yt_dlp/extractor/tv4.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     parse_iso8601,
   7 )
   8
   9
  10 class TV4IE(InfoExtractor):
  11     IE_DESC = 'tv4.se and tv4play.se'
  12     _VALID_URL = r'''(?x)https?://(?:www\.)?
  13         (?:
  14             tv4\.se/(?:[^/]+)/klipp/(?:.*)-|
  15             tv4play\.se/
  16             (?:
  17                 (?:program|barn)/(?:(?:[^/]+/){1,2}|(?:[^\?]+)\?video_id=)|
  18                 iframe/video/|
  19                 film/|
  20                 sport/|
  21             )
  22         )(?P<id>[0-9]+)'''
  23     _GEO_COUNTRIES = ['SE']
  24     _TESTS = [
  25         {
  26             'url': 'http://www.tv4.se/kalla-fakta/klipp/kalla-fakta-5-english-subtitles-2491650',
  27             'md5': 'cb837212f342d77cec06e6dad190e96d',
  28             'info_dict': {
  29                 'id': '2491650',
  30                 'ext': 'mp4',
  31                 'title': 'Kalla Fakta 5 (english subtitles)',
  32                 'thumbnail': r're:^https?://.*\.jpg$',
  33                 'timestamp': int,
  34                 'upload_date': '20131125',
  35             },
  36         },
  37         {
  38             'url': 'http://www.tv4play.se/iframe/video/3054113',
  39             'md5': 'cb837212f342d77cec06e6dad190e96d',
  40             'info_dict': {
  41                 'id': '3054113',
  42                 'ext': 'mp4',
  43                 'title': 'Så här jobbar ficktjuvarna - se avslöjande bilder',
  44                 'thumbnail': r're:^https?://.*\.jpg$',
  45                 'description': 'Unika bilder avslöjar hur turisternas fickor vittjas mitt på Stockholms central. Två experter på ficktjuvarna avslöjar knepen du ska se upp för.',
  46                 'timestamp': int,
  47                 'upload_date': '20150130',
  48             },
  49         },
  50         {
  51             'url': 'http://www.tv4play.se/sport/3060959',
  52             'only_matching': True,
  53         },
  54         {
  55             'url': 'http://www.tv4play.se/film/2378136',
  56             'only_matching': True,
  57         },
  58         {
  59             'url': 'http://www.tv4play.se/barn/looney-tunes?video_id=3062412',
  60             'only_matching': True,
  61         },
  62         {
  63             'url': 'http://www.tv4play.se/program/farang/3922081',
  64             'only_matching': True,
  65         },
  66         {
  67             'url': 'https://www.tv4play.se/program/nyheterna/avsnitt/13315940',
  68             'only_matching': True,
  69         }
  70     ]
  71
  72     def _real_extract(self, url):
  73         video_id = self._match_id(url)
  74
  75         info = self._download_json(
  76             'https://playback-api.b17g.net/asset/%s' % video_id,
  77             video_id, 'Downloading video info JSON', query={
  78                 'service': 'tv4',
  79                 'device': 'browser',
  80                 'protocol': 'hls,dash',
  81                 'drm': 'widevine',
  82             })['metadata']
  83
  84         title = info['title']
  85
  86         manifest_url = self._download_json(
  87             'https://playback-api.b17g.net/media/' + video_id,
  88             video_id, query={
  89                 'service': 'tv4',
  90                 'device': 'browser',
  91                 'protocol': 'hls',
  92             })['playbackItem']['manifestUrl']
  93         formats = []
  94         subtitles = {}
  95
  96         fmts, subs = self._extract_m3u8_formats_and_subtitles(
  97             manifest_url, video_id, 'mp4',
  98             'm3u8_native', m3u8_id='hls', fatal=False)
  99         formats.extend(fmts)
 100         subtitles = self._merge_subtitles(subtitles, subs)
 101
 102         fmts, subs = self._extract_mpd_formats_and_subtitles(
 103             manifest_url.replace('.m3u8', '.mpd'),
 104             video_id, mpd_id='dash', fatal=False)
 105         formats.extend(fmts)
 106         subtitles = self._merge_subtitles(subtitles, subs)
 107
 108         fmts = self._extract_f4m_formats(
 109             manifest_url.replace('.m3u8', '.f4m'),
 110             video_id, f4m_id='hds', fatal=False)
 111         formats.extend(fmts)
 112
 113         fmts, subs = self._extract_ism_formats_and_subtitles(
 114             re.sub(r'\.ism/.*?\.m3u8', r'.ism/Manifest', manifest_url),
 115             video_id, ism_id='mss', fatal=False)
 116         formats.extend(fmts)
 117         subtitles = self._merge_subtitles(subtitles, subs)
 118
 119         if not formats and info.get('is_geo_restricted'):
 120             self.raise_geo_restricted(countries=self._GEO_COUNTRIES, metadata_available=True)
 121
 122         return {
 123             'id': video_id,
 124             'title': title,
 125             'formats': formats,
 126             'subtitles': subtitles,
 127             'description': info.get('description'),
 128             'timestamp': parse_iso8601(info.get('broadcast_date_time')),
 129             'duration': int_or_none(info.get('duration')),
 130             'thumbnail': info.get('image'),
 131             'is_live': info.get('isLive') is True,
 132             'series': info.get('seriesTitle'),
 133             'season_number': int_or_none(info.get('seasonNumber')),
 134             'episode': info.get('episodeTitle'),
 135             'episode_number': int_or_none(info.get('episodeNumber')),
 136         }