_ 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'''(?x)https?://(?:www\.)?(?:
  15             discovery|
  16             investigationdiscovery|
  17             discoverylife|
  18             animalplanet|
  19             ahctv|
  20             destinationamerica|
  21             sciencechannel|
  22             tlc|
  23             velocitychannel
  24         )go\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'''
  25     _TEST = {
  26         'url': 'https://www.discoverygo.com/love-at-first-kiss/kiss-first-ask-questions-later/',
  27         'info_dict': {
  28             'id': '57a33c536b66d1cd0345eeb1',
  29             'ext': 'mp4',
  30             'title': 'Kiss First, Ask Questions Later!',
  31             'description': 'md5:fe923ba34050eae468bffae10831cb22',
  32             'duration': 2579,
  33             'series': 'Love at First Kiss',
  34             'season_number': 1,
  35             'episode_number': 1,
  36             'age_limit': 14,
  37         },
  38     }
  39
  40     def _real_extract(self, url):
  41         display_id = self._match_id(url)
  42
  43         webpage = self._download_webpage(url, display_id)
  44
  45         container = extract_attributes(
  46             self._search_regex(
  47                 r'(<div[^>]+class=["\']video-player-container[^>]+>)',
  48                 webpage, 'video container'))
  49
  50         video = self._parse_json(
  51             unescapeHTML(container.get('data-video') or container.get('data-json')),
  52             display_id)
  53
  54         title = video['name']
  55
  56         stream = video['stream']
  57         STREAM_URL_SUFFIX = 'streamUrl'
  58         formats = []
  59         for stream_kind in ('', 'hds'):
  60             suffix = STREAM_URL_SUFFIX.capitalize() if stream_kind else STREAM_URL_SUFFIX
  61             stream_url = stream.get('%s%s' % (stream_kind, suffix))
  62             if not stream_url:
  63                 continue
  64             if stream_kind == '':
  65                 formats.extend(self._extract_m3u8_formats(
  66                     stream_url, display_id, 'mp4', entry_protocol='m3u8_native',
  67                     m3u8_id='hls', fatal=False))
  68             elif stream_kind == 'hds':
  69                 formats.extend(self._extract_f4m_formats(
  70                     stream_url, display_id, f4m_id=stream_kind, fatal=False))
  71         self._sort_formats(formats)
  72
  73         video_id = video.get('id') or display_id
  74         description = video.get('description', {}).get('detailed')
  75         duration = int_or_none(video.get('duration'))
  76
  77         series = video.get('show', {}).get('name')
  78         season_number = int_or_none(video.get('season', {}).get('number'))
  79         episode_number = int_or_none(video.get('episodeNumber'))
  80
  81         tags = video.get('tags')
  82         age_limit = parse_age_limit(video.get('parental', {}).get('rating'))
  83
  84         subtitles = {}
  85         captions = stream.get('captions')
  86         if isinstance(captions, list):
  87             for caption in captions:
  88                 subtitle_url = caption.get('fileUrl')
  89                 if (not subtitle_url or not isinstance(subtitle_url, compat_str) or
  90                         not subtitle_url.startswith('http')):
  91                     continue
  92                 lang = caption.get('fileLang', 'en')
  93                 subtitles.setdefault(lang, []).append({'url': subtitle_url})
  94
  95         return {
  96             'id': video_id,
  97             'display_id': display_id,
  98             'title': title,
  99             'description': description,
 100             'duration': duration,
 101             'series': series,
 102             'season_number': season_number,
 103             'episode_number': episode_number,
 104             'tags': tags,
 105             'age_limit': age_limit,
 106             'formats': formats,
 107             'subtitles': subtitles,
 108         }