yt_dlp/extractor/libraryofcongress.py

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5 from ..utils import (
   6     determine_ext,
   7     float_or_none,
   8     int_or_none,
   9     parse_filesize,
  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>[0-9a-z_.]+)'
  17     _TESTS = [{
  18         # embedded via <div class="media-player"
  19         'url': 'http://loc.gov/item/90716351/',
  20         'md5': '6ec0ae8f07f86731b1b2ff70f046210a',
  21         'info_dict': {
  22             'id': '90716351',
  23             'ext': 'mp4',
  24             'title': "Pa's trip to Mars",
  25             'duration': 0,
  26             'view_count': int,
  27         },
  28     }, {
  29         # webcast embedded via mediaObjectId
  30         'url': 'https://www.loc.gov/today/cyberlc/feature_wdesc.php?rec=5578',
  31         'info_dict': {
  32             'id': '5578',
  33             'ext': 'mp4',
  34             'title': 'Help! Preservation Training Needs Here, There & Everywhere',
  35             'duration': 3765,
  36             'view_count': int,
  37             'subtitles': 'mincount:1',
  38         },
  39         'params': {
  40             'skip_download': True,
  41         },
  42     }, {
  43         # with direct download links
  44         'url': 'https://www.loc.gov/item/78710669/',
  45         'info_dict': {
  46             'id': '78710669',
  47             'ext': 'mp4',
  48             'title': 'La vie et la passion de Jesus-Christ',
  49             'duration': 0,
  50             'view_count': int,
  51             'formats': 'mincount:4',
  52         },
  53         'params': {
  54             'skip_download': True,
  55         },
  56     }, {
  57         'url': 'https://www.loc.gov/item/ihas.200197114/',
  58         'only_matching': True,
  59     }, {
  60         'url': 'https://www.loc.gov/item/afc1981005_afs20503/',
  61         'only_matching': True,
  62     }]
  63
  64     def _real_extract(self, url):
  65         video_id = self._match_id(url)
  66         webpage = self._download_webpage(url, video_id)
  67
  68         media_id = self._search_regex(
  69             (r'id=(["\'])media-player-(?P<id>.+?)\1',
  70              r'<video[^>]+id=(["\'])uuid-(?P<id>.+?)\1',
  71              r'<video[^>]+data-uuid=(["\'])(?P<id>.+?)\1',
  72              r'mediaObjectId\s*:\s*(["\'])(?P<id>.+?)\1',
  73              r'data-tab="share-media-(?P<id>[0-9A-F]{32})"'),
  74             webpage, 'media id', group='id')
  75
  76         data = self._download_json(
  77             'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id,
  78             media_id)['mediaObject']
  79
  80         derivative = data['derivatives'][0]
  81         media_url = derivative['derivativeUrl']
  82
  83         title = derivative.get('shortName') or data.get('shortName') or self._og_search_title(
  84             webpage)
  85
  86         # Following algorithm was extracted from setAVSource js function
  87         # found in webpage
  88         media_url = media_url.replace('rtmp', 'https')
  89
  90         is_video = data.get('mediaType', 'v').lower() == 'v'
  91         ext = determine_ext(media_url)
  92         if ext not in ('mp4', 'mp3'):
  93             media_url += '.mp4' if is_video else '.mp3'
  94
  95         formats = []
  96         if '/vod/mp4:' in media_url:
  97             formats.append({
  98                 'url': media_url.replace('/vod/mp4:', '/hls-vod/media/') + '.m3u8',
  99                 'format_id': 'hls',
 100                 'ext': 'mp4',
 101                 'protocol': 'm3u8_native',
 102                 'quality': 1,
 103             })
 104         http_format = {
 105             'url': re.sub(r'(://[^/]+/)(?:[^/]+/)*(?:mp4|mp3):', r'\1', media_url),
 106             'format_id': 'http',
 107             'quality': 1,
 108         }
 109         if not is_video:
 110             http_format['vcodec'] = 'none'
 111         formats.append(http_format)
 112
 113         download_urls = set()
 114         for m in re.finditer(
 115                 r'<option[^>]+value=(["\'])(?P<url>.+?)\1[^>]+data-file-download=[^>]+>\s*(?P<id>.+?)(?:(?:&nbsp;|\s+)\((?P<size>.+?)\))?\s*<', webpage):
 116             format_id = m.group('id').lower()
 117             if format_id in ('gif', 'jpeg'):
 118                 continue
 119             download_url = m.group('url')
 120             if download_url in download_urls:
 121                 continue
 122             download_urls.add(download_url)
 123             formats.append({
 124                 'url': download_url,
 125                 'format_id': format_id,
 126                 'filesize_approx': parse_filesize(m.group('size')),
 127             })
 128
 129         duration = float_or_none(data.get('duration'))
 130         view_count = int_or_none(data.get('viewCount'))
 131
 132         subtitles = {}
 133         cc_url = data.get('ccUrl')
 134         if cc_url:
 135             subtitles.setdefault('en', []).append({
 136                 'url': cc_url,
 137                 'ext': 'ttml',
 138             })
 139
 140         return {
 141             'id': video_id,
 142             'title': title,
 143             'thumbnail': self._og_search_thumbnail(webpage, default=None),
 144             'duration': duration,
 145             'view_count': view_count,
 146             'formats': formats,
 147             'subtitles': subtitles,
 148         }