yt-dlp/yt_dlp/extractor/dailymail.py
bashonly 6aaf96a3d6
[cleanup] Misc (#10075)
Closes #10303
Authored by: bashonly, seproDev, jucor, c-basalt

Co-authored-by: sepro <4618135+seproDev@users.noreply.github.com>
Co-authored-by: Julien Cornebise <julien@cornebise.com>
Co-authored-by: c-basalt <117849907+c-basalt@users.noreply.github.com>
2024-07-01 22:51:27 +00:00

74 lines
2.8 KiB
Python

from .common import InfoExtractor
from ..utils import (
determine_protocol,
int_or_none,
join_nonempty,
try_get,
unescapeHTML,
)
class DailyMailIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/(?:video/[^/]+/video-|embed/video/)(?P<id>[0-9]+)'
_EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?dailymail\.co\.uk/embed/video/\d+\.html)']
_TESTS = [{
'url': 'http://www.dailymail.co.uk/video/tvshowbiz/video-1295863/The-Mountain-appears-sparkling-water-ad-Heavy-Bubbles.html',
'md5': 'f6129624562251f628296c3a9ffde124',
'info_dict': {
'id': '1295863',
'ext': 'mp4',
'title': 'The Mountain appears in sparkling water ad for \'Heavy Bubbles\'',
'description': 'md5:a93d74b6da172dd5dc4d973e0b766a84',
},
}, {
'url': 'http://www.dailymail.co.uk/embed/video/1295863.html',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_data = self._parse_json(self._search_regex(
r"data-opts='({.+?})'", webpage, 'video data'), video_id)
title = unescapeHTML(video_data['title'])
sources_url = (try_get(
video_data,
(lambda x: x['plugins']['sources']['url'],
lambda x: x['sources']['url']), str)
or f'http://www.dailymail.co.uk/api/player/{video_id}/video-sources.json')
video_sources = self._download_json(sources_url, video_id)
body = video_sources.get('body')
if body:
video_sources = body
formats = []
for rendition in video_sources['renditions']:
rendition_url = rendition.get('url')
if not rendition_url:
continue
tbr = int_or_none(rendition.get('encodingRate'), 1000)
container = rendition.get('videoContainer')
is_hls = container == 'M2TS'
protocol = 'm3u8_native' if is_hls else determine_protocol({'url': rendition_url})
formats.append({
'format_id': join_nonempty('hls' if is_hls else protocol, tbr),
'url': rendition_url,
'width': int_or_none(rendition.get('frameWidth')),
'height': int_or_none(rendition.get('frameHeight')),
'tbr': tbr,
'vcodec': rendition.get('videoCodec'),
'container': container,
'protocol': protocol,
'ext': 'mp4' if is_hls else None,
})
return {
'id': video_id,
'title': title,
'description': unescapeHTML(video_data.get('descr')),
'thumbnail': video_data.get('poster') or video_data.get('thumbnail'),
'formats': formats,
}