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

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