2 from __future__ import unicode_literals
6 from .common import InfoExtractor
15 class ExpressenIE(InfoExtractor):
18 (?:www\.)?expressen\.se/
19 (?:(?:tvspelare/video|videoplayer/embed)/)?
24 'url': 'https://www.expressen.se/tv/ledare/ledarsnack/ledarsnack-om-arbetslosheten-bland-kvinnor-i-speciellt-utsatta-omraden/',
25 'md5': '2fbbe3ca14392a6b1b36941858d33a45',
29 'title': 'Ledarsnack: Om arbetslösheten bland kvinnor i speciellt utsatta områden',
30 'description': 'md5:f38c81ff69f3de4d269bbda012fcbbba',
31 'thumbnail': r're:^https?://.*\.jpg$',
33 'timestamp': 1526639109,
34 'upload_date': '20180518',
37 'url': 'https://www.expressen.se/tv/kultur/kulturdebatt-med-expressens-karin-olsson/',
38 'only_matching': True,
40 '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',
41 'only_matching': True,
43 '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',
44 'only_matching': True,
48 def _extract_urls(webpage):
50 mobj.group('url') for mobj in re.finditer(
51 r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?expressen\.se/(?:tvspelare/video|videoplayer/embed)/tv/.+?)\1',
54 def _real_extract(self, url):
55 display_id = self._match_id(url)
57 webpage = self._download_webpage(url, display_id)
59 def extract_data(name):
60 return self._parse_json(
62 r'data-%s=(["\'])(?P<value>(?:(?!\1).)+)\1' % name,
63 webpage, 'info', group='value'),
64 display_id, transform_source=unescapeHTML)
66 info = extract_data('video-tracking-info')
67 video_id = info['videoId']
69 data = extract_data('article-data')
70 stream = data['stream']
72 if determine_ext(stream) == 'm3u8':
73 formats = self._extract_m3u8_formats(
74 stream, display_id, 'mp4', entry_protocol='m3u8_native',
80 self._sort_formats(formats)
82 title = info.get('titleRaw') or data['title']
83 description = info.get('descriptionRaw')
84 thumbnail = info.get('socialMediaImage') or data.get('image')
85 duration = int_or_none(info.get('videoTotalSecondsDuration')
86 or data.get('totalSecondsDuration'))
87 timestamp = unified_timestamp(info.get('publishDate'))
91 'display_id': display_id,
93 'description': description,
94 'thumbnail': thumbnail,
96 'timestamp': timestamp,