youtube_dl/extractor/viki.py

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