yt_dlp/extractor/arkena.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     float_or_none,
   5     int_or_none,
   6     parse_iso8601,
   7     parse_qs,
   8     try_get,
   9 )
  10
  11
  12 class ArkenaIE(InfoExtractor):
  13     _VALID_URL = r'''(?x)
  14                         https?://
  15                             (?:
  16                                 video\.(?:arkena|qbrick)\.com/play2/embed/player\?|
  17                                 play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)
  18                             )
  19                         '''
  20     # See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
  21     _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1']
  22     _TESTS = [{
  23         'url': 'https://video.qbrick.com/play2/embed/player?accountId=1034090&mediaId=d8ab4607-00090107-aab86310',
  24         'md5': '97f117754e5f3c020f5f26da4a44ebaf',
  25         'info_dict': {
  26             'id': 'd8ab4607-00090107-aab86310',
  27             'ext': 'mp4',
  28             'title': 'EM_HT20_117_roslund_v2.mp4',
  29             'timestamp': 1608285912,
  30             'upload_date': '20201218',
  31             'duration': 1429.162667,
  32             'subtitles': {
  33                 'sv': 'count:3',
  34             },
  35         },
  36     }, {
  37         'url': 'https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411',
  38         'only_matching': True,
  39     }, {
  40         'url': 'https://play.arkena.com/config/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411/?callbackMethod=jQuery1111023664739129262213_1469227693893',
  41         'only_matching': True,
  42     }, {
  43         'url': 'http://play.arkena.com/config/avp/v1/player/media/327336/darkmatter/131064/?callbackMethod=jQuery1111002221189684892677_1469227595972',
  44         'only_matching': True,
  45     }, {
  46         'url': 'http://play.arkena.com/embed/avp/v1/player/media/327336/darkmatter/131064/',
  47         'only_matching': True,
  48     }, {
  49         'url': 'http://video.arkena.com/play2/embed/player?accountId=472718&mediaId=35763b3b-00090078-bf604299&pageStyling=styled',
  50         'only_matching': True,
  51     }]
  52
  53     def _real_extract(self, url):
  54         mobj = self._match_valid_url(url)
  55         video_id = mobj.group('id')
  56         account_id = mobj.group('account_id')
  57
  58         # Handle http://video.arkena.com/play2/embed/player URL
  59         if not video_id:
  60             qs = parse_qs(url)
  61             video_id = qs.get('mediaId', [None])[0]
  62             account_id = qs.get('accountId', [None])[0]
  63             if not video_id or not account_id:
  64                 raise ExtractorError('Invalid URL', expected=True)
  65
  66         media = self._download_json(
  67             f'https://video.qbrick.com/api/v1/public/accounts/{account_id}/medias/{video_id}',
  68             video_id, query={
  69                 # https://video.qbrick.com/docs/api/examples/library-api.html
  70                 'fields': 'asset/resources/*/renditions/*(height,id,language,links/*(href,mimeType),type,size,videos/*(audios/*(codec,sampleRate),bitrate,codec,duration,height,width),width),created,metadata/*(title,description),tags',
  71             })
  72         metadata = media.get('metadata') or {}
  73         title = metadata['title']
  74
  75         duration = None
  76         formats = []
  77         thumbnails = []
  78         subtitles = {}
  79         for resource in media['asset']['resources']:
  80             for rendition in (resource.get('renditions') or []):
  81                 rendition_type = rendition.get('type')
  82                 for i, link in enumerate(rendition.get('links') or []):
  83                     href = link.get('href')
  84                     if not href:
  85                         continue
  86                     if rendition_type == 'image':
  87                         thumbnails.append({
  88                             'filesize': int_or_none(rendition.get('size')),
  89                             'height': int_or_none(rendition.get('height')),
  90                             'id': rendition.get('id'),
  91                             'url': href,
  92                             'width': int_or_none(rendition.get('width')),
  93                         })
  94                     elif rendition_type == 'subtitle':
  95                         subtitles.setdefault(rendition.get('language') or 'en', []).append({
  96                             'url': href,
  97                         })
  98                     elif rendition_type == 'video':
  99                         f = {
 100                             'filesize': int_or_none(rendition.get('size')),
 101                             'format_id': rendition.get('id'),
 102                             'url': href,
 103                         }
 104                         video = try_get(rendition, lambda x: x['videos'][i], dict)
 105                         if video:
 106                             if not duration:
 107                                 duration = float_or_none(video.get('duration'))
 108                             f.update({
 109                                 'height': int_or_none(video.get('height')),
 110                                 'tbr': int_or_none(video.get('bitrate'), 1000),
 111                                 'vcodec': video.get('codec'),
 112                                 'width': int_or_none(video.get('width')),
 113                             })
 114                             audio = try_get(video, lambda x: x['audios'][0], dict)
 115                             if audio:
 116                                 f.update({
 117                                     'acodec': audio.get('codec'),
 118                                     'asr': int_or_none(audio.get('sampleRate')),
 119                                 })
 120                         formats.append(f)
 121                     elif rendition_type == 'index':
 122                         mime_type = link.get('mimeType')
 123                         if mime_type == 'application/smil+xml':
 124                             formats.extend(self._extract_smil_formats(
 125                                 href, video_id, fatal=False))
 126                         elif mime_type == 'application/x-mpegURL':
 127                             formats.extend(self._extract_m3u8_formats(
 128                                 href, video_id, 'mp4', 'm3u8_native',
 129                                 m3u8_id='hls', fatal=False))
 130                         elif mime_type == 'application/hds+xml':
 131                             formats.extend(self._extract_f4m_formats(
 132                                 href, video_id, f4m_id='hds', fatal=False))
 133                         elif mime_type == 'application/dash+xml':
 134                             formats.extend(self._extract_mpd_formats(
 135                                 href, video_id, mpd_id='dash', fatal=False))
 136                         elif mime_type == 'application/vnd.ms-sstr+xml':
 137                             formats.extend(self._extract_ism_formats(
 138                                 href, video_id, ism_id='mss', fatal=False))
 139
 140         return {
 141             'id': video_id,
 142             'title': title,
 143             'description': metadata.get('description'),
 144             'timestamp': parse_iso8601(media.get('created')),
 145             'thumbnails': thumbnails,
 146             'subtitles': subtitles,
 147             'duration': duration,
 148             'tags': media.get('tags'),
 149             'formats': formats,
 150         }