yt_dlp/extractor/ccc.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     parse_iso8601,
   5     try_get,
   6     url_or_none,
   7 )
   8
   9
  10 class CCCIE(InfoExtractor):
  11     IE_NAME = 'media.ccc.de'
  12     _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/v/(?P<id>[^/?#&]+)'
  13
  14     _TESTS = [{
  15         'url': 'https://media.ccc.de/v/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor#video',
  16         'md5': '3a1eda8f3a29515d27f5adb967d7e740',
  17         'info_dict': {
  18             'id': '1839',
  19             'ext': 'mp4',
  20             'title': 'Introduction to Processor Design',
  21             'creator': 'byterazor',
  22             'description': 'md5:df55f6d073d4ceae55aae6f2fd98a0ac',
  23             'thumbnail': r're:^https?://.*\.jpg$',
  24             'upload_date': '20131228',
  25             'timestamp': 1388188800,
  26             'duration': 3710,
  27             'tags': list,
  28         },
  29     }, {
  30         'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download',
  31         'only_matching': True,
  32     }]
  33
  34     def _real_extract(self, url):
  35         display_id = self._match_id(url)
  36         webpage = self._download_webpage(url, display_id)
  37         event_id = self._search_regex(r"data-id='(\d+)'", webpage, 'event id')
  38         event_data = self._download_json(f'https://media.ccc.de/public/events/{event_id}', event_id)
  39
  40         formats = []
  41         for recording in event_data.get('recordings', []):
  42             recording_url = recording.get('recording_url')
  43             if not recording_url:
  44                 continue
  45             language = recording.get('language')
  46             folder = recording.get('folder')
  47             format_id = None
  48             if language:
  49                 format_id = language
  50             if folder:
  51                 if language:
  52                     format_id += '-' + folder
  53                 else:
  54                     format_id = folder
  55             vcodec = 'h264' if 'h264' in folder else (
  56                 'none' if folder in ('mp3', 'opus') else None
  57             )
  58             formats.append({
  59                 'format_id': format_id,
  60                 'url': recording_url,
  61                 'width': int_or_none(recording.get('width')),
  62                 'height': int_or_none(recording.get('height')),
  63                 'filesize': int_or_none(recording.get('size'), invscale=1024 * 1024),
  64                 'language': language,
  65                 'vcodec': vcodec,
  66             })
  67
  68         return {
  69             'id': event_id,
  70             'display_id': display_id,
  71             'title': event_data['title'],
  72             'creator': try_get(event_data, lambda x: ', '.join(x['persons'])),
  73             'description': event_data.get('description'),
  74             'thumbnail': event_data.get('thumb_url'),
  75             'timestamp': parse_iso8601(event_data.get('date')),
  76             'duration': int_or_none(event_data.get('length')),
  77             'view_count': int_or_none(event_data.get('view_count')),
  78             'tags': event_data.get('tags'),
  79             'formats': formats,
  80         }
  81
  82
  83 class CCCPlaylistIE(InfoExtractor):
  84     IE_NAME = 'media.ccc.de:lists'
  85     _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/c/(?P<id>[^/?#&]+)'
  86     _TESTS = [{
  87         'url': 'https://media.ccc.de/c/30c3',
  88         'info_dict': {
  89             'title': '30C3',
  90             'id': '30c3',
  91         },
  92         'playlist_count': 135,
  93     }, {
  94         'url': 'https://media.ccc.de/c/DS2023',
  95         'info_dict': {
  96             'title': 'Datenspuren 2023',
  97             'id': 'DS2023',
  98         },
  99         'playlist_count': 37,
 100     }]
 101
 102     def _real_extract(self, url):
 103         playlist_id = self._match_id(url)
 104
 105         conf = self._download_json(
 106             'https://media.ccc.de/public/conferences/' + playlist_id,
 107             playlist_id)
 108
 109         entries = []
 110         for e in conf['events']:
 111             event_url = url_or_none(e.get('frontend_link'))
 112             if event_url:
 113                 entries.append(self.url_result(event_url, ie=CCCIE.ie_key()))
 114
 115         return self.playlist_result(entries, playlist_id, conf.get('title'))