2 from __future__
import unicode_literals
5 from .common
import InfoExtractor
6 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
= self
._match
_valid
_url
(url
)
66 kind
, video_id
= mobj
.group('kind', 'id')
68 webpage
= self
._download
_webpage
(url
, video_id
)
70 player_config
= self
._parse
_json
(
72 r
'data-player-conf=(["\'])(?P
<data
>{.+?}
)\
1', webpage,
73 'player config
', default='{}', group='data
'),
74 video_id, transform_source=unescapeHTML, fatal=False)
77 player_config = self._parse_json(
79 r'playerConf\s
*=\s
*({.+?}
)\s
*;', webpage, 'player config
',
81 video_id, transform_source=js_to_json, fatal=False) or {}
83 source = player_config.get('source
') or {}
85 video_id = compat_str(source.get('videoId
') or video_id)
87 devapi = self._download_json(
88 'http
://api
.watchbox
.de
/devapi
/id/%s' % video_id, video_id, query={
93 item = try_get(devapi, lambda x: x['items
'][0], dict) or {}
95 title = item.get('title
') or try_get(
96 item, lambda x: x['movie
']['headline_movie
'],
97 compat_str) or source['title
']
100 hls_url = item.get('media_videourl_hls
') or source.get('hls
')
102 formats.extend(self._extract_m3u8_formats(
103 hls_url, video_id, 'mp4
', entry_protocol='m3u8_native
',
104 m3u8_id='hls
', fatal=False))
105 dash_url = item.get('media_videourl_wv
') or source.get('dash
')
107 formats.extend(self._extract_mpd_formats(
108 dash_url, video_id, mpd_id='dash
', fatal=False))
109 mp4_url = item.get('media_videourl
')
114 'width
': int_or_none(item.get('width
')),
115 'height
': int_or_none(item.get('height
')),
116 'tbr
': int_or_none(item.get('bitrate
')),
118 self._sort_formats(formats)
120 description = strip_or_none(item.get('descr
'))
121 thumbnail = item.get('media_content_thumbnail_large
') or source.get('poster
') or item.get('media_thumbnail
')
122 duration = int_or_none(item.get('media_length
') or source.get('length
'))
123 timestamp = unified_timestamp(item.get('pubDate
'))
124 view_count = int_or_none(item.get('media_views
'))
125 age_limit = int_or_none(try_get(item, lambda x: x['movie
']['fsk
']))
126 release_year = int_or_none(try_get(item, lambda x: x['movie
']['rel_year
']))
131 'description
': description,
132 'thumbnail
': thumbnail,
133 'duration
': duration,
134 'timestamp
': timestamp,
135 'view_count
': view_count,
136 'age_limit
': age_limit,
137 'release_year
': release_year,
141 if kind.lower() == 'serien
':
143 item, lambda x: x['special
']['title
'],
144 compat_str) or source.get('format
')
145 season_number = int_or_none(self._search_regex(
146 r'^
S(\d{1,2}
)\s
*E\d{1,2}
', title, 'season number
',
147 default=None) or self._search_regex(
148 r'/staffel
-(\d
+)/', url, 'season number
', default=None))
149 episode = source.get('title
')
150 episode_number = int_or_none(self._search_regex(
151 r'^S\d{1,2}\s
*E(\d{1,2}
)', title, 'episode number
',
155 'season_number
': season_number,
157 'episode_number
': episode_number,