+class ARDMediathekBaseIE(InfoExtractor):
+ _GEO_COUNTRIES = ['DE']
+
+ def _extract_media_info(self, media_info_url, webpage, video_id):
+ media_info = self._download_json(
+ media_info_url, video_id, 'Downloading media JSON')
+ return self._parse_media_info(media_info, video_id, '"fsk"' in webpage)
+
+ def _parse_media_info(self, media_info, video_id, fsk):
+ formats = self._extract_formats(media_info, video_id)
+
+ if not formats:
+ if fsk:
+ raise ExtractorError(
+ 'This video is only available after 20:00', expected=True)
+ elif media_info.get('_geoblocked'):
+ self.raise_geo_restricted(
+ 'This video is not available due to geoblocking',
+ countries=self._GEO_COUNTRIES)
+
+ self._sort_formats(formats)
+
+ subtitles = {}
+ subtitle_url = media_info.get('_subtitleUrl')
+ if subtitle_url:
+ subtitles['de'] = [{
+ 'ext': 'ttml',
+ 'url': subtitle_url,
+ }]
+
+ return {
+ 'id': video_id,
+ 'duration': int_or_none(media_info.get('_duration')),
+ 'thumbnail': media_info.get('_previewImage'),
+ 'is_live': media_info.get('_isLive') is True,
+ 'formats': formats,
+ 'subtitles': subtitles,
+ }
+
+ def _extract_formats(self, media_info, video_id):
+ type_ = media_info.get('_type')
+ media_array = media_info.get('_mediaArray', [])
+ formats = []
+ for num, media in enumerate(media_array):
+ for stream in media.get('_mediaStreamArray', []):
+ stream_urls = stream.get('_stream')
+ if not stream_urls:
+ continue
+ if not isinstance(stream_urls, list):
+ stream_urls = [stream_urls]
+ quality = stream.get('_quality')
+ server = stream.get('_server')
+ for stream_url in stream_urls:
+ if not url_or_none(stream_url):
+ continue
+ ext = determine_ext(stream_url)
+ if quality != 'auto' and ext in ('f4m', 'm3u8'):
+ continue
+ if ext == 'f4m':
+ formats.extend(self._extract_f4m_formats(
+ update_url_query(stream_url, {
+ 'hdcore': '3.1.1',
+ 'plugin': 'aasp-3.1.1.69.124'
+ }), video_id, f4m_id='hds', fatal=False))
+ elif ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ stream_url, video_id, 'mp4', 'm3u8_native',
+ m3u8_id='hls', fatal=False))
+ else:
+ if server and server.startswith('rtmp'):
+ f = {
+ 'url': server,
+ 'play_path': stream_url,
+ 'format_id': 'a%s-rtmp-%s' % (num, quality),
+ }
+ else:
+ f = {
+ 'url': stream_url,
+ 'format_id': 'a%s-%s-%s' % (num, ext, quality)
+ }
+ m = re.search(
+ r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$',
+ stream_url)
+ if m:
+ f.update({
+ 'width': int(m.group('width')),
+ 'height': int(m.group('height')),
+ })
+ if type_ == 'audio':
+ f['vcodec'] = 'none'
+ formats.append(f)
+ return formats
+
+
+class ARDMediathekIE(ARDMediathekBaseIE):
+ IE_NAME = 'ARD:mediathek'
+ _VALID_URL = r'^https?://(?:(?:(?:www|classic)\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
Rapsys Git / youtubedl / blobdiff