_ Git - youtube-dl/blob - youtube_dl/extractor/discoverygo.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_str
   5 from ..utils import (
   6     extract_attributes,
   7     int_or_none,
   8     parse_age_limit,
   9     unescapeHTML,
  10 )
  11
  12
  13 class DiscoveryGoIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?discoverygo\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
  15     _TEST = {
  16         'url': 'https://www.discoverygo.com/love-at-first-kiss/kiss-first-ask-questions-later/',
  17         'info_dict': {
  18             'id': '57a33c536b66d1cd0345eeb1',
  19             'ext': 'mp4',
  20             'title': 'Kiss First, Ask Questions Later!',
  21             'description': 'md5:fe923ba34050eae468bffae10831cb22',
  22             'duration': 2579,
  23             'series': 'Love at First Kiss',
  24             'season_number': 1,
  25             'episode_number': 1,
  26             'age_limit': 14,
  27         },
  28     }
  29
  30     def _real_extract(self, url):
  31         display_id = self._match_id(url)
  32
  33         webpage = self._download_webpage(url, display_id)
  34
  35         container = extract_attributes(
  36             self._search_regex(
  37                 r'(<div[^>]+class=["\']video-player-container[^>]+>)',
  38                 webpage, 'video container'))
  39
  40         video = self._parse_json(
  41             unescapeHTML(container.get('data-video') or container.get('data-json')),
  42             display_id)
  43
  44         title = video['name']
  45
  46         stream = video['stream']
  47         STREAM_URL_SUFFIX = 'streamUrl'
  48         formats = []
  49         for stream_kind in ('', 'hds'):
  50             suffix = STREAM_URL_SUFFIX.capitalize() if stream_kind else STREAM_URL_SUFFIX
  51             stream_url = stream.get('%s%s' % (stream_kind, suffix))
  52             if not stream_url:
  53                 continue
  54             if stream_kind == '':
  55                 formats.extend(self._extract_m3u8_formats(
  56                     stream_url, display_id, 'mp4', entry_protocol='m3u8_native',
  57                     m3u8_id='hls', fatal=False))
  58             elif stream_kind == 'hds':
  59                 formats.extend(self._extract_f4m_formats(
  60                     stream_url, display_id, f4m_id=stream_kind, fatal=False))
  61         self._sort_formats(formats)
  62
  63         video_id = video.get('id') or display_id
  64         description = video.get('description', {}).get('detailed')
  65         duration = int_or_none(video.get('duration'))
  66
  67         series = video.get('show', {}).get('name')
  68         season_number = int_or_none(video.get('season', {}).get('number'))
  69         episode_number = int_or_none(video.get('episodeNumber'))
  70
  71         tags = video.get('tags')
  72         age_limit = parse_age_limit(video.get('parental', {}).get('rating'))
  73
  74         subtitles = {}
  75         captions = stream.get('captions')
  76         if isinstance(captions, list):
  77             for caption in captions:
  78                 subtitle_url = caption.get('fileUrl')
  79                 if (not subtitle_url or not isinstance(subtitle_url, compat_str) or
  80                         not subtitle_url.startswith('http')):
  81                     continue
  82                 lang = caption.get('fileLang', 'en')
  83                 subtitles.setdefault(lang, []).append({'url': subtitle_url})
  84
  85         return {
  86             'id': video_id,
  87             'display_id': display_id,
  88             'title': title,
  89             'description': description,
  90             'duration': duration,
  91             'series': series,
  92             'season_number': season_number,
  93             'episode_number': episode_number,
  94             'tags': tags,
  95             'age_limit': age_limit,
  96             'formats': formats,
  97             'subtitles': subtitles,
  98         }