yt_dlp/extractor/watchbox.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     int_or_none,
   5     js_to_json,
   6     strip_or_none,
   7     try_get,
   8     unescapeHTML,
   9     unified_timestamp,
  10 )
  11
  12
  13 class WatchBoxIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?watchbox\.de/(?P<kind>serien|filme)/(?:[^/]+/)*[^/]+-(?P<id>\d+)'
  15     _TESTS = [{
  16         # film
  17         'url': 'https://www.watchbox.de/filme/free-jimmy-12325.html',
  18         'info_dict': {
  19             'id': '341368',
  20             'ext': 'mp4',
  21             'title': 'Free Jimmy',
  22             'description': 'md5:bcd8bafbbf9dc0ef98063d344d7cc5f6',
  23             'thumbnail': r're:^https?://.*\.jpg$',
  24             'duration': 4890,
  25             'age_limit': 16,
  26             'release_year': 2009,
  27         },
  28         'params': {
  29             'skip_download': True,
  30         },
  31         'expected_warnings': ['Failed to download m3u8 information'],
  32     }, {
  33         # episode
  34         'url': 'https://www.watchbox.de/serien/ugly-americans-12231/staffel-1/date-in-der-hoelle-328286.html',
  35         'info_dict': {
  36             'id': '328286',
  37             'ext': 'mp4',
  38             'title': 'S01 E01 - Date in der Hölle',
  39             'description': 'md5:2f31c74a8186899f33cb5114491dae2b',
  40             'thumbnail': r're:^https?://.*\.jpg$',
  41             'duration': 1291,
  42             'age_limit': 12,
  43             'release_year': 2010,
  44             'series': 'Ugly Americans',
  45             'season_number': 1,
  46             'episode': 'Date in der Hölle',
  47             'episode_number': 1,
  48         },
  49         'params': {
  50             'skip_download': True,
  51         },
  52         'expected_warnings': ['Failed to download m3u8 information'],
  53     }, {
  54         'url': 'https://www.watchbox.de/serien/ugly-americans-12231/staffel-2/der-ring-des-powers-328270',
  55         'only_matching': True,
  56     }]
  57
  58     def _real_extract(self, url):
  59         mobj = self._match_valid_url(url)
  60         kind, video_id = mobj.group('kind', 'id')
  61
  62         webpage = self._download_webpage(url, video_id)
  63
  64         player_config = self._parse_json(
  65             self._search_regex(
  66                 r'data-player-conf=(["\'])(?P<data>{.+?})\1', webpage,
  67                 'player config', default='{}', group='data'),
  68             video_id, transform_source=unescapeHTML, fatal=False)
  69
  70         if not player_config:
  71             player_config = self._parse_json(
  72                 self._search_regex(
  73                     r'playerConf\s*=\s*({.+?})\s*;', webpage, 'player config',
  74                     default='{}'),
  75                 video_id, transform_source=js_to_json, fatal=False) or {}
  76
  77         source = player_config.get('source') or {}
  78
  79         video_id = compat_str(source.get('videoId') or video_id)
  80
  81         devapi = self._download_json(
  82             'http://api.watchbox.de/devapi/id/%s' % video_id, video_id, query={
  83                 'format': 'json',
  84                 'apikey': 'hbbtv',
  85             }, fatal=False)
  86
  87         item = try_get(devapi, lambda x: x['items'][0], dict) or {}
  88
  89         title = item.get('title') or try_get(
  90             item, lambda x: x['movie']['headline_movie'],
  91             compat_str) or source['title']
  92
  93         formats = []
  94         hls_url = item.get('media_videourl_hls') or source.get('hls')
  95         if hls_url:
  96             formats.extend(self._extract_m3u8_formats(
  97                 hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
  98                 m3u8_id='hls', fatal=False))
  99         dash_url = item.get('media_videourl_wv') or source.get('dash')
 100         if dash_url:
 101             formats.extend(self._extract_mpd_formats(
 102                 dash_url, video_id, mpd_id='dash', fatal=False))
 103         mp4_url = item.get('media_videourl')
 104         if mp4_url:
 105             formats.append({
 106                 'url': mp4_url,
 107                 'format_id': 'mp4',
 108                 'width': int_or_none(item.get('width')),
 109                 'height': int_or_none(item.get('height')),
 110                 'tbr': int_or_none(item.get('bitrate')),
 111             })
 112
 113         description = strip_or_none(item.get('descr'))
 114         thumbnail = item.get('media_content_thumbnail_large') or source.get('poster') or item.get('media_thumbnail')
 115         duration = int_or_none(item.get('media_length') or source.get('length'))
 116         timestamp = unified_timestamp(item.get('pubDate'))
 117         view_count = int_or_none(item.get('media_views'))
 118         age_limit = int_or_none(try_get(item, lambda x: x['movie']['fsk']))
 119         release_year = int_or_none(try_get(item, lambda x: x['movie']['rel_year']))
 120
 121         info = {
 122             'id': video_id,
 123             'title': title,
 124             'description': description,
 125             'thumbnail': thumbnail,
 126             'duration': duration,
 127             'timestamp': timestamp,
 128             'view_count': view_count,
 129             'age_limit': age_limit,
 130             'release_year': release_year,
 131             'formats': formats,
 132         }
 133
 134         if kind.lower() == 'serien':
 135             series = try_get(
 136                 item, lambda x: x['special']['title'],
 137                 compat_str) or source.get('format')
 138             season_number = int_or_none(self._search_regex(
 139                 r'^S(\d{1,2})\s*E\d{1,2}', title, 'season number',
 140                 default=None) or self._search_regex(
 141                     r'/staffel-(\d+)/', url, 'season number', default=None))
 142             episode = source.get('title')
 143             episode_number = int_or_none(self._search_regex(
 144                 r'^S\d{1,2}\s*E(\d{1,2})', title, 'episode number',
 145                 default=None))
 146             info.update({
 147                 'series': series,
 148                 'season_number': season_number,
 149                 'episode': episode,
 150                 'episode_number': episode_number,
 151             })
 152
 153         return info