X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/e76f531201cd41dfc0ce00be28bcc5c575c7acc5..3e696c728febc53e74c912c40ccd3b9504d536df:/youtube_dl/extractor/limelight.py diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index fb03dd5..b7bfa7a 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -34,13 +34,16 @@ class LimelightBaseIE(InfoExtractor): def _extract_info(self, streams, mobile_urls, properties): video_id = properties['media_id'] formats = [] - + urls = [] for stream in streams: stream_url = stream.get('url') - if not stream_url: + if not stream_url or stream.get('drmProtected') or stream_url in urls: continue - if '.f4m' in stream_url: - formats.extend(self._extract_f4m_formats(stream_url, video_id)) + urls.append(stream_url) + ext = determine_ext(stream_url) + if ext == 'f4m': + formats.extend(self._extract_f4m_formats( + stream_url, video_id, f4m_id='hds', fatal=False)) else: fmt = { 'url': stream_url, @@ -49,13 +52,21 @@ class LimelightBaseIE(InfoExtractor): 'fps': float_or_none(stream.get('videoFrameRate')), 'width': int_or_none(stream.get('videoWidthInPixels')), 'height': int_or_none(stream.get('videoHeightInPixels')), - 'ext': determine_ext(stream_url) + 'ext': ext, } - rtmp = re.search(r'^(?Prtmpe?://[^/]+/(?P.+))/(?Pmp4:.+)$', stream_url) + rtmp = re.search(r'^(?Prtmpe?://(?P[^/]+)/(?P.+))/(?Pmp4:.+)$', stream_url) if rtmp: format_id = 'rtmp' if stream.get('videoBitRate'): format_id += '-%d' % int_or_none(stream['videoBitRate']) + http_url = 'http://cpl.delvenetworks.com/' + rtmp.group('playpath')[4:] + urls.append(http_url) + http_fmt = fmt.copy() + http_fmt.update({ + 'url': http_url, + 'format_id': format_id.replace('rtmp', 'http'), + }) + formats.append(http_fmt) fmt.update({ 'url': rtmp.group('url'), 'play_path': rtmp.group('playpath'), @@ -67,18 +78,24 @@ class LimelightBaseIE(InfoExtractor): for mobile_url in mobile_urls: media_url = mobile_url.get('mobileUrl') - if not media_url: - continue format_id = mobile_url.get('targetMediaPlatform') - if determine_ext(media_url) == 'm3u8': + if not media_url or format_id in ('Widevine', 'SmoothStreaming') or media_url in urls: + continue + urls.append(media_url) + ext = determine_ext(media_url) + if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - media_url, video_id, 'mp4', entry_protocol='m3u8_native', - preference=-1, m3u8_id=format_id)) + media_url, video_id, 'mp4', 'm3u8_native', + m3u8_id=format_id, fatal=False)) + elif ext == 'f4m': + formats.extend(self._extract_f4m_formats( + stream_url, video_id, f4m_id=format_id, fatal=False)) else: formats.append({ 'url': media_url, 'format_id': format_id, 'preference': -1, + 'ext': ext, }) self._sort_formats(formats) @@ -97,13 +114,19 @@ class LimelightBaseIE(InfoExtractor): } for thumbnail in properties.get('thumbnails', []) if thumbnail.get('url')] subtitles = {} - for caption in properties.get('captions', {}): + for caption in properties.get('captions', []): lang = caption.get('language_code') subtitles_url = caption.get('url') if lang and subtitles_url: - subtitles[lang] = [{ + subtitles.setdefault(lang, []).append({ 'url': subtitles_url, - }] + }) + closed_captions_url = properties.get('closed_captions_url') + if closed_captions_url: + subtitles.setdefault('en', []).append({ + 'url': closed_captions_url, + 'ext': 'ttml', + }) return { 'id': video_id, @@ -122,12 +145,23 @@ class LimelightBaseIE(InfoExtractor): class LimelightMediaIE(LimelightBaseIE): IE_NAME = 'limelight' - _VALID_URL = r'(?:limelight:media:|http://link\.videoplatform\.limelight\.com/media/\??\bmediaId=)(?P[a-z0-9]{32})' + _VALID_URL = r'''(?x) + (?: + limelight:media:| + https?:// + (?: + link\.videoplatform\.limelight\.com/media/| + assets\.delvenetworks\.com/player/loader\.swf + ) + \?.*?\bmediaId= + ) + (?P[a-z0-9]{32}) + ''' _TESTS = [{ 'url': 'http://link.videoplatform.limelight.com/media/?mediaId=3ffd040b522b4485b6d84effc750cd86', 'info_dict': { 'id': '3ffd040b522b4485b6d84effc750cd86', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'HaP and the HB Prince Trailer', 'description': 'md5:8005b944181778e313d95c1237ddb640', 'thumbnail': 're:^https?://.*\.jpeg$', @@ -136,27 +170,26 @@ class LimelightMediaIE(LimelightBaseIE): 'upload_date': '20090604', }, 'params': { - # rtmp download + # m3u8 download 'skip_download': True, }, }, { # video with subtitles 'url': 'limelight:media:a3e00274d4564ec4a9b29b9466432335', + 'md5': '2fa3bad9ac321e23860ca23bc2c69e3d', 'info_dict': { 'id': 'a3e00274d4564ec4a9b29b9466432335', - 'ext': 'flv', + 'ext': 'mp4', 'title': '3Play Media Overview Video', - 'description': '', 'thumbnail': 're:^https?://.*\.jpeg$', 'duration': 78.101, 'timestamp': 1338929955, 'upload_date': '20120605', 'subtitles': 'mincount:9', }, - 'params': { - # rtmp download - 'skip_download': True, - }, + }, { + 'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452', + 'only_matching': True, }] _PLAYLIST_SERVICE_PATH = 'media' _API_PATH = 'media' @@ -175,15 +208,29 @@ class LimelightMediaIE(LimelightBaseIE): class LimelightChannelIE(LimelightBaseIE): IE_NAME = 'limelight:channel' - _VALID_URL = r'(?:limelight:channel:|http://link\.videoplatform\.limelight\.com/media/\??\bchannelId=)(?P[a-z0-9]{32})' - _TEST = { + _VALID_URL = r'''(?x) + (?: + limelight:channel:| + https?:// + (?: + link\.videoplatform\.limelight\.com/media/| + assets\.delvenetworks\.com/player/loader\.swf + ) + \?.*?\bchannelId= + ) + (?P[a-z0-9]{32}) + ''' + _TESTS = [{ 'url': 'http://link.videoplatform.limelight.com/media/?channelId=ab6a524c379342f9b23642917020c082', 'info_dict': { 'id': 'ab6a524c379342f9b23642917020c082', 'title': 'Javascript Sample Code', }, 'playlist_mincount': 3, - } + }, { + 'url': 'http://assets.delvenetworks.com/player/loader.swf?channelId=ab6a524c379342f9b23642917020c082', + 'only_matching': True, + }] _PLAYLIST_SERVICE_PATH = 'channel' _API_PATH = 'channels' @@ -206,15 +253,29 @@ class LimelightChannelIE(LimelightBaseIE): class LimelightChannelListIE(LimelightBaseIE): IE_NAME = 'limelight:channel_list' - _VALID_URL = r'(?:limelight:channel_list:|http://link\.videoplatform\.limelight\.com/media/\?.*?\bchannelListId=)(?P[a-z0-9]{32})' - _TEST = { + _VALID_URL = r'''(?x) + (?: + limelight:channel_list:| + https?:// + (?: + link\.videoplatform\.limelight\.com/media/| + assets\.delvenetworks\.com/player/loader\.swf + ) + \?.*?\bchannelListId= + ) + (?P[a-z0-9]{32}) + ''' + _TESTS = [{ 'url': 'http://link.videoplatform.limelight.com/media/?channelListId=301b117890c4465c8179ede21fd92e2b', 'info_dict': { 'id': '301b117890c4465c8179ede21fd92e2b', 'title': 'Website - Hero Player', }, 'playlist_mincount': 2, - } + }, { + 'url': 'https://assets.delvenetworks.com/player/loader.swf?channelListId=301b117890c4465c8179ede21fd92e2b', + 'only_matching': True, + }] _PLAYLIST_SERVICE_PATH = 'channel_list' def _real_extract(self, url):