]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/malltv.py
1 from .common
import InfoExtractor
13 class MallTVIE(InfoExtractor
):
14 _VALID_URL
= r
'https?://(?:(?:www|sk)\.)?mall\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
16 'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
17 'md5': '1c4a37f080e1f3023103a7b43458e518',
20 'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
22 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?',
23 'description': 'md5:db7d5744a4bd4043d9d98324aa72ab35',
25 'timestamp': 1538870400,
26 'upload_date': '20181007',
30 'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
31 'only_matching': True,
33 'url': 'https://sk.mall.tv/gejmhaus/reklamacia-nehreje-vyrobnik-tepla-alebo-spekacka',
34 'only_matching': True,
37 def _real_extract(self
, url
):
38 display_id
= self
._match
_id
(url
)
40 webpage
= self
._download
_webpage
(
41 url
, display_id
, headers
=self
.geo_verification_headers())
43 video
= self
._parse
_json
(self
._search
_regex
(
44 r
'videoObject\s*=\s*JSON\.parse\(JSON\.stringify\(({.+?})\)\);',
45 webpage
, 'video object'), display_id
)
46 video_source
= video
['VideoSource']
47 video_id
= self
._search
_regex
(
48 r
'/([\da-z]+)/index\b', video_source
, 'video id')
50 formats
= self
._extract
_m
3u8_formats
(
51 video_source
+ '.m3u8', video_id
, 'mp4', 'm3u8_native')
52 self
._sort
_formats
(formats
)
55 for s
in (video
.get('Subtitles') or {}):
59 subtitles
.setdefault(s
.get('Language') or 'cz', []).append({
63 entity_counts
= video
.get('EntityCounts') or {}
66 v
= entity_counts
.get(k
+ 's') or {}
67 return int_or_none(dict_get(v
, ('Count', 'StrCount')))
69 info
= self
._search
_json
_ld
(webpage
, video_id
, default
={})
73 'display_id': display_id
,
74 'title': video
.get('Title'),
75 'description': clean_html(video
.get('Description')),
76 'thumbnail': video
.get('ThumbnailUrl'),
78 'subtitles': subtitles
,
79 'duration': int_or_none(video
.get('DurationSeconds')) or parse_duration(video
.get('Duration')),
80 'view_count': get_count('View'),
81 'like_count': get_count('Like'),
82 'dislike_count': get_count('Dislike'),
83 'average_rating': float_or_none(try_get(video
, lambda x
: x
['EntityRating']['AvarageRate'])),
84 'comment_count': get_count('Comment'),