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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .adobepass import AdobePassIE
   7 from ..utils import (
   8     smuggle_url,
   9     url_basename,
  10     update_url_query,
  11     get_element_by_class,
  12 )
  13
  14
  15 class NationalGeographicVideoIE(InfoExtractor):
  16     IE_NAME = 'natgeo:video'
  17     _VALID_URL = r'https?://video\.nationalgeographic\.com/.*?'
  18
  19     _TESTS = [
  20         {
  21             'url': 'http://video.nationalgeographic.com/video/news/150210-news-crab-mating-vin?source=featuredvideo',
  22             'md5': '730855d559abbad6b42c2be1fa584917',
  23             'info_dict': {
  24                 'id': '0000014b-70a1-dd8c-af7f-f7b559330001',
  25                 'ext': 'mp4',
  26                 'title': 'Mating Crabs Busted by Sharks',
  27                 'description': 'md5:16f25aeffdeba55aaa8ec37e093ad8b3',
  28                 'timestamp': 1423523799,
  29                 'upload_date': '20150209',
  30                 'uploader': 'NAGS',
  31             },
  32             'add_ie': ['ThePlatform'],
  33         },
  34         {
  35             'url': 'http://video.nationalgeographic.com/wild/when-sharks-attack/the-real-jaws',
  36             'md5': '6a3105eb448c070503b3105fb9b320b5',
  37             'info_dict': {
  38                 'id': 'ngc-I0IauNSWznb_UV008GxSbwY35BZvgi2e',
  39                 'ext': 'mp4',
  40                 'title': 'The Real Jaws',
  41                 'description': 'md5:8d3e09d9d53a85cd397b4b21b2c77be6',
  42                 'timestamp': 1433772632,
  43                 'upload_date': '20150608',
  44                 'uploader': 'NAGS',
  45             },
  46             'add_ie': ['ThePlatform'],
  47         },
  48     ]
  49
  50     def _real_extract(self, url):
  51         name = url_basename(url)
  52
  53         webpage = self._download_webpage(url, name)
  54         guid = self._search_regex(
  55             r'id="(?:videoPlayer|player-container)"[^>]+data-guid="([^"]+)"',
  56             webpage, 'guid')
  57
  58         return {
  59             '_type': 'url_transparent',
  60             'ie_key': 'ThePlatform',
  61             'url': smuggle_url(
  62                 'http://link.theplatform.com/s/ngs/media/guid/2423130747/%s?mbr=true' % guid,
  63                 {'force_smil_url': True}),
  64             'id': guid,
  65         }
  66
  67
  68 class NationalGeographicIE(AdobePassIE):
  69     IE_NAME = 'natgeo'
  70     _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?[^/]+/(?:videos|episodes)/(?P<id>[^/?]+)'
  71
  72     _TESTS = [
  73         {
  74             'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/videos/uncovering-a-universal-knowledge/',
  75             'md5': '518c9aa655686cf81493af5cc21e2a04',
  76             'info_dict': {
  77                 'id': 'vKInpacll2pC',
  78                 'ext': 'mp4',
  79                 'title': 'Uncovering a Universal Knowledge',
  80                 'description': 'md5:1a89148475bf931b3661fcd6ddb2ae3a',
  81                 'timestamp': 1458680907,
  82                 'upload_date': '20160322',
  83                 'uploader': 'NEWA-FNG-NGTV',
  84             },
  85             'add_ie': ['ThePlatform'],
  86         },
  87         {
  88             'url': 'http://channel.nationalgeographic.com/wild/destination-wild/videos/the-stunning-red-bird-of-paradise/',
  89             'md5': 'c4912f656b4cbe58f3e000c489360989',
  90             'info_dict': {
  91                 'id': 'Pok5lWCkiEFA',
  92                 'ext': 'mp4',
  93                 'title': 'The Stunning Red Bird of Paradise',
  94                 'description': 'md5:7bc8cd1da29686be4d17ad1230f0140c',
  95                 'timestamp': 1459362152,
  96                 'upload_date': '20160330',
  97                 'uploader': 'NEWA-FNG-NGTV',
  98             },
  99             'add_ie': ['ThePlatform'],
 100         },
 101         {
 102             'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episodes/the-power-of-miracles/',
 103             'only_matching': True,
 104         }
 105     ]
 106
 107     def _real_extract(self, url):
 108         display_id = self._match_id(url)
 109         webpage = self._download_webpage(url, display_id)
 110         release_url = self._search_regex(
 111             r'video_auth_playlist_url\s*=\s*"([^"]+)"',
 112             webpage, 'release url')
 113         query = {
 114             'mbr': 'true',
 115             'switch': 'http',
 116         }
 117         is_auth = self._search_regex(r'video_is_auth\s*=\s*"([^"]+)"', webpage, 'is auth', fatal=False)
 118         if is_auth == 'auth':
 119             auth_resource_id = self._search_regex(
 120                 r"video_auth_resourceId\s*=\s*'([^']+)'",
 121                 webpage, 'auth resource id')
 122             query['auth'] = self._extract_mvpd_auth(url, display_id, 'natgeo', auth_resource_id)
 123
 124         return {
 125             '_type': 'url_transparent',
 126             'ie_key': 'ThePlatform',
 127             'url': smuggle_url(
 128                 update_url_query(release_url, query),
 129                 {'force_smil_url': True}),
 130             'display_id': display_id,
 131         }
 132
 133
 134 class NationalGeographicEpisodeGuideIE(InfoExtractor):
 135     IE_NAME = 'natgeo:episodeguide'
 136     _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?(?P<id>[^/]+)/episode-guide'
 137     _TESTS = [
 138         {
 139             'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episode-guide/',
 140             'info_dict': {
 141                 'id': 'the-story-of-god-with-morgan-freeman-season-1',
 142                 'title': 'The Story of God with Morgan Freeman - Season 1',
 143             },
 144             'playlist_mincount': 6,
 145         },
 146         {
 147             'url': 'http://channel.nationalgeographic.com/underworld-inc/episode-guide/?s=2',
 148             'info_dict': {
 149                 'id': 'underworld-inc-season-2',
 150                 'title': 'Underworld, Inc. - Season 2',
 151             },
 152             'playlist_mincount': 7,
 153         },
 154     ]
 155
 156     def _real_extract(self, url):
 157         display_id = self._match_id(url)
 158         webpage = self._download_webpage(url, display_id)
 159         show = get_element_by_class('show', webpage)
 160         selected_season = self._search_regex(
 161             r'<div[^>]+class="select-seasons[^"]*".*?<a[^>]*>(.*?)</a>',
 162             webpage, 'selected season')
 163         entries = [
 164             self.url_result(self._proto_relative_url(entry_url), 'NationalGeographic')
 165             for entry_url in re.findall('(?s)<div[^>]+class="col-inner"[^>]*?>.*?<a[^>]+href="([^"]+)"', webpage)]
 166         return self.playlist_result(
 167             entries, '%s-%s' % (display_id, selected_season.lower().replace(' ', '-')),
 168             '%s - %s' % (show, selected_season))