yt_dlp/extractor/gmanetwork.py

   1 from .common import InfoExtractor
   2 from .dailymotion import DailymotionIE
   3 from .youtube import YoutubeIE
   4
   5
   6 class GMANetworkVideoIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www)\.gmanetwork\.com/(?:\w+/){3}(?P<id>\d+)/(?P<display_id>[\w-]+)/video'
   8     _TESTS = [{
   9         'url': 'https://www.gmanetwork.com/fullepisodes/home/running_man_philippines/168677/running-man-philippines-catch-the-thief-full-chapter-2/video?section=home',
  10         'info_dict': {
  11             'id': '28BqW0AXPe0',
  12             'ext': 'mp4',
  13             'upload_date': '20220919',
  14             'uploader_url': 'http://www.youtube.com/channel/UChsoPNR5x-wdSO2GrOSIWqQ',
  15             'like_count': int,
  16             'view_count': int,
  17             'uploader': 'YoüLOL',
  18             'channel_id': 'UChsoPNR5x-wdSO2GrOSIWqQ',
  19             'duration': 5313,
  20             'comment_count': int,
  21             'tags': 'count:22',
  22             'uploader_id': 'UChsoPNR5x-wdSO2GrOSIWqQ',
  23             'title': 'Running Man Philippines: Catch the Thief (FULL CHAPTER 2)',
  24             'channel_url': 'https://www.youtube.com/channel/UChsoPNR5x-wdSO2GrOSIWqQ',
  25             'thumbnail': 'https://i.ytimg.com/vi/28BqW0AXPe0/maxresdefault.jpg',
  26             'release_timestamp': 1663594212,
  27             'age_limit': 0,
  28             'channel_follower_count': int,
  29             'categories': ['Entertainment'],
  30             'description': 'md5:811bdcea74f9c48051824e494756e926',
  31             'live_status': 'not_live',
  32             'playable_in_embed': True,
  33             'channel': 'YoüLOL',
  34             'availability': 'public',
  35             'release_date': '20220919',
  36         },
  37     }, {
  38         'url': 'https://www.gmanetwork.com/fullepisodes/home/more_than_words/87059/more-than-words-full-episode-80/video?section=home',
  39         'info_dict': {
  40             'id': 'yiDOExw2aSA',
  41             'ext': 'mp4',
  42             'live_status': 'not_live',
  43             'channel': 'GMANetwork',
  44             'like_count': int,
  45             'channel_follower_count': int,
  46             'description': 'md5:6d00cd658394fa1a5071200d3ed4be05',
  47             'duration': 1419,
  48             'age_limit': 0,
  49             'comment_count': int,
  50             'upload_date': '20181003',
  51             'thumbnail': 'https://i.ytimg.com/vi_webp/yiDOExw2aSA/maxresdefault.webp',
  52             'availability': 'public',
  53             'playable_in_embed': True,
  54             'channel_id': 'UCKL5hAuzgFQsyrsQKgU0Qng',
  55             'title': 'More Than Words: Full Episode 80 (Finale)',
  56             'uploader_id': 'GMANETWORK',
  57             'categories': ['Entertainment'],
  58             'uploader': 'GMANetwork',
  59             'channel_url': 'https://www.youtube.com/channel/UCKL5hAuzgFQsyrsQKgU0Qng',
  60             'tags': 'count:29',
  61             'view_count': int,
  62             'uploader_url': 'http://www.youtube.com/user/GMANETWORK',
  63         },
  64     }]
  65
  66     def _real_extract(self, url):
  67         content_id, display_id = self._match_valid_url(url).group('id', 'display_id')
  68         webpage = self._download_webpage(url, display_id)
  69         # webpage route
  70         youtube_id = self._search_regex(
  71             r'var\s*YOUTUBE_VIDEO\s*=\s*[\'"]+(?P<yt_id>[\w-]+)', webpage, 'youtube_id', fatal=False)
  72         if youtube_id:
  73             return self.url_result(youtube_id, YoutubeIE, youtube_id)
  74
  75         # api call route
  76         # more info at https://aphrodite.gmanetwork.com/fullepisodes/assets/fullepisodes/js/dist/fullepisodes_video.js?v=1.1.11
  77         network_url = self._search_regex(
  78             r'NETWORK_URL\s*=\s*[\'"](?P<url>[^\'"]+)', webpage, 'network_url')
  79         json_data = self._download_json(f'{network_url}api/data/content/video/{content_id}', display_id)
  80         if json_data.get('video_file'):
  81             return self.url_result(json_data['video_file'], YoutubeIE, json_data['video_file'])
  82         else:
  83             return self.url_result(json_data['dailymotion_file'], DailymotionIE, json_data['dailymotion_file'])