Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/contv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     float_or_none,
   7     int_or_none,
   8 )
   9
  10
  11 class CONtvIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?contv\.com/details-movie/(?P<id>[^/]+)'
  13     _TESTS = [{
  14         'url': 'https://www.contv.com/details-movie/CEG10022949/days-of-thrills-&-laughter',
  15         'info_dict': {
  16             'id': 'CEG10022949',
  17             'ext': 'mp4',
  18             'title': 'Days Of Thrills & Laughter',
  19             'description': 'md5:5d6b3d0b1829bb93eb72898c734802eb',
  20             'upload_date': '20180703',
  21             'timestamp': 1530634789.61,
  22         },
  23         'params': {
  24             # m3u8 download
  25             'skip_download': True,
  26         },
  27     }, {
  28         'url': 'https://www.contv.com/details-movie/CLIP-show_fotld_bts/fight-of-the-living-dead:-behind-the-scenes-bites',
  29         'info_dict': {
  30             'id': 'CLIP-show_fotld_bts',
  31             'title': 'Fight of the Living Dead: Behind the Scenes Bites',
  32         },
  33         'playlist_mincount': 7,
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38         details = self._download_json(
  39             'http://metax.contv.live.junctiontv.net/metax/2.5/details/' + video_id,
  40             video_id, query={'device': 'web'})
  41
  42         if details.get('type') == 'episodic':
  43             seasons = self._download_json(
  44                 'http://metax.contv.live.junctiontv.net/metax/2.5/seriesfeed/json/' + video_id,
  45                 video_id)
  46             entries = []
  47             for season in seasons:
  48                 for episode in season.get('episodes', []):
  49                     episode_id = episode.get('id')
  50                     if not episode_id:
  51                         continue
  52                     entries.append(self.url_result(
  53                         'https://www.contv.com/details-movie/' + episode_id,
  54                         CONtvIE.ie_key(), episode_id))
  55             return self.playlist_result(entries, video_id, details.get('title'))
  56
  57         m_details = details['details']
  58         title = details['title']
  59
  60         formats = []
  61
  62         media_hls_url = m_details.get('media_hls_url')
  63         if media_hls_url:
  64             formats.extend(self._extract_m3u8_formats(
  65                 media_hls_url, video_id, 'mp4',
  66                 m3u8_id='hls', fatal=False))
  67
  68         media_mp4_url = m_details.get('media_mp4_url')
  69         if media_mp4_url:
  70             formats.append({
  71                 'format_id': 'http',
  72                 'url': media_mp4_url,
  73             })
  74
  75         self._sort_formats(formats)
  76
  77         subtitles = {}
  78         captions = m_details.get('captions') or {}
  79         for caption_url in captions.values():
  80             subtitles.setdefault('en', []).append({
  81                 'url': caption_url
  82             })
  83
  84         thumbnails = []
  85         for image in m_details.get('images', []):
  86             image_url = image.get('url')
  87             if not image_url:
  88                 continue
  89             thumbnails.append({
  90                 'url': image_url,
  91                 'width': int_or_none(image.get('width')),
  92                 'height': int_or_none(image.get('height')),
  93             })
  94
  95         description = None
  96         for p in ('large_', 'medium_', 'small_', ''):
  97             d = m_details.get(p + 'description')
  98             if d:
  99                 description = d
 100                 break
 101
 102         return {
 103             'id': video_id,
 104             'title': title,
 105             'formats': formats,
 106             'thumbnails': thumbnails,
 107             'description': description,
 108             'timestamp': float_or_none(details.get('metax_added_on'), 1000),
 109             'subtitles': subtitles,
 110             'duration': float_or_none(m_details.get('duration'), 1000),
 111             'view_count': int_or_none(details.get('num_watched')),
 112             'like_count': int_or_none(details.get('num_fav')),
 113             'categories': details.get('category'),
 114             'tags': details.get('tags'),
 115             'season_number': int_or_none(details.get('season')),
 116             'episode_number': int_or_none(details.get('episode')),
 117             'release_year': int_or_none(details.get('pub_year')),
 118         }