yt_dlp/extractor/contv.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     float_or_none,
   4     int_or_none,
   5 )
   6
   7
   8 class CONtvIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?contv\.com/details-movie/(?P<id>[^/]+)'
  10     _TESTS = [{
  11         'url': 'https://www.contv.com/details-movie/CEG10022949/days-of-thrills-&-laughter',
  12         'info_dict': {
  13             'id': 'CEG10022949',
  14             'ext': 'mp4',
  15             'title': 'Days Of Thrills & Laughter',
  16             'description': 'md5:5d6b3d0b1829bb93eb72898c734802eb',
  17             'upload_date': '20180703',
  18             'timestamp': 1530634789.61,
  19         },
  20         'params': {
  21             # m3u8 download
  22             'skip_download': True,
  23         },
  24     }, {
  25         'url': 'https://www.contv.com/details-movie/CLIP-show_fotld_bts/fight-of-the-living-dead:-behind-the-scenes-bites',
  26         'info_dict': {
  27             'id': 'CLIP-show_fotld_bts',
  28             'title': 'Fight of the Living Dead: Behind the Scenes Bites',
  29         },
  30         'playlist_mincount': 7,
  31     }]
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35         details = self._download_json(
  36             'http://metax.contv.live.junctiontv.net/metax/2.5/details/' + video_id,
  37             video_id, query={'device': 'web'})
  38
  39         if details.get('type') == 'episodic':
  40             seasons = self._download_json(
  41                 'http://metax.contv.live.junctiontv.net/metax/2.5/seriesfeed/json/' + video_id,
  42                 video_id)
  43             entries = []
  44             for season in seasons:
  45                 for episode in season.get('episodes', []):
  46                     episode_id = episode.get('id')
  47                     if not episode_id:
  48                         continue
  49                     entries.append(self.url_result(
  50                         'https://www.contv.com/details-movie/' + episode_id,
  51                         CONtvIE.ie_key(), episode_id))
  52             return self.playlist_result(entries, video_id, details.get('title'))
  53
  54         m_details = details['details']
  55         title = details['title']
  56
  57         formats = []
  58
  59         media_hls_url = m_details.get('media_hls_url')
  60         if media_hls_url:
  61             formats.extend(self._extract_m3u8_formats(
  62                 media_hls_url, video_id, 'mp4',
  63                 m3u8_id='hls', fatal=False))
  64
  65         media_mp4_url = m_details.get('media_mp4_url')
  66         if media_mp4_url:
  67             formats.append({
  68                 'format_id': 'http',
  69                 'url': media_mp4_url,
  70             })
  71
  72         subtitles = {}
  73         captions = m_details.get('captions') or {}
  74         for caption_url in captions.values():
  75             subtitles.setdefault('en', []).append({
  76                 'url': caption_url,
  77             })
  78
  79         thumbnails = []
  80         for image in m_details.get('images', []):
  81             image_url = image.get('url')
  82             if not image_url:
  83                 continue
  84             thumbnails.append({
  85                 'url': image_url,
  86                 'width': int_or_none(image.get('width')),
  87                 'height': int_or_none(image.get('height')),
  88             })
  89
  90         description = None
  91         for p in ('large_', 'medium_', 'small_', ''):
  92             d = m_details.get(p + 'description')
  93             if d:
  94                 description = d
  95                 break
  96
  97         return {
  98             'id': video_id,
  99             'title': title,
 100             'formats': formats,
 101             'thumbnails': thumbnails,
 102             'description': description,
 103             'timestamp': float_or_none(details.get('metax_added_on'), 1000),
 104             'subtitles': subtitles,
 105             'duration': float_or_none(m_details.get('duration'), 1000),
 106             'view_count': int_or_none(details.get('num_watched')),
 107             'like_count': int_or_none(details.get('num_fav')),
 108             'categories': details.get('category'),
 109             'tags': details.get('tags'),
 110             'season_number': int_or_none(details.get('season')),
 111             'episode_number': int_or_none(details.get('episode')),
 112             'release_year': int_or_none(details.get('pub_year')),
 113         }