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