Raphaël G. Git Repositories - youtubedl/blob - 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     _TEST = {
  11         'url': 'http://www.hgtv.com/shows/flip-or-flop/flip-or-flop-full-episodes-videos',
  12         'info_dict': {
  13             'id': 'flip-or-flop-full-episodes-videos',
  14             'title': 'Flip or Flop Full Episodes',
  15         },
  16         'playlist_mincount': 15,
  17     }
  18
  19     def _real_extract(self, url):
  20         display_id = self._match_id(url)
  21
  22         webpage = self._download_webpage(url, display_id)
  23
  24         config = self._parse_json(
  25             self._search_regex(
  26                 r'(?s)data-module=["\']video["\'][^>]*>.*?<script[^>]+type=["\']text/x-config["\'][^>]*>(.+?)</script',
  27                 webpage, 'video config'),
  28             display_id)['channels'][0]
  29
  30         entries = [
  31             self.url_result(video['releaseUrl'])
  32             for video in config['videos'] if video.get('releaseUrl')]
  33
  34         return self.playlist_result(
  35             entries, display_id, config.get('title'), config.get('description'))