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 ..utils import (
   6     unified_strdate,
   7     int_or_none,
   8     qualities,
   9     unescapeHTML,
  10 )
  11
  12
  13 class OdnoklassnikiIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>\d+)'
  15     _TESTS = [{
  16         'url': 'http://ok.ru/video/20079905452',
  17         'md5': '8e24ad2da6f387948e7a7d44eb8668fe',
  18         'info_dict': {
  19             'id': '20079905452',
  20             'ext': 'mp4',
  21             'title': 'Культура меняет нас (прекрасный ролик!))',
  22             'duration': 100,
  23             'upload_date': '20141207',
  24             'uploader_id': '330537914540',
  25             'uploader': 'Виталий Добровольский',
  26             'like_count': int,
  27             'age_limit': 0,
  28         },
  29     }, {
  30         'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
  31         'only_matching': True,
  32     }]
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36
  37         webpage = self._download_webpage(url, video_id)
  38
  39         player = self._parse_json(
  40             unescapeHTML(self._search_regex(
  41                 r'data-attributes="([^"]+)"', webpage, 'player')),
  42             video_id)
  43
  44         metadata = self._parse_json(player['flashvars']['metadata'], video_id)
  45
  46         movie = metadata['movie']
  47         title = movie['title']
  48         thumbnail = movie.get('poster')
  49         duration = int_or_none(movie.get('duration'))
  50
  51         author = metadata.get('author', {})
  52         uploader_id = author.get('id')
  53         uploader = author.get('name')
  54
  55         upload_date = unified_strdate(self._html_search_meta(
  56             'ya:ovs:upload_date', webpage, 'upload date'))
  57
  58         age_limit = None
  59         adult = self._html_search_meta(
  60             'ya:ovs:adult', webpage, 'age limit')
  61         if adult:
  62             age_limit = 18 if adult == 'true' else 0
  63
  64         like_count = int_or_none(metadata.get('likeCount'))
  65
  66         quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd'))
  67
  68         formats = [{
  69             'url': f['url'],
  70             'ext': 'mp4',
  71             'format_id': f['name'],
  72             'quality': quality(f['name']),
  73         } for f in metadata['videos']]
  74
  75         return {
  76             'id': video_id,
  77             'title': title,
  78             'thumbnail': thumbnail,
  79             'duration': duration,
  80             'upload_date': upload_date,
  81             'uploader': uploader,
  82             'uploader_id': uploader_id,
  83             'like_count': like_count,
  84             'age_limit': age_limit,
  85             'formats': formats,
  86         }