yt_dlp/extractor/rtbf.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     float_or_none,
   7     int_or_none,
   8     strip_or_none,
   9 )
  10
  11
  12 class RTBFIE(InfoExtractor):
  13     _VALID_URL = r'''(?x)
  14         https?://(?:www\.)?rtbf\.be/
  15         (?:
  16             video/[^?]+\?.*\bid=|
  17             ouftivi/(?:[^/]+/)*[^?]+\?.*\bvideoId=|
  18             auvio/[^/]+\?.*\b(?P<live>l)?id=
  19         )(?P<id>\d+)'''
  20     _TESTS = [{
  21         'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274',
  22         'md5': '8c876a1cceeb6cf31b476461ade72384',
  23         'info_dict': {
  24             'id': '1921274',
  25             'ext': 'mp4',
  26             'title': 'Les Diables au coeur (épisode 2)',
  27             'description': '(du 25/04/2014)',
  28             'duration': 3099.54,
  29             'upload_date': '20140425',
  30             'timestamp': 1398456300,
  31         }
  32     }, {
  33         # geo restricted
  34         'url': 'http://www.rtbf.be/ouftivi/heros/detail_scooby-doo-mysteres-associes?id=1097&videoId=2057442',
  35         'only_matching': True,
  36     }, {
  37         'url': 'http://www.rtbf.be/ouftivi/niouzz?videoId=2055858',
  38         'only_matching': True,
  39     }, {
  40         'url': 'http://www.rtbf.be/auvio/detail_jeudi-en-prime-siegfried-bracke?id=2102996',
  41         'only_matching': True,
  42     }, {
  43         # Live
  44         'url': 'https://www.rtbf.be/auvio/direct_pure-fm?lid=134775',
  45         'only_matching': True,
  46     }, {
  47         # Audio
  48         'url': 'https://www.rtbf.be/auvio/detail_cinq-heures-cinema?id=2360811',
  49         'only_matching': True,
  50     }, {
  51         # With Subtitle
  52         'url': 'https://www.rtbf.be/auvio/detail_les-carnets-du-bourlingueur?id=2361588',
  53         'only_matching': True,
  54     }]
  55     _IMAGE_HOST = 'http://ds1.ds.static.rtbf.be'
  56     _PROVIDERS = {
  57         'YOUTUBE': 'Youtube',
  58         'DAILYMOTION': 'Dailymotion',
  59         'VIMEO': 'Vimeo',
  60     }
  61     _QUALITIES = [
  62         ('mobile', 'SD'),
  63         ('web', 'MD'),
  64         ('high', 'HD'),
  65     ]
  66
  67     def _real_extract(self, url):
  68         live, media_id = self._match_valid_url(url).groups()
  69         embed_page = self._download_webpage(
  70             'https://www.rtbf.be/auvio/embed/' + ('direct' if live else 'media'),
  71             media_id, query={'id': media_id})
  72         data = self._parse_json(self._html_search_regex(
  73             r'data-media="([^"]+)"', embed_page, 'media data'), media_id)
  74
  75         error = data.get('error')
  76         if error:
  77             raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
  78
  79         provider = data.get('provider')
  80         if provider in self._PROVIDERS:
  81             return self.url_result(data['url'], self._PROVIDERS[provider])
  82
  83         title = data['title']
  84         is_live = data.get('isLive')
  85         height_re = r'-(\d+)p\.'
  86         formats = []
  87
  88         m3u8_url = data.get('urlHlsAes128') or data.get('urlHls')
  89         if m3u8_url:
  90             formats.extend(self._extract_m3u8_formats(
  91                 m3u8_url, media_id, 'mp4', m3u8_id='hls', fatal=False))
  92
  93         fix_url = lambda x: x.replace('//rtbf-vod.', '//rtbf.') if '/geo/drm/' in x else x
  94         http_url = data.get('url')
  95         if formats and http_url and re.search(height_re, http_url):
  96             http_url = fix_url(http_url)
  97             for m3u8_f in formats[:]:
  98                 height = m3u8_f.get('height')
  99                 if not height:
 100                     continue
 101                 f = m3u8_f.copy()
 102                 del f['protocol']
 103                 f.update({
 104                     'format_id': m3u8_f['format_id'].replace('hls-', 'http-'),
 105                     'url': re.sub(height_re, '-%dp.' % height, http_url),
 106                 })
 107                 formats.append(f)
 108         else:
 109             sources = data.get('sources') or {}
 110             for key, format_id in self._QUALITIES:
 111                 format_url = sources.get(key)
 112                 if not format_url:
 113                     continue
 114                 height = int_or_none(self._search_regex(
 115                     height_re, format_url, 'height', default=None))
 116                 formats.append({
 117                     'format_id': format_id,
 118                     'url': fix_url(format_url),
 119                     'height': height,
 120                 })
 121
 122         mpd_url = data.get('urlDash')
 123         if mpd_url and (self.get_param('allow_unplayable_formats') or not data.get('drm')):
 124             formats.extend(self._extract_mpd_formats(
 125                 mpd_url, media_id, mpd_id='dash', fatal=False))
 126
 127         audio_url = data.get('urlAudio')
 128         if audio_url:
 129             formats.append({
 130                 'format_id': 'audio',
 131                 'url': audio_url,
 132                 'vcodec': 'none',
 133             })
 134         self._sort_formats(formats)
 135
 136         subtitles = {}
 137         for track in (data.get('tracks') or {}).values():
 138             sub_url = track.get('url')
 139             if not sub_url:
 140                 continue
 141             subtitles.setdefault(track.get('lang') or 'fr', []).append({
 142                 'url': sub_url,
 143             })
 144
 145         return {
 146             'id': media_id,
 147             'formats': formats,
 148             'title': title,
 149             'description': strip_or_none(data.get('description')),
 150             'thumbnail': data.get('thumbnail'),
 151             'duration': float_or_none(data.get('realDuration')),
 152             'timestamp': int_or_none(data.get('liveFrom')),
 153             'series': data.get('programLabel'),
 154             'subtitles': subtitles,
 155             'is_live': is_live,
 156         }