Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rtbf.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     unescapeHTML,
   8 )
   9
  10
  11 class RTBFIE(InfoExtractor):
  12     _VALID_URL = r'https?://www.rtbf.be/video/[^\?]+\?id=(?P<id>\d+)'
  13     _TEST = {
  14         'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274',
  15         'md5': '799f334ddf2c0a582ba80c44655be570',
  16         'info_dict': {
  17             'id': '1921274',
  18             'ext': 'mp4',
  19             'title': 'Les Diables au coeur (épisode 2)',
  20             'duration': 3099,
  21         }
  22     }
  23
  24     _QUALITIES = [
  25         ('mobile', 'mobile'),
  26         ('web', 'SD'),
  27         ('url', 'MD'),
  28         ('high', 'HD'),
  29     ]
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33
  34         webpage = self._download_webpage(
  35             'http://www.rtbf.be/video/embed?id=%s' % video_id, video_id)
  36
  37         data = self._parse_json(
  38             unescapeHTML(self._search_regex(
  39                 r'data-video="([^"]+)"', webpage, 'data video')),
  40             video_id)
  41
  42         if data.get('provider').lower() == 'youtube':
  43             video_url = data.get('downloadUrl') or data.get('url')
  44             return self.url_result(video_url, 'Youtube')
  45         formats = []
  46         for key, format_id in self._QUALITIES:
  47             format_url = data['sources'].get(key)
  48             if format_url:
  49                 formats.append({
  50                     'format_id': format_id,
  51                     'url': format_url,
  52                 })
  53
  54         return {
  55             'id': video_id,
  56             'formats': formats,
  57             'title': data['title'],
  58             'description': data.get('description') or data.get('subtitle'),
  59             'thumbnail': data.get('thumbnail'),
  60             'duration': data.get('duration') or data.get('realDuration'),
  61             'timestamp': int_or_none(data.get('created')),
  62             'view_count': int_or_none(data.get('viewCount')),
  63         }