youtube_dl/extractor/cultureunplugged.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import time
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     int_or_none,
   9     HEADRequest,
  10 )
  11
  12
  13 class CultureUnpluggedIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?cultureunplugged\.com/documentary/watch-online/play/(?P<id>\d+)(?:/(?P<display_id>[^/]+))?'
  15     _TESTS = [{
  16         'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662/The-Next--Best-West',
  17         'md5': 'ac6c093b089f7d05e79934dcb3d228fc',
  18         'info_dict': {
  19             'id': '53662',
  20             'display_id': 'The-Next--Best-West',
  21             'ext': 'mp4',
  22             'title': 'The Next, Best West',
  23             'description': 'md5:0423cd00833dea1519cf014e9d0903b1',
  24             'thumbnail': r're:^https?://.*\.jpg$',
  25             'creator': 'Coldstream Creative',
  26             'duration': 2203,
  27             'view_count': int,
  28         }
  29     }, {
  30         'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662',
  31         'only_matching': True,
  32     }]
  33
  34     def _real_extract(self, url):
  35         mobj = re.match(self._VALID_URL, url)
  36         video_id = mobj.group('id')
  37         display_id = mobj.group('display_id') or video_id
  38
  39         # request setClientTimezone.php to get PHPSESSID cookie which is need to get valid json data in the next request
  40         self._request_webpage(HEADRequest(
  41             'http://www.cultureunplugged.com/setClientTimezone.php?timeOffset=%d' % -(time.timezone / 3600)), display_id)
  42         movie_data = self._download_json(
  43             'http://www.cultureunplugged.com/movie-data/cu-%s.json' % video_id, display_id)
  44
  45         video_url = movie_data['url']
  46         title = movie_data['title']
  47
  48         description = movie_data.get('synopsis')
  49         creator = movie_data.get('producer')
  50         duration = int_or_none(movie_data.get('duration'))
  51         view_count = int_or_none(movie_data.get('views'))
  52
  53         thumbnails = [{
  54             'url': movie_data['%s_thumb' % size],
  55             'id': size,
  56             'preference': preference,
  57         } for preference, size in enumerate((
  58             'small', 'large')) if movie_data.get('%s_thumb' % size)]
  59
  60         return {
  61             'id': video_id,
  62             'display_id': display_id,
  63             'url': video_url,
  64             'title': title,
  65             'description': description,
  66             'creator': creator,
  67             'duration': duration,
  68             'view_count': view_count,
  69             'thumbnails': thumbnails,
  70         }