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