+ 'subtitles': subtitles,
+ 'is_live': is_live,
+ }
+
+
+class NPOLiveIE(NPOBaseIE):
+ IE_NAME = 'npo.nl:live'
+ _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P<id>[^/?#&]+))?'
+
+ _TESTS = [{
+ 'url': 'http://www.npo.nl/live/npo-1',
+ 'info_dict': {
+ 'id': 'LI_NL1_4188102',
+ 'display_id': 'npo-1',
+ 'ext': 'mp4',
+ 'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+ 'is_live': True,
+ },
+ 'params': {
+ 'skip_download': True,
+ }
+ }, {
+ 'url': 'http://www.npo.nl/live',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.npostart.nl/live/npo-1',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url) or 'npo-1'
+
+ webpage = self._download_webpage(url, display_id)
+
+ live_id = self._search_regex(
+ [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')
+
+ return {
+ '_type': 'url_transparent',
+ 'url': 'npo:%s' % live_id,
+ 'ie_key': NPOIE.ie_key(),
+ 'id': live_id,
+ 'display_id': display_id,
+ }
+
+
+class NPORadioIE(InfoExtractor):
+ IE_NAME = 'npo.nl:radio'
+ _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)'
+
+ _TEST = {
+ 'url': 'http://www.npo.nl/radio/radio-1',
+ 'info_dict': {
+ 'id': 'radio-1',
+ 'ext': 'mp3',
+ 'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+ 'is_live': True,
+ },
+ 'params': {
+ 'skip_download': True,
+ }
+ }
+
+ @classmethod
+ def suitable(cls, url):
+ return False if NPORadioFragmentIE.suitable(url) else super(NPORadioIE, cls).suitable(url)
+
+ @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 NPODataMidEmbedIE(InfoExtractor):
+ 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).)+)\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