- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
- part_id = mobj.group('part_id')
- baseurl = mobj.group('baseurl')
-
- webpage = self._download_webpage(url, video_id)
-
- title = self._html_search_meta(
- 'title', webpage, 'title')
- description = self._html_search_meta(
- 'description', webpage, 'description')
-
- thumbnail = self._html_search_regex(
- r'data-posterimage="([^"]+)"',
- webpage, 'thumbnail', fatal=False)
- upload_date = unified_strdate(self._html_search_meta(
- 'rightsfrom', webpage, 'upload date', fatal=False))
- duration = float_or_none(self._html_search_regex(
- r'data-duration="([^"]+)"',
- webpage, 'duration', fatal=False))
-
- # playlist
- parts = re.findall(
- r'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage)
- if parts:
- entries = []
- for current_part_id, stream_url, part_title in parts:
- if part_id and current_part_id != part_id:
- continue
- video_part_id = '%s-part%s' % (video_id, current_part_id)
- formats = self._extract_f4m(stream_url, video_part_id)
- entries.append({
- 'id': video_part_id,
- 'title': part_title,
- 'description': description,
- 'thumbnail': thumbnail,
- 'upload_date': upload_date,
- 'formats': formats,
- })
- if part_id:
- if entries:
- return entries[0]
- else:
- playlist = self.playlist_result(entries, video_id, title, description)
- playlist.update({
- 'thumbnail': thumbnail,
- 'upload_date': upload_date,
- 'duration': duration,
- })
- return playlist
-
- formats = []
-
- f4m_url = re.search(r'data-media="([^"]+)"', webpage)
- if f4m_url:
- formats.extend(self._extract_f4m(f4m_url.group(1), video_id))
-
- m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage)
- if m3u8_url:
- formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4'))
- self._sort_formats(formats)
-
- subtitles_url = self._html_search_regex(
- r'data-subtitlesurl[ ]*=[ ]*"([^"]+)"',
- webpage, 'subtitle URL', default=None)
- subtitles = None
- if subtitles_url:
- subtitles = self._extract_captions(subtitles_url, video_id, baseurl)
- if self._downloader.params.get('listsubtitles', False):
- self._list_available_subtitles(video_id, subtitles)
- return
-
- return {
- 'id': video_id,
- 'title': title,
- 'description': description,
- 'thumbnail': thumbnail,
- 'upload_date': upload_date,
- 'duration': duration,
- 'formats': formats,
- 'subtitles': subtitles,
- }
+ playlist_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, playlist_id)
+
+ entries = [
+ self.url_result('nrk:%s' % video_id, 'NRK')
+ for video_id in re.findall(
+ r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
+ webpage)
+ ]
+
+ playlist_title = self._og_search_title(webpage)
+ playlist_description = self._og_search_description(webpage)
+
+ return self.playlist_result(
+ entries, playlist_id, playlist_title, playlist_description)
+
+
+class NRKSkoleIE(InfoExtractor):
+ IE_DESC = 'NRK Skole'
+ _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'
+
+ _TESTS = [{
+ 'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
+ 'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6',
+ 'info_dict': {
+ 'id': '6021',
+ 'ext': 'mp4',
+ 'title': 'Genetikk og eneggede tvillinger',
+ 'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
+ 'duration': 399,
+ },
+ }, {
+ 'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(
+ 'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id,
+ video_id)
+
+ nrk_id = self._parse_json(
+ self._search_regex(
+ r'<script[^>]+type=["\']application/json["\'][^>]*>({.+?})</script>',
+ webpage, 'application json'),
+ video_id)['activeMedia']['psId']
+
+ return self.url_result('nrk:%s' % nrk_id)
Rapsys Git / youtubedl / blobdiff