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