Raphaël G. Git Repositories - youtubedl/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 .theplatform import ThePlatformIE
   8 from ..utils import (
   9     smuggle_url,
  10     url_basename,
  11     update_url_query,
  12     get_element_by_class,
  13 )
  14
  15
  16 class NationalGeographicVideoIE(InfoExtractor):
  17     IE_NAME = 'natgeo:video'
  18     _VALID_URL = r'https?://video\.nationalgeographic\.com/.*?'
  19
  20     _TESTS = [
  21         {
  22             'url': 'http://video.nationalgeographic.com/video/news/150210-news-crab-mating-vin?source=featuredvideo',
  23             'md5': '730855d559abbad6b42c2be1fa584917',
  24             'info_dict': {
  25                 'id': '0000014b-70a1-dd8c-af7f-f7b559330001',
  26                 'ext': 'mp4',
  27                 'title': 'Mating Crabs Busted by Sharks',
  28                 'description': 'md5:16f25aeffdeba55aaa8ec37e093ad8b3',
  29                 'timestamp': 1423523799,
  30                 'upload_date': '20150209',
  31                 'uploader': 'NAGS',
  32             },
  33             'add_ie': ['ThePlatform'],
  34         },
  35         {
  36             'url': 'http://video.nationalgeographic.com/wild/when-sharks-attack/the-real-jaws',
  37             'md5': '6a3105eb448c070503b3105fb9b320b5',
  38             'info_dict': {
  39                 'id': 'ngc-I0IauNSWznb_UV008GxSbwY35BZvgi2e',
  40                 'ext': 'mp4',
  41                 'title': 'The Real Jaws',
  42                 'description': 'md5:8d3e09d9d53a85cd397b4b21b2c77be6',
  43                 'timestamp': 1433772632,
  44                 'upload_date': '20150608',
  45                 'uploader': 'NAGS',
  46             },
  47             'add_ie': ['ThePlatform'],
  48         },
  49     ]
  50
  51     def _real_extract(self, url):
  52         name = url_basename(url)
  53
  54         webpage = self._download_webpage(url, name)
  55         guid = self._search_regex(
  56             r'id="(?:videoPlayer|player-container)"[^>]+data-guid="([^"]+)"',
  57             webpage, 'guid')
  58
  59         return {
  60             '_type': 'url_transparent',
  61             'ie_key': 'ThePlatform',
  62             'url': smuggle_url(
  63                 'http://link.theplatform.com/s/ngs/media/guid/2423130747/%s?mbr=true' % guid,
  64                 {'force_smil_url': True}),
  65             'id': guid,
  66         }
  67
  68
  69 class NationalGeographicIE(ThePlatformIE, AdobePassIE):
  70     IE_NAME = 'natgeo'
  71     _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:(?:(?:wild/)?[^/]+/)?(?:videos|episodes)|u)/(?P<id>[^/?]+)'
  72
  73     _TESTS = [
  74         {
  75             'url': 'http://channel.nationalgeographic.com/u/kdi9Ld0PN2molUUIMSBGxoeDhD729KRjQcnxtetilWPMevo8ZwUBIDuPR0Q3D2LVaTsk0MPRkRWDB8ZhqWVeyoxfsZZm36yRp1j-zPfsHEyI_EgAeFY/',
  76             'md5': '518c9aa655686cf81493af5cc21e2a04',
  77             'info_dict': {
  78                 'id': 'vKInpacll2pC',
  79                 'ext': 'mp4',
  80                 'title': 'Uncovering a Universal Knowledge',
  81                 'description': 'md5:1a89148475bf931b3661fcd6ddb2ae3a',
  82                 'timestamp': 1458680907,
  83                 'upload_date': '20160322',
  84                 'uploader': 'NEWA-FNG-NGTV',
  85             },
  86             'add_ie': ['ThePlatform'],
  87         },
  88         {
  89             'url': 'http://channel.nationalgeographic.com/u/kdvOstqYaBY-vSBPyYgAZRUL4sWUJ5XUUPEhc7ISyBHqoIO4_dzfY3K6EjHIC0hmFXoQ7Cpzm6RkET7S3oMlm6CFnrQwSUwo/',
  90             'md5': 'c4912f656b4cbe58f3e000c489360989',
  91             'info_dict': {
  92                 'id': 'Pok5lWCkiEFA',
  93                 'ext': 'mp4',
  94                 'title': 'The Stunning Red Bird of Paradise',
  95                 'description': 'md5:7bc8cd1da29686be4d17ad1230f0140c',
  96                 'timestamp': 1459362152,
  97                 'upload_date': '20160330',
  98                 'uploader': 'NEWA-FNG-NGTV',
  99             },
 100             'add_ie': ['ThePlatform'],
 101         },
 102         {
 103             'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episodes/the-power-of-miracles/',
 104             'only_matching': True,
 105         },
 106         {
 107             'url': 'http://channel.nationalgeographic.com/videos/treasures-rediscovered/',
 108             'only_matching': True,
 109         },
 110         {
 111             'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/videos/uncovering-a-universal-knowledge/',
 112             'only_matching': True,
 113         },
 114         {
 115             'url': 'http://channel.nationalgeographic.com/wild/destination-wild/videos/the-stunning-red-bird-of-paradise/',
 116             'only_matching': True,
 117         }
 118     ]
 119
 120     def _real_extract(self, url):
 121         display_id = self._match_id(url)
 122         webpage = self._download_webpage(url, display_id)
 123         release_url = self._search_regex(
 124             r'video_auth_playlist_url\s*=\s*"([^"]+)"',
 125             webpage, 'release url')
 126         theplatform_path = self._search_regex(r'https?://link\.theplatform\.com/s/([^?]+)', release_url, 'theplatform path')
 127         video_id = theplatform_path.split('/')[-1]
 128         query = {
 129             'mbr': 'true',
 130         }
 131         is_auth = self._search_regex(r'video_is_auth\s*=\s*"([^"]+)"', webpage, 'is auth', fatal=False)
 132         if is_auth == 'auth':
 133             auth_resource_id = self._search_regex(
 134                 r"video_auth_resourceId\s*=\s*'([^']+)'",
 135                 webpage, 'auth resource id')
 136             query['auth'] = self._extract_mvpd_auth(url, video_id, 'natgeo', auth_resource_id)
 137
 138         formats = []
 139         subtitles = {}
 140         for key, value in (('switch', 'http'), ('manifest', 'm3u')):
 141             tp_query = query.copy()
 142             tp_query.update({
 143                 key: value,
 144             })
 145             tp_formats, tp_subtitles = self._extract_theplatform_smil(
 146                 update_url_query(release_url, tp_query), video_id, 'Downloading %s SMIL data' % value)
 147             formats.extend(tp_formats)
 148             subtitles = self._merge_subtitles(subtitles, tp_subtitles)
 149         self._sort_formats(formats)
 150
 151         info = self._extract_theplatform_metadata(theplatform_path, display_id)
 152         info.update({
 153             'id': video_id,
 154             'formats': formats,
 155             'subtitles': subtitles,
 156             'display_id': display_id,
 157         })
 158         return info
 159
 160
 161 class NationalGeographicEpisodeGuideIE(InfoExtractor):
 162     IE_NAME = 'natgeo:episodeguide'
 163     _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?(?P<id>[^/]+)/episode-guide'
 164     _TESTS = [
 165         {
 166             'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episode-guide/',
 167             'info_dict': {
 168                 'id': 'the-story-of-god-with-morgan-freeman-season-1',
 169                 'title': 'The Story of God with Morgan Freeman - Season 1',
 170             },
 171             'playlist_mincount': 6,
 172         },
 173         {
 174             'url': 'http://channel.nationalgeographic.com/underworld-inc/episode-guide/?s=2',
 175             'info_dict': {
 176                 'id': 'underworld-inc-season-2',
 177                 'title': 'Underworld, Inc. - Season 2',
 178             },
 179             'playlist_mincount': 7,
 180         },
 181     ]
 182
 183     def _real_extract(self, url):
 184         display_id = self._match_id(url)
 185         webpage = self._download_webpage(url, display_id)
 186         show = get_element_by_class('show', webpage)
 187         selected_season = self._search_regex(
 188             r'<div[^>]+class="select-seasons[^"]*".*?<a[^>]*>(.*?)</a>',
 189             webpage, 'selected season')
 190         entries = [
 191             self.url_result(self._proto_relative_url(entry_url), 'NationalGeographic')
 192             for entry_url in re.findall('(?s)<div[^>]+class="col-inner"[^>]*?>.*?<a[^>]+href="([^"]+)"', webpage)]
 193         return self.playlist_result(
 194             entries, '%s-%s' % (display_id, selected_season.lower().replace(' ', '-')),
 195             '%s - %s' % (show, selected_season))