1 from __future__ import unicode_literals
3 from .common import InfoExtractor
10 class NationalGeographicIE(InfoExtractor):
11 _VALID_URL = r'http://video\.nationalgeographic\.com/video/.*?'
14 'url': 'http://video.nationalgeographic.com/video/news/150210-news-crab-mating-vin?source=featuredvideo',
18 'title': 'Mating Crabs Busted by Sharks',
19 'description': 'md5:16f25aeffdeba55aaa8ec37e093ad8b3',
21 'add_ie': ['ThePlatform'],
24 def _real_extract(self, url):
25 name = url_basename(url)
27 webpage = self._download_webpage(url, name)
28 feed_url = self._search_regex(r'data-feed-url="([^"]+)"', webpage, 'feed url')
29 guid = self._search_regex(r'data-video-guid="([^"]+)"', webpage, 'guid')
31 feed = self._download_xml('%s?byGuid=%s' % (feed_url, guid), name)
32 content = feed.find('.//{http://search.yahoo.com/mrss/}content')
33 theplatform_id = url_basename(content.attrib.get('url'))
35 return self.url_result(smuggle_url(
36 'http://link.theplatform.com/s/ngs/%s?format=SMIL&formats=MPEG4&manifest=f4m' % theplatform_id,
37 # For some reason, the normal links don't work and we must force the use of f4m
38 {'force_smil_url': True}))