_ Git - youtube-dl/blob - youtube_dl/extractor/libraryofcongress.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6 from ..utils import (
   7     determine_ext,
   8     float_or_none,
   9     int_or_none,
  10 )
  11
  12
  13 class LibraryOfCongressIE(InfoExtractor):
  14     IE_NAME = 'loc'
  15     IE_DESC = 'Library of Congress'
  16     _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P<id>[0-9]+)'
  17     _TESTS = [{
  18         # embedded via <div class="media-player"
  19         'url': 'http://loc.gov/item/90716351/',
  20         'md5': '353917ff7f0255aa6d4b80a034833de8',
  21         'info_dict': {
  22             'id': '90716351',
  23             'ext': 'mp4',
  24             'title': "Pa's trip to Mars",
  25             'thumbnail': 're:^https?://.*\.jpg$',
  26             'duration': 0,
  27             'view_count': int,
  28         },
  29     }, {
  30         # webcast embedded via mediaObjectId
  31         'url': 'https://www.loc.gov/today/cyberlc/feature_wdesc.php?rec=5578',
  32         'info_dict': {
  33             'id': '5578',
  34             'ext': 'mp4',
  35             'title': 'Help! Preservation Training Needs Here, There & Everywhere',
  36             'duration': 3765,
  37             'view_count': int,
  38             'subtitles': 'mincount:1',
  39         },
  40         'params': {
  41             'skip_download': True,
  42         },
  43     }]
  44
  45     def _real_extract(self, url):
  46         video_id = self._match_id(url)
  47         webpage = self._download_webpage(url, video_id)
  48
  49         media_id = self._search_regex(
  50             (r'id=(["\'])media-player-(?P<id>.+?)\1',
  51              r'<video[^>]+id=(["\'])uuid-(?P<id>.+?)\1',
  52              r'<video[^>]+data-uuid=(["\'])(?P<id>.+?)\1',
  53              r'mediaObjectId\s*:\s*(["\'])(?P<id>.+?)\1'),
  54             webpage, 'media id', group='id')
  55
  56         data = self._download_json(
  57             'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id,
  58             video_id)['mediaObject']
  59
  60         derivative = data['derivatives'][0]
  61         media_url = derivative['derivativeUrl']
  62
  63         # Following algorithm was extracted from setAVSource js function
  64         # found in webpage
  65         media_url = media_url.replace('rtmp', 'https')
  66
  67         is_video = data.get('mediaType', 'v').lower() == 'v'
  68         ext = determine_ext(media_url)
  69         if ext not in ('mp4', 'mp3'):
  70             media_url += '.mp4' if is_video else '.mp3'
  71
  72         if 'vod/mp4:' in media_url:
  73             formats = [{
  74                 'url': media_url.replace('vod/mp4:', 'hls-vod/media/') + '.m3u8',
  75                 'format_id': 'hls',
  76                 'ext': 'mp4',
  77                 'protocol': 'm3u8_native',
  78             }]
  79         elif 'vod/mp3:' in media_url:
  80             formats = [{
  81                 'url': media_url.replace('vod/mp3:', ''),
  82                 'vcodec': 'none',
  83             }]
  84
  85         self._sort_formats(formats)
  86
  87         title = derivative.get('shortName') or data.get('shortName') or self._og_search_title(webpage)
  88         duration = float_or_none(data.get('duration'))
  89         view_count = int_or_none(data.get('viewCount'))
  90
  91         subtitles = {}
  92         cc_url = data.get('ccUrl')
  93         if cc_url:
  94             subtitles.setdefault('en', []).append({
  95                 'url': cc_url,
  96                 'ext': 'ttml',
  97             })
  98
  99         return {
 100             'id': video_id,
 101             'title': title,
 102             'thumbnail': self._og_search_thumbnail(webpage, default=None),
 103             'duration': duration,
 104             'view_count': view_count,
 105             'formats': formats,
 106             'subtitles': subtitles,
 107         }