+ # TODO: webvtt in m3u8
+ subtitles = {}
+ sami_path = video.get('sami_path')
+ if sami_path:
+ lang = self._search_regex(
+ r'_([a-z]{2})\.xml', sami_path, 'lang',
+ default=compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1])
+ subtitles[lang] = [{
+ 'url': sami_path,
+ }]
+
+ series = video.get('format_title')
+ episode_number = int_or_none(video.get('format_position', {}).get('episode'))
+ season = video.get('_embedded', {}).get('season', {}).get('title')
+ season_number = int_or_none(video.get('format_position', {}).get('season'))
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': video.get('description'),
+ 'series': series,
+ 'episode_number': episode_number,
+ 'season': season,
+ 'season_number': season_number,
+ 'duration': int_or_none(video.get('duration')),
+ 'timestamp': parse_iso8601(video.get('created_at')),
+ 'view_count': try_get(video, lambda x: x['views']['total'], int),
+ 'age_limit': int_or_none(video.get('age_limit', 0)),
+ 'formats': formats,
+ 'subtitles': subtitles,
+ }
+
+
+class ViafreeIE(InfoExtractor):
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:www\.)?
+ viafree\.
+ (?:
+ (?:dk|no)/programmer|
+ se/program
+ )
+ /(?:[^/]+/)+(?P<id>[^/?#&]+)
+ '''
+ _TESTS = [{
+ 'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2',
+ 'info_dict': {
+ 'id': '395375',
+ 'ext': 'mp4',
+ 'title': 'Husräddarna S02E02',
+ 'description': 'md5:4db5c933e37db629b5a2f75dfb34829e',
+ 'series': 'Husräddarna',
+ 'season': 'Säsong 2',
+ 'season_number': 2,
+ 'duration': 2576,
+ 'timestamp': 1400596321,
+ 'upload_date': '20140520',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'add_ie': [TVPlayIE.ie_key()],
+ }, {
+ # with relatedClips
+ 'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1',
+ 'info_dict': {
+ 'id': '758770',
+ 'ext': 'mp4',
+ 'title': 'Sommaren med YouTube-stjärnorna S01E01',
+ 'description': 'md5:2bc69dce2c4bb48391e858539bbb0e3f',
+ 'series': 'Sommaren med YouTube-stjärnorna',
+ 'season': 'Säsong 1',
+ 'season_number': 1,
+ 'duration': 1326,
+ 'timestamp': 1470905572,
+ 'upload_date': '20160811',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'add_ie': [TVPlayIE.ie_key()],
+ }, {
+ # Different og:image URL schema
+ 'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-2',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.viafree.dk/programmer/reality/paradise-hotel/saeson-7/episode-5',
+ 'only_matching': True,
+ }]
+
+ @classmethod
+ def suitable(cls, url):
+ return False if TVPlayIE.suitable(url) else super(ViafreeIE, cls).suitable(url)
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ data = self._parse_json(
+ self._search_regex(
+ r'(?s)window\.App\s*=\s*({.+?})\s*;\s*</script',
+ webpage, 'data', default='{}'),
+ video_id, transform_source=lambda x: re.sub(
+ r'(?s)function\s+[a-zA-Z_][\da-zA-Z_]*\s*\([^)]*\)\s*{[^}]*}\s*',
+ 'null', x), fatal=False)
+
+ video_id = None
+
+ if data:
+ video_id = try_get(
+ data, lambda x: x['context']['dispatcher']['stores'][
+ 'ContentPageProgramStore']['currentVideo']['id'],
+ compat_str)
+
+ # Fallback #1 (extract from og:image URL schema)
+ if not video_id:
+ thumbnail = self._og_search_thumbnail(webpage, default=None)
+ if thumbnail:
+ video_id = self._search_regex(
+ # Patterns seen:
+ # http://cdn.playapi.mtgx.tv/imagecache/600x315/cloud/content-images/inbox/765166/a2e95e5f1d735bab9f309fa345cc3f25.jpg
+ # http://cdn.playapi.mtgx.tv/imagecache/600x315/cloud/content-images/seasons/15204/758770/4a5ba509ca8bc043e1ebd1a76131cdf2.jpg
+ r'https?://[^/]+/imagecache/(?:[^/]+/)+(\d{6,})/',
+ thumbnail, 'video id', default=None)
+
+ # Fallback #2. Extract from raw JSON string.
+ # May extract wrong video id if relatedClips is present.
+ if not video_id:
+ video_id = self._search_regex(
+ r'currentVideo["\']\s*:\s*.+?["\']id["\']\s*:\s*["\'](\d{6,})',
+ webpage, 'video id')
+
+ return self.url_result(
+ smuggle_url(
+ 'mtg:%s' % video_id,
+ {
+ 'geo_countries': [
+ compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1]],
+ # rtmp host mtgfs.fplive.net for viafree is unresolvable
+ 'skip_rtmp': True,
+ }),
+ ie=TVPlayIE.ie_key(), video_id=video_id)
+
+
+class TVPlayHomeIE(InfoExtractor):
+ _VALID_URL = r'https?://tvplay\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/[^/]+/[^/?#&]+-(?P<id>\d+)'
+ _TESTS = [{
+ 'url': 'https://tvplay.tv3.lt/aferistai-n-7/aferistai-10047125/',
+ 'info_dict': {
+ 'id': '366367',
+ 'ext': 'mp4',
+ 'title': 'Aferistai',
+ 'description': 'Aferistai. Kalėdinė pasaka.',
+ 'series': 'Aferistai [N-7]',
+ 'season': '1 sezonas',
+ 'season_number': 1,
+ 'duration': 464,
+ 'timestamp': 1394209658,
+ 'upload_date': '20140307',
+ 'age_limit': 18,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'add_ie': [TVPlayIE.ie_key()],
+ }, {
+ 'url': 'https://tvplay.skaties.lv/vinas-melo-labak/vinas-melo-labak-10280317/',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://tvplay.tv3.ee/cool-d-ga-mehhikosse/cool-d-ga-mehhikosse-10044354/',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_id = self._search_regex(
+ r'data-asset-id\s*=\s*["\'](\d{5,7})\b', webpage, 'video id',
+ default=None)
+
+ if video_id:
+ return self.url_result(
+ 'mtg:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id)
+
+ m3u8_url = self._search_regex(
+ r'data-file\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+ 'm3u8 url', group='url')
+
+ formats = self._extract_m3u8_formats(
+ m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls')
+ self._sort_formats(formats)
+
+ title = self._search_regex(
+ r'data-title\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
+ 'title', default=None, group='value') or self._html_search_meta(
+ 'title', webpage, default=None) or self._og_search_title(
+ webpage)
+
+ description = self._html_search_meta(
+ 'description', webpage,
+ default=None) or self._og_search_description(webpage)
+
+ thumbnail = self._search_regex(
+ r'data-image\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+ 'thumbnail', default=None, group='url') or self._html_search_meta(
+ 'thumbnail', webpage, default=None) or self._og_search_thumbnail(
+ webpage)
+
+ duration = int_or_none(self._search_regex(
+ r'data-duration\s*=\s*["\'](\d+)', webpage, 'duration',
+ fatal=False))
+
+ season = self._search_regex(
+ (r'data-series-title\s*=\s*(["\'])[^/]+/(?P<value>(?:(?!\1).)+)\1',
+ r'\bseason\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
+ 'season', default=None, group='value')
+ season_number = int_or_none(self._search_regex(
+ r'(\d+)(?:[.\s]+sezona|\s+HOOAEG)', season or '', 'season number',
+ default=None))
+ episode = self._search_regex(
+ r'(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'episode',
+ default=None, group='value')
+ episode_number = int_or_none(self._search_regex(
+ r'(?:S[eē]rija|Osa)\s+(\d+)', episode or '', 'episode number',
+ default=None))
+
Rapsys Git / youtubedl / blobdiff