id>%s)
+ (?P<id>%s)(?!/(?:episodes|broadcasts|clips))
''' % _ID_REGEX
_MEDIASELECTOR_URLS = [
_MEDIASELECTION_NS = 'http://bbc.co.uk/2008/mp/mediaselection'
_EMP_PLAYLIST_NS = 'http://bbc.co.uk/2008/emp/playlist'
+ # Unified Streaming Platform
+ _USP_RE = r'/([^/]+)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'
_NAMESPACES = (
_MEDIASELECTION_NS,
'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
'info_dict': {
'id': 'b039d07m',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4',
'description': 'The Canadian poet and songwriter reflects on his musical career.',
},
'params': {
- # rtmp download
'skip_download': True,
}
},
# rtmp download
'skip_download': True,
},
- 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
+ 'skip': 'this episode is not currently available',
},
{
'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
# rtmp download
'skip_download': True,
},
- 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
+ 'skip': 'this episode is not currently available',
}, {
'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
'info_dict': {
'note': 'Audio',
'info_dict': {
'id': 'p022h44j',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'BBC Proms Music Guides, Rachmaninov: Symphonic Dances',
'description': "In this Proms Music Guide, Andrew McGregor looks at Rachmaninov's Symphonic Dances.",
'duration': 227,
},
'params': {
- # rtmp download
'skip_download': True,
}
}, {
'note': 'Video',
'info_dict': {
'id': 'p025c103',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
'duration': 226,
},
'params': {
- # rtmp download
'skip_download': True,
}
}, {
# rtmp download
'skip_download': True,
},
- 'skip': 'geolocation',
+ 'skip': 'this episode is not currently available',
}, {
'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition',
'info_dict': {
# rtmp download
'skip_download': True,
},
- 'skip': 'geolocation',
+ 'skip': 'this episode is not currently available',
}, {
# iptv-all mediaset fails with geolocation however there is no geo restriction
# for this programme at all
# rtmp download
'skip_download': True,
},
+ 'skip': 'this episode is not currently available on BBC iPlayer Radio',
}, {
# compact player (https://github.com/rg3/youtube-dl/issues/8147)
'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',
'info_dict': {
'id': 'p028bfkj',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
'description': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
},
'params': {
- # rtmp download
'skip_download': True,
},
}, {
elif transfer_format == 'dash':
pass
elif transfer_format == 'hls':
- formats.extend(self._extract_m3u8_formats(
+ is_unified_streaming = re.search(self._USP_RE, href)
+ if is_unified_streaming:
+ href = re.sub(self._USP_RE, r'/\1.ism/\1.m3u8', href)
+ m3u8_formats = self._extract_m3u8_formats(
href, programme_id, ext='mp4', entry_protocol='m3u8_native',
- m3u8_id=supplier, fatal=False))
+ m3u8_id=supplier, fatal=False)
+ if is_unified_streaming:
+ self._check_formats(m3u8_formats, programme_id)
+ formats.extend(m3u8_formats)
# Direct link
else:
formats.append({
for connection in self._extract_connections(media):
conn_formats = self._extract_connection(connection, programme_id)
for format in conn_formats:
- format.update({
- 'width': width,
- 'height': height,
- 'vbr': vbr,
- 'vcodec': vcodec,
- 'filesize': file_size,
- })
+ if format.get('protocol') != 'm3u8_native':
+ format.update({
+ 'width': width,
+ 'height': height,
+ 'vbr': vbr,
+ 'vcodec': vcodec,
+ 'filesize': file_size,
+ })
if service:
format['format_id'] = '%s_%s' % (service, format['format_id'])
formats.extend(conn_formats)
'format_id': '%s_%s' % (service, format['format_id']),
'abr': abr,
'acodec': acodec,
+ 'vcodec': 'none',
})
formats.extend(conn_formats)
return formats
'info_dict': {
'id': '34475836',
'title': 'Jurgen Klopp: Furious football from a witty and winning coach',
+ 'description': 'Fast-paced football, wit, wisdom and a ready smile - why Liverpool fans should come to love new boss Jurgen Klopp.',
},
'playlist_count': 3,
}, {
# custom redirection to www.bbc.com
'url': 'http://www.bbc.co.uk/news/science-environment-33661876',
'only_matching': True,
+ }, {
+ # single video article embedded with data-media-vpid
+ 'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
+ 'only_matching': True,
}]
@classmethod
def suitable(cls, url):
- return False if BBCCoUkIE.suitable(url) or BBCCoUkArticleIE.suitable(url) else super(BBCIE, cls).suitable(url)
+ EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerPlaylistIE, BBCCoUkPlaylistIE)
+ return (False if any(ie.suitable(url) for ie in EXCLUDE_IE)
+ else super(BBCIE, cls).suitable(url))
def _extract_from_media_meta(self, media_meta, video_id):
# Direct links to media in media metadata (e.g.
# single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
programme_id = self._search_regex(
- [r'data-video-player-vpid="(%s)"' % self._ID_REGEX,
+ [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX,
r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
webpage, 'vpid', default=None)
class BBCCoUkArticleIE(InfoExtractor):
- _VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
+ _VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
IE_NAME = 'bbc.co.uk:article'
IE_DESC = 'BBC articles'
r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)]
return self.playlist_result(entries, playlist_id, title, description)
+
+
+class BBCCoUkPlaylistBaseIE(InfoExtractor):
+ def _real_extract(self, url):
+ playlist_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, playlist_id)
+
+ entries = [
+ self.url_result(self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
+ for video_id in re.findall(
+ self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage)]
+
+ title, description = self._extract_title_and_description(webpage)
+
+ return self.playlist_result(entries, playlist_id, title, description)
+
+
+class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
+ IE_NAME = 'bbc.co.uk:iplayer:playlist'
+ _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/episodes/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
+ _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s'
+ _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)'
+ _TEST = {
+ 'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v',
+ 'info_dict': {
+ 'id': 'b05rcz9v',
+ 'title': 'The Disappearance',
+ 'description': 'French thriller serial about a missing teenager.',
+ },
+ 'playlist_mincount': 6,
+ }
+
+ def _extract_title_and_description(self, webpage):
+ title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
+ description = self._search_regex(
+ r'<p[^>]+class=(["\'])subtitle\1[^>]*>(?P<value>[^<]+)</p>',
+ webpage, 'description', fatal=False, group='value')
+ return title, description
+
+
+class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):
+ IE_NAME = 'bbc.co.uk:playlist'
+ _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/(?P<id>%s)/(?:episodes|broadcasts|clips)' % BBCCoUkIE._ID_REGEX
+ _URL_TEMPLATE = 'http://www.bbc.co.uk/programmes/%s'
+ _VIDEO_ID_TEMPLATE = r'data-pid=["\'](%s)'
+ _TESTS = [{
+ 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
+ 'info_dict': {
+ 'id': 'b05rcz9v',
+ 'title': 'The Disappearance - Clips - BBC Four',
+ 'description': 'French thriller serial about a missing teenager.',
+ },
+ 'playlist_mincount': 7,
+ }, {
+ 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.bbc.co.uk/programmes/b055jkys/episodes/player',
+ 'only_matching': True,
+ }]
+
+ def _extract_title_and_description(self, webpage):
+ title = self._og_search_title(webpage, fatal=False)
+ description = self._og_search_description(webpage)
+ return title, description
projects / youtube-dl / blobdiff