X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/03342304420e5daeb428ffdcc7bbd2bbfecfa61a..2b4515201a54c38e34434ea2817d606be134a7c9:/youtube_dl/extractor/limelight.py?ds=inline diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index 1a0625a..422be25 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -4,10 +4,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_HTTPError from ..utils import ( determine_ext, float_or_none, int_or_none, + unsmuggle_url, + ExtractorError, ) @@ -15,33 +18,46 @@ class LimelightBaseIE(InfoExtractor): _PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s' _API_URL = 'http://api.video.limelight.com/rest/organizations/%s/%s/%s/%s.json' - def _call_playlist_service(self, item_id, method, fatal=True): - return self._download_json( - self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method), - item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal) + def _call_playlist_service(self, item_id, method, fatal=True, referer=None): + headers = {} + if referer: + headers['Referer'] = referer + try: + return self._download_json( + self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method), + item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + error = self._parse_json(e.cause.read().decode(), item_id)['detail']['contentAccessPermission'] + if error == 'CountryDisabled': + self.raise_geo_restricted() + raise ExtractorError(error, expected=True) + raise def _call_api(self, organization_id, item_id, method): return self._download_json( self._API_URL % (organization_id, self._API_PATH, item_id, method), item_id, 'Downloading API %s JSON' % method) - def _extract(self, item_id, pc_method, mobile_method, meta_method): - pc = self._call_playlist_service(item_id, pc_method) + def _extract(self, item_id, pc_method, mobile_method, meta_method, referer=None): + pc = self._call_playlist_service(item_id, pc_method, referer=referer) metadata = self._call_api(pc['orgId'], item_id, meta_method) - mobile = self._call_playlist_service(item_id, mobile_method, fatal=False) + mobile = self._call_playlist_service(item_id, mobile_method, fatal=False, referer=referer) return pc, mobile, metadata 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: + urls.append(stream_url) + ext = determine_ext(stream_url) + if ext == 'f4m': formats.extend(self._extract_f4m_formats( - stream_url, video_id, fatal=False)) + stream_url, video_id, f4m_id='hds', fatal=False)) else: fmt = { 'url': stream_url, @@ -50,13 +66,33 @@ 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_format_id = format_id.replace('rtmp', 'http') + + CDN_HOSTS = ( + ('delvenetworks.com', 'cpl.delvenetworks.com'), + ('video.llnw.net', 's2.content.video.llnw.net'), + ) + for cdn_host, http_host in CDN_HOSTS: + if cdn_host not in rtmp.group('host').lower(): + continue + http_url = 'http://%s/%s' % (http_host, rtmp.group('playpath')[4:]) + urls.append(http_url) + if self._is_valid_url(http_url, video_id, http_format_id): + http_fmt = fmt.copy() + http_fmt.update({ + 'url': http_url, + 'format_id': http_format_id, + }) + formats.append(http_fmt) + break + fmt.update({ 'url': rtmp.group('url'), 'play_path': rtmp.group('playpath'), @@ -68,18 +104,24 @@ 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', '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) @@ -98,13 +140,19 @@ 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, @@ -123,50 +171,64 @@ 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$', + 'thumbnail': r're:^https?://.*\.jpeg$', 'duration': 144.23, 'timestamp': 1244136834, '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$', + 'thumbnail': r're:^https?://.*\.jpeg$', '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' def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) video_id = self._match_id(url) + self._initialize_geo_bypass(smuggled_data.get('geo_countries')) pc, mobile, metadata = self._extract( - video_id, 'getPlaylistByMediaId', 'getMobilePlaylistByMediaId', 'properties') + video_id, 'getPlaylistByMediaId', + 'getMobilePlaylistByMediaId', 'properties', + smuggled_data.get('source_url')) return self._extract_info( pc['playlistItems'][0].get('streams', []), @@ -176,24 +238,40 @@ 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' def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) channel_id = self._match_id(url) pc, mobile, medias = self._extract( channel_id, 'getPlaylistByChannelId', - 'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1', 'media') + 'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1', + 'media', smuggled_data.get('source_url')) entries = [ self._extract_info( @@ -207,15 +285,29 @@ 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):