[curiositystream] fix format extraction(closes #26845, closes #28668)

This commit is contained in:
Remita Amine 2021-04-07 09:27:05 +01:00
parent 72a2c0a9ed
commit c0c5134c57

View File

@ -25,12 +25,12 @@ class CuriosityStreamBaseIE(InfoExtractor):
raise ExtractorError( raise ExtractorError(
'%s said: %s' % (self.IE_NAME, error), expected=True) '%s said: %s' % (self.IE_NAME, error), expected=True)
def _call_api(self, path, video_id): def _call_api(self, path, video_id, query=None):
headers = {} headers = {}
if self._auth_token: if self._auth_token:
headers['X-Auth-Token'] = self._auth_token headers['X-Auth-Token'] = self._auth_token
result = self._download_json( result = self._download_json(
self._API_BASE_URL + path, video_id, headers=headers) self._API_BASE_URL + path, video_id, headers=headers, query=query)
self._handle_errors(result) self._handle_errors(result)
return result['data'] return result['data']
@ -52,62 +52,75 @@ class CuriosityStreamIE(CuriosityStreamBaseIE):
_VALID_URL = r'https?://(?:app\.)?curiositystream\.com/video/(?P<id>\d+)' _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/video/(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'https://app.curiositystream.com/video/2', 'url': 'https://app.curiositystream.com/video/2',
'md5': '262bb2f257ff301115f1973540de8983',
'info_dict': { 'info_dict': {
'id': '2', 'id': '2',
'ext': 'mp4', 'ext': 'mp4',
'title': 'How Did You Develop The Internet?', 'title': 'How Did You Develop The Internet?',
'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.', 'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
} },
'params': {
'format': 'bestvideo',
# m3u8 download
'skip_download': True,
},
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
media = self._call_api('media/' + video_id, video_id)
title = media['title']
formats = [] formats = []
for encoding in media.get('encodings', []): for encoding_format in ('m3u8', 'mpd'):
m3u8_url = encoding.get('master_playlist_url') media = self._call_api('media/' + video_id, video_id, query={
if m3u8_url: 'encodingsNew': 'true',
formats.extend(self._extract_m3u8_formats( 'encodingsFormat': encoding_format,
m3u8_url, video_id, 'mp4', 'm3u8_native', })
m3u8_id='hls', fatal=False)) for encoding in media.get('encodings', []):
encoding_url = encoding.get('url') playlist_url = encoding.get('master_playlist_url')
file_url = encoding.get('file_url') if encoding_format == 'm3u8':
if not encoding_url and not file_url: # use `m3u8` entry_protocol until EXT-X-MAP is properly supported by `m3u8_native` entry_protocol
continue formats.extend(self._extract_m3u8_formats(
f = { playlist_url, video_id, 'mp4',
'width': int_or_none(encoding.get('width')), m3u8_id='hls', fatal=False))
'height': int_or_none(encoding.get('height')), elif encoding_format == 'mpd':
'vbr': int_or_none(encoding.get('video_bitrate')), formats.extend(self._extract_mpd_formats(
'abr': int_or_none(encoding.get('audio_bitrate')), playlist_url, video_id, mpd_id='dash', fatal=False))
'filesize': int_or_none(encoding.get('size_in_bytes')), encoding_url = encoding.get('url')
'vcodec': encoding.get('video_codec'), file_url = encoding.get('file_url')
'acodec': encoding.get('audio_codec'), if not encoding_url and not file_url:
'container': encoding.get('container_type'),
}
for f_url in (encoding_url, file_url):
if not f_url:
continue continue
fmt = f.copy() f = {
rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', f_url) 'width': int_or_none(encoding.get('width')),
if rtmp: 'height': int_or_none(encoding.get('height')),
fmt.update({ 'vbr': int_or_none(encoding.get('video_bitrate')),
'url': rtmp.group('url'), 'abr': int_or_none(encoding.get('audio_bitrate')),
'play_path': rtmp.group('playpath'), 'filesize': int_or_none(encoding.get('size_in_bytes')),
'app': rtmp.group('app'), 'vcodec': encoding.get('video_codec'),
'ext': 'flv', 'acodec': encoding.get('audio_codec'),
'format_id': 'rtmp', 'container': encoding.get('container_type'),
}) }
else: for f_url in (encoding_url, file_url):
fmt.update({ if not f_url:
'url': f_url, continue
'format_id': 'http', fmt = f.copy()
}) rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', f_url)
formats.append(fmt) if rtmp:
fmt.update({
'url': rtmp.group('url'),
'play_path': rtmp.group('playpath'),
'app': rtmp.group('app'),
'ext': 'flv',
'format_id': 'rtmp',
})
else:
fmt.update({
'url': f_url,
'format_id': 'http',
})
formats.append(fmt)
self._sort_formats(formats) self._sort_formats(formats)
title = media['title']
subtitles = {} subtitles = {}
for closed_caption in media.get('closed_captions', []): for closed_caption in media.get('closed_captions', []):
sub_url = closed_caption.get('file') sub_url = closed_caption.get('file')
@ -140,7 +153,7 @@ class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
'title': 'Curious Minds: The Internet', 'title': 'Curious Minds: The Internet',
'description': 'How is the internet shaping our lives in the 21st Century?', 'description': 'How is the internet shaping our lives in the 21st Century?',
}, },
'playlist_mincount': 17, 'playlist_mincount': 16,
}, { }, {
'url': 'https://curiositystream.com/series/2', 'url': 'https://curiositystream.com/series/2',
'only_matching': True, 'only_matching': True,