yt_dlp/extractor/watchbox.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     int_or_none,
   9     js_to_json,
  10     strip_or_none,
  11     try_get,
  12     unescapeHTML,
  13     unified_timestamp,
  14 )
  15
  16
  17 class WatchBoxIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?watchbox\.de/(?P<kind>serien|filme)/(?:[^/]+/)*[^/]+-(?P<id>\d+)'
  19     _TESTS = [{
  20         # film
  21         'url': 'https://www.watchbox.de/filme/free-jimmy-12325.html',
  22         'info_dict': {
  23             'id': '341368',
  24             'ext': 'mp4',
  25             'title': 'Free Jimmy',
  26             'description': 'md5:bcd8bafbbf9dc0ef98063d344d7cc5f6',
  27             'thumbnail': r're:^https?://.*\.jpg$',
  28             'duration': 4890,
  29             'age_limit': 16,
  30             'release_year': 2009,
  31         },
  32         'params': {
  33             'skip_download': True,
  34         },
  35         'expected_warnings': ['Failed to download m3u8 information'],
  36     }, {
  37         # episode
  38         'url': 'https://www.watchbox.de/serien/ugly-americans-12231/staffel-1/date-in-der-hoelle-328286.html',
  39         'info_dict': {
  40             'id': '328286',
  41             'ext': 'mp4',
  42             'title': 'S01 E01 - Date in der Hölle',
  43             'description': 'md5:2f31c74a8186899f33cb5114491dae2b',
  44             'thumbnail': r're:^https?://.*\.jpg$',
  45             'duration': 1291,
  46             'age_limit': 12,
  47             'release_year': 2010,
  48             'series': 'Ugly Americans',
  49             'season_number': 1,
  50             'episode': 'Date in der Hölle',
  51             'episode_number': 1,
  52         },
  53         'params': {
  54             'skip_download': True,
  55         },
  56         'expected_warnings': ['Failed to download m3u8 information'],
  57     }, {
  58         'url': 'https://www.watchbox.de/serien/ugly-americans-12231/staffel-2/der-ring-des-powers-328270',
  59         'only_matching': True,
  60     }]
  61
  62     def _real_extract(self, url):
  63         mobj = self._match_valid_url(url)
  64         kind, video_id = mobj.group('kind', 'id')
  65
  66         webpage = self._download_webpage(url, video_id)
  67
  68         player_config = self._parse_json(
  69             self._search_regex(
  70                 r'data-player-conf=(["\'])(?P<data>{.+?})\1', webpage,
  71                 'player config', default='{}', group='data'),
  72             video_id, transform_source=unescapeHTML, fatal=False)
  73
  74         if not player_config:
  75             player_config = self._parse_json(
  76                 self._search_regex(
  77                     r'playerConf\s*=\s*({.+?})\s*;', webpage, 'player config',
  78                     default='{}'),
  79                 video_id, transform_source=js_to_json, fatal=False) or {}
  80
  81         source = player_config.get('source') or {}
  82
  83         video_id = compat_str(source.get('videoId') or video_id)
  84
  85         devapi = self._download_json(
  86             'http://api.watchbox.de/devapi/id/%s' % video_id, video_id, query={
  87                 'format': 'json',
  88                 'apikey': 'hbbtv',
  89             }, fatal=False)
  90
  91         item = try_get(devapi, lambda x: x['items'][0], dict) or {}
  92
  93         title = item.get('title') or try_get(
  94             item, lambda x: x['movie']['headline_movie'],
  95             compat_str) or source['title']
  96
  97         formats = []
  98         hls_url = item.get('media_videourl_hls') or source.get('hls')
  99         if hls_url:
 100             formats.extend(self._extract_m3u8_formats(
 101                 hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
 102                 m3u8_id='hls', fatal=False))
 103         dash_url = item.get('media_videourl_wv') or source.get('dash')
 104         if dash_url:
 105             formats.extend(self._extract_mpd_formats(
 106                 dash_url, video_id, mpd_id='dash', fatal=False))
 107         mp4_url = item.get('media_videourl')
 108         if mp4_url:
 109             formats.append({
 110                 'url': mp4_url,
 111                 'format_id': 'mp4',
 112                 'width': int_or_none(item.get('width')),
 113                 'height': int_or_none(item.get('height')),
 114                 'tbr': int_or_none(item.get('bitrate')),
 115             })
 116         self._sort_formats(formats)
 117
 118         description = strip_or_none(item.get('descr'))
 119         thumbnail = item.get('media_content_thumbnail_large') or source.get('poster') or item.get('media_thumbnail')
 120         duration = int_or_none(item.get('media_length') or source.get('length'))
 121         timestamp = unified_timestamp(item.get('pubDate'))
 122         view_count = int_or_none(item.get('media_views'))
 123         age_limit = int_or_none(try_get(item, lambda x: x['movie']['fsk']))
 124         release_year = int_or_none(try_get(item, lambda x: x['movie']['rel_year']))
 125
 126         info = {
 127             'id': video_id,
 128             'title': title,
 129             'description': description,
 130             'thumbnail': thumbnail,
 131             'duration': duration,
 132             'timestamp': timestamp,
 133             'view_count': view_count,
 134             'age_limit': age_limit,
 135             'release_year': release_year,
 136             'formats': formats,
 137         }
 138
 139         if kind.lower() == 'serien':
 140             series = try_get(
 141                 item, lambda x: x['special']['title'],
 142                 compat_str) or source.get('format')
 143             season_number = int_or_none(self._search_regex(
 144                 r'^S(\d{1,2})\s*E\d{1,2}', title, 'season number',
 145                 default=None) or self._search_regex(
 146                     r'/staffel-(\d+)/', url, 'season number', default=None))
 147             episode = source.get('title')
 148             episode_number = int_or_none(self._search_regex(
 149                 r'^S\d{1,2}\s*E(\d{1,2})', title, 'episode number',
 150                 default=None))
 151             info.update({
 152                 'series': series,
 153                 'season_number': season_number,
 154                 'episode': episode,
 155                 'episode_number': episode_number,
 156             })
 157
 158         return info