yt_dlp/extractor/rtbf.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     float_or_none,
  10     int_or_none,
  11     strip_or_none,
  12 )
  13
  14
  15 class RTBFIE(InfoExtractor):
  16     _VALID_URL = r'''(?x)
  17         https?://(?:www\.)?rtbf\.be/
  18         (?:
  19             video/[^?]+\?.*\bid=|
  20             ouftivi/(?:[^/]+/)*[^?]+\?.*\bvideoId=|
  21             auvio/[^/]+\?.*\b(?P<live>l)?id=
  22         )(?P<id>\d+)'''
  23     _TESTS = [{
  24         'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274',
  25         'md5': '8c876a1cceeb6cf31b476461ade72384',
  26         'info_dict': {
  27             'id': '1921274',
  28             'ext': 'mp4',
  29             'title': 'Les Diables au coeur (épisode 2)',
  30             'description': '(du 25/04/2014)',
  31             'duration': 3099.54,
  32             'upload_date': '20140425',
  33             'timestamp': 1398456300,
  34         }
  35     }, {
  36         # geo restricted
  37         'url': 'http://www.rtbf.be/ouftivi/heros/detail_scooby-doo-mysteres-associes?id=1097&videoId=2057442',
  38         'only_matching': True,
  39     }, {
  40         'url': 'http://www.rtbf.be/ouftivi/niouzz?videoId=2055858',
  41         'only_matching': True,
  42     }, {
  43         'url': 'http://www.rtbf.be/auvio/detail_jeudi-en-prime-siegfried-bracke?id=2102996',
  44         'only_matching': True,
  45     }, {
  46         # Live
  47         'url': 'https://www.rtbf.be/auvio/direct_pure-fm?lid=134775',
  48         'only_matching': True,
  49     }, {
  50         # Audio
  51         'url': 'https://www.rtbf.be/auvio/detail_cinq-heures-cinema?id=2360811',
  52         'only_matching': True,
  53     }, {
  54         # With Subtitle
  55         'url': 'https://www.rtbf.be/auvio/detail_les-carnets-du-bourlingueur?id=2361588',
  56         'only_matching': True,
  57     }]
  58     _IMAGE_HOST = 'http://ds1.ds.static.rtbf.be'
  59     _PROVIDERS = {
  60         'YOUTUBE': 'Youtube',
  61         'DAILYMOTION': 'Dailymotion',
  62         'VIMEO': 'Vimeo',
  63     }
  64     _QUALITIES = [
  65         ('mobile', 'SD'),
  66         ('web', 'MD'),
  67         ('high', 'HD'),
  68     ]
  69
  70     def _real_extract(self, url):
  71         live, media_id = self._match_valid_url(url).groups()
  72         embed_page = self._download_webpage(
  73             'https://www.rtbf.be/auvio/embed/' + ('direct' if live else 'media'),
  74             media_id, query={'id': media_id})
  75         data = self._parse_json(self._html_search_regex(
  76             r'data-media="([^"]+)"', embed_page, 'media data'), media_id)
  77
  78         error = data.get('error')
  79         if error:
  80             raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
  81
  82         provider = data.get('provider')
  83         if provider in self._PROVIDERS:
  84             return self.url_result(data['url'], self._PROVIDERS[provider])
  85
  86         title = data['title']
  87         is_live = data.get('isLive')
  88         height_re = r'-(\d+)p\.'
  89         formats = []
  90
  91         m3u8_url = data.get('urlHlsAes128') or data.get('urlHls')
  92         if m3u8_url:
  93             formats.extend(self._extract_m3u8_formats(
  94                 m3u8_url, media_id, 'mp4', m3u8_id='hls', fatal=False))
  95
  96         fix_url = lambda x: x.replace('//rtbf-vod.', '//rtbf.') if '/geo/drm/' in x else x
  97         http_url = data.get('url')
  98         if formats and http_url and re.search(height_re, http_url):
  99             http_url = fix_url(http_url)
 100             for m3u8_f in formats[:]:
 101                 height = m3u8_f.get('height')
 102                 if not height:
 103                     continue
 104                 f = m3u8_f.copy()
 105                 del f['protocol']
 106                 f.update({
 107                     'format_id': m3u8_f['format_id'].replace('hls-', 'http-'),
 108                     'url': re.sub(height_re, '-%dp.' % height, http_url),
 109                 })
 110                 formats.append(f)
 111         else:
 112             sources = data.get('sources') or {}
 113             for key, format_id in self._QUALITIES:
 114                 format_url = sources.get(key)
 115                 if not format_url:
 116                     continue
 117                 height = int_or_none(self._search_regex(
 118                     height_re, format_url, 'height', default=None))
 119                 formats.append({
 120                     'format_id': format_id,
 121                     'url': fix_url(format_url),
 122                     'height': height,
 123                 })
 124
 125         mpd_url = data.get('urlDash')
 126         if mpd_url and (self.get_param('allow_unplayable_formats') or not data.get('drm')):
 127             formats.extend(self._extract_mpd_formats(
 128                 mpd_url, media_id, mpd_id='dash', fatal=False))
 129
 130         audio_url = data.get('urlAudio')
 131         if audio_url:
 132             formats.append({
 133                 'format_id': 'audio',
 134                 'url': audio_url,
 135                 'vcodec': 'none',
 136             })
 137         self._sort_formats(formats)
 138
 139         subtitles = {}
 140         for track in (data.get('tracks') or {}).values():
 141             sub_url = track.get('url')
 142             if not sub_url:
 143                 continue
 144             subtitles.setdefault(track.get('lang') or 'fr', []).append({
 145                 'url': sub_url,
 146             })
 147
 148         return {
 149             'id': media_id,
 150             'formats': formats,
 151             'title': title,
 152             'description': strip_or_none(data.get('description')),
 153             'thumbnail': data.get('thumbnail'),
 154             'duration': float_or_none(data.get('realDuration')),
 155             'timestamp': int_or_none(data.get('liveFrom')),
 156             'series': data.get('programLabel'),
 157             'subtitles': subtitles,
 158             'is_live': is_live,
 159         }