_ Git - youtube-dl/blob - youtube_dl/extractor/history.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import smuggle_url
   5 from ..compat import compat_urllib_parse
   6
   7
   8 class HistoryIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?history\.com/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])'
  10
  11     _TESTS = [{
  12         'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
  13         'md5': '6fe632d033c92aa10b8d4a9be047a7c5',
  14         'info_dict': {
  15             'id': 'bLx5Dv5Aka1G',
  16             'ext': 'mp4',
  17             'title': "Bet You Didn't Know: Valentine's Day",
  18             'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
  19         },
  20         'add_ie': ['ThePlatform'],
  21     }]
  22
  23     _VIDEO_URL_RE = [
  24         r"media_url\s*=\s*'[^']'",
  25         r'data-mediaurl="([^"]+)"'
  26     ]
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         webpage = self._download_webpage(url, video_id)
  32
  33         media_url = self._search_regex(self._VIDEO_URL_RE, webpage, 'video url')
  34
  35         pdk_signature = webpage = self._download_webpage(
  36             'https://signature.video.aetndigital.com/?' +
  37             compat_urllib_parse.urlencode({'url': media_url}), video_id)
  38
  39         return self.url_result(smuggle_url(
  40             media_url + '?mbr=true&format=smil&sig=' + pdk_signature, {'force_smil_url': True}))