2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..compat import compat_str
17 class WatchBoxIE(InfoExtractor):
18 _VALID_URL = r'https?://(?:www\.)?watchbox\.de/(?P<kind>serien|filme)/(?:[^/]+/)*[^/]+-(?P<id>\d+)'
21 'url': 'https://www.watchbox.de/filme/free-jimmy-12325.html',
25 'title': 'Free Jimmy',
26 'description': 'md5:bcd8bafbbf9dc0ef98063d344d7cc5f6',
27 'thumbnail': r're:^https?://.*\.jpg$',
33 'format': 'bestvideo',
34 'skip_download': True,
36 'expected_warnings': ['Failed to download m3u8 information'],
39 'url': 'https://www.watchbox.de/serien/ugly-americans-12231/staffel-1/date-in-der-hoelle-328286.html',
43 'title': 'S01 E01 - Date in der Hölle',
44 'description': 'md5:2f31c74a8186899f33cb5114491dae2b',
45 'thumbnail': r're:^https?://.*\.jpg$',
49 'series': 'Ugly Americans',
51 'episode': 'Date in der Hölle',
55 'format': 'bestvideo',
56 'skip_download': True,
58 'expected_warnings': ['Failed to download m3u8 information'],
60 'url': 'https://www.watchbox.de/serien/ugly-americans-12231/staffel-2/der-ring-des-powers-328270',
61 'only_matching': True,
64 def _real_extract(self, url):
65 mobj = re.match(self._VALID_URL, url)
66 kind, video_id = mobj.group('kind', 'id')
68 webpage = self._download_webpage(url, video_id)
70 source = (self._parse_json(
72 r'playerConf\s*=\s*({.+?})\s*;', webpage, 'player config',
74 video_id, transform_source=js_to_json,
75 fatal=False) or {}).get('source') or {}
77 video_id = compat_str(source.get('videoId') or video_id)
79 devapi = self._download_json(
80 'http://api.watchbox.de/devapi/id/%s' % video_id, video_id, query={
85 item = try_get(devapi, lambda x: x['items'][0], dict) or {}
87 title = item.get('title') or try_get(
88 item, lambda x: x['movie']['headline_movie'],
89 compat_str) or source['title']
92 hls_url = item.get('media_videourl_hls') or source.get('hls')
94 formats.extend(self._extract_m3u8_formats(
95 hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
96 m3u8_id='hls', fatal=False))
97 dash_url = item.get('media_videourl_wv') or source.get('dash')
99 formats.extend(self._extract_mpd_formats(
100 dash_url, video_id, mpd_id='dash', fatal=False))
101 mp4_url = item.get('media_videourl')
106 'width': int_or_none(item.get('width')),
107 'height': int_or_none(item.get('height')),
108 'tbr': int_or_none(item.get('bitrate')),
110 self._sort_formats(formats)
112 description = strip_or_none(item.get('descr'))
113 thumbnail = item.get('media_content_thumbnail_large') or source.get('poster') or item.get('media_thumbnail')
114 duration = int_or_none(item.get('media_length') or source.get('length'))
115 timestamp = unified_timestamp(item.get('pubDate'))
116 view_count = int_or_none(item.get('media_views'))
117 age_limit = int_or_none(try_get(item, lambda x: x['movie']['fsk']))
118 release_year = int_or_none(try_get(item, lambda x: x['movie']['rel_year']))
123 'description': description,
124 'thumbnail': thumbnail,
125 'duration': duration,
126 'timestamp': timestamp,
127 'view_count': view_count,
128 'age_limit': age_limit,
129 'release_year': release_year,
133 if kind.lower() == 'serien':
135 item, lambda x: x['special']['title'],
136 compat_str) or source.get('format')
137 season_number = int_or_none(self._search_regex(
138 r'^S(\d{1,2})\s*E\d{1,2}', title, 'season number',
139 default=None) or self._search_regex(
140 r'/staffel-(\d+)/', url, 'season number', default=None))
141 episode = source.get('title')
142 episode_number = int_or_none(self._search_regex(
143 r'^S\d{1,2}\s*E(\d{1,2})', title, 'episode number',
147 'season_number': season_number,
149 'episode_number': episode_number,