Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/philharmoniedeparis.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_str
   6 from ..utils import (
   7     try_get,
   8     urljoin,
   9 )
  10
  11
  12 class PhilharmonieDeParisIE(InfoExtractor):
  13     IE_DESC = 'Philharmonie de Paris'
  14     _VALID_URL = r'''(?x)
  15                     https?://
  16                         (?:
  17                             live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)|
  18                             pad\.philharmoniedeparis\.fr/doc/CIMU/
  19                         )
  20                         (?P<id>\d+)
  21                     '''
  22     _TESTS = [{
  23         'url': 'http://pad.philharmoniedeparis.fr/doc/CIMU/1086697/jazz-a-la-villette-knower',
  24         'md5': 'a0a4b195f544645073631cbec166a2c2',
  25         'info_dict': {
  26             'id': '1086697',
  27             'ext': 'mp4',
  28             'title': 'Jazz à la Villette : Knower',
  29         },
  30     }, {
  31         'url': 'http://live.philharmoniedeparis.fr/concert/1032066.html',
  32         'info_dict': {
  33             'id': '1032066',
  34             'title': 'md5:0a031b81807b3593cffa3c9a87a167a0',
  35         },
  36         'playlist_mincount': 2,
  37     }, {
  38         'url': 'http://live.philharmoniedeparis.fr/Concert/1030324.html',
  39         'only_matching': True,
  40     }, {
  41         'url': 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=1030324&track=&lang=fr',
  42         'only_matching': True,
  43     }]
  44     _LIVE_URL = 'https://live.philharmoniedeparis.fr'
  45
  46     def _real_extract(self, url):
  47         video_id = self._match_id(url)
  48
  49         config = self._download_json(
  50             '%s/otoPlayer/config.ashx' % self._LIVE_URL, video_id, query={
  51                 'id': video_id,
  52                 'lang': 'fr-FR',
  53             })
  54
  55         def extract_entry(source):
  56             if not isinstance(source, dict):
  57                 return
  58             title = source.get('title')
  59             if not title:
  60                 return
  61             files = source.get('files')
  62             if not isinstance(files, dict):
  63                 return
  64             format_urls = set()
  65             formats = []
  66             for format_id in ('mobile', 'desktop'):
  67                 format_url = try_get(
  68                     files, lambda x: x[format_id]['file'], compat_str)
  69                 if not format_url or format_url in format_urls:
  70                     continue
  71                 format_urls.add(format_url)
  72                 m3u8_url = urljoin(self._LIVE_URL, format_url)
  73                 formats.extend(self._extract_m3u8_formats(
  74                     m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
  75                     m3u8_id='hls', fatal=False))
  76             if not formats:
  77                 return
  78             self._sort_formats(formats)
  79             return {
  80                 'title': title,
  81                 'formats': formats,
  82             }
  83
  84         thumbnail = urljoin(self._LIVE_URL, config.get('image'))
  85
  86         info = extract_entry(config)
  87         if info:
  88             info.update({
  89                 'id': video_id,
  90                 'thumbnail': thumbnail,
  91             })
  92             return info
  93
  94         entries = []
  95         for num, chapter in enumerate(config['chapters'], start=1):
  96             entry = extract_entry(chapter)
  97             entry['id'] = '%s-%d' % (video_id, num)
  98             entries.append(entry)
  99
 100         return self.playlist_result(entries, video_id, config.get('title'))