Raphaël G. Git Repositories - youtubedl/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': '6ec0ae8f07f86731b1b2ff70f046210a',
  24         'info_dict': {
  25             'id': '90716351',
  26             'ext': 'mp4',
  27             'title': "Pa's trip to Mars",
  28             'duration': 0,
  29             'view_count': int,
  30         },
  31     }, {
  32         # webcast embedded via mediaObjectId
  33         'url': 'https://www.loc.gov/today/cyberlc/feature_wdesc.php?rec=5578',
  34         'info_dict': {
  35             'id': '5578',
  36             'ext': 'mp4',
  37             'title': 'Help! Preservation Training Needs Here, There & Everywhere',
  38             'duration': 3765,
  39             'view_count': int,
  40             'subtitles': 'mincount:1',
  41         },
  42         'params': {
  43             'skip_download': True,
  44         },
  45     }, {
  46         # with direct download links
  47         'url': 'https://www.loc.gov/item/78710669/',
  48         'info_dict': {
  49             'id': '78710669',
  50             'ext': 'mp4',
  51             'title': 'La vie et la passion de Jesus-Christ',
  52             'duration': 0,
  53             'view_count': int,
  54             'formats': 'mincount:4',
  55         },
  56         'params': {
  57             'skip_download': True,
  58         },
  59     }, {
  60         'url': 'https://www.loc.gov/item/ihas.200197114/',
  61         'only_matching': True,
  62     }, {
  63         'url': 'https://www.loc.gov/item/afc1981005_afs20503/',
  64         'only_matching': True,
  65     }]
  66
  67     def _real_extract(self, url):
  68         video_id = self._match_id(url)
  69         webpage = self._download_webpage(url, video_id)
  70
  71         media_id = self._search_regex(
  72             (r'id=(["\'])media-player-(?P<id>.+?)\1',
  73              r'<video[^>]+id=(["\'])uuid-(?P<id>.+?)\1',
  74              r'<video[^>]+data-uuid=(["\'])(?P<id>.+?)\1',
  75              r'mediaObjectId\s*:\s*(["\'])(?P<id>.+?)\1',
  76              r'data-tab="share-media-(?P<id>[0-9A-F]{32})"'),
  77             webpage, 'media id', group='id')
  78
  79         data = self._download_json(
  80             'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id,
  81             media_id)['mediaObject']
  82
  83         derivative = data['derivatives'][0]
  84         media_url = derivative['derivativeUrl']
  85
  86         title = derivative.get('shortName') or data.get('shortName') or self._og_search_title(
  87             webpage)
  88
  89         # Following algorithm was extracted from setAVSource js function
  90         # found in webpage
  91         media_url = media_url.replace('rtmp', 'https')
  92
  93         is_video = data.get('mediaType', 'v').lower() == 'v'
  94         ext = determine_ext(media_url)
  95         if ext not in ('mp4', 'mp3'):
  96             media_url += '.mp4' if is_video else '.mp3'
  97
  98         formats = []
  99         if '/vod/mp4:' in media_url:
 100             formats.append({
 101                 'url': media_url.replace('/vod/mp4:', '/hls-vod/media/') + '.m3u8',
 102                 'format_id': 'hls',
 103                 'ext': 'mp4',
 104                 'protocol': 'm3u8_native',
 105                 'quality': 1,
 106             })
 107         http_format = {
 108             'url': re.sub(r'(://[^/]+/)(?:[^/]+/)*(?:mp4|mp3):', r'\1', media_url),
 109             'format_id': 'http',
 110             'quality': 1,
 111         }
 112         if not is_video:
 113             http_format['vcodec'] = 'none'
 114         formats.append(http_format)
 115
 116         download_urls = set()
 117         for m in re.finditer(
 118                 r'<option[^>]+value=(["\'])(?P<url>.+?)\1[^>]+data-file-download=[^>]+>\s*(?P<id>.+?)(?:(?:&nbsp;|\s+)\((?P<size>.+?)\))?\s*<', webpage):
 119             format_id = m.group('id').lower()
 120             if format_id in ('gif', 'jpeg'):
 121                 continue
 122             download_url = m.group('url')
 123             if download_url in download_urls:
 124                 continue
 125             download_urls.add(download_url)
 126             formats.append({
 127                 'url': download_url,
 128                 'format_id': format_id,
 129                 'filesize_approx': parse_filesize(m.group('size')),
 130             })
 131
 132         self._sort_formats(formats)
 133
 134         duration = float_or_none(data.get('duration'))
 135         view_count = int_or_none(data.get('viewCount'))
 136
 137         subtitles = {}
 138         cc_url = data.get('ccUrl')
 139         if cc_url:
 140             subtitles.setdefault('en', []).append({
 141                 'url': cc_url,
 142                 'ext': 'ttml',
 143             })
 144
 145         return {
 146             'id': video_id,
 147             'title': title,
 148             'thumbnail': self._og_search_thumbnail(webpage, default=None),
 149             'duration': duration,
 150             'view_count': view_count,
 151             'formats': formats,
 152             'subtitles': subtitles,
 153         }