+
+
+class DPlayItIE(InfoExtractor):
+ _VALID_URL = r'https?://it\.dplay\.com/[^/]+/[^/]+/(?P<id>[^/?#]+)'
+ _GEO_COUNTRIES = ['IT']
+ _TEST = {
+ 'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/',
+ 'md5': '2b808ffb00fc47b884a172ca5d13053c',
+ 'info_dict': {
+ 'id': '6918',
+ 'display_id': 'luigi-di-maio-la-psicosi-di-stanislawskij',
+ 'ext': 'mp4',
+ 'title': 'Biografie imbarazzanti: Luigi Di Maio: la psicosi di Stanislawskij',
+ 'description': 'md5:3c7a4303aef85868f867a26f5cc14813',
+ 'thumbnail': r're:^https?://.*\.jpe?g',
+ 'upload_date': '20160524',
+ 'series': 'Biografie imbarazzanti',
+ 'season_number': 1,
+ 'episode': 'Luigi Di Maio: la psicosi di Stanislawskij',
+ 'episode_number': 1,
+ },
+ }
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, display_id)
+
+ title = remove_end(self._og_search_title(webpage), ' | Dplay')
+
+ video_id = None
+
+ info = self._search_regex(
+ r'playback_json\s*:\s*JSON\.parse\s*\(\s*("(?:\\.|[^"\\])+?")',
+ webpage, 'playback JSON', default=None)
+ if info:
+ for _ in range(2):
+ info = self._parse_json(info, display_id, fatal=False)
+ if not info:
+ break
+ else:
+ video_id = try_get(info, lambda x: x['data']['id'])
+
+ if not info:
+ info_url = self._search_regex(
+ (r'playback_json_url\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
+ r'url\s*[:=]\s*["\'](?P<url>(?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)'),
+ webpage, 'info url', group='url')
+
+ info_url = urljoin(url, info_url)
+ video_id = info_url.rpartition('/')[-1]
+
+ try:
+ info = self._download_json(
+ info_url, display_id, headers={
+ 'Authorization': 'Bearer %s' % self._get_cookies(url).get(
+ 'dplayit_token').value,
+ 'Referer': url,
+ })
+ if isinstance(info, compat_str):
+ info = self._parse_json(info, display_id)
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403):
+ info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
+ error = info['errors'][0]
+ if error.get('code') == 'access.denied.geoblocked':
+ self.raise_geo_restricted(
+ msg=error.get('detail'), countries=self._GEO_COUNTRIES)
+ raise ExtractorError(info['errors'][0]['detail'], expected=True)
+ raise
+
+ hls_url = info['data']['attributes']['streaming']['hls']['url']
+
+ formats = self._extract_m3u8_formats(
+ hls_url, display_id, ext='mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls')
+ self._sort_formats(formats)
+
+ series = self._html_search_regex(
+ r'(?s)<h1[^>]+class=["\'].*?\bshow_title\b.*?["\'][^>]*>(.+?)</h1>',
+ webpage, 'series', fatal=False)
+ episode = self._search_regex(
+ r'<p[^>]+class=["\'].*?\bdesc_ep\b.*?["\'][^>]*>\s*<br/>\s*<b>([^<]+)',
+ webpage, 'episode', fatal=False)
+
+ mobj = re.search(
+ r'(?s)<span[^>]+class=["\']dates["\'][^>]*>.+?\bS\.(?P<season_number>\d+)\s+E\.(?P<episode_number>\d+)\s*-\s*(?P<upload_date>\d{2}/\d{2}/\d{4})',
+ webpage)
+ if mobj:
+ season_number = int(mobj.group('season_number'))
+ episode_number = int(mobj.group('episode_number'))
+ upload_date = unified_strdate(mobj.group('upload_date'))
+ else:
+ season_number = episode_number = upload_date = None
+
+ return {
+ 'id': compat_str(video_id or display_id),
+ 'display_id': display_id,
+ 'title': title,
+ 'description': self._og_search_description(webpage),
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ 'series': series,
+ 'season_number': season_number,
+ 'episode': episode,
+ 'episode_number': episode_number,
+ 'upload_date': upload_date,
+ 'formats': formats,
+ }
Rapsys Git / youtubedl / blobdiff