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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urllib_parse_unquote
   6 from ..utils import (
   7     ExtractorError,
   8     unified_strdate,
   9     int_or_none,
  10     qualities,
  11     unescapeHTML,
  12 )
  13
  14
  15 class OdnoklassnikiIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?(?:odnoklassniki|ok)\.ru/(?:video(?:embed)?|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
  17     _TESTS = [{
  18         # metadata in JSON
  19         'url': 'http://ok.ru/video/20079905452',
  20         'md5': '6ba728d85d60aa2e6dd37c9e70fdc6bc',
  21         'info_dict': {
  22             'id': '20079905452',
  23             'ext': 'mp4',
  24             'title': 'Культура меняет нас (прекрасный ролик!))',
  25             'duration': 100,
  26             'upload_date': '20141207',
  27             'uploader_id': '330537914540',
  28             'uploader': 'Виталий Добровольский',
  29             'like_count': int,
  30             'age_limit': 0,
  31         },
  32         'skip': 'Video has been blocked',
  33     }, {
  34         # metadataUrl
  35         'url': 'http://ok.ru/video/63567059965189-0',
  36         'md5': '9676cf86eff5391d35dea675d224e131',
  37         'info_dict': {
  38             'id': '63567059965189-0',
  39             'ext': 'mp4',
  40             'title': 'Девушка без комплексов ...',
  41             'duration': 191,
  42             'upload_date': '20150518',
  43             'uploader_id': '534380003155',
  44             'uploader': '☭ Андрей Мещанинов ☭',
  45             'like_count': int,
  46             'age_limit': 0,
  47         },
  48     }, {
  49         # YouTube embed (metadataUrl, provider == USER_YOUTUBE)
  50         'url': 'http://ok.ru/video/64211978996595-1',
  51         'md5': '5d7475d428845cd2e13bae6f1a992278',
  52         'info_dict': {
  53             'id': '64211978996595-1',
  54             'ext': 'mp4',
  55             'title': 'Космическая среда от 26 августа 2015',
  56             'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0',
  57             'duration': 440,
  58             'upload_date': '20150826',
  59             'uploader_id': '750099571',
  60             'uploader': 'Алина П',
  61             'age_limit': 0,
  62         },
  63     }, {
  64         'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
  65         'only_matching': True,
  66     }, {
  67         'url': 'http://www.ok.ru/video/20648036891',
  68         'only_matching': True,
  69     }, {
  70         'url': 'http://www.ok.ru/videoembed/20648036891',
  71         'only_matching': True,
  72     }]
  73
  74     def _real_extract(self, url):
  75         video_id = self._match_id(url)
  76
  77         webpage = self._download_webpage(
  78             'http://ok.ru/video/%s' % video_id, video_id)
  79
  80         error = self._search_regex(
  81             r'[^>]+class="vp_video_stub_txt"[^>]*>([^<]+)<',
  82             webpage, 'error', default=None)
  83         if error:
  84             raise ExtractorError(error, expected=True)
  85
  86         player = self._parse_json(
  87             unescapeHTML(self._search_regex(
  88                 r'data-options=(?P<quote>["\'])(?P<player>{.+?%s.+?})(?P=quote)' % video_id,
  89                 webpage, 'player', group='player')),
  90             video_id)
  91
  92         flashvars = player['flashvars']
  93
  94         metadata = flashvars.get('metadata')
  95         if metadata:
  96             metadata = self._parse_json(metadata, video_id)
  97         else:
  98             metadata = self._download_json(
  99                 compat_urllib_parse_unquote(flashvars['metadataUrl']),
 100                 video_id, 'Downloading metadata JSON')
 101
 102         movie = metadata['movie']
 103         title = movie['title']
 104         thumbnail = movie.get('poster')
 105         duration = int_or_none(movie.get('duration'))
 106
 107         author = metadata.get('author', {})
 108         uploader_id = author.get('id')
 109         uploader = author.get('name')
 110
 111         upload_date = unified_strdate(self._html_search_meta(
 112             'ya:ovs:upload_date', webpage, 'upload date', default=None))
 113
 114         age_limit = None
 115         adult = self._html_search_meta(
 116             'ya:ovs:adult', webpage, 'age limit', default=None)
 117         if adult:
 118             age_limit = 18 if adult == 'true' else 0
 119
 120         like_count = int_or_none(metadata.get('likeCount'))
 121
 122         info = {
 123             'id': video_id,
 124             'title': title,
 125             'thumbnail': thumbnail,
 126             'duration': duration,
 127             'upload_date': upload_date,
 128             'uploader': uploader,
 129             'uploader_id': uploader_id,
 130             'like_count': like_count,
 131             'age_limit': age_limit,
 132         }
 133
 134         if metadata.get('provider') == 'USER_YOUTUBE':
 135             info.update({
 136                 '_type': 'url_transparent',
 137                 'url': movie['contentId'],
 138             })
 139             return info
 140
 141         quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd'))
 142
 143         formats = [{
 144             'url': f['url'],
 145             'ext': 'mp4',
 146             'format_id': f['name'],
 147             'quality': quality(f['name']),
 148         } for f in metadata['videos']]
 149         self._sort_formats(formats)
 150
 151         info['formats'] = formats
 152         return info