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     update_url_query,
   8 )
   9
  10
  11 class NationalGeographicIE(InfoExtractor):
  12     IE_NAME = 'natgeo'
  13     _VALID_URL = r'https?://video\.nationalgeographic\.com/.*?'
  14
  15     _TESTS = [
  16         {
  17             'url': 'http://video.nationalgeographic.com/video/news/150210-news-crab-mating-vin?source=featuredvideo',
  18             'md5': '730855d559abbad6b42c2be1fa584917',
  19             'info_dict': {
  20                 'id': '0000014b-70a1-dd8c-af7f-f7b559330001',
  21                 'ext': 'mp4',
  22                 'title': 'Mating Crabs Busted by Sharks',
  23                 'description': 'md5:16f25aeffdeba55aaa8ec37e093ad8b3',
  24                 'timestamp': 1423523799,
  25                 'upload_date': '20150209',
  26                 'uploader': 'NAGS',
  27             },
  28             'add_ie': ['ThePlatform'],
  29         },
  30         {
  31             'url': 'http://video.nationalgeographic.com/wild/when-sharks-attack/the-real-jaws',
  32             'md5': '6a3105eb448c070503b3105fb9b320b5',
  33             'info_dict': {
  34                 'id': 'ngc-I0IauNSWznb_UV008GxSbwY35BZvgi2e',
  35                 'ext': 'mp4',
  36                 'title': 'The Real Jaws',
  37                 'description': 'md5:8d3e09d9d53a85cd397b4b21b2c77be6',
  38                 'timestamp': 1433772632,
  39                 'upload_date': '20150608',
  40                 'uploader': 'NAGS',
  41             },
  42             'add_ie': ['ThePlatform'],
  43         },
  44     ]
  45
  46     def _real_extract(self, url):
  47         name = url_basename(url)
  48
  49         webpage = self._download_webpage(url, name)
  50         guid = self._search_regex(
  51             r'id="(?:videoPlayer|player-container)"[^>]+data-guid="([^"]+)"',
  52             webpage, 'guid')
  53
  54         return {
  55             '_type': 'url_transparent',
  56             'ie_key': 'ThePlatform',
  57             'url': smuggle_url(
  58                 'http://link.theplatform.com/s/ngs/media/guid/2423130747/%s?mbr=true' % guid,
  59                 {'force_smil_url': True}),
  60             'id': guid,
  61         }
  62
  63
  64 class NationalGeographicChannelIE(InfoExtractor):
  65     IE_NAME = 'natgeo:channel'
  66     _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?[^/]+/videos/(?P<id>[^/?]+)'
  67
  68     _TESTS = [
  69         {
  70             'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/videos/uncovering-a-universal-knowledge/',
  71             'md5': '518c9aa655686cf81493af5cc21e2a04',
  72             'info_dict': {
  73                 'id': 'nB5vIAfmyllm',
  74                 'ext': 'mp4',
  75                 'title': 'Uncovering a Universal Knowledge',
  76                 'description': 'md5:1a89148475bf931b3661fcd6ddb2ae3a',
  77                 'timestamp': 1458680907,
  78                 'upload_date': '20160322',
  79                 'uploader': 'NEWA-FNG-NGTV',
  80             },
  81             'add_ie': ['ThePlatform'],
  82         },
  83         {
  84             'url': 'http://channel.nationalgeographic.com/wild/destination-wild/videos/the-stunning-red-bird-of-paradise/',
  85             'md5': 'c4912f656b4cbe58f3e000c489360989',
  86             'info_dict': {
  87                 'id': '3TmMv9OvGwIR',
  88                 'ext': 'mp4',
  89                 'title': 'The Stunning Red Bird of Paradise',
  90                 'description': 'md5:7bc8cd1da29686be4d17ad1230f0140c',
  91                 'timestamp': 1459362152,
  92                 'upload_date': '20160330',
  93                 'uploader': 'NEWA-FNG-NGTV',
  94             },
  95             'add_ie': ['ThePlatform'],
  96         },
  97     ]
  98
  99     def _real_extract(self, url):
 100         display_id = self._match_id(url)
 101         webpage = self._download_webpage(url, display_id)
 102         release_url = self._search_regex(
 103             r'video_auth_playlist_url\s*=\s*"([^"]+)"',
 104             webpage, 'release url')
 105
 106         return {
 107             '_type': 'url_transparent',
 108             'ie_key': 'ThePlatform',
 109             'url': smuggle_url(
 110                 update_url_query(release_url, {'mbr': 'true', 'switch': 'http'}),
 111                 {'force_smil_url': True}),
 112             'display_id': display_id,
 113         }