Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/mychannels.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class MyChannelsIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?mychannels\.com/.*(?P<id_type>video|production)_id=(?P<id>[0-9]+)'
  11     _TEST = {
  12         'url': 'https://mychannels.com/missholland/miss-holland?production_id=3416',
  13         'md5': 'b8993daad4262dd68d89d651c0c52c45',
  14         'info_dict': {
  15             'id': 'wUUDZZep6vQD',
  16             'ext': 'mp4',
  17             'title': 'Miss Holland joins VOTE LEAVE',
  18             'description': 'Miss Holland | #13 Not a potato',
  19             'uploader': 'Miss Holland',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         id_type, url_id = re.match(self._VALID_URL, url).groups()
  25         webpage = self._download_webpage(url, url_id)
  26         video_data = self._html_search_regex(r'<div([^>]+data-%s-id="%s"[^>]+)>' % (id_type, url_id), webpage, 'video data')
  27
  28         def extract_data_val(attr, fatal=False):
  29             return self._html_search_regex(r'data-%s\s*=\s*"([^"]+)"' % attr, video_data, attr, fatal=fatal)
  30         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')
  31
  32         return {
  33             '_type': 'url_transparent',
  34             'url': 'minoto:%s' % minoto_id,
  35             'id': url_id,
  36             'title': extract_data_val('title', True),
  37             'description': extract_data_val('description'),
  38             'thumbnail': extract_data_val('image'),
  39             'uploader': extract_data_val('channel'),
  40         }