youtube_dl/extractor/hgtv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class HGTVComShowIE(InfoExtractor):
   8     IE_NAME = 'hgtv.com:show'
   9     _VALID_URL = r'https?://(?:www\.)?hgtv\.com/shows/[^/]+/(?P<id>[^/?#&]+)'
  10     _TESTS = [{
  11         # data-module="video"
  12         'url': 'http://www.hgtv.com/shows/flip-or-flop/flip-or-flop-full-episodes-season-4-videos',
  13         'info_dict': {
  14             'id': 'flip-or-flop-full-episodes-season-4-videos',
  15             'title': 'Flip or Flop Full Episodes',
  16         },
  17         'playlist_mincount': 15,
  18     }, {
  19         # data-deferred-module="video"
  20         'url': 'http://www.hgtv.com/shows/good-bones/episodes/an-old-victorian-house-gets-a-new-facelift',
  21         'only_matching': True,
  22     }]
  23
  24     def _real_extract(self, url):
  25         display_id = self._match_id(url)
  26
  27         webpage = self._download_webpage(url, display_id)
  28
  29         config = self._parse_json(
  30             self._search_regex(
  31                 r'(?s)data-(?:deferred-)?module=["\']video["\'][^>]*>.*?<script[^>]+type=["\']text/x-config["\'][^>]*>(.+?)</script',
  32                 webpage, 'video config'),
  33             display_id)['channels'][0]
  34
  35         entries = [
  36             self.url_result(video['releaseUrl'])
  37             for video in config['videos'] if video.get('releaseUrl')]
  38
  39         return self.playlist_result(
  40             entries, display_id, config.get('title'), config.get('description'))