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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class DBTVIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?dagbladet\.no/video/(?:(?:embed|(?P<display_id>[^/]+))/)?(?P<id>[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8})'
  11     _TESTS = [{
  12         'url': 'https://www.dagbladet.no/video/PynxJnNWChE/',
  13         'md5': 'b8f850ba1860adbda668d367f9b77699',
  14         'info_dict': {
  15             'id': 'PynxJnNWChE',
  16             'ext': 'mp4',
  17             'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen',
  18             'description': 'md5:49cc8370e7d66e8a2ef15c3b4631fd3f',
  19             'thumbnail': r're:https?://.*\.jpg',
  20             'upload_date': '20160916',
  21             'duration': 69,
  22             'uploader_id': 'UCk5pvsyZJoYJBd7_oFPTlRQ',
  23             'uploader': 'Dagbladet',
  24         },
  25         'add_ie': ['Youtube']
  26     }, {
  27         'url': 'https://www.dagbladet.no/video/embed/xlGmyIeN9Jo/?autoplay=false',
  28         'only_matching': True,
  29     }, {
  30         'url': 'https://www.dagbladet.no/video/truer-iran-bor-passe-dere/PalfB2Cw',
  31         'only_matching': True,
  32     }]
  33
  34     @staticmethod
  35     def _extract_urls(webpage):
  36         return [url for _, url in re.findall(
  37             r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?dagbladet\.no/video/embed/(?:[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8}).*?)\1',
  38             webpage)]
  39
  40     def _real_extract(self, url):
  41         display_id, video_id = re.match(self._VALID_URL, url).groups()
  42         info = {
  43             '_type': 'url_transparent',
  44             'id': video_id,
  45             'display_id': display_id,
  46         }
  47         if len(video_id) == 11:
  48             info.update({
  49                 'url': video_id,
  50                 'ie_key': 'Youtube',
  51             })
  52         else:
  53             info.update({
  54                 'url': 'jwplatform:' + video_id,
  55                 'ie_key': 'JWPlatform',
  56             })
  57         return info