From 1e0d65f0bded292440d55ca37449038c8b5d9344 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= Date: Sun, 14 May 2017 10:04:42 +0200 Subject: [PATCH] [beam:vod] Add extractor --- youtube_dl/extractor/beampro.py | 121 ++++++++++++++++++++++++++--- youtube_dl/extractor/extractors.py | 5 +- 2 files changed, 116 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/beampro.py b/youtube_dl/extractor/beampro.py index f3a9e3278..79c5fe5cd 100644 --- a/youtube_dl/extractor/beampro.py +++ b/youtube_dl/extractor/beampro.py @@ -6,16 +6,30 @@ from ..utils import ( ExtractorError, clean_html, compat_str, + float_or_none, int_or_none, parse_iso8601, try_get, + urljoin, ) -class BeamProLiveIE(InfoExtractor): +class BeamProBaseIE(InfoExtractor): + _RATINGS = {'family': 0, 'teen': 13, '18+': 18} + + def _extract_channel_info(self, chan): + user_id = chan.get('userId') or try_get(chan, lambda x: x['user']['id']) + return { + 'uploader': chan.get('token') or try_get( + chan, lambda x: x['user']['username'], compat_str), + 'uploader_id': compat_str(user_id) if user_id else None, + 'age_limit': self._RATINGS.get(chan.get('audience')), + } + + +class BeamProLiveIE(BeamProBaseIE): IE_NAME = 'Beam:live' _VALID_URL = r'https?://(?:\w+\.)?beam\.pro/(?P[^/?#&]+)' - _RATINGS = {'family': 0, 'teen': 13, '18+': 18} _TEST = { 'url': 'http://www.beam.pro/niterhayven', 'info_dict': { @@ -38,6 +52,10 @@ class BeamProLiveIE(InfoExtractor): }, } + @classmethod + def suitable(cls, url): + return False if BeamProVodIE.suitable(url) else super(BeamProLiveIE, cls).suitable(url) + def _real_extract(self, url): channel_name = self._match_id(url) @@ -55,19 +73,104 @@ class BeamProLiveIE(InfoExtractor): channel_name, ext='mp4', m3u8_id='hls', fatal=False) self._sort_formats(formats) - user_id = chan.get('userId') or try_get(chan, lambda x: x['user']['id']) - - return { + info = { 'id': compat_str(chan.get('id') or channel_name), 'title': self._live_title(chan.get('name') or channel_name), 'description': clean_html(chan.get('description')), 'thumbnail': try_get(chan, lambda x: x['thumbnail']['url'], compat_str), 'timestamp': parse_iso8601(chan.get('updatedAt')), - 'uploader': chan.get('token') or try_get( - chan, lambda x: x['user']['username'], compat_str), - 'uploader_id': compat_str(user_id) if user_id else None, - 'age_limit': self._RATINGS.get(chan.get('audience')), 'is_live': True, 'view_count': int_or_none(chan.get('viewersTotal')), 'formats': formats, } + info.update(self._extract_channel_info(chan)) + + return info + + +class BeamProVodIE(BeamProBaseIE): + IE_NAME = 'Beam:vod' + _VALID_URL = r'https?://(?:\w+\.)?beam\.pro/[^/?#&]+.*[?&]vod=(?P\d+)' + _TEST = { + 'url': 'https://beam.pro/willow8714?vod=2259830', + 'md5': 'b2431e6e8347dc92ebafb565d368b76b', + 'info_dict': { + 'id': '2259830', + 'ext': 'mp4', + 'title': 'willow8714\'s Channel', + 'duration': 6828.15, + 'thumbnail': r're:https://.*source\.png$', + 'timestamp': 1494046474, + 'upload_date': '20170506', + 'uploader': 'willow8714', + 'uploader_id': '6085379', + 'age_limit': 13, + 'view_count': int, + }, + } + + def _extract_format(self, vod, vod_type): + if not vod.get('baseUrl'): + return [] + + if vod_type == 'hls': + filename, protocol = 'manifest.m3u8', 'm3u8' + elif vod_type == 'raw': + filename, protocol = 'source.mp4', 'https' + else: + return [] + + data = vod.get('data') or {} + + format_id = [vod_type] + if 'Height' in data: + format_id.append('%sp' % data['Height']) + + return [{ + 'url': urljoin(vod['baseUrl'], filename), + 'format_id': '-'.join(format_id), + 'ext': 'mp4', + 'protocol': protocol, + 'width': int_or_none(data.get('Width')), + 'height': int_or_none(data.get('Height')), + 'fps': int_or_none(data.get('Fps')), + 'tbr': int_or_none(data.get('Bitrate'), 1000), + }] + + def _real_extract(self, url): + vod_id = self._match_id(url) + + vod_info = self._download_json( + 'https://beam.pro/api/v1/recordings/%s' % vod_id, vod_id) + + state = vod_info.get('state') + if state != 'AVAILABLE': + raise ExtractorError( + 'VOD %s is not available (state: %s)' % (vod_id, state), expected=True) + + formats = [] + thumbnail_url = None + + for vod in vod_info['vods']: + vod_type = vod.get('format') + if vod_type in ('hls', 'raw'): + formats.extend(self._extract_format(vod, vod_type)) + elif vod_type == 'thumbnail': + thumbnail_url = urljoin(vod.get('baseUrl'), 'source.png') + + self._sort_formats(formats) + + info = { + 'id': vod_id, + 'title': vod_info.get('name') or vod_id, + 'duration': float_or_none(vod_info.get('duration')), + 'thumbnail': thumbnail_url, + 'timestamp': parse_iso8601(vod_info.get('createdAt')), + 'view_count': int_or_none(vod_info.get('viewsTotal')), + 'formats': formats, + } + + chan = vod_info.get('channel') or {} + info.update(self._extract_channel_info(chan)) + + return info diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 558c910d4..aecd08ac1 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -98,7 +98,10 @@ from .bbc import ( BBCCoUkPlaylistIE, BBCIE, ) -from .beampro import BeamProLiveIE +from .beampro import ( + BeamProLiveIE, + BeamProVodIE, +) from .beeg import BeegIE from .behindkink import BehindKinkIE from .bellmedia import BellMediaIE