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 (
   6     compat_parse_qs,
   7     compat_urllib_parse_unquote,
   8     compat_urllib_parse_urlparse,
   9 )
  10 from ..utils import (
  11     ExtractorError,
  12     unified_strdate,
  13     int_or_none,
  14     qualities,
  15     unescapeHTML,
  16 )
  17
  18
  19 class OdnoklassnikiIE(InfoExtractor):
  20     _VALID_URL = r'https?://(?:(?:www|m|mobile)\.)?(?:odnoklassniki|ok)\.ru/(?:video(?:embed)?|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
  21     _TESTS = [{
  22         # metadata in JSON
  23         'url': 'http://ok.ru/video/20079905452',
  24         'md5': '6ba728d85d60aa2e6dd37c9e70fdc6bc',
  25         'info_dict': {
  26             'id': '20079905452',
  27             'ext': 'mp4',
  28             'title': 'Культура меняет нас (прекрасный ролик!))',
  29             'duration': 100,
  30             'upload_date': '20141207',
  31             'uploader_id': '330537914540',
  32             'uploader': 'Виталий Добровольский',
  33             'like_count': int,
  34             'age_limit': 0,
  35         },
  36         'skip': 'Video has been blocked',
  37     }, {
  38         # metadataUrl
  39         'url': 'http://ok.ru/video/63567059965189-0?fromTime=5',
  40         'md5': '9676cf86eff5391d35dea675d224e131',
  41         'info_dict': {
  42             'id': '63567059965189-0',
  43             'ext': 'mp4',
  44             'title': 'Девушка без комплексов ...',
  45             'duration': 191,
  46             'upload_date': '20150518',
  47             'uploader_id': '534380003155',
  48             'uploader': '☭ Андрей Мещанинов ☭',
  49             'like_count': int,
  50             'age_limit': 0,
  51             'start_time': 5,
  52         },
  53     }, {
  54         # YouTube embed (metadataUrl, provider == USER_YOUTUBE)
  55         'url': 'http://ok.ru/video/64211978996595-1',
  56         'md5': '5d7475d428845cd2e13bae6f1a992278',
  57         'info_dict': {
  58             'id': '64211978996595-1',
  59             'ext': 'mp4',
  60             'title': 'Космическая среда от 26 августа 2015',
  61             'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0',
  62             'duration': 440,
  63             'upload_date': '20150826',
  64             'uploader_id': '750099571',
  65             'uploader': 'Алина П',
  66             'age_limit': 0,
  67         },
  68     }, {
  69         # YouTube embed (metadata, provider == USER_YOUTUBE, no metadata.movie.title field)
  70         'url': 'http://ok.ru/video/62036049272859-0',
  71         'info_dict': {
  72             'id': '62036049272859-0',
  73             'ext': 'mp4',
  74             'title': 'МУЗЫКА     ДОЖДЯ .',
  75             'description': 'md5:6f1867132bd96e33bf53eda1091e8ed0',
  76             'upload_date': '20120106',
  77             'uploader_id': '473534735899',
  78             'uploader': 'МARINA D',
  79             'age_limit': 0,
  80         },
  81         'params': {
  82             'skip_download': True,
  83         },
  84     }, {
  85         'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
  86         'only_matching': True,
  87     }, {
  88         'url': 'http://www.ok.ru/video/20648036891',
  89         'only_matching': True,
  90     }, {
  91         'url': 'http://www.ok.ru/videoembed/20648036891',
  92         'only_matching': True,
  93     }, {
  94         'url': 'http://m.ok.ru/video/20079905452',
  95         'only_matching': True,
  96     }, {
  97         'url': 'http://mobile.ok.ru/video/20079905452',
  98         'only_matching': True,
  99     }]
 100
 101     def _real_extract(self, url):
 102         start_time = int_or_none(compat_parse_qs(
 103             compat_urllib_parse_urlparse(url).query).get('fromTime', [None])[0])
 104
 105         video_id = self._match_id(url)
 106
 107         webpage = self._download_webpage(
 108             'http://ok.ru/video/%s' % video_id, video_id)
 109
 110         error = self._search_regex(
 111             r'[^>]+class="vp_video_stub_txt"[^>]*>([^<]+)<',
 112             webpage, 'error', default=None)
 113         if error:
 114             raise ExtractorError(error, expected=True)
 115
 116         player = self._parse_json(
 117             unescapeHTML(self._search_regex(
 118                 r'data-options=(?P<quote>["\'])(?P<player>{.+?%s.+?})(?P=quote)' % video_id,
 119                 webpage, 'player', group='player')),
 120             video_id)
 121
 122         flashvars = player['flashvars']
 123
 124         metadata = flashvars.get('metadata')
 125         if metadata:
 126             metadata = self._parse_json(metadata, video_id)
 127         else:
 128             metadata = self._download_json(
 129                 compat_urllib_parse_unquote(flashvars['metadataUrl']),
 130                 video_id, 'Downloading metadata JSON')
 131
 132         movie = metadata['movie']
 133
 134         # Some embedded videos may not contain title in movie dict (e.g.
 135         # http://ok.ru/video/62036049272859-0) thus we allow missing title
 136         # here and it's going to be extracted later by an extractor that
 137         # will process the actual embed.
 138         provider = metadata.get('provider')
 139         title = movie['title'] if provider == 'UPLOADED_ODKL' else movie.get('title')
 140
 141         thumbnail = movie.get('poster')
 142         duration = int_or_none(movie.get('duration'))
 143
 144         author = metadata.get('author', {})
 145         uploader_id = author.get('id')
 146         uploader = author.get('name')
 147
 148         upload_date = unified_strdate(self._html_search_meta(
 149             'ya:ovs:upload_date', webpage, 'upload date', default=None))
 150
 151         age_limit = None
 152         adult = self._html_search_meta(
 153             'ya:ovs:adult', webpage, 'age limit', default=None)
 154         if adult:
 155             age_limit = 18 if adult == 'true' else 0
 156
 157         like_count = int_or_none(metadata.get('likeCount'))
 158
 159         info = {
 160             'id': video_id,
 161             'title': title,
 162             'thumbnail': thumbnail,
 163             'duration': duration,
 164             'upload_date': upload_date,
 165             'uploader': uploader,
 166             'uploader_id': uploader_id,
 167             'like_count': like_count,
 168             'age_limit': age_limit,
 169             'start_time': start_time,
 170         }
 171
 172         if provider == 'USER_YOUTUBE':
 173             info.update({
 174                 '_type': 'url_transparent',
 175                 'url': movie['contentId'],
 176             })
 177             return info
 178
 179         quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd'))
 180
 181         formats = [{
 182             'url': f['url'],
 183             'ext': 'mp4',
 184             'format_id': f['name'],
 185             'quality': quality(f['name']),
 186         } for f in metadata['videos']]
 187         self._sort_formats(formats)
 188
 189         info['formats'] = formats
 190         return info