yt_dlp/extractor/libraryofcongress.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     determine_ext,
   6     float_or_none,
   7     int_or_none,
   8     parse_filesize,
   9 )
  10
  11
  12 class LibraryOfCongressIE(InfoExtractor):
  13     IE_NAME = 'loc'
  14     IE_DESC = 'Library of Congress'
  15     _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P<id>[0-9a-z_.]+)'
  16     _TESTS = [{
  17         # embedded via <div class="media-player"
  18         'url': 'http://loc.gov/item/90716351/',
  19         'md5': '6ec0ae8f07f86731b1b2ff70f046210a',
  20         'info_dict': {
  21             'id': '90716351',
  22             'ext': 'mp4',
  23             'title': "Pa's trip to Mars",
  24             'duration': 0,
  25             'view_count': int,
  26         },
  27     }, {
  28         # webcast embedded via mediaObjectId
  29         'url': 'https://www.loc.gov/today/cyberlc/feature_wdesc.php?rec=5578',
  30         'info_dict': {
  31             'id': '5578',
  32             'ext': 'mp4',
  33             'title': 'Help! Preservation Training Needs Here, There & Everywhere',
  34             'duration': 3765,
  35             'view_count': int,
  36             'subtitles': 'mincount:1',
  37         },
  38         'params': {
  39             'skip_download': True,
  40         },
  41     }, {
  42         # with direct download links
  43         'url': 'https://www.loc.gov/item/78710669/',
  44         'info_dict': {
  45             'id': '78710669',
  46             'ext': 'mp4',
  47             'title': 'La vie et la passion de Jesus-Christ',
  48             'duration': 0,
  49             'view_count': int,
  50             'formats': 'mincount:4',
  51         },
  52         'params': {
  53             'skip_download': True,
  54         },
  55     }, {
  56         'url': 'https://www.loc.gov/item/ihas.200197114/',
  57         'only_matching': True,
  58     }, {
  59         'url': 'https://www.loc.gov/item/afc1981005_afs20503/',
  60         'only_matching': True,
  61     }]
  62
  63     def _real_extract(self, url):
  64         video_id = self._match_id(url)
  65         webpage = self._download_webpage(url, video_id)
  66
  67         media_id = self._search_regex(
  68             (r'id=(["\'])media-player-(?P<id>.+?)\1',
  69              r'<video[^>]+id=(["\'])uuid-(?P<id>.+?)\1',
  70              r'<video[^>]+data-uuid=(["\'])(?P<id>.+?)\1',
  71              r'mediaObjectId\s*:\s*(["\'])(?P<id>.+?)\1',
  72              r'data-tab="share-media-(?P<id>[0-9A-F]{32})"'),
  73             webpage, 'media id', group='id')
  74
  75         data = self._download_json(
  76             f'https://media.loc.gov/services/v1/media?id={media_id}&context=json',
  77             media_id)['mediaObject']
  78
  79         derivative = data['derivatives'][0]
  80         media_url = derivative['derivativeUrl']
  81
  82         title = derivative.get('shortName') or data.get('shortName') or self._og_search_title(
  83             webpage)
  84
  85         # Following algorithm was extracted from setAVSource js function
  86         # found in webpage
  87         media_url = media_url.replace('rtmp', 'https')
  88
  89         is_video = data.get('mediaType', 'v').lower() == 'v'
  90         ext = determine_ext(media_url)
  91         if ext not in ('mp4', 'mp3'):
  92             media_url += '.mp4' if is_video else '.mp3'
  93
  94         formats = []
  95         if '/vod/mp4:' in media_url:
  96             formats.append({
  97                 'url': media_url.replace('/vod/mp4:', '/hls-vod/media/') + '.m3u8',
  98                 'format_id': 'hls',
  99                 'ext': 'mp4',
 100                 'protocol': 'm3u8_native',
 101                 'quality': 1,
 102             })
 103         http_format = {
 104             'url': re.sub(r'(://[^/]+/)(?:[^/]+/)*(?:mp4|mp3):', r'\1', media_url),
 105             'format_id': 'http',
 106             'quality': 1,
 107         }
 108         if not is_video:
 109             http_format['vcodec'] = 'none'
 110         formats.append(http_format)
 111
 112         download_urls = set()
 113         for m in re.finditer(
 114                 r'<option[^>]+value=(["\'])(?P<url>.+?)\1[^>]+data-file-download=[^>]+>\s*(?P<id>.+?)(?:(?:&nbsp;|\s+)\((?P<size>.+?)\))?\s*<', webpage):
 115             format_id = m.group('id').lower()
 116             if format_id in ('gif', 'jpeg'):
 117                 continue
 118             download_url = m.group('url')
 119             if download_url in download_urls:
 120                 continue
 121             download_urls.add(download_url)
 122             formats.append({
 123                 'url': download_url,
 124                 'format_id': format_id,
 125                 'filesize_approx': parse_filesize(m.group('size')),
 126             })
 127
 128         duration = float_or_none(data.get('duration'))
 129         view_count = int_or_none(data.get('viewCount'))
 130
 131         subtitles = {}
 132         cc_url = data.get('ccUrl')
 133         if cc_url:
 134             subtitles.setdefault('en', []).append({
 135                 'url': cc_url,
 136                 'ext': 'ttml',
 137             })
 138
 139         return {
 140             'id': video_id,
 141             'title': title,
 142             'thumbnail': self._og_search_thumbnail(webpage, default=None),
 143             'duration': duration,
 144             'view_count': view_count,
 145             'formats': formats,
 146             'subtitles': subtitles,
 147         }