X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/f46044c66663049e286c20ee015db99d47d9dd8a..647c9744516f7b5be3611b67e02201fb0146a638:/youtube_dl/extractor/nationalgeographic.py?ds=sidebyside diff --git a/youtube_dl/extractor/nationalgeographic.py b/youtube_dl/extractor/nationalgeographic.py index c18640c..ee12e2b 100644 --- a/youtube_dl/extractor/nationalgeographic.py +++ b/youtube_dl/extractor/nationalgeographic.py @@ -1,38 +1,82 @@ from __future__ import unicode_literals from .common import InfoExtractor +from .fox import FOXIE from ..utils import ( smuggle_url, url_basename, ) -class NationalGeographicIE(InfoExtractor): - _VALID_URL = r'http://video\.nationalgeographic\.com/video/.*?' +class NationalGeographicVideoIE(InfoExtractor): + IE_NAME = 'natgeo:video' + _VALID_URL = r'https?://video\.nationalgeographic\.com/.*?' - _TEST = { - 'url': 'http://video.nationalgeographic.com/video/news/150210-news-crab-mating-vin?source=featuredvideo', - 'info_dict': { - 'id': '4DmDACA6Qtk_', - 'ext': 'flv', - 'title': 'Mating Crabs Busted by Sharks', - 'description': 'md5:16f25aeffdeba55aaa8ec37e093ad8b3', + _TESTS = [ + { + 'url': 'http://video.nationalgeographic.com/video/news/150210-news-crab-mating-vin?source=featuredvideo', + 'md5': '730855d559abbad6b42c2be1fa584917', + 'info_dict': { + 'id': '0000014b-70a1-dd8c-af7f-f7b559330001', + 'ext': 'mp4', + 'title': 'Mating Crabs Busted by Sharks', + 'description': 'md5:16f25aeffdeba55aaa8ec37e093ad8b3', + 'timestamp': 1423523799, + 'upload_date': '20150209', + 'uploader': 'NAGS', + }, + 'add_ie': ['ThePlatform'], + }, + { + 'url': 'http://video.nationalgeographic.com/wild/when-sharks-attack/the-real-jaws', + 'md5': '6a3105eb448c070503b3105fb9b320b5', + 'info_dict': { + 'id': 'ngc-I0IauNSWznb_UV008GxSbwY35BZvgi2e', + 'ext': 'mp4', + 'title': 'The Real Jaws', + 'description': 'md5:8d3e09d9d53a85cd397b4b21b2c77be6', + 'timestamp': 1433772632, + 'upload_date': '20150608', + 'uploader': 'NAGS', + }, + 'add_ie': ['ThePlatform'], }, - 'add_ie': ['ThePlatform'], - } + ] def _real_extract(self, url): name = url_basename(url) webpage = self._download_webpage(url, name) - feed_url = self._search_regex(r'data-feed-url="([^"]+)"', webpage, 'feed url') - guid = self._search_regex(r'data-video-guid="([^"]+)"', webpage, 'guid') + guid = self._search_regex( + r'id="(?:videoPlayer|player-container)"[^>]+data-guid="([^"]+)"', + webpage, 'guid') + + return { + '_type': 'url_transparent', + 'ie_key': 'ThePlatform', + 'url': smuggle_url( + 'http://link.theplatform.com/s/ngs/media/guid/2423130747/%s?mbr=true' % guid, + {'force_smil_url': True}), + 'id': guid, + } - feed = self._download_xml('%s?byGuid=%s' % (feed_url, guid), name) - content = feed.find('.//{http://search.yahoo.com/mrss/}content') - theplatform_id = url_basename(content.attrib.get('url')) - return self.url_result(smuggle_url( - 'http://link.theplatform.com/s/ngs/%s?format=SMIL&formats=MPEG4&manifest=f4m' % theplatform_id, - # For some reason, the normal links don't work and we must force the use of f4m - {'force_smil_url': True})) +class NationalGeographicTVIE(FOXIE): + _VALID_URL = r'https?://(?:www\.)?nationalgeographic\.com/tv/watch/(?P[\da-fA-F]+)' + _TESTS = [{ + 'url': 'https://www.nationalgeographic.com/tv/watch/6a875e6e734b479beda26438c9f21138/', + 'info_dict': { + 'id': '6a875e6e734b479beda26438c9f21138', + 'ext': 'mp4', + 'title': 'Why Nat Geo? Valley of the Boom', + 'description': 'The lives of prominent figures in the tech world, including their friendships, rivalries, victories and failures.', + 'timestamp': 1542662458, + 'upload_date': '20181119', + 'age_limit': 14, + }, + 'params': { + 'skip_download': True, + }, + }] + _HOME_PAGE_URL = 'https://www.nationalgeographic.com/tv/' + _API_KEY = '238bb0a0c2aba67922c48709ce0c06fd'