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
   6 from ..utils import (
   7     unified_strdate,
   8     int_or_none,
   9     qualities,
  10     unescapeHTML,
  11 )
  12
  13
  14 class OdnoklassnikiIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
  16     _TESTS = [{
  17         # metadata in JSON
  18         'url': 'http://ok.ru/video/20079905452',
  19         'md5': '8e24ad2da6f387948e7a7d44eb8668fe',
  20         'info_dict': {
  21             'id': '20079905452',
  22             'ext': 'mp4',
  23             'title': 'Культура меняет нас (прекрасный ролик!))',
  24             'duration': 100,
  25             'uploader_id': '330537914540',
  26             'uploader': 'Виталий Добровольский',
  27             'like_count': int,
  28         },
  29     }, {
  30         # metadataUrl
  31         'url': 'http://ok.ru/video/63567059965189-0',
  32         'md5': '9676cf86eff5391d35dea675d224e131',
  33         'info_dict': {
  34             'id': '63567059965189-0',
  35             'ext': 'mp4',
  36             'title': 'Девушка без комплексов ...',
  37             'duration': 191,
  38             'uploader_id': '534380003155',
  39             'uploader': 'Андрей Мещанинов',
  40             'like_count': int,
  41         },
  42     }, {
  43         'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
  44         'only_matching': True,
  45     }]
  46
  47     def _real_extract(self, url):
  48         video_id = self._match_id(url)
  49
  50         webpage = self._download_webpage(
  51             'http://ok.ru/video/%s' % video_id, video_id)
  52
  53         player = self._parse_json(
  54             unescapeHTML(self._search_regex(
  55                 r'data-attributes="([^"]+)"', webpage, 'player')),
  56             video_id)
  57
  58         flashvars = player['flashvars']
  59
  60         metadata = flashvars.get('metadata')
  61         if metadata:
  62             metadata = self._parse_json(metadata, video_id)
  63         else:
  64             metadata = self._download_json(
  65                 compat_urllib_parse.unquote(flashvars['metadataUrl']),
  66                 video_id, 'Downloading metadata JSON')
  67
  68         movie = metadata['movie']
  69         title = movie['title']
  70         thumbnail = movie.get('poster')
  71         duration = int_or_none(movie.get('duration'))
  72
  73         author = metadata.get('author', {})
  74         uploader_id = author.get('id')
  75         uploader = author.get('name')
  76
  77         upload_date = unified_strdate(self._html_search_meta(
  78             'ya:ovs:upload_date', webpage, 'upload date', default=None))
  79
  80         age_limit = None
  81         adult = self._html_search_meta(
  82             'ya:ovs:adult', webpage, 'age limit', default=None)
  83         if adult:
  84             age_limit = 18 if adult == 'true' else 0
  85
  86         like_count = int_or_none(metadata.get('likeCount'))
  87
  88         quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd'))
  89
  90         formats = [{
  91             'url': f['url'],
  92             'ext': 'mp4',
  93             'format_id': f['name'],
  94             'quality': quality(f['name']),
  95         } for f in metadata['videos']]
  96
  97         return {
  98             'id': video_id,
  99             'title': title,
 100             'thumbnail': thumbnail,
 101             'duration': duration,
 102             'upload_date': upload_date,
 103             'uploader': uploader,
 104             'uploader_id': uploader_id,
 105             'like_count': like_count,
 106             'age_limit': age_limit,
 107             'formats': formats,
 108         }