youtube-dl

Another place where youtube-dl lives on
git clone git://git.oshgnacknak.de/youtube-dl.git
Log | Files | Refs | README | LICENSE

expressen.py (3865B)

      1 # coding: utf-8
      2 from __future__ import unicode_literals
      3 
      4 import re
      5 
      6 from .common import InfoExtractor
      7 from ..utils import (
      8     determine_ext,
      9     int_or_none,
     10     unescapeHTML,
     11     unified_timestamp,
     12 )
     13 
     14 
     15 class ExpressenIE(InfoExtractor):
     16     _VALID_URL = r'''(?x)
     17                     https?://
     18                         (?:www\.)?(?:expressen|di)\.se/
     19                         (?:(?:tvspelare/video|videoplayer/embed)/)?
     20                         tv/(?:[^/]+/)*
     21                         (?P<id>[^/?#&]+)
     22                     '''
     23     _TESTS = [{
     24         'url': 'https://www.expressen.se/tv/ledare/ledarsnack/ledarsnack-om-arbetslosheten-bland-kvinnor-i-speciellt-utsatta-omraden/',
     25         'md5': '2fbbe3ca14392a6b1b36941858d33a45',
     26         'info_dict': {
     27             'id': '8690962',
     28             'ext': 'mp4',
     29             'title': 'Ledarsnack: Om arbetslösheten bland kvinnor i speciellt utsatta områden',
     30             'description': 'md5:f38c81ff69f3de4d269bbda012fcbbba',
     31             'thumbnail': r're:^https?://.*\.jpg$',
     32             'duration': 788,
     33             'timestamp': 1526639109,
     34             'upload_date': '20180518',
     35         },
     36     }, {
     37         'url': 'https://www.expressen.se/tv/kultur/kulturdebatt-med-expressens-karin-olsson/',
     38         'only_matching': True,
     39     }, {
     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,
     42     }, {
     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,
     45     }, {
     46         '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',
     47         'only_matching': True,
     48     }]
     49 
     50     @staticmethod
     51     def _extract_urls(webpage):
     52         return [
     53             mobj.group('url') for mobj in re.finditer(
     54                 r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?(?:expressen|di)\.se/(?:tvspelare/video|videoplayer/embed)/tv/.+?)\1',
     55                 webpage)]
     56 
     57     def _real_extract(self, url):
     58         display_id = self._match_id(url)
     59 
     60         webpage = self._download_webpage(url, display_id)
     61 
     62         def extract_data(name):
     63             return self._parse_json(
     64                 self._search_regex(
     65                     r'data-%s=(["\'])(?P<value>(?:(?!\1).)+)\1' % name,
     66                     webpage, 'info', group='value'),
     67                 display_id, transform_source=unescapeHTML)
     68 
     69         info = extract_data('video-tracking-info')
     70         video_id = info['videoId']
     71 
     72         data = extract_data('article-data')
     73         stream = data['stream']
     74 
     75         if determine_ext(stream) == 'm3u8':
     76             formats = self._extract_m3u8_formats(
     77                 stream, display_id, 'mp4', entry_protocol='m3u8_native',
     78                 m3u8_id='hls')
     79         else:
     80             formats = [{
     81                 'url': stream,
     82             }]
     83         self._sort_formats(formats)
     84 
     85         title = info.get('titleRaw') or data['title']
     86         description = info.get('descriptionRaw')
     87         thumbnail = info.get('socialMediaImage') or data.get('image')
     88         duration = int_or_none(info.get('videoTotalSecondsDuration')
     89                                or data.get('totalSecondsDuration'))
     90         timestamp = unified_timestamp(info.get('publishDate'))
     91 
     92         return {
     93             'id': video_id,
     94             'display_id': display_id,
     95             'title': title,
     96             'description': description,
     97             'thumbnail': thumbnail,
     98             'duration': duration,
     99             'timestamp': timestamp,
    100             'formats': formats,
    101         }