_ Git - youtube-dl/blob - youtube_dl/extractor/viki.py

   1 import re
   2
   3 from ..utils import (
   4     unified_strdate,
   5 )
   6 from .subtitles import SubtitlesInfoExtractor
   7
   8
   9 class VikiIE(SubtitlesInfoExtractor):
  10     IE_NAME = u'viki'
  11
  12     _VALID_URL = r'^https?://(?:www\.)?viki\.com/videos/(?P<id>[0-9]+v)'
  13     _TEST = {
  14         u'url': u'http://www.viki.com/videos/1023585v-heirs-episode-14',
  15         u'file': u'1023585v.mp4',
  16         u'md5': u'a21454021c2646f5433514177e2caa5f',
  17         u'info_dict': {
  18             u'title': u'Heirs Episode 14',
  19             u'uploader': u'SBS',
  20             u'description': u'md5:c4b17b9626dd4b143dcc4d855ba3474e',
  21             u'upload_date': u'20131121',
  22             u'age_limit': 13,
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         video_id = mobj.group(1)
  29
  30         webpage = self._download_webpage(url, video_id)
  31         title = self._og_search_title(webpage)
  32         description = self._og_search_description(webpage)
  33         thumbnail = self._og_search_thumbnail(webpage)
  34
  35         uploader = self._html_search_regex(
  36             r'<strong>Broadcast Network: </strong>\s*([^<]*)<', webpage,
  37             u'uploader')
  38         if uploader is not None:
  39             uploader = uploader.strip()
  40
  41         rating_str = self._html_search_regex(
  42             r'<strong>Rating: </strong>\s*([^<]*)<', webpage,
  43             u'rating information', default='').strip()
  44         RATINGS = {
  45             'G': 0,
  46             'PG': 10,
  47             'PG-13': 13,
  48             'R': 16,
  49             'NC': 18,
  50         }
  51         age_limit = RATINGS.get(rating_str)
  52
  53         info_url = 'http://www.viki.com/player5_fragment/%s?action=show&controller=videos' % video_id
  54         info_webpage = self._download_webpage(
  55             info_url, video_id, note=u'Downloading info page')
  56         video_url = self._html_search_regex(
  57             r'<source[^>]+src="([^"]+)"', info_webpage, u'video URL')
  58
  59         upload_date_str = self._html_search_regex(
  60             r'"created_at":"([^"]+)"', info_webpage, u'upload date')
  61         upload_date = (
  62             unified_strdate(upload_date_str)
  63             if upload_date_str is not None
  64             else None
  65         )
  66
  67         # subtitles
  68         video_subtitles = self.extract_subtitles(video_id, info_webpage)
  69         if self._downloader.params.get('listsubtitles', False):
  70             self._list_available_subtitles(video_id, info_webpage)
  71             return
  72
  73         return {
  74             'id': video_id,
  75             'title': title,
  76             'url': video_url,
  77             'description': description,
  78             'thumbnail': thumbnail,
  79             'age_limit': age_limit,
  80             'uploader': uploader,
  81             'subtitles': video_subtitles,
  82             'upload_date': upload_date,
  83         }
  84
  85     def _get_available_subtitles(self, video_id, info_webpage):
  86         res = {}
  87         for sturl in re.findall(r'<track src="([^"]+)"/>'):
  88             m = re.search(r'/(?P<lang>[a-z]+)\.vtt', sturl)
  89             if not m:
  90                 continue
  91             res[m.group('lang')] = sturl
  92         return res