1 from .common
import InfoExtractor
10 class DailyMailIE(InfoExtractor
):
11 _VALID_URL
= r
'https?://(?:www\.)?dailymail\.co\.uk/(?:video/[^/]+/video-|embed/video/)(?P<id>[0-9]+)'
12 _EMBED_REGEX
= [r
'<iframe\b[^>]+\bsrc=["\'](?P
<url
>(?
:https?
:)?
//(?
:www\
.)?dailymail\
.co\
.uk
/embed
/video
/\d
+\
.html
)']
14 'url
': 'http
://www
.dailymail
.co
.uk
/video
/tvshowbiz
/video
-1295863/The
-Mountain
-appears
-sparkling
-water
-ad
-Heavy
-Bubbles
.html
',
15 'md5
': 'f6129624562251f628296c3a9ffde124
',
19 'title
': 'The Mountain appears
in sparkling water ad
for \'Heavy Bubbles
\'',
20 'description
': 'md5
:a93d74b6da172dd5dc4d973e0b766a84
',
23 'url
': 'http
://www
.dailymail
.co
.uk
/embed
/video
/1295863.html
',
24 'only_matching
': True,
27 def _real_extract(self, url):
28 video_id = self._match_id(url)
29 webpage = self._download_webpage(url, video_id)
30 video_data = self._parse_json(self._search_regex(
31 r"data-opts='({.+?}
)'", webpage, 'video data
'), video_id)
32 title = unescapeHTML(video_data['title
'])
34 sources_url = (try_get(
36 (lambda x: x['plugins
']['sources
']['url
'],
37 lambda x: x['sources
']['url
']), str)
38 or f'http
://www
.dailymail
.co
.uk
/api
/player
/{video_id}
/video
-sources
.json
')
40 video_sources = self._download_json(sources_url, video_id)
41 body = video_sources.get('body
')
46 for rendition in video_sources['renditions
']:
47 rendition_url = rendition.get('url
')
50 tbr = int_or_none(rendition.get('encodingRate
'), 1000)
51 container = rendition.get('videoContainer
')
52 is_hls = container == 'M2TS
'
53 protocol = 'm3u8_native
' if is_hls else determine_protocol({'url': rendition_url})
55 'format_id
': ('hls
' if is_hls else protocol) + (f'-{tbr}
' if tbr else ''),
57 'width
': int_or_none(rendition.get('frameWidth
')),
58 'height
': int_or_none(rendition.get('frameHeight
')),
60 'vcodec
': rendition.get('videoCodec
'),
61 'container
': container,
63 'ext
': 'mp4
' if is_hls else None,
69 'description
': unescapeHTML(video_data.get('descr
')),
70 'thumbnail
': video_data.get('poster
') or video_data.get('thumbnail
'),