yt_dlp/extractor/mychannels.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6
   7
   8 class MyChannelsIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?mychannels\.com/.*(?P<id_type>video|production)_id=(?P<id>[0-9]+)'
  10     _TEST = {
  11         'url': 'https://mychannels.com/missholland/miss-holland?production_id=3416',
  12         'md5': 'b8993daad4262dd68d89d651c0c52c45',
  13         'info_dict': {
  14             'id': 'wUUDZZep6vQD',
  15             'ext': 'mp4',
  16             'title': 'Miss Holland joins VOTE LEAVE',
  17             'description': 'Miss Holland | #13 Not a potato',
  18             'uploader': 'Miss Holland',
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         id_type, url_id = self._match_valid_url(url).groups()
  24         webpage = self._download_webpage(url, url_id)
  25         video_data = self._html_search_regex(r'<div([^>]+data-%s-id="%s"[^>]+)>' % (id_type, url_id), webpage, 'video data')
  26
  27         def extract_data_val(attr, fatal=False):
  28             return self._html_search_regex(r'data-%s\s*=\s*"([^"]+)"' % attr, video_data, attr, fatal=fatal)
  29         minoto_id = extract_data_val('minoto-id') or self._search_regex(r'/id/([a-zA-Z0-9]+)', extract_data_val('video-src', True), 'minoto id')
  30
  31         return {
  32             '_type': 'url_transparent',
  33             'url': 'minoto:%s' % minoto_id,
  34             'id': url_id,
  35             'title': extract_data_val('title', True),
  36             'description': extract_data_val('description'),
  37             'thumbnail': extract_data_val('image'),
  38             'uploader': extract_data_val('channel'),
  39         }