youtube_dl/extractor/arkena.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_urlparse
   8 from ..utils import (
   9     ExtractorError,
  10     float_or_none,
  11     int_or_none,
  12     parse_iso8601,
  13     try_get,
  14 )
  15
  16
  17 class ArkenaIE(InfoExtractor):
  18     _VALID_URL = r'''(?x)
  19                         https?://
  20                             (?:
  21                                 video\.(?:arkena|qbrick)\.com/play2/embed/player\?|
  22                                 play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)
  23                             )
  24                         '''
  25     _TESTS = [{
  26         'url': 'https://video.qbrick.com/play2/embed/player?accountId=1034090&mediaId=d8ab4607-00090107-aab86310',
  27         'md5': '97f117754e5f3c020f5f26da4a44ebaf',
  28         'info_dict': {
  29             'id': 'd8ab4607-00090107-aab86310',
  30             'ext': 'mp4',
  31             'title': 'EM_HT20_117_roslund_v2.mp4',
  32             'timestamp': 1608285912,
  33             'upload_date': '20201218',
  34             'duration': 1429.162667,
  35             'subtitles': {
  36                 'sv': 'count:3',
  37             },
  38         },
  39     }, {
  40         'url': 'https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411',
  41         'only_matching': True,
  42     }, {
  43         'url': 'https://play.arkena.com/config/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411/?callbackMethod=jQuery1111023664739129262213_1469227693893',
  44         'only_matching': True,
  45     }, {
  46         'url': 'http://play.arkena.com/config/avp/v1/player/media/327336/darkmatter/131064/?callbackMethod=jQuery1111002221189684892677_1469227595972',
  47         'only_matching': True,
  48     }, {
  49         'url': 'http://play.arkena.com/embed/avp/v1/player/media/327336/darkmatter/131064/',
  50         'only_matching': True,
  51     }, {
  52         'url': 'http://video.arkena.com/play2/embed/player?accountId=472718&mediaId=35763b3b-00090078-bf604299&pageStyling=styled',
  53         'only_matching': True,
  54     }]
  55
  56     @staticmethod
  57     def _extract_url(webpage):
  58         # See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
  59         mobj = re.search(
  60             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1',
  61             webpage)
  62         if mobj:
  63             return mobj.group('url')
  64
  65     def _real_extract(self, url):
  66         mobj = re.match(self._VALID_URL, url)
  67         video_id = mobj.group('id')
  68         account_id = mobj.group('account_id')
  69
  70         # Handle http://video.arkena.com/play2/embed/player URL
  71         if not video_id:
  72             qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
  73             video_id = qs.get('mediaId', [None])[0]
  74             account_id = qs.get('accountId', [None])[0]
  75             if not video_id or not account_id:
  76                 raise ExtractorError('Invalid URL', expected=True)
  77
  78         media = self._download_json(
  79             'https://video.qbrick.com/api/v1/public/accounts/%s/medias/%s' % (account_id, video_id),
  80             video_id, query={
  81                 # https://video.qbrick.com/docs/api/examples/library-api.html
  82                 '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',
  83             })
  84         metadata = media.get('metadata') or {}
  85         title = metadata['title']
  86
  87         duration = None
  88         formats = []
  89         thumbnails = []
  90         subtitles = {}
  91         for resource in media['asset']['resources']:
  92             for rendition in (resource.get('renditions') or []):
  93                 rendition_type = rendition.get('type')
  94                 for i, link in enumerate(rendition.get('links') or []):
  95                     href = link.get('href')
  96                     if not href:
  97                         continue
  98                     if rendition_type == 'image':
  99                         thumbnails.append({
 100                             'filesize': int_or_none(rendition.get('size')),
 101                             'height': int_or_none(rendition.get('height')),
 102                             'id': rendition.get('id'),
 103                             'url': href,
 104                             'width': int_or_none(rendition.get('width')),
 105                         })
 106                     elif rendition_type == 'subtitle':
 107                         subtitles.setdefault(rendition.get('language') or 'en', []).append({
 108                             'url': href,
 109                         })
 110                     elif rendition_type == 'video':
 111                         f = {
 112                             'filesize': int_or_none(rendition.get('size')),
 113                             'format_id': rendition.get('id'),
 114                             'url': href,
 115                         }
 116                         video = try_get(rendition, lambda x: x['videos'][i], dict)
 117                         if video:
 118                             if not duration:
 119                                 duration = float_or_none(video.get('duration'))
 120                             f.update({
 121                                 'height': int_or_none(video.get('height')),
 122                                 'tbr': int_or_none(video.get('bitrate'), 1000),
 123                                 'vcodec': video.get('codec'),
 124                                 'width': int_or_none(video.get('width')),
 125                             })
 126                             audio = try_get(video, lambda x: x['audios'][0], dict)
 127                             if audio:
 128                                 f.update({
 129                                     'acodec': audio.get('codec'),
 130                                     'asr': int_or_none(audio.get('sampleRate')),
 131                                 })
 132                         formats.append(f)
 133                     elif rendition_type == 'index':
 134                         mime_type = link.get('mimeType')
 135                         if mime_type == 'application/smil+xml':
 136                             formats.extend(self._extract_smil_formats(
 137                                 href, video_id, fatal=False))
 138                         elif mime_type == 'application/x-mpegURL':
 139                             formats.extend(self._extract_m3u8_formats(
 140                                 href, video_id, 'mp4', 'm3u8_native',
 141                                 m3u8_id='hls', fatal=False))
 142                         elif mime_type == 'application/hds+xml':
 143                             formats.extend(self._extract_f4m_formats(
 144                                 href, video_id, f4m_id='hds', fatal=False))
 145                         elif mime_type == 'application/dash+xml':
 146                             formats.extend(self._extract_f4m_formats(
 147                                 href, video_id, f4m_id='hds', fatal=False))
 148                         elif mime_type == 'application/vnd.ms-sstr+xml':
 149                             formats.extend(self._extract_ism_formats(
 150                                 href, video_id, ism_id='mss', fatal=False))
 151         self._sort_formats(formats)
 152
 153         return {
 154             'id': video_id,
 155             'title': title,
 156             'description': metadata.get('description'),
 157             'timestamp': parse_iso8601(media.get('created')),
 158             'thumbnails': thumbnails,
 159             'subtitles': subtitles,
 160             'duration': duration,
 161             'tags': media.get('tags'),
 162             'formats': formats,
 163         }