]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/dailymail.py
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
11 class DailyMailIE(InfoExtractor
):
12 _VALID_URL
= r
'https?://(?:www\.)?dailymail\.co\.uk/video/[^/]+/video-(?P<id>[0-9]+)'
14 'url': 'http://www.dailymail.co.uk/video/sciencetech/video-1288527/Turn-video-impressionist-masterpiece.html',
15 'md5': '2f639d446394f53f3a33658b518b6615',
19 'title': 'Turn any video into an impressionist masterpiece',
20 'description': 'md5:88ddbcb504367987b2708bb38677c9d2',
24 def _real_extract(self
, url
):
25 video_id
= self
._match
_id
(url
)
26 webpage
= self
._download
_webpage
(url
, video_id
)
27 video_data
= self
._parse
_json
(self
._search
_regex
(
28 r
"data-opts='({.+?})'", webpage
, 'video data'), video_id
)
29 title
= video_data
['title']
30 video_sources
= self
._download
_json
(video_data
.get(
31 'sources', {}).get('url') or 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id
, video_id
)
34 for rendition
in video_sources
['renditions']:
35 rendition_url
= rendition
.get('url')
38 tbr
= int_or_none(rendition
.get('encodingRate'), 1000)
39 container
= rendition
.get('videoContainer')
40 is_hls
= container
== 'M2TS'
41 protocol
= 'm3u8_native' if is_hls
else determine_protocol({'url': rendition_url}
)
43 'format_id': ('hls' if is_hls
else protocol
) + ('-%d' % tbr
if tbr
else ''),
45 'width': int_or_none(rendition
.get('frameWidth')),
46 'height': int_or_none(rendition
.get('frameHeight')),
48 'vcodec': rendition
.get('videoCodec'),
49 'container': container
,
51 'ext': 'mp4' if is_hls
else None,
53 self
._sort
_formats
(formats
)
58 'description': video_data
.get('descr'),
59 'thumbnail': video_data
.get('poster') or video_data
.get('thumbnail'),