youtube_dl/extractor/ccc.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     parse_iso8601,
   8     try_get,
   9 )
  10
  11
  12 class CCCIE(InfoExtractor):
  13     IE_NAME = 'media.ccc.de'
  14     _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/v/(?P<id>[^/?#&]+)'
  15
  16     _TESTS = [{
  17         'url': 'https://media.ccc.de/v/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor#video',
  18         'md5': '3a1eda8f3a29515d27f5adb967d7e740',
  19         'info_dict': {
  20             'id': '1839',
  21             'ext': 'mp4',
  22             'title': 'Introduction to Processor Design',
  23             'creator': 'byterazor',
  24             'description': 'md5:df55f6d073d4ceae55aae6f2fd98a0ac',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26             'upload_date': '20131228',
  27             'timestamp': 1388188800,
  28             'duration': 3710,
  29             'tags': list,
  30         }
  31     }, {
  32         'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download',
  33         'info_dict': {
  34             'id': '2835',
  35             'ext': 'mp4',
  36             'title': 'Shopshifting',
  37             'creator': 'Karsten Nohl, Fabian Bräunlein, dexter',
  38             'description': 'md5:0fade0535e9dc3076d0cbda4958a18eb',
  39             'upload_date': '20151227',
  40             'timestamp': 1451249100,
  41             'tags': list,
  42         }
  43     }]
  44
  45     def _real_extract(self, url):
  46         display_id = self._match_id(url)
  47         webpage = self._download_webpage(url, display_id)
  48         event_id = self._search_regex(r"data-id='(\d+)'", webpage, 'event id')
  49         event_data = self._download_json('https://media.ccc.de/public/events/%s' % event_id, event_id)
  50
  51         formats = []
  52         for recording in event_data.get('recordings', []):
  53             recording_url = recording.get('recording_url')
  54             if not recording_url:
  55                 continue
  56             language = recording.get('language')
  57             folder = recording.get('folder')
  58             format_id = None
  59             if language:
  60                 format_id = language
  61             if folder:
  62                 if language:
  63                     format_id += '-' + folder
  64                 else:
  65                     format_id = folder
  66             vcodec = 'h264' if 'h264' in folder else (
  67                 'none' if folder in ('mp3', 'opus') else None
  68             )
  69             formats.append({
  70                 'format_id': format_id,
  71                 'url': recording_url,
  72                 'width': int_or_none(recording.get('width')),
  73                 'height': int_or_none(recording.get('height')),
  74                 'filesize': int_or_none(recording.get('size'), invscale=1024 * 1024),
  75                 'language': language,
  76                 'vcodec': vcodec,
  77             })
  78         self._sort_formats(formats)
  79
  80         return {
  81             'id': event_id,
  82             'display_id': display_id,
  83             'title': event_data['title'],
  84             'creator': try_get(event_data, lambda x: ', '.join(x['persons'])),
  85             'description': event_data.get('description'),
  86             'thumbnail': event_data.get('thumb_url'),
  87             'timestamp': parse_iso8601(event_data.get('date')),
  88             'duration': int_or_none(event_data.get('length')),
  89             'tags': event_data.get('tags'),
  90             'formats': formats,
  91         }
  92
  93
  94 class CCCPlaylistIE(InfoExtractor):
  95     IE_NAME = 'media.ccc.de:lists'
  96     _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/c/(?P<id>[^/?#&]+)'
  97     _TESTS = [{
  98         'url': 'https://media.ccc.de/c/30c3',
  99         'info_dict': {
 100             'title': '30C3',
 101             'id': '30c3',
 102         },
 103         'playlist_count': 135,
 104     }]
 105
 106     def _real_extract(self, url):
 107         acronym = self._match_id(url).lower()
 108
 109         conf = self._download_json('https://media.ccc.de/public/conferences/' + acronym, acronym)
 110
 111         return self.playlist_result(
 112             [self.url_result(event['frontend_link']) for event in conf['events']],
 113             acronym,
 114             conf['title'],
 115         )