yt_dlp/extractor/tv2hu.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     traverse_obj,
   7     UnsupportedError,
   8 )
   9
  10
  11 class TV2HuIE(InfoExtractor):
  12     IE_NAME = 'tv2play.hu'
  13     _VALID_URL = r'https?://(?:www\.)?tv2play\.hu/(?!szalag/)(?P<id>[^#&?]+)'
  14     _TESTS = [{
  15         'url': 'https://tv2play.hu/mintaapak/mintaapak_213_epizod_resz',
  16         'info_dict': {
  17             'id': '249240',
  18             'ext': 'mp4',
  19             'title': 'Mintaapák - 213. epizód',
  20             'series': 'Mintaapák',
  21             'duration': 2164,
  22             'description': 'md5:7350147e75485a59598e806c47967b07',
  23             'thumbnail': r're:^https?://.*\.jpg$',
  24             'release_date': '20210825',
  25             'season_number': None,
  26             'episode_number': 213,
  27         },
  28         'params': {
  29             'skip_download': True,
  30         },
  31     }, {
  32         'url': 'https://tv2play.hu/taxi_2',
  33         'md5': '585e58e2e090f34603804bb2c48e98d8',
  34         'info_dict': {
  35             'id': '199363',
  36             'ext': 'mp4',
  37             'title': 'Taxi 2',
  38             'series': 'Taxi 2',
  39             'duration': 5087,
  40             'description': 'md5:47762155dc9a50241797ded101b1b08c',
  41             'thumbnail': r're:^https?://.*\.jpg$',
  42             'release_date': '20210118',
  43             'season_number': None,
  44             'episode_number': None,
  45         },
  46         'params': {
  47             'skip_download': True,
  48         },
  49     }]
  50
  51     def _real_extract(self, url):
  52         id = self._match_id(url)
  53         json_data = self._download_json(f'https://tv2play.hu/api/search/{id}', id)
  54
  55         if json_data['contentType'] == 'showpage':
  56             ribbon_ids = traverse_obj(json_data, ('pages', ..., 'tabs', ..., 'ribbonIds'), get_all=False, expected_type=list)
  57             entries = [self.url_result(f'https://tv2play.hu/szalag/{ribbon_id}',
  58                                        ie=TV2HuSeriesIE.ie_key(), video_id=ribbon_id) for ribbon_id in ribbon_ids]
  59             return self.playlist_result(entries, playlist_id=id)
  60         elif json_data['contentType'] != 'video':
  61             raise UnsupportedError(url)
  62
  63         video_id = str(json_data['id'])
  64         player_id = json_data.get('playerId')
  65         series_json = json_data.get('seriesInfo', {})
  66
  67         video_json_url = self._download_json(f'https://tv2play.hu/api/streaming-url?playerId={player_id}', video_id)['url']
  68         video_json = self._download_json(video_json_url, video_id)
  69         m3u8_url = self._proto_relative_url(traverse_obj(video_json, ('bitrates', 'hls')))
  70         formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id)
  71         self._sort_formats(formats)
  72
  73         return {
  74             'id': video_id,
  75             'title': json_data['title'],
  76             'series': json_data.get('seriesTitle'),
  77             'duration': json_data.get('length'),
  78             'description': json_data.get('description'),
  79             'thumbnail': 'https://tv2play.hu' + json_data.get('thumbnailUrl'),
  80             'release_date': json_data.get('uploadedAt').replace('.', ''),
  81             'season_number': series_json.get('seasonNr'),
  82             'episode_number': series_json.get('episodeNr'),
  83             'formats': formats,
  84             'subtitles': subtitles,
  85         }
  86
  87
  88 class TV2HuSeriesIE(InfoExtractor):
  89     IE_NAME = 'tv2playseries.hu'
  90     _VALID_URL = r'https?://(?:www\.)?tv2play\.hu/szalag/(?P<id>[^#&?]+)'
  91
  92     _TESTS = [{
  93         'url': 'https://tv2play.hu/szalag/59?rendezes=nepszeruseg',
  94         'playlist_mincount': 284,
  95         'info_dict': {
  96             'id': '59',
  97         }
  98     }]
  99
 100     def _real_extract(self, url):
 101         id = self._match_id(url)
 102         json_data = self._download_json(f'https://tv2play.hu/api/ribbons/{id}/0?size=100000', id)
 103         entries = []
 104         for card in json_data.get('cards', []):
 105             video_id = card.get('slug')
 106             if video_id:
 107                 entries.append(self.url_result(f'https://tv2play.hu/{video_id}',
 108                                                ie=TV2HuIE.ie_key(), video_id=video_id))
 109
 110         return self.playlist_result(entries, playlist_id=id)