+ 'subtitles': subtitles,
+ }
+
+
+class NPOLiveIE(NPOBaseIE):
+ IE_NAME = 'npo.nl:live'
+ _VALID_URL = r'https?://(?:www\.)?npo\.nl/live/(?P<id>.+)'
+
+ _TEST = {
+ 'url': 'http://www.npo.nl/live/npo-1',
+ 'info_dict': {
+ 'id': 'LI_NEDERLAND1_136692',
+ 'display_id': 'npo-1',
+ 'ext': 'mp4',
+ 'title': 're:^Nederland 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+ 'description': 'Livestream',
+ 'is_live': True,
+ },
+ 'params': {
+ 'skip_download': True,
+ }
+ }
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, display_id)
+
+ live_id = self._search_regex(
+ r'data-prid="([^"]+)"', webpage, 'live id')
+
+ metadata = self._download_json(
+ 'http://e.omroep.nl/metadata/%s' % live_id,
+ display_id, transform_source=strip_jsonp)
+
+ token = self._get_token(display_id)
+
+ formats = []
+
+ streams = metadata.get('streams')
+ if streams:
+ for stream in streams:
+ stream_type = stream.get('type').lower()
+ # smooth streaming is not supported
+ if stream_type in ['ss', 'ms']:
+ continue
+ stream_info = self._download_json(
+ 'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp'
+ % (stream.get('url'), token),
+ display_id, 'Downloading %s JSON' % stream_type)
+ if stream_info.get('error_code', 0) or stream_info.get('errorcode', 0):
+ continue
+ stream_url = self._download_json(
+ stream_info['stream'], display_id,
+ 'Downloading %s URL' % stream_type,
+ 'Unable to download %s URL' % stream_type,
+ transform_source=strip_jsonp, fatal=False)
+ if not stream_url:
+ continue
+ if stream_type == 'hds':
+ f4m_formats = self._extract_f4m_formats(stream_url, display_id)
+ # f4m downloader downloads only piece of live stream
+ for f4m_format in f4m_formats:
+ f4m_format['preference'] = -1
+ formats.extend(f4m_formats)
+ elif stream_type == 'hls':
+ formats.extend(self._extract_m3u8_formats(stream_url, display_id, 'mp4'))
+ else:
+ formats.append({
+ 'url': stream_url,
+ 'preference': -10,
+ })
+
+ self._sort_formats(formats)
+
+ return {
+ 'id': live_id,
+ 'display_id': display_id,
+ 'title': self._live_title(metadata['titel']),
+ 'description': metadata['info'],
+ 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
+ 'formats': formats,
+ 'is_live': True,
+ }
+
+
+class NPORadioIE(InfoExtractor):
+ IE_NAME = 'npo.nl:radio'
+ _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)/?$'
+
+ _TEST = {
+ 'url': 'http://www.npo.nl/radio/radio-1',
+ 'info_dict': {
+ 'id': 'radio-1',
+ 'ext': 'mp3',
+ 'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+ 'is_live': True,
+ },
+ 'params': {
+ 'skip_download': True,
+ }
+ }
+
+ @staticmethod
+ def _html_get_attribute_regex(attribute):
+ return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ title = self._html_search_regex(
+ self._html_get_attribute_regex('data-channel'), webpage, 'title')
+
+ stream = self._parse_json(
+ self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
+ video_id)
+
+ codec = stream.get('codec')
+
+ return {
+ 'id': video_id,
+ 'url': stream['url'],
+ 'title': self._live_title(title),
+ 'acodec': codec,
+ 'ext': codec,
+ 'is_live': True,
+ }
+
+
+class NPORadioFragmentIE(InfoExtractor):
+ IE_NAME = 'npo.nl:radio:fragment'
+ _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
+
+ _TEST = {
+ 'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
+ 'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
+ 'info_dict': {
+ 'id': '174356',
+ 'ext': 'mp3',
+ 'title': 'Jubileumconcert Willeke Alberti',
+ },
+ }
+
+ def _real_extract(self, url):
+ audio_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, audio_id)
+
+ title = self._html_search_regex(
+ r'href="/radio/[^/]+/fragment/%s" title="([^"]+)"' % audio_id,
+ webpage, 'title')
+
+ audio_url = self._search_regex(
+ r"data-streams='([^']+)'", webpage, 'audio url')
+
+ return {
+ 'id': audio_id,
+ 'url': audio_url,
+ 'title': title,
+ }
+
+
+class SchoolTVIE(InfoExtractor):
+ IE_NAME = 'schooltv'
+ _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
+
+ _TEST = {
+ 'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/',
+ 'info_dict': {
+ 'id': 'WO_NTR_429477',
+ 'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
+ 'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?',
+ 'ext': 'mp4',
+ 'description': 'md5:abfa0ff690adb73fd0297fd033aaa631'
+ },
+ 'params': {
+ # Skip because of m3u8 download
+ 'skip_download': True
+ }
+ }
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+ webpage = self._download_webpage(url, display_id)
+ video_id = self._search_regex(
+ r'data-mid=(["\'])(?P<id>.+?)\1', webpage, 'video_id', group='id')
+ return {
+ '_type': 'url_transparent',
+ 'ie_key': 'NPO',
+ 'url': 'npo:%s' % video_id,
+ 'display_id': display_id
Rapsys Git / youtubedl / blobdiff