+
+
+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
+ }
+
+
+class VPROIE(NPOIE):
+ IE_NAME = 'vpro'
+ _VALID_URL = r'https?://(?:www\.)?(?:tegenlicht\.)?vpro\.nl/(?:[^/]+/){2,}(?P<id>[^/]+)\.html'
+
+ _TESTS = [
+ {
+ 'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
+ 'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
+ 'info_dict': {
+ 'id': 'VPWON_1169289',
+ 'ext': 'm4v',
+ 'title': 'De toekomst komt uit Afrika',
+ 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
+ 'upload_date': '20130225',
+ },
+ },
+ {
+ 'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
+ 'info_dict': {
+ 'id': 'sergio-herman',
+ 'title': 'Sergio Herman: Fucking perfect',
+ },
+ 'playlist_count': 2,
+ },
+ {
+ # playlist with youtube embed
+ 'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
+ 'info_dict': {
+ 'id': 'education-education',
+ 'title': '2Doc',
+ },
+ 'playlist_count': 2,
+ }
+ ]
+
+ def _real_extract(self, url):
+ playlist_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, playlist_id)
+
+ entries = [
+ self.url_result('npo:%s' % video_id if not video_id.startswith('http') else video_id)
+ for video_id in re.findall(r'data-media-id="([^"]+)"', webpage)
+ ]
+
+ playlist_title = self._search_regex(
+ r'<title>\s*([^>]+?)\s*-\s*Teledoc\s*-\s*VPRO\s*</title>',
+ webpage, 'playlist title', default=None) or self._og_search_title(webpage)
+
+ return self.playlist_result(entries, playlist_id, playlist_title)
+
+
+class WNLIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
+
+ _TEST = {
+ 'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
+ 'info_dict': {
+ 'id': 'vandaag-de-dag-6-mei',
+ 'title': 'Vandaag de Dag 6 mei',
+ },
+ 'playlist_count': 4,
+ }
+
+ def _real_extract(self, url):
+ playlist_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, playlist_id)
+
+ entries = [
+ self.url_result('npo:%s' % video_id, 'NPO')
+ for video_id, part in re.findall(
+ r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>(Deel \d+)', webpage)
+ ]
+
+ playlist_title = self._html_search_regex(
+ r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>',
+ webpage, 'playlist title')
+
+ return self.playlist_result(entries, playlist_id, playlist_title)
Rapsys Git / youtubedl / blobdiff