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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8 from ..utils import (
   9     determine_ext,
  10     float_or_none,
  11     int_or_none,
  12     parse_filesize,
  13 )
  14
  15
  16 class LibraryOfCongressIE(InfoExtractor):
  17     IE_NAME = 'loc'
  18     IE_DESC = 'Library of Congress'
  19     _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P<id>[0-9a-z_.]+)'
  20     _TESTS = [{
  21         # embedded via <div class="media-player"
  22         'url': 'http://loc.gov/item/90716351/',
  23         'md5': '353917ff7f0255aa6d4b80a034833de8',
  24         'info_dict': {
  25             'id': '90716351',
  26             'ext': 'mp4',
  27             'title': "Pa's trip to Mars",
  28             'thumbnail': r're:^https?://.*\.jpg$',
  29             'duration': 0,
  30             'view_count': int,
  31         },
  32     }, {
  33         # webcast embedded via mediaObjectId
  34         'url': 'https://www.loc.gov/today/cyberlc/feature_wdesc.php?rec=5578',
  35         'info_dict': {
  36             'id': '5578',
  37             'ext': 'mp4',
  38             'title': 'Help! Preservation Training Needs Here, There & Everywhere',
  39             'duration': 3765,
  40             'view_count': int,
  41             'subtitles': 'mincount:1',
  42         },
  43         'params': {
  44             'skip_download': True,
  45         },
  46     }, {
  47         # with direct download links
  48         'url': 'https://www.loc.gov/item/78710669/',
  49         'info_dict': {
  50             'id': '78710669',
  51             'ext': 'mp4',
  52             'title': 'La vie et la passion de Jesus-Christ',
  53             'duration': 0,
  54             'view_count': int,
  55             'formats': 'mincount:4',
  56         },
  57         'params': {
  58             'skip_download': True,
  59         },
  60     }, {
  61         'url': 'https://www.loc.gov/item/ihas.200197114/',
  62         'only_matching': True,
  63     }, {
  64         'url': 'https://www.loc.gov/item/afc1981005_afs20503/',
  65         'only_matching': True,
  66     }]
  67
  68     def _real_extract(self, url):
  69         video_id = self._match_id(url)
  70         webpage = self._download_webpage(url, video_id)
  71
  72         media_id = self._search_regex(
  73             (r'id=(["\'])media-player-(?P<id>.+?)\1',
  74              r'<video[^>]+id=(["\'])uuid-(?P<id>.+?)\1',
  75              r'<video[^>]+data-uuid=(["\'])(?P<id>.+?)\1',
  76              r'mediaObjectId\s*:\s*(["\'])(?P<id>.+?)\1',
  77              r'data-tab="share-media-(?P<id>[0-9A-F]{32})"'),
  78             webpage, 'media id', group='id')
  79
  80         data = self._download_json(
  81             'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id,
  82             media_id)['mediaObject']
  83
  84         derivative = data['derivatives'][0]
  85         media_url = derivative['derivativeUrl']
  86
  87         title = derivative.get('shortName') or data.get('shortName') or self._og_search_title(
  88             webpage)
  89
  90         # Following algorithm was extracted from setAVSource js function
  91         # found in webpage
  92         media_url = media_url.replace('rtmp', 'https')
  93
  94         is_video = data.get('mediaType', 'v').lower() == 'v'
  95         ext = determine_ext(media_url)
  96         if ext not in ('mp4', 'mp3'):
  97             media_url += '.mp4' if is_video else '.mp3'
  98
  99         formats = []
 100         if '/vod/mp4:' in media_url:
 101             formats.append({
 102                 'url': media_url.replace('/vod/mp4:', '/hls-vod/media/') + '.m3u8',
 103                 'format_id': 'hls',
 104                 'ext': 'mp4',
 105                 'protocol': 'm3u8_native',
 106                 'quality': 1,
 107             })
 108         http_format = {
 109             'url': re.sub(r'(://[^/]+/)(?:[^/]+/)*(?:mp4|mp3):', r'\1', media_url),
 110             'format_id': 'http',
 111             'quality': 1,
 112         }
 113         if not is_video:
 114             http_format['vcodec'] = 'none'
 115         formats.append(http_format)
 116
 117         download_urls = set()
 118         for m in re.finditer(
 119                 r'<option[^>]+value=(["\'])(?P<url>.+?)\1[^>]+data-file-download=[^>]+>\s*(?P<id>.+?)(?:(?:&nbsp;|\s+)\((?P<size>.+?)\))?\s*<', webpage):
 120             format_id = m.group('id').lower()
 121             if format_id in ('gif', 'jpeg'):
 122                 continue
 123             download_url = m.group('url')
 124             if download_url in download_urls:
 125                 continue
 126             download_urls.add(download_url)
 127             formats.append({
 128                 'url': download_url,
 129                 'format_id': format_id,
 130                 'filesize_approx': parse_filesize(m.group('size')),
 131             })
 132
 133         self._sort_formats(formats)
 134
 135         duration = float_or_none(data.get('duration'))
 136         view_count = int_or_none(data.get('viewCount'))
 137
 138         subtitles = {}
 139         cc_url = data.get('ccUrl')
 140         if cc_url:
 141             subtitles.setdefault('en', []).append({
 142                 'url': cc_url,
 143                 'ext': 'ttml',
 144             })
 145
 146         return {
 147             'id': video_id,
 148             'title': title,
 149             'thumbnail': self._og_search_thumbnail(webpage, default=None),
 150             'duration': duration,
 151             'view_count': view_count,
 152             'formats': formats,
 153             'subtitles': subtitles,
 154         }