yt_dlp/extractor/malltv.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     dict_get,
   5     float_or_none,
   6     int_or_none,
   7     merge_dicts,
   8     parse_duration,
   9     try_get,
  10 )
  11
  12
  13 class MallTVIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:(?:www|sk)\.)?mall\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
  15     _TESTS = [{
  16         'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
  17         'md5': 'cd69ce29176f6533b65bff69ed9a5f2a',
  18         'info_dict': {
  19             'id': 't0zzt0',
  20             'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
  21             'ext': 'mp4',
  22             'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?',
  23             'description': 'md5:db7d5744a4bd4043d9d98324aa72ab35',
  24             'duration': 216,
  25             'timestamp': 1538870400,
  26             'upload_date': '20181007',
  27             'view_count': int,
  28             'comment_count': int,
  29             'thumbnail': 'https://cdn.vpplayer.tech/agmipnzv/encode/vjsnigfq/thumbnails/retina.jpg',
  30             'average_rating': 9.060869565217391,
  31             'dislike_count': int,
  32             'like_count': int,
  33         }
  34     }, {
  35         'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
  36         'only_matching': True,
  37     }, {
  38         'url': 'https://sk.mall.tv/gejmhaus/reklamacia-nehreje-vyrobnik-tepla-alebo-spekacka',
  39         'only_matching': True,
  40     }, {
  41         'url': 'https://www.mall.tv/zivoty-slavnych/nadeje-vychodu-i-zapadu-jak-michail-gorbacov-zmenil-politickou-mapu-sveta-a-ziskal-za-to-nobelovu-cenu-miru',
  42         'info_dict': {
  43             'id': 'yx010y',
  44             'ext': 'mp4',
  45             'dislike_count': int,
  46             'description': 'md5:aee02bee5a8d072c6a8207b91d1905a9',
  47             'thumbnail': 'https://cdn.vpplayer.tech/agmipnzv/encode/vjsnjdeu/thumbnails/retina.jpg',
  48             'comment_count': int,
  49             'display_id': 'md5:0ec2afa94d2e2b7091c019cef2a43a9b',
  50             'like_count': int,
  51             'duration': 752,
  52             'timestamp': 1646956800,
  53             'title': 'md5:fe79385daaf16d74c12c1ec4a26687af',
  54             'view_count': int,
  55             'upload_date': '20220311',
  56             'average_rating': 9.685714285714285,
  57         }
  58     }]
  59
  60     def _real_extract(self, url):
  61         display_id = self._match_id(url)
  62
  63         webpage = self._download_webpage(
  64             url, display_id, headers=self.geo_verification_headers())
  65
  66         video = self._parse_json(self._search_regex(
  67             r'videoObject\s*=\s*JSON\.parse\(JSON\.stringify\(({.+?})\)\);',
  68             webpage, 'video object'), display_id)
  69
  70         video_id = self._search_regex(
  71             r'<input\s*id\s*=\s*player-id-name\s*[^>]+value\s*=\s*(\w+)', webpage, 'video id')
  72
  73         formats = self._extract_m3u8_formats(
  74             video['VideoSource'], video_id, 'mp4', 'm3u8_native')
  75
  76         subtitles = {}
  77         for s in (video.get('Subtitles') or {}):
  78             s_url = s.get('Url')
  79             if not s_url:
  80                 continue
  81             subtitles.setdefault(s.get('Language') or 'cz', []).append({
  82                 'url': s_url,
  83             })
  84
  85         entity_counts = video.get('EntityCounts') or {}
  86
  87         def get_count(k):
  88             v = entity_counts.get(k + 's') or {}
  89             return int_or_none(dict_get(v, ('Count', 'StrCount')))
  90
  91         info = self._search_json_ld(webpage, video_id, default={})
  92
  93         return merge_dicts({
  94             'id': str(video_id),
  95             'display_id': display_id,
  96             'title': video.get('Title'),
  97             'description': clean_html(video.get('Description')),
  98             'thumbnail': video.get('ThumbnailUrl'),
  99             'formats': formats,
 100             'subtitles': subtitles,
 101             'duration': int_or_none(video.get('DurationSeconds')) or parse_duration(video.get('Duration')),
 102             'view_count': get_count('View'),
 103             'like_count': get_count('Like'),
 104             'dislike_count': get_count('Dislike'),
 105             'average_rating': float_or_none(try_get(video, lambda x: x['EntityRating']['AvarageRate'])),
 106             'comment_count': get_count('Comment'),
 107         }, info)