)
from ..compat import compat_HTTPError
+
class BBCCoUkIE(InfoExtractor):
IE_NAME = 'bbc.co.uk'
IE_DESC = 'BBC iPlayer'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
- _MEDIASELECTOR_URL = 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s'
+ _MEDIASELECTOR_URLS = [
+ 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s',
+ ]
_TESTS = [
{
}
]
+ class MediaSelectionError(Exception):
+ def __init__(self, id):
+ self.id = id
+
def _extract_asx_playlist(self, connection, programme_id):
asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
return [ref.get('href') for ref in asx.findall('./Entry/ref')]
def _extract_medias(self, media_selection):
error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error')
if error is not None:
- raise ExtractorError(
- '%s returned error: %s' % (self.IE_NAME, error.get('id')), expected=True)
+ raise BBCCoUkIE.MediaSelectionError(error.get('id'))
return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')
def _extract_connections(self, media):
]
return subtitles
+ def _raise_extractor_error(self, media_selection_error):
+ raise ExtractorError(
+ '%s returned error: %s' % (self.IE_NAME, media_selection_error.id),
+ expected=True)
+
def _download_media_selector(self, programme_id):
- try:
- return self._download_media_selector_url(
- self._MEDIASELECTOR_URL % programme_id, programme_id)
- except ExtractorError as e:
- if hasattr(self, '_MEDIASELECTOR_ALT_URL') and str(e) == 'bbc returned error: notukerror':
- # notukerror on bbc.com/travel using bbc news mediaselector: fallback to /mediaselector/5/
- return self._download_media_selector_url(
- self._MEDIASELECTOR_ALT_URL % programme_id, programme_id)
- else:
- raise
+ last_exception = None
+ for mediaselector_url in self._MEDIASELECTOR_URLS:
+ try:
+ return self._download_media_selector_url(
+ mediaselector_url % programme_id, programme_id)
+ except BBCCoUkIE.MediaSelectionError as e:
+ if e.id == 'notukerror':
+ last_exception = e
+ continue
+ self._raise_extractor_error(e)
+ self._raise_extractor_error(last_exception)
def _download_media_selector_url(self, url, programme_id=None):
try:
IE_DESC = 'BBC'
_VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)'
- # fails with notukerror for some videos ( non news sites such as bbc.com/travel )
- _MEDIASELECTOR_URL = 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s'
- # limited selection of formats but may work where the above does not
- _MEDIASELECTOR_ALT_URL = 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s'
+ _MEDIASELECTOR_URLS = [
+ # Provides more formats, namely direct mp4 links, but fails on some videos with
+ # notukerror for non UK (?) users (e.g.
+ # http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
+ 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s',
+ # Provides fewer formats, but works everywhere for everybody (hopefully)
+ 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s',
+ ]
_TESTS = [{
# article with multiple videos embedded with data-media-meta containing
},
'playlist_count': 9,
'skip': 'Save time',
+ }, {
+ # article with multiple videos embedded with `new SMP()`
+ 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
+ 'info_dict': {
+ 'id': '3662a707-0af9-3149-963f-47bea720b460',
+ 'title': 'BBC Blogs - Adam Curtis - BUGGER',
+ },
+ 'playlist_count': 18,
}, {
# single video embedded with mediaAssetPage.init()
'url': 'http://www.bbc.com/news/world-europe-32041533',
'params': {
'skip_download': True,
}
+ }, {
+ # single video from video playlist embedded with vxp-playlist-data JSON
+ 'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376',
+ 'info_dict': {
+ 'id': 'p02w6qjc',
+ 'ext': 'mp4',
+ 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
+ 'duration': 56,
+ },
+ 'params': {
+ 'skip_download': True,
+ }
}, {
# single video story with digitalData
'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret',
playlist_title = self._html_search_regex(
r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title')
- playlist_description = self._og_search_description(webpage)
+ playlist_description = self._og_search_description(webpage, default=None)
+
+ def extract_all(pattern):
+ return list(filter(None, map(
+ lambda s: self._parse_json(s, playlist_id, fatal=False),
+ re.findall(pattern, webpage))))
+
+ # Multiple video article (e.g.
+ # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
+ EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?'
+ entries = []
+ for match in extract_all(r'new\s+SMP\(({.+?})\)'):
+ embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')
+ if embed_url and re.match(EMBED_URL, embed_url):
+ entries.append(embed_url)
+ entries.extend(re.findall(
+ r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage))
+ if entries:
+ return self.playlist_result(
+ [self.url_result(entry, 'BBCCoUk') for entry in entries],
+ playlist_id, playlist_title, playlist_description)
# Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
- medias = list(filter(None, map(
- lambda s: self._parse_json(s, playlist_id, fatal=False),
- re.findall(r"data-media-meta='({[^']+})'", webpage))))
+ medias = extract_all(r"data-media-meta='({[^']+})'")
if not medias:
# Single video article (e.g. http://www.bbc.com/news/video_and_audio/international)
- media_asset_page = self._parse_json(
+ media_asset = self._search_regex(
+ r'mediaAssetPage\.init\(\s*({.+?}), "/',
+ webpage, 'media asset', default=None)
+ if media_asset:
+ media_asset_page = self._parse_json(media_asset, playlist_id, fatal=False)
+ medias = []
+ for video in media_asset_page.get('videos', {}).values():
+ medias.extend(video.values())
+
+ if not medias:
+ # Multiple video playlist with single `now playing` entry (e.g.
+ # http://www.bbc.com/news/video_and_audio/must_see/33767813)
+ vxp_playlist = self._parse_json(
self._search_regex(
- r'mediaAssetPage\.init\(\s*({.+?}), "/', webpage, 'media asset'),
+ r'<script[^>]+class="vxp-playlist-data"[^>]+type="application/json"[^>]*>([^<]+)</script>',
+ webpage, 'playlist data'),
playlist_id)
- medias = []
- for video in media_asset_page.get('videos', {}).values():
- medias.extend(video.values())
+ playlist_medias = []
+ for item in vxp_playlist:
+ media = item.get('media')
+ if not media:
+ continue
+ playlist_medias.append(media)
+ # Download single video if found media with asset id matching the video id from URL
+ if item.get('advert', {}).get('assetId') == playlist_id:
+ medias = [media]
+ break
+ # Fallback to the whole playlist
+ if not medias:
+ medias = playlist_medias
entries = []
for num, media_meta in enumerate(medias, start=1):
projects / youtube-dl / blobdiff