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/|embed(?:app)?/|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         'url': 'https://live.philharmoniedeparis.fr/embedapp/1098406/berlioz-fantastique-lelio-les-siecles-national-youth-choir-of.html?lang=fr-FR',
  45         'only_matching': True,
  46     }, {
  47         'url': 'https://live.philharmoniedeparis.fr/embed/1098406/berlioz-fantastique-lelio-les-siecles-national-youth-choir-of.html?lang=fr-FR',
  48         'only_matching': True,
  49     }]
  50     _LIVE_URL = 'https://live.philharmoniedeparis.fr'
  51
  52     def _real_extract(self, url):
  53         video_id = self._match_id(url)
  54
  55         config = self._download_json(
  56             '%s/otoPlayer/config.ashx' % self._LIVE_URL, video_id, query={
  57                 'id': video_id,
  58                 'lang': 'fr-FR',
  59             })
  60
  61         def extract_entry(source):
  62             if not isinstance(source, dict):
  63                 return
  64             title = source.get('title')
  65             if not title:
  66                 return
  67             files = source.get('files')
  68             if not isinstance(files, dict):
  69                 return
  70             format_urls = set()
  71             formats = []
  72             for format_id in ('mobile', 'desktop'):
  73                 format_url = try_get(
  74                     files, lambda x: x[format_id]['file'], compat_str)
  75                 if not format_url or format_url in format_urls:
  76                     continue
  77                 format_urls.add(format_url)
  78                 m3u8_url = urljoin(self._LIVE_URL, format_url)
  79                 formats.extend(self._extract_m3u8_formats(
  80                     m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
  81                     m3u8_id='hls', fatal=False))
  82             if not formats:
  83                 return
  84             self._sort_formats(formats)
  85             return {
  86                 'title': title,
  87                 'formats': formats,
  88             }
  89
  90         thumbnail = urljoin(self._LIVE_URL, config.get('image'))
  91
  92         info = extract_entry(config)
  93         if info:
  94             info.update({
  95                 'id': video_id,
  96                 'thumbnail': thumbnail,
  97             })
  98             return info
  99
 100         entries = []
 101         for num, chapter in enumerate(config['chapters'], start=1):
 102             entry = extract_entry(chapter)
 103             entry['id'] = '%s-%d' % (video_id, num)
 104             entries.append(entry)
 105
 106         return self.playlist_result(entries, video_id, config.get('title'))