yt_dlp/extractor/tv4.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     int_or_none,
   9     parse_iso8601,
  10 )
  11
  12
  13 class TV4IE(InfoExtractor):
  14     IE_DESC = 'tv4.se and tv4play.se'
  15     _VALID_URL = r'''(?x)https?://(?:www\.)?
  16         (?:
  17             tv4\.se/(?:[^/]+)/klipp/(?:.*)-|
  18             tv4play\.se/
  19             (?:
  20                 (?:program|barn)/(?:(?:[^/]+/){1,2}|(?:[^\?]+)\?video_id=)|
  21                 iframe/video/|
  22                 film/|
  23                 sport/|
  24             )
  25         )(?P<id>[0-9]+)'''
  26     _GEO_COUNTRIES = ['SE']
  27     _TESTS = [
  28         {
  29             'url': 'http://www.tv4.se/kalla-fakta/klipp/kalla-fakta-5-english-subtitles-2491650',
  30             'md5': 'cb837212f342d77cec06e6dad190e96d',
  31             'info_dict': {
  32                 'id': '2491650',
  33                 'ext': 'mp4',
  34                 'title': 'Kalla Fakta 5 (english subtitles)',
  35                 'thumbnail': r're:^https?://.*\.jpg$',
  36                 'timestamp': int,
  37                 'upload_date': '20131125',
  38             },
  39         },
  40         {
  41             'url': 'http://www.tv4play.se/iframe/video/3054113',
  42             'md5': 'cb837212f342d77cec06e6dad190e96d',
  43             'info_dict': {
  44                 'id': '3054113',
  45                 'ext': 'mp4',
  46                 'title': 'Så här jobbar ficktjuvarna - se avslöjande bilder',
  47                 'thumbnail': r're:^https?://.*\.jpg$',
  48                 'description': 'Unika bilder avslöjar hur turisternas fickor vittjas mitt på Stockholms central. Två experter på ficktjuvarna avslöjar knepen du ska se upp för.',
  49                 'timestamp': int,
  50                 'upload_date': '20150130',
  51             },
  52         },
  53         {
  54             'url': 'http://www.tv4play.se/sport/3060959',
  55             'only_matching': True,
  56         },
  57         {
  58             'url': 'http://www.tv4play.se/film/2378136',
  59             'only_matching': True,
  60         },
  61         {
  62             'url': 'http://www.tv4play.se/barn/looney-tunes?video_id=3062412',
  63             'only_matching': True,
  64         },
  65         {
  66             'url': 'http://www.tv4play.se/program/farang/3922081',
  67             'only_matching': True,
  68         },
  69         {
  70             'url': 'https://www.tv4play.se/program/nyheterna/avsnitt/13315940',
  71             'only_matching': True,
  72         }
  73     ]
  74
  75     def _real_extract(self, url):
  76         video_id = self._match_id(url)
  77
  78         info = self._download_json(
  79             'https://playback-api.b17g.net/asset/%s' % video_id,
  80             video_id, 'Downloading video info JSON', query={
  81                 'service': 'tv4',
  82                 'device': 'browser',
  83                 'protocol': 'hls,dash',
  84                 'drm': 'widevine',
  85             })['metadata']
  86
  87         title = info['title']
  88
  89         manifest_url = self._download_json(
  90             'https://playback-api.b17g.net/media/' + video_id,
  91             video_id, query={
  92                 'service': 'tv4',
  93                 'device': 'browser',
  94                 'protocol': 'hls',
  95             })['playbackItem']['manifestUrl']
  96         formats = []
  97         subtitles = {}
  98
  99         fmts, subs = self._extract_m3u8_formats_and_subtitles(
 100             manifest_url, video_id, 'mp4',
 101             'm3u8_native', m3u8_id='hls', fatal=False)
 102         formats.extend(fmts)
 103         subtitles = self._merge_subtitles(subtitles, subs)
 104
 105         fmts, subs = self._extract_mpd_formats_and_subtitles(
 106             manifest_url.replace('.m3u8', '.mpd'),
 107             video_id, mpd_id='dash', fatal=False)
 108         formats.extend(fmts)
 109         subtitles = self._merge_subtitles(subtitles, subs)
 110
 111         fmts = self._extract_f4m_formats(
 112             manifest_url.replace('.m3u8', '.f4m'),
 113             video_id, f4m_id='hds', fatal=False)
 114         formats.extend(fmts)
 115
 116         fmts, subs = self._extract_ism_formats_and_subtitles(
 117             re.sub(r'\.ism/.*?\.m3u8', r'.ism/Manifest', manifest_url),
 118             video_id, ism_id='mss', fatal=False)
 119         formats.extend(fmts)
 120         subtitles = self._merge_subtitles(subtitles, subs)
 121
 122         if not formats and info.get('is_geo_restricted'):
 123             self.raise_geo_restricted(countries=self._GEO_COUNTRIES, metadata_available=True)
 124
 125         self._sort_formats(formats)
 126
 127         return {
 128             'id': video_id,
 129             'title': title,
 130             'formats': formats,
 131             'subtitles': subtitles,
 132             'description': info.get('description'),
 133             'timestamp': parse_iso8601(info.get('broadcast_date_time')),
 134             'duration': int_or_none(info.get('duration')),
 135             'thumbnail': info.get('image'),
 136             'is_live': info.get('isLive') is True,
 137             'series': info.get('seriesTitle'),
 138             'season_number': int_or_none(info.get('seasonNumber')),
 139             'episode': info.get('episodeTitle'),
 140             'episode_number': int_or_none(info.get('episodeNumber')),
 141         }