yt_dlp/extractor/tvigle.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     float_or_none,
   5     int_or_none,
   6     parse_age_limit,
   7     try_get,
   8     url_or_none,
   9 )
  10
  11
  12 class TvigleIE(InfoExtractor):
  13     IE_NAME = 'tvigle'
  14     IE_DESC = 'Интернет-телевидение Tvigle.ru'
  15     _VALID_URL = r'https?://(?:www\.)?(?:tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$|cloud\.tvigle\.ru/video/(?P<id>\d+))'
  16     _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1']
  17
  18     _GEO_BYPASS = False
  19     _GEO_COUNTRIES = ['RU']
  20
  21     _TESTS = [
  22         {
  23             'url': 'http://www.tvigle.ru/video/sokrat/',
  24             'info_dict': {
  25                 'id': '1848932',
  26                 'display_id': 'sokrat',
  27                 'ext': 'mp4',
  28                 'title': 'Сократ',
  29                 'description': 'md5:d6b92ffb7217b4b8ebad2e7665253c17',
  30                 'duration': 6586,
  31                 'age_limit': 12,
  32             },
  33             'skip': 'georestricted',
  34         },
  35         {
  36             'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/',
  37             'info_dict': {
  38                 'id': '5142516',
  39                 'ext': 'flv',
  40                 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком',
  41                 'description': 'md5:027f7dc872948f14c96d19b4178428a4',
  42                 'duration': 186.080,
  43                 'age_limit': 0,
  44             },
  45             'skip': 'georestricted',
  46         }, {
  47             'url': 'https://cloud.tvigle.ru/video/5267604/',
  48             'only_matching': True,
  49         },
  50     ]
  51
  52     def _real_extract(self, url):
  53         mobj = self._match_valid_url(url)
  54         video_id = mobj.group('id')
  55         display_id = mobj.group('display_id')
  56
  57         if not video_id:
  58             webpage = self._download_webpage(url, display_id)
  59             video_id = self._html_search_regex(
  60                 (r'<div[^>]+class=["\']player["\'][^>]+id=["\'](\d+)',
  61                  r'cloudId\s*=\s*["\'](\d+)',
  62                  r'class="video-preview current_playing" id="(\d+)"'),
  63                 webpage, 'video id')
  64
  65         video_data = self._download_json(
  66             f'http://cloud.tvigle.ru/api/play/video/{video_id}/', display_id)
  67
  68         item = video_data['playlist']['items'][0]
  69
  70         videos = item.get('videos')
  71
  72         error_message = item.get('errorMessage')
  73         if not videos and error_message:
  74             if item.get('isGeoBlocked') is True:
  75                 self.raise_geo_restricted(
  76                     msg=error_message, countries=self._GEO_COUNTRIES)
  77             else:
  78                 raise ExtractorError(
  79                     f'{self.IE_NAME} returned error: {error_message}',
  80                     expected=True)
  81
  82         title = item['title']
  83         description = item.get('description')
  84         thumbnail = item.get('thumbnail')
  85         duration = float_or_none(item.get('durationMilliseconds'), 1000)
  86         age_limit = parse_age_limit(item.get('ageRestrictions'))
  87
  88         formats = []
  89         for vcodec, url_or_fmts in item['videos'].items():
  90             if vcodec == 'hls':
  91                 m3u8_url = url_or_none(url_or_fmts)
  92                 if not m3u8_url:
  93                     continue
  94                 formats.extend(self._extract_m3u8_formats(
  95                     m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native',
  96                     m3u8_id='hls', fatal=False))
  97             elif vcodec == 'dash':
  98                 mpd_url = url_or_none(url_or_fmts)
  99                 if not mpd_url:
 100                     continue
 101                 formats.extend(self._extract_mpd_formats(
 102                     mpd_url, video_id, mpd_id='dash', fatal=False))
 103             else:
 104                 if not isinstance(url_or_fmts, dict):
 105                     continue
 106                 for format_id, video_url in url_or_fmts.items():
 107                     if format_id == 'm3u8':
 108                         continue
 109                     video_url = url_or_none(video_url)
 110                     if not video_url:
 111                         continue
 112                     height = self._search_regex(
 113                         r'^(\d+)[pP]$', format_id, 'height', default=None)
 114                     filesize = int_or_none(try_get(
 115                         item, lambda x: x['video_files_size'][vcodec][format_id]))
 116                     formats.append({
 117                         'url': video_url,
 118                         'format_id': f'{vcodec}-{format_id}',
 119                         'vcodec': vcodec,
 120                         'height': int_or_none(height),
 121                         'filesize': filesize,
 122                     })
 123
 124         return {
 125             'id': video_id,
 126             'display_id': display_id,
 127             'title': title,
 128             'description': description,
 129             'thumbnail': thumbnail,
 130             'duration': duration,
 131             'age_limit': age_limit,
 132             'formats': formats,
 133         }