yt-dlp/yt_dlp/extractor/expressen.py

92 lines
3.7 KiB
Python
Raw Normal View History

2018-06-16 14:14:36 +00:00
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
unescapeHTML,
unified_timestamp,
)
class ExpressenIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
2020-10-07 03:34:22 +00:00
(?:www\.)?(?:expressen|di)\.se/
(?:(?:tvspelare/video|videoplayer/embed)/)?
tv/(?:[^/]+/)*
(?P<id>[^/?#&]+)
'''
_EMBED_REGEX = [r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?(?:expressen|di)\.se/(?:tvspelare/video|videoplayer/embed)/tv/.+?)\1']
2018-06-16 14:14:36 +00:00
_TESTS = [{
'url': 'https://www.expressen.se/tv/ledare/ledarsnack/ledarsnack-om-arbetslosheten-bland-kvinnor-i-speciellt-utsatta-omraden/',
'md5': 'deb2ca62e7b1dcd19fa18ba37523f66e',
2018-06-16 14:14:36 +00:00
'info_dict': {
'id': 'ba90f5a9-78d1-4511-aa02-c177b9c99136',
'display_id': 'ledarsnack-om-arbetslosheten-bland-kvinnor-i-speciellt-utsatta-omraden',
2018-06-16 14:14:36 +00:00
'ext': 'mp4',
'title': 'Ledarsnack: Om arbetslösheten bland kvinnor i speciellt utsatta områden',
'description': 'md5:f38c81ff69f3de4d269bbda012fcbbba',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 788,
'timestamp': 1526639109,
'upload_date': '20180518',
},
}, {
'url': 'https://www.expressen.se/tv/kultur/kulturdebatt-med-expressens-karin-olsson/',
'only_matching': True,
}, {
'url': 'https://www.expressen.se/tvspelare/video/tv/ditv/ekonomistudion/experterna-har-ar-fragorna-som-avgor-valet/?embed=true&external=true&autoplay=true&startVolume=0&partnerId=di',
'only_matching': True,
}, {
'url': 'https://www.expressen.se/videoplayer/embed/tv/ditv/ekonomistudion/experterna-har-ar-fragorna-som-avgor-valet/?embed=true&external=true&autoplay=true&startVolume=0&partnerId=di',
'only_matching': True,
2020-10-07 03:34:22 +00:00
}, {
'url': 'https://www.di.se/videoplayer/embed/tv/ditv/borsmorgon/implantica-rusar-70--under-borspremiaren-hor-styrelsemedlemmen/?embed=true&external=true&autoplay=true&startVolume=0&partnerId=di',
'only_matching': True,
2018-06-16 14:14:36 +00:00
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
def extract_data(name):
return self._parse_json(
self._search_regex(
r'data-%s=(["\'])(?P<value>(?:(?!\1).)+)\1' % name,
webpage, 'info', group='value'),
display_id, transform_source=unescapeHTML)
info = extract_data('video-tracking-info')
video_id = info['contentId']
2018-06-16 14:14:36 +00:00
data = extract_data('article-data')
stream = data['stream']
if determine_ext(stream) == 'm3u8':
formats = self._extract_m3u8_formats(
stream, display_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
else:
formats = [{
'url': stream,
}]
self._sort_formats(formats)
title = info.get('titleRaw') or data['title']
description = info.get('descriptionRaw')
thumbnail = info.get('socialMediaImage') or data.get('image')
duration = int_or_none(info.get('videoTotalSecondsDuration')
or data.get('totalSecondsDuration'))
2018-06-16 14:14:36 +00:00
timestamp = unified_timestamp(info.get('publishDate'))
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'formats': formats,
}