yt_dlp/extractor/lego.py

   1 import uuid
   2
   3 from .common import InfoExtractor
   4 from ..networking.exceptions import HTTPError
   5 from ..utils import (
   6     ExtractorError,
   7     int_or_none,
   8     join_nonempty,
   9     qualities,
  10 )
  11
  12
  13 class LEGOIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?lego\.com/(?P<locale>[a-z]{2}-[a-z]{2})/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P<id>[0-9a-f]{32})'
  15     _TESTS = [{
  16         'url': 'http://www.lego.com/en-us/videos/themes/club/blocumentary-kawaguchi-55492d823b1b4d5e985787fa8c2973b1',
  17         'md5': 'f34468f176cfd76488767fc162c405fa',
  18         'info_dict': {
  19             'id': '55492d82-3b1b-4d5e-9857-87fa8c2973b1_en-US',
  20             'ext': 'mp4',
  21             'title': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
  22             'description': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
  23         },
  24     }, {
  25         # geo-restricted but the contentUrl contain a valid url
  26         'url': 'http://www.lego.com/nl-nl/videos/themes/nexoknights/episode-20-kingdom-of-heroes-13bdc2299ab24d9685701a915b3d71e7##sp=399',
  27         'md5': 'c7420221f7ffd03ff056f9db7f8d807c',
  28         'info_dict': {
  29             'id': '13bdc229-9ab2-4d96-8570-1a915b3d71e7_nl-NL',
  30             'ext': 'mp4',
  31             'title': 'Aflevering 20:  Helden van het koninkrijk',
  32             'description': 'md5:8ee499aac26d7fa8bcb0cedb7f9c3941',
  33             'age_limit': 5,
  34         },
  35     }, {
  36         # with subtitle
  37         'url': 'https://www.lego.com/nl-nl/kids/videos/classic/creative-storytelling-the-little-puppy-aa24f27c7d5242bc86102ebdc0f24cba',
  38         'info_dict': {
  39             'id': 'aa24f27c-7d52-42bc-8610-2ebdc0f24cba_nl-NL',
  40             'ext': 'mp4',
  41             'title': 'De kleine puppy',
  42             'description': 'md5:5b725471f849348ac73f2e12cfb4be06',
  43             'age_limit': 1,
  44             'subtitles': {
  45                 'nl': [{
  46                     'ext': 'srt',
  47                     'url': r're:^https://.+\.srt$',
  48                 }],
  49             },
  50         },
  51         'params': {
  52             'skip_download': True,
  53         },
  54     }]
  55     _QUALITIES = {
  56         'Lowest': (64, 180, 320),
  57         'Low': (64, 270, 480),
  58         'Medium': (96, 360, 640),
  59         'High': (128, 540, 960),
  60         'Highest': (128, 720, 1280),
  61     }
  62
  63     def _real_extract(self, url):
  64         locale, video_id = self._match_valid_url(url).groups()
  65         countries = [locale.split('-')[1].upper()]
  66         self._initialize_geo_bypass({
  67             'countries': countries,
  68         })
  69
  70         try:
  71             item = self._download_json(
  72                 # https://contentfeed.services.lego.com/api/v2/item/[VIDEO_ID]?culture=[LOCALE]&contentType=Video
  73                 'https://services.slingshot.lego.com/mediaplayer/v2',
  74                 video_id, query={
  75                     'videoId': '%s_%s' % (uuid.UUID(video_id), locale),
  76                 }, headers=self.geo_verification_headers())
  77         except ExtractorError as e:
  78             if isinstance(e.cause, HTTPError) and e.cause.status == 451:
  79                 self.raise_geo_restricted(countries=countries)
  80             raise
  81
  82         video = item['Video']
  83         video_id = video['Id']
  84         title = video['Title']
  85
  86         q = qualities(['Lowest', 'Low', 'Medium', 'High', 'Highest'])
  87         formats = []
  88         for video_source in item.get('VideoFormats', []):
  89             video_source_url = video_source.get('Url')
  90             if not video_source_url:
  91                 continue
  92             video_source_format = video_source.get('Format')
  93             if video_source_format == 'F4M':
  94                 formats.extend(self._extract_f4m_formats(
  95                     video_source_url, video_id,
  96                     f4m_id=video_source_format, fatal=False))
  97             elif video_source_format == 'M3U8':
  98                 formats.extend(self._extract_m3u8_formats(
  99                     video_source_url, video_id, 'mp4', 'm3u8_native',
 100                     m3u8_id=video_source_format, fatal=False))
 101             else:
 102                 video_source_quality = video_source.get('Quality')
 103                 f = {
 104                     'format_id': join_nonempty(video_source_format, video_source_quality),
 105                     'quality': q(video_source_quality),
 106                     'url': video_source_url,
 107                 }
 108                 quality = self._QUALITIES.get(video_source_quality)
 109                 if quality:
 110                     f.update({
 111                         'abr': quality[0],
 112                         'height': quality[1],
 113                         'width': quality[2],
 114                     }),
 115                 formats.append(f)
 116
 117         subtitles = {}
 118         sub_file_id = video.get('SubFileId')
 119         if sub_file_id and sub_file_id != '00000000-0000-0000-0000-000000000000':
 120             net_storage_path = video.get('NetstoragePath')
 121             invariant_id = video.get('InvariantId')
 122             video_file_id = video.get('VideoFileId')
 123             video_version = video.get('VideoVersion')
 124             if net_storage_path and invariant_id and video_file_id and video_version:
 125                 subtitles.setdefault(locale[:2], []).append({
 126                     'url': 'https://lc-mediaplayerns-live-s.legocdn.com/public/%s/%s_%s_%s_%s_sub.srt' % (net_storage_path, invariant_id, video_file_id, locale, video_version),
 127                 })
 128
 129         return {
 130             'id': video_id,
 131             'title': title,
 132             'description': video.get('Description'),
 133             'thumbnail': video.get('GeneratedCoverImage') or video.get('GeneratedThumbnail'),
 134             'duration': int_or_none(video.get('Length')),
 135             'formats': formats,
 136             'subtitles': subtitles,
 137             'age_limit': int_or_none(video.get('AgeFrom')),
 138             'season': video.get('SeasonTitle'),
 139             'season_number': int_or_none(video.get('Season')) or None,
 140             'episode_number': int_or_none(video.get('Episode')) or None,
 141         }