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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     smuggle_url,
   6     url_basename,
   7 )
   8
   9
  10 class NationalGeographicIE(InfoExtractor):
  11     _VALID_URL = r'http://video\.nationalgeographic\.com/video/.*?'
  12
  13     _TEST = {
  14         'url': 'http://video.nationalgeographic.com/video/news/150210-news-crab-mating-vin?source=featuredvideo',
  15         'info_dict': {
  16             'id': '4DmDACA6Qtk_',
  17             'ext': 'flv',
  18             'title': 'Mating Crabs Busted by Sharks',
  19             'description': 'md5:16f25aeffdeba55aaa8ec37e093ad8b3',
  20         },
  21         'add_ie': ['ThePlatform'],
  22     }
  23
  24     def _real_extract(self, url):
  25         name = url_basename(url)
  26
  27         webpage = self._download_webpage(url, name)
  28         feed_url = self._search_regex(
  29             r'data-feed-url="([^"]+)"', webpage, 'feed url')
  30         guid = self._search_regex(
  31             r'id="(?:videoPlayer|player-container)"[^>]+data-guid="([^"]+)"',
  32             webpage, 'guid')
  33
  34         feed = self._download_xml('%s?byGuid=%s' % (feed_url, guid), name)
  35         content = feed.find('.//{http://search.yahoo.com/mrss/}content')
  36         theplatform_id = url_basename(content.attrib.get('url'))
  37
  38         return self.url_result(smuggle_url(
  39             'http://link.theplatform.com/s/ngs/%s?format=SMIL&formats=MPEG4&manifest=f4m' % theplatform_id,
  40             # For some reason, the normal links don't work and we must force the use of f4m
  41             {'force_smil_url': True}))