X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fnationalgeographic.py;h=1dcf27afef331ceb3b09d6ade66cde65e92e3cd6;hb=e14c82bd6b6cfc1e904b067350d818657c911e07;hp=72251866303885f6cd9b040ec9ad3f042d8add6a;hpb=d6712378e73951bede475569c887a1ac73f660a9;p=youtube-dl diff --git a/youtube_dl/extractor/nationalgeographic.py b/youtube_dl/extractor/nationalgeographic.py index 722518663..1dcf27afe 100644 --- a/youtube_dl/extractor/nationalgeographic.py +++ b/youtube_dl/extractor/nationalgeographic.py @@ -1,15 +1,19 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor +from .adobepass import AdobePassIE from ..utils import ( smuggle_url, url_basename, update_url_query, + get_element_by_class, ) -class NationalGeographicIE(InfoExtractor): - IE_NAME = 'natgeo' +class NationalGeographicVideoIE(InfoExtractor): + IE_NAME = 'natgeo:video' _VALID_URL = r'https?://video\.nationalgeographic\.com/.*?' _TESTS = [ @@ -61,16 +65,16 @@ class NationalGeographicIE(InfoExtractor): } -class NationalGeographicChannelIE(InfoExtractor): - IE_NAME = 'natgeo:channel' - _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?[^/]+/videos/(?P[^/?]+)' +class NationalGeographicIE(AdobePassIE): + IE_NAME = 'natgeo' + _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?[^/]+/(?:videos|episodes)/(?P[^/?]+)' _TESTS = [ { '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', @@ -84,7 +88,7 @@ class NationalGeographicChannelIE(InfoExtractor): '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', @@ -94,6 +98,10 @@ class NationalGeographicChannelIE(InfoExtractor): }, 'add_ie': ['ThePlatform'], }, + { + 'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episodes/the-power-of-miracles/', + 'only_matching': True, + } ] def _real_extract(self, url): @@ -102,12 +110,59 @@ class NationalGeographicChannelIE(InfoExtractor): release_url = self._search_regex( r'video_auth_playlist_url\s*=\s*"([^"]+)"', webpage, 'release url') + 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) return { '_type': 'url_transparent', 'ie_key': 'ThePlatform', 'url': smuggle_url( - update_url_query(release_url, {'mbr': 'true', 'switch': 'http'}), + update_url_query(release_url, query), {'force_smil_url': True}), 'display_id': display_id, } + + +class NationalGeographicEpisodeGuideIE(InfoExtractor): + IE_NAME = 'natgeo:episodeguide' + _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?(?P[^/]+)/episode-guide' + _TESTS = [ + { + 'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episode-guide/', + 'info_dict': { + 'id': 'the-story-of-god-with-morgan-freeman-season-1', + 'title': 'The Story of God with Morgan Freeman - Season 1', + }, + 'playlist_mincount': 6, + }, + { + 'url': 'http://channel.nationalgeographic.com/underworld-inc/episode-guide/?s=2', + 'info_dict': { + 'id': 'underworld-inc-season-2', + 'title': 'Underworld, Inc. - Season 2', + }, + 'playlist_mincount': 7, + }, + ] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + show = get_element_by_class('show', webpage) + selected_season = self._search_regex( + r']+class="select-seasons[^"]*".*?]*>(.*?)', + webpage, 'selected season') + entries = [ + 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))