youtube_dl/extractor/freespeech.py



    1 from __future__ import unicode_literals
    2 
    3 from .common import InfoExtractor
    4 
    5 
    6 class FreespeechIE(InfoExtractor):
    7     IE_NAME = 'freespeech.org'
    8     _VALID_URL = r'https?://(?:www\.)?freespeech\.org/stories/(?P<id>.+)'
    9     _TEST = {
   10         'add_ie': ['Youtube'],
   11         'url': 'http://www.freespeech.org/stories/fcc-announces-net-neutrality-rollback-whats-stake/',
   12         'info_dict': {
   13             'id': 'waRk6IPqyWM',
   14             'ext': 'mp4',
   15             'title': 'What\'s At Stake - Net Neutrality Special',
   16             'description': 'Presented by MNN and FSTV',
   17             'upload_date': '20170728',
   18             'uploader_id': 'freespeechtv',
   19             'uploader': 'freespeechtv',
   20         },
   21     }
   22 
   23     def _real_extract(self, url):
   24         display_id = self._match_id(url)
   25         webpage = self._download_webpage(url, display_id)
   26         youtube_url = self._search_regex(
   27             r'data-video-url="([^"]+)"',
   28             webpage, 'youtube url')
   29 
   30         return {
   31             '_type': 'url',
   32             'url': youtube_url,
   33             'ie_key': 'Youtube',
   34         }