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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     extract_attributes,
   9 )
  10
  11
  12 class NZZIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?nzz\.ch/(?:[^/]+/)*[^/?#]+-ld\.(?P<id>\d+)'
  14     _TEST = {
  15         'url': 'http://www.nzz.ch/zuerich/gymizyte/gymizyte-schreiben-schueler-heute-noch-diktate-ld.9153',
  16         'info_dict': {
  17             'id': '9153',
  18         },
  19         'playlist_mincount': 6,
  20     }
  21
  22     def _real_extract(self, url):
  23         page_id = self._match_id(url)
  24         webpage = self._download_webpage(url, page_id)
  25
  26         entries = []
  27         for player_element in re.findall(r'(<[^>]+class="kalturaPlayer"[^>]*>)', webpage):
  28             player_params = extract_attributes(player_element)
  29             if player_params.get('data-type') not in ('kaltura_singleArticle',):
  30                 self.report_warning('Unsupported player type')
  31                 continue
  32             entry_id = player_params['data-id']
  33             entries.append(self.url_result(
  34                 'kaltura:1750922:' + entry_id, 'Kaltura', entry_id))
  35
  36         return self.playlist_result(entries, page_id)