Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rtvnh.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import ExtractorError
   6
   7
   8 class RTVNHIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?rtvnh\.nl/video/(?P<id>[0-9]+)'
  10     _TEST = {
  11         'url': 'http://www.rtvnh.nl/video/131946',
  12         'md5': '6e1d0ab079e2a00b6161442d3ceacfc1',
  13         'info_dict': {
  14             'id': '131946',
  15             'ext': 'mp4',
  16             'title': 'Grote zoektocht in zee bij Zandvoort naar vermiste vrouw',
  17             'thumbnail': 're:^https?:.*\.jpg$'
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         video_id = self._match_id(url)
  23
  24         meta = self._parse_json(self._download_webpage(
  25             'http://www.rtvnh.nl/video/json?m=' + video_id, video_id), video_id)
  26
  27         status = meta.get('status')
  28         if status != 200:
  29             raise ExtractorError(
  30                 '%s returned error code %d' % (self.IE_NAME, status), expected=True)
  31
  32         formats = self._extract_smil_formats(
  33             'http://www.rtvnh.nl/video/smil?m=' + video_id, video_id, fatal=False)
  34
  35         for item in meta['source']['fb']:
  36             if item.get('type') == 'hls':
  37                 formats.extend(self._extract_m3u8_formats(
  38                     item['file'], video_id, ext='mp4', entry_protocol='m3u8_native'))
  39             elif item.get('type') == '':
  40                 formats.append({'url': item['file']})
  41         self._sort_formats(formats)
  42
  43         return {
  44             'id': video_id,
  45             'title': meta['title'].strip(),
  46             'thumbnail': meta.get('image'),
  47             'formats': formats
  48         }