projects / yt-dlp.git / blame
| Commit | Line | Data |
|---|---|---|
| e496fa50 RA |
1 | # coding: utf-8 |
| 2 | from __future__ import unicode_literals | |
| 3 | ||
| 4 | from .common import InfoExtractor | |
| 8bdd16b4 | 5 | from ..utils import ( |
| 6 | dict_get, | |
| 7 | int_or_none, | |
| 8 | unified_timestamp, | |
| 9 | ) | |
| e496fa50 RA |
10 | |
| 11 | ||
| 12 | class URPlayIE(InfoExtractor): | |
| efb62429 RA |
13 | _VALID_URL = r'https?://(?:www\.)?ur(?:play|skola)\.se/(?:program|Produkter)/(?P<id>[0-9]+)' |
| 14 | _TESTS = [{ | |
| d347b52b | 15 | 'url': 'https://urplay.se/program/203704-ur-samtiden-livet-universum-och-rymdens-markliga-musik-om-vetenskap-kritiskt-tankande-och-motstand', |
| 16 | 'md5': 'ff5b0c89928f8083c74bbd5099c9292d', | |
| 17 | 'info_dict': { | |
| 18 | 'id': '203704', | |
| 19 | 'ext': 'mp4', | |
| 8bdd16b4 | 20 | 'title': 'UR Samtiden - Livet, universum och rymdens märkliga musik : Om vetenskap, kritiskt tänkande och motstånd', |
| d347b52b | 21 | 'description': 'md5:5344508a52aa78c1ced6c1b8b9e44e9a', |
| fb9c36c4 | 22 | 'timestamp': 1513292400, |
| 23 | 'upload_date': '20171214', | |
| d347b52b | 24 | }, |
| 25 | }, { | |
| 26 | 'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde', | |
| e496fa50 RA |
27 | 'info_dict': { |
| 28 | 'id': '190031', | |
| 29 | 'ext': 'mp4', | |
| 30 | 'title': 'Tripp, Trapp, Träd : Sovkudde', | |
| 31 | 'description': 'md5:b86bffdae04a7e9379d1d7e5947df1d1', | |
| 8bdd16b4 | 32 | 'timestamp': 1440086400, |
| d347b52b | 33 | 'upload_date': '20150820', |
| efb62429 RA |
34 | }, |
| 35 | }, { | |
| 36 | 'url': 'http://urskola.se/Produkter/155794-Smasagor-meankieli-Grodan-i-vida-varlden', | |
| 37 | 'only_matching': True, | |
| 38 | }] | |
| e496fa50 RA |
39 | |
| 40 | def _real_extract(self, url): | |
| 41 | video_id = self._match_id(url) | |
| 8bdd16b4 | 42 | url = url.replace('skola.se/Produkter', 'play.se/program') |
| e496fa50 | 43 | webpage = self._download_webpage(url, video_id) |
| 8bdd16b4 | 44 | urplayer_data = self._parse_json(self._html_search_regex( |
| cc2db878 | 45 | r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"', |
| 46 | webpage, 'urplayer data'), video_id)['accessibleEpisodes'][0] | |
| 8bdd16b4 | 47 | episode = urplayer_data['title'] |
| e496fa50 | 48 | |
| fb9c36c4 | 49 | host = self._download_json('http://streaming-loadbalancer.ur.se/loadbalancer.json', video_id)['redirect'] |
| e496fa50 | 50 | formats = [] |
| 8bdd16b4 | 51 | urplayer_streams = urplayer_data.get('streamingInfo', {}) |
| 52 | ||
| 53 | for k, v in urplayer_streams.get('raw', {}).items(): | |
| 54 | if not (k in ('sd', 'hd') and isinstance(v, dict)): | |
| 55 | continue | |
| 56 | file_http = v.get('location') | |
| 57 | if file_http: | |
| efb62429 | 58 | formats.extend(self._extract_wowza_formats( |
| 8bdd16b4 | 59 | 'http://%s/%splaylist.m3u8' % (host, file_http), |
| 60 | video_id, skip_protocols=['f4m', 'rtmp', 'rtsp'])) | |
| e496fa50 | 61 | self._sort_formats(formats) |
| 8bdd16b4 | 62 | |
| e496fa50 | 63 | subtitles = {} |
| fb9c36c4 | 64 | subs = urplayer_streams.get("sweComplete", {}).get("tt", {}).get("location") |
| 65 | if subs: | |
| 66 | subtitles.setdefault('Svenska', []).append({ | |
| 67 | 'url': subs, | |
| e496fa50 RA |
68 | }) |
| 69 | ||
| 8bdd16b4 | 70 | image = urplayer_data.get('image') or {} |
| 71 | thumbnails = [] | |
| 72 | for k, v in image.items(): | |
| 73 | t = { | |
| 74 | 'id': k, | |
| 75 | 'url': v, | |
| 76 | } | |
| 77 | wh = k.split('x') | |
| 78 | if len(wh) == 2: | |
| 79 | t.update({ | |
| 80 | 'width': int_or_none(wh[0]), | |
| 81 | 'height': int_or_none(wh[1]), | |
| 82 | }) | |
| 83 | thumbnails.append(t) | |
| 84 | ||
| 85 | series = urplayer_data.get('series') or {} | |
| 86 | series_title = dict_get(series, ('seriesTitle', 'title')) or dict_get(urplayer_data, ('seriesTitle', 'mainTitle')) | |
| 87 | ||
| e496fa50 RA |
88 | return { |
| 89 | 'id': video_id, | |
| e496fa50 | 90 | 'subtitles': subtitles, |
| 8bdd16b4 | 91 | 'title': '%s : %s' % (series_title, episode) if series_title else episode, |
| 92 | 'description': urplayer_data.get('description'), | |
| 93 | 'thumbnails': thumbnails, | |
| 94 | 'timestamp': unified_timestamp(urplayer_data.get('publishedAt')), | |
| 95 | 'series': series_title, | |
| e496fa50 | 96 | 'formats': formats, |
| 8bdd16b4 | 97 | 'duration': int_or_none(urplayer_data.get('duration')), |
| 98 | 'categories': urplayer_data.get('categories'), | |
| 99 | 'tags': urplayer_data.get('keywords'), | |
| 100 | 'season': series.get('label'), | |
| 101 | 'episode': episode, | |
| 102 | 'episode_number': int_or_none(urplayer_data.get('episodeNumber')), | |
| 4d86d200 | 103 | } |