youtube_dl/extractor/vrak.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from .brightcove import BrightcoveNewIE
   8 from ..utils import (
   9     int_or_none,
  10     parse_age_limit,
  11     smuggle_url,
  12     unescapeHTML,
  13 )
  14
  15
  16 class VrakIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?vrak\.tv/videos\?.*?\btarget=(?P<id>[\d.]+)'
  18     _TEST = {
  19         'url': 'http://www.vrak.tv/videos?target=1.2306782&filtre=emission&id=1.1806721',
  20         'info_dict': {
  21             'id': '5345661243001',
  22             'ext': 'mp4',
  23             'title': 'Obésité, film de hockey et Roseline Filion',
  24             'timestamp': 1488492126,
  25             'upload_date': '20170302',
  26             'uploader_id': '2890187628001',
  27             'creator': 'VRAK.TV',
  28             'age_limit': 8,
  29             'series': 'ALT (Actualité Légèrement Tordue)',
  30             'episode': 'Obésité, film de hockey et Roseline Filion',
  31             'tags': list,
  32         },
  33         'params': {
  34             'skip_download': True,
  35         },
  36     }
  37     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/2890187628001/default_default/index.html?videoId=%s'
  38
  39     def _real_extract(self, url):
  40         video_id = self._match_id(url)
  41
  42         webpage = self._download_webpage(url, video_id)
  43
  44         title = self._html_search_regex(
  45             r'<h\d\b[^>]+\bclass=["\']videoTitle["\'][^>]*>([^<]+)',
  46             webpage, 'title', default=None) or self._og_search_title(webpage)
  47
  48         content = self._parse_json(
  49             self._search_regex(
  50                 r'data-player-options-content=(["\'])(?P<content>{.+?})\1',
  51                 webpage, 'content', default='{}', group='content'),
  52             video_id, transform_source=unescapeHTML)
  53
  54         ref_id = content.get('refId') or self._search_regex(
  55             r'refId&quot;:&quot;([^&]+)&quot;', webpage, 'ref id')
  56
  57         brightcove_id = self._search_regex(
  58             r'''(?x)
  59                 java\.lang\.String\s+value\s*=\s*["']brightcove\.article\.\d+\.%s
  60                 [^>]*
  61                 java\.lang\.String\s+value\s*=\s*["'](\d+)
  62             ''' % re.escape(ref_id), webpage, 'brightcove id')
  63
  64         return {
  65             '_type': 'url_transparent',
  66             'ie_key': BrightcoveNewIE.ie_key(),
  67             'url': smuggle_url(
  68                 self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
  69                 {'geo_countries': ['CA']}),
  70             'id': brightcove_id,
  71             'description': content.get('description'),
  72             'creator': content.get('brand'),
  73             'age_limit': parse_age_limit(content.get('rating')),
  74             'series': content.get('showName') or content.get(
  75                 'episodeName'),  # this is intentional
  76             'season_number': int_or_none(content.get('seasonNumber')),
  77             'episode': title,
  78             'episode_number': int_or_none(content.get('episodeNumber')),
  79             'tags': content.get('tags', []),
  80         }