Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/lego.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import uuid
   6
   7 from .common import InfoExtractor
   8 from ..compat import compat_HTTPError
   9 from ..utils import (
  10     ExtractorError,
  11     int_or_none,
  12     qualities,
  13 )
  14
  15
  16 class LEGOIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?lego\.com/(?P<locale>[a-z]{2}-[a-z]{2})/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P<id>[0-9a-f]{32})'
  18     _TESTS = [{
  19         'url': 'http://www.lego.com/en-us/videos/themes/club/blocumentary-kawaguchi-55492d823b1b4d5e985787fa8c2973b1',
  20         'md5': 'f34468f176cfd76488767fc162c405fa',
  21         'info_dict': {
  22             'id': '55492d82-3b1b-4d5e-9857-87fa8c2973b1_en-US',
  23             'ext': 'mp4',
  24             'title': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
  25             'description': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
  26         },
  27     }, {
  28         # geo-restricted but the contentUrl contain a valid url
  29         'url': 'http://www.lego.com/nl-nl/videos/themes/nexoknights/episode-20-kingdom-of-heroes-13bdc2299ab24d9685701a915b3d71e7##sp=399',
  30         'md5': 'c7420221f7ffd03ff056f9db7f8d807c',
  31         'info_dict': {
  32             'id': '13bdc229-9ab2-4d96-8570-1a915b3d71e7_nl-NL',
  33             'ext': 'mp4',
  34             'title': 'Aflevering 20:  Helden van het koninkrijk',
  35             'description': 'md5:8ee499aac26d7fa8bcb0cedb7f9c3941',
  36             'age_limit': 5,
  37         },
  38     }, {
  39         # with subtitle
  40         'url': 'https://www.lego.com/nl-nl/kids/videos/classic/creative-storytelling-the-little-puppy-aa24f27c7d5242bc86102ebdc0f24cba',
  41         'info_dict': {
  42             'id': 'aa24f27c-7d52-42bc-8610-2ebdc0f24cba_nl-NL',
  43             'ext': 'mp4',
  44             'title': 'De kleine puppy',
  45             'description': 'md5:5b725471f849348ac73f2e12cfb4be06',
  46             'age_limit': 1,
  47             'subtitles': {
  48                 'nl': [{
  49                     'ext': 'srt',
  50                     'url': r're:^https://.+\.srt$',
  51                 }],
  52             },
  53         },
  54         'params': {
  55             'skip_download': True,
  56         },
  57     }]
  58     _QUALITIES = {
  59         'Lowest': (64, 180, 320),
  60         'Low': (64, 270, 480),
  61         'Medium': (96, 360, 640),
  62         'High': (128, 540, 960),
  63         'Highest': (128, 720, 1280),
  64     }
  65
  66     def _real_extract(self, url):
  67         locale, video_id = re.match(self._VALID_URL, url).groups()
  68         countries = [locale.split('-')[1].upper()]
  69         self._initialize_geo_bypass({
  70             'countries': countries,
  71         })
  72
  73         try:
  74             item = self._download_json(
  75                 # https://contentfeed.services.lego.com/api/v2/item/[VIDEO_ID]?culture=[LOCALE]&contentType=Video
  76                 'https://services.slingshot.lego.com/mediaplayer/v2',
  77                 video_id, query={
  78                     'videoId': '%s_%s' % (uuid.UUID(video_id), locale),
  79                 }, headers=self.geo_verification_headers())
  80         except ExtractorError as e:
  81             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 451:
  82                 self.raise_geo_restricted(countries=countries)
  83             raise
  84
  85         video = item['Video']
  86         video_id = video['Id']
  87         title = video['Title']
  88
  89         q = qualities(['Lowest', 'Low', 'Medium', 'High', 'Highest'])
  90         formats = []
  91         for video_source in item.get('VideoFormats', []):
  92             video_source_url = video_source.get('Url')
  93             if not video_source_url:
  94                 continue
  95             video_source_format = video_source.get('Format')
  96             if video_source_format == 'F4M':
  97                 formats.extend(self._extract_f4m_formats(
  98                     video_source_url, video_id,
  99                     f4m_id=video_source_format, fatal=False))
 100             elif video_source_format == 'M3U8':
 101                 formats.extend(self._extract_m3u8_formats(
 102                     video_source_url, video_id, 'mp4', 'm3u8_native',
 103                     m3u8_id=video_source_format, fatal=False))
 104             else:
 105                 video_source_quality = video_source.get('Quality')
 106                 format_id = []
 107                 for v in (video_source_format, video_source_quality):
 108                     if v:
 109                         format_id.append(v)
 110                 f = {
 111                     'format_id': '-'.join(format_id),
 112                     'quality': q(video_source_quality),
 113                     'url': video_source_url,
 114                 }
 115                 quality = self._QUALITIES.get(video_source_quality)
 116                 if quality:
 117                     f.update({
 118                         'abr': quality[0],
 119                         'height': quality[1],
 120                         'width': quality[2],
 121                     }),
 122                 formats.append(f)
 123         self._sort_formats(formats)
 124
 125         subtitles = {}
 126         sub_file_id = video.get('SubFileId')
 127         if sub_file_id and sub_file_id != '00000000-0000-0000-0000-000000000000':
 128             net_storage_path = video.get('NetstoragePath')
 129             invariant_id = video.get('InvariantId')
 130             video_file_id = video.get('VideoFileId')
 131             video_version = video.get('VideoVersion')
 132             if net_storage_path and invariant_id and video_file_id and video_version:
 133                 subtitles.setdefault(locale[:2], []).append({
 134                     '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),
 135                 })
 136
 137         return {
 138             'id': video_id,
 139             'title': title,
 140             'description': video.get('Description'),
 141             'thumbnail': video.get('GeneratedCoverImage') or video.get('GeneratedThumbnail'),
 142             'duration': int_or_none(video.get('Length')),
 143             'formats': formats,
 144             'subtitles': subtitles,
 145             'age_limit': int_or_none(video.get('AgeFrom')),
 146             'season': video.get('SeasonTitle'),
 147             'season_number': int_or_none(video.get('Season')) or None,
 148             'episode_number': int_or_none(video.get('Episode')) or None,
 149         }