yt_dlp/extractor/microsoftembed.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     traverse_obj,
   5     unified_timestamp,
   6 )
   7
   8
   9 class MicrosoftEmbedIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?microsoft\.com/(?:[^/]+/)?videoplayer/embed/(?P<id>[a-z0-9A-Z]+)'
  11
  12     _TESTS = [{
  13         'url': 'https://www.microsoft.com/en-us/videoplayer/embed/RWL07e',
  14         'md5': 'eb0ae9007f9b305f9acd0a03e74cb1a9',
  15         'info_dict': {
  16             'id': 'RWL07e',
  17             'title': 'Microsoft for Public Health and Social Services',
  18             'ext': 'mp4',
  19             'thumbnail': 'http://img-prod-cms-rt-microsoft-com.akamaized.net/cms/api/am/imageFileData/RWL7Ju?ver=cae5',
  20             'age_limit': 0,
  21             'timestamp': 1631658316,
  22             'upload_date': '20210914'
  23         }
  24     }]
  25     _API_URL = 'https://prod-video-cms-rt-microsoft-com.akamaized.net/vhs/api/videos/'
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         metadata = self._download_json(self._API_URL + video_id, video_id)
  30
  31         formats = []
  32         for source_type, source in metadata['streams'].items():
  33             if source_type == 'smooth_Streaming':
  34                 formats.extend(self._extract_ism_formats(source['url'], video_id, 'mss'))
  35             elif source_type == 'apple_HTTP_Live_Streaming':
  36                 formats.extend(self._extract_m3u8_formats(source['url'], video_id, 'mp4'))
  37             elif source_type == 'mPEG_DASH':
  38                 formats.extend(self._extract_mpd_formats(source['url'], video_id))
  39             else:
  40                 formats.append({
  41                     'format_id': source_type,
  42                     'url': source['url'],
  43                     'height': source.get('heightPixels'),
  44                     'width': source.get('widthPixels'),
  45                 })
  46         self._sort_formats(formats)
  47
  48         subtitles = {
  49             lang: [{
  50                 'url': data.get('url'),
  51                 'ext': 'vtt',
  52             }] for lang, data in traverse_obj(metadata, 'captions', default={}).items()
  53         }
  54
  55         thumbnails = [{
  56             'url': thumb.get('url'),
  57             'width': thumb.get('width') or None,
  58             'height': thumb.get('height') or None,
  59         } for thumb in traverse_obj(metadata, ('snippet', 'thumbnails', ...))]
  60         self._remove_duplicate_formats(thumbnails)
  61
  62         return {
  63             'id': video_id,
  64             'title': traverse_obj(metadata, ('snippet', 'title')),
  65             'timestamp': unified_timestamp(traverse_obj(metadata, ('snippet', 'activeStartDate'))),
  66             'age_limit': int_or_none(traverse_obj(metadata, ('snippet', 'minimumAge'))) or 0,
  67             'formats': formats,
  68             'subtitles': subtitles,
  69             'thumbnails': thumbnails,
  70         }