youtube_dl/extractor/hgtv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     js_to_json,
   8     smuggle_url,
   9 )
  10
  11
  12 class HGTVIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?hgtv\.ca/[^/]+/video/(?P<id>[^/]+)/video.html'
  14     _TEST = {
  15         'url': 'http://www.hgtv.ca/homefree/video/overnight-success/video.html?v=738081859718&p=1&s=da#video',
  16         'md5': '',
  17         'info_dict': {
  18             'id': 'aFH__I_5FBOX',
  19             'ext': 'mp4',
  20             'title': 'Overnight Success',
  21             'description': 'After weeks of hard work, high stakes, breakdowns and pep talks, the final 2 contestants compete to win the ultimate dream.',
  22             'uploader': 'SHWM-NEW',
  23             'timestamp': 1470320034,
  24             'upload_date': '20160804',
  25         },
  26         'params': {
  27             # m3u8 download
  28             'skip_download': True,
  29         },
  30     }
  31
  32     def _real_extract(self, url):
  33         display_id = self._match_id(url)
  34         webpage = self._download_webpage(url, display_id)
  35         embed_vars = self._parse_json(self._search_regex(
  36             r'(?s)embed_vars\s*=\s*({.*?});',
  37             webpage, 'embed vars'), display_id, js_to_json)
  38         return {
  39             '_type': 'url_transparent',
  40             'url': smuggle_url(
  41                 'http://link.theplatform.com/s/dtjsEC/%s?mbr=true&manifest=m3u' % embed_vars['pid'], {
  42                     'force_smil_url': True
  43                 }),
  44             'series': embed_vars.get('show'),
  45             'season_number': int_or_none(embed_vars.get('season')),
  46             'episode_number': int_or_none(embed_vars.get('episode')),
  47             'ie_key': 'ThePlatform',
  48         }
  49
  50
  51 class HGTVComShowIE(InfoExtractor):
  52     IE_NAME = 'hgtv.com:show'
  53     _VALID_URL = r'https?://(?:www\.)?hgtv\.com/shows/[^/]+/(?P<id>[^/?#&]+)'
  54     _TEST = {
  55         'url': 'http://www.hgtv.com/shows/flip-or-flop/flip-or-flop-full-episodes-videos',
  56         'info_dict': {
  57             'id': 'flip-or-flop-full-episodes-videos',
  58             'title': 'Flip or Flop Full Episodes',
  59         },
  60         'playlist_mincount': 15,
  61     }
  62
  63     def _real_extract(self, url):
  64         display_id = self._match_id(url)
  65
  66         webpage = self._download_webpage(url, display_id)
  67
  68         config = self._parse_json(
  69             self._search_regex(
  70                 r'(?s)data-module=["\']video["\'][^>]*>.*?<script[^>]+type=["\']text/x-config["\'][^>]*>(.+?)</script',
  71                 webpage, 'video config'),
  72             display_id)['channels'][0]
  73
  74         entries = [
  75             self.url_result(video['releaseUrl'])
  76             for video in config['videos'] if video.get('releaseUrl')]
  77
  78         return self.playlist_result(
  79             entries, display_id, config.get('title'), config.get('description'))