Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/archiveorg.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import unified_strdate
   5
   6
   7 class ArchiveOrgIE(InfoExtractor):
   8     IE_NAME = 'archive.org'
   9     IE_DESC = 'archive.org videos'
  10     _VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
  11     _TESTS = [{
  12         'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
  13         'md5': '8af1d4cf447933ed3c7f4871162602db',
  14         'info_dict': {
  15             'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
  16             'ext': 'ogv',
  17             'title': '1968 Demo - FJCC Conference Presentation Reel #1',
  18             'description': 'md5:1780b464abaca9991d8968c877bb53ed',
  19             'upload_date': '19681210',
  20             'uploader': 'SRI International'
  21         }
  22     }, {
  23         'url': 'https://archive.org/details/Cops1922',
  24         'md5': '18f2a19e6d89af8425671da1cf3d4e04',
  25         'info_dict': {
  26             'id': 'Cops1922',
  27             'ext': 'ogv',
  28             'title': 'Buster Keaton\'s "Cops" (1922)',
  29             'description': 'md5:70f72ee70882f713d4578725461ffcc3',
  30         }
  31     }]
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35
  36         json_url = url + ('?' if '?' in url else '&') + 'output=json'
  37         data = self._download_json(json_url, video_id)
  38
  39         def get_optional(data_dict, field):
  40             return data_dict['metadata'].get(field, [None])[0]
  41
  42         title = get_optional(data, 'title')
  43         description = get_optional(data, 'description')
  44         uploader = get_optional(data, 'creator')
  45         upload_date = unified_strdate(get_optional(data, 'date'))
  46
  47         formats = [
  48             {
  49                 'format': fdata['format'],
  50                 'url': 'http://' + data['server'] + data['dir'] + fn,
  51                 'file_size': int(fdata['size']),
  52             }
  53             for fn, fdata in data['files'].items()
  54             if 'Video' in fdata['format']]
  55
  56         self._sort_formats(formats)
  57
  58         return {
  59             '_type': 'video',
  60             'id': video_id,
  61             'title': title,
  62             'formats': formats,
  63             'description': description,
  64             'uploader': uploader,
  65             'upload_date': upload_date,
  66             'thumbnail': data.get('misc', {}).get('image'),
  67         }