X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fnationalgeographic.py;h=9e8d28f4848165ccdfda771800031e6c68359684;hb=939be9adfe810ada7dbd5e9032bcfec19fafa14b;hp=fe43d4bc8b4c809ebbe0c728c00243f553ba02c1;hpb=1891ea2d760a49d356a472516db40bad8309ef3c;p=youtube-dl diff --git a/youtube_dl/extractor/nationalgeographic.py b/youtube_dl/extractor/nationalgeographic.py index fe43d4bc8..9e8d28f48 100644 --- a/youtube_dl/extractor/nationalgeographic.py +++ b/youtube_dl/extractor/nationalgeographic.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from .adobepass import AdobePassIE from .theplatform import ThePlatformIE from ..utils import ( smuggle_url, @@ -65,7 +66,7 @@ class NationalGeographicVideoIE(InfoExtractor): } -class NationalGeographicIE(ThePlatformIE): +class NationalGeographicIE(ThePlatformIE, AdobePassIE): IE_NAME = 'natgeo' _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?[^/]+/(?:videos|episodes)/(?P[^/?]+)' @@ -74,7 +75,7 @@ class NationalGeographicIE(ThePlatformIE): 'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/videos/uncovering-a-universal-knowledge/', 'md5': '518c9aa655686cf81493af5cc21e2a04', 'info_dict': { - 'id': 'nB5vIAfmyllm', + 'id': 'vKInpacll2pC', 'ext': 'mp4', 'title': 'Uncovering a Universal Knowledge', 'description': 'md5:1a89148475bf931b3661fcd6ddb2ae3a', @@ -88,7 +89,7 @@ class NationalGeographicIE(ThePlatformIE): 'url': 'http://channel.nationalgeographic.com/wild/destination-wild/videos/the-stunning-red-bird-of-paradise/', 'md5': 'c4912f656b4cbe58f3e000c489360989', 'info_dict': { - 'id': '3TmMv9OvGwIR', + 'id': 'Pok5lWCkiEFA', 'ext': 'mp4', 'title': 'The Stunning Red Bird of Paradise', 'description': 'md5:7bc8cd1da29686be4d17ad1230f0140c', @@ -110,28 +111,42 @@ class NationalGeographicIE(ThePlatformIE): release_url = self._search_regex( r'video_auth_playlist_url\s*=\s*"([^"]+)"', webpage, 'release url') + theplatform_path = self._search_regex(r'https?://link\.theplatform\.com/s/([^?]+)', release_url, 'theplatform path') + video_id = theplatform_path.split('/')[-1] query = { 'mbr': 'true', - 'switch': 'http', } is_auth = self._search_regex(r'video_is_auth\s*=\s*"([^"]+)"', webpage, 'is auth', fatal=False) if is_auth == 'auth': auth_resource_id = self._search_regex( r"video_auth_resourceId\s*=\s*'([^']+)'", webpage, 'auth resource id') - query['auth'] = self._extract_mvpd_auth(url, display_id, 'natgeo', auth_resource_id) or '' - - return { - '_type': 'url_transparent', - 'ie_key': 'ThePlatform', - 'url': smuggle_url( - update_url_query(release_url, query), - {'force_smil_url': True}), + query['auth'] = self._extract_mvpd_auth(url, video_id, 'natgeo', auth_resource_id) + + formats = [] + subtitles = {} + for key, value in (('switch', 'http'), ('manifest', 'm3u')): + tp_query = query.copy() + tp_query.update({ + key: value, + }) + tp_formats, tp_subtitles = self._extract_theplatform_smil( + update_url_query(release_url, tp_query), video_id, 'Downloading %s SMIL data' % value) + formats.extend(tp_formats) + subtitles = self._merge_subtitles(subtitles, tp_subtitles) + self._sort_formats(formats) + + info = self._extract_theplatform_metadata(theplatform_path, display_id) + info.update({ + 'id': video_id, + 'formats': formats, + 'subtitles': subtitles, 'display_id': display_id, - } + }) + return info -class NationalGeographicEpisodeGuideIE(ThePlatformIE): +class NationalGeographicEpisodeGuideIE(InfoExtractor): IE_NAME = 'natgeo:episodeguide' _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?(?P[^/]+)/episode-guide' _TESTS = [ @@ -161,8 +176,8 @@ class NationalGeographicEpisodeGuideIE(ThePlatformIE): r']+class="select-seasons[^"]*".*?]*>(.*?)', webpage, 'selected season') entries = [ - self.url_result(self._proto_relative_url(url), 'NationalGeographic') - for url in re.findall('(?s)]+class="col-inner"[^>]*?>.*?]+href="([^"]+)"', webpage)] + self.url_result(self._proto_relative_url(entry_url), 'NationalGeographic') + for entry_url in re.findall('(?s)]+class="col-inner"[^>]*?>.*?]+href="([^"]+)"', webpage)] return self.playlist_result( entries, '%s-%s' % (display_id, selected_season.lower().replace(' ', '-')), '%s - %s' % (show, selected_season))