diff options
Diffstat (limited to 'hypervideo_dl/extractor/urplay.py')
| -rw-r--r-- | hypervideo_dl/extractor/urplay.py | 53 |
1 files changed, 41 insertions, 12 deletions
diff --git a/hypervideo_dl/extractor/urplay.py b/hypervideo_dl/extractor/urplay.py index 753ffa4..eb2ab26 100644 --- a/hypervideo_dl/extractor/urplay.py +++ b/hypervideo_dl/extractor/urplay.py @@ -4,7 +4,11 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( dict_get, + ExtractorError, int_or_none, + ISO639Utils, + parse_age_limit, + try_get, unified_timestamp, ) @@ -23,9 +27,10 @@ class URPlayIE(InfoExtractor): 'upload_date': '20171214', 'series': 'UR Samtiden - Livet, universum och rymdens märkliga musik', 'duration': 2269, - 'categories': ['Kultur & historia'], + 'categories': ['Vetenskap & teknik'], 'tags': ['Kritiskt tänkande', 'Vetenskap', 'Vetenskaplig verksamhet'], 'episode': 'Om vetenskap, kritiskt tänkande och motstånd', + 'age_limit': 15, }, }, { 'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde', @@ -50,11 +55,16 @@ class URPlayIE(InfoExtractor): video_id = self._match_id(url) url = url.replace('skola.se/Produkter', 'play.se/program') webpage = self._download_webpage(url, video_id) - vid = int(video_id) - accessible_episodes = self._parse_json(self._html_search_regex( - r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"', - webpage, 'urplayer data'), video_id)['accessibleEpisodes'] - urplayer_data = next(e for e in accessible_episodes if e.get('id') == vid) + urplayer_data = self._search_nextjs_data(webpage, video_id, fatal=False) or {} + if urplayer_data: + urplayer_data = try_get(urplayer_data, lambda x: x['props']['pageProps']['program'], dict) + if not urplayer_data: + raise ExtractorError('Unable to parse __NEXT_DATA__') + else: + accessible_episodes = self._parse_json(self._html_search_regex( + r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"', + webpage, 'urplayer data'), video_id)['accessibleEpisodes'] + urplayer_data = next(e for e in accessible_episodes if e.get('id') == int_or_none(video_id)) episode = urplayer_data['title'] host = self._download_json('http://streaming-loadbalancer.ur.se/loadbalancer.json', video_id)['redirect'] @@ -72,11 +82,28 @@ class URPlayIE(InfoExtractor): self._sort_formats(formats) subtitles = {} - subs = urplayer_streams.get("sweComplete", {}).get("tt", {}).get("location") - if subs: - subtitles.setdefault('Svenska', []).append({ - 'url': subs, - }) + + def parse_lang_code(code): + "3-character language code or None (utils candidate)" + if code is None: + return + lang = code.lower() + if not ISO639Utils.long2short(lang): + lang = ISO639Utils.short2long(lang) + return lang or None + + for k, v in (urplayer_data['streamingInfo'].get('sweComplete') or {}).items(): + if (k in ('sd', 'hd') or not isinstance(v, dict)): + continue + lang, sttl_url = (v.get(kk) for kk in ('language', 'location', )) + if not sttl_url: + continue + lang = parse_lang_code(lang) + if not lang: + continue + sttl = subtitles.get(lang) or [] + sttl.append({'ext': k, 'url': sttl_url, }) + subtitles[lang] = sttl image = urplayer_data.get('image') or {} thumbnails = [] @@ -98,7 +125,6 @@ class URPlayIE(InfoExtractor): return { 'id': video_id, - 'subtitles': subtitles, 'title': '%s : %s' % (series_title, episode) if series_title else episode, 'description': urplayer_data.get('description'), 'thumbnails': thumbnails, @@ -111,4 +137,7 @@ class URPlayIE(InfoExtractor): 'season': series.get('label'), 'episode': episode, 'episode_number': int_or_none(urplayer_data.get('episodeNumber')), + 'age_limit': parse_age_limit(min(try_get(a, lambda x: x['from'], int) or 0 + for a in urplayer_data.get('ageRanges', []))), + 'subtitles': subtitles, } |