From 3d3538e422a711aab238f4d1ab667d72cc9bbdbf Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 7 Jan 2014 09:35:34 +0100 Subject: [PATCH] [khanacademy] Add support (Fixes #2066) --- test/test_playlists.py | 12 ++++- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/common.py | 10 ++++ youtube_dl/extractor/khanacademy.py | 71 +++++++++++++++++++++++++++++ 4 files changed, 93 insertions(+), 1 deletion(-) create mode 100644 youtube_dl/extractor/khanacademy.py diff --git a/test/test_playlists.py b/test/test_playlists.py index 9d522b357..3229823b6 100644 --- a/test/test_playlists.py +++ b/test/test_playlists.py @@ -1,7 +1,6 @@ #!/usr/bin/env python # encoding: utf-8 - # Allow direct execution import os import sys @@ -30,6 +29,7 @@ from youtube_dl.extractor import ( SmotriUserIE, IviCompilationIE, ImdbListIE, + KhanAcademyIE, ) @@ -198,6 +198,16 @@ class TestPlaylists(unittest.TestCase): self.assertEqual(result['title'], u'Animated and Family Films') self.assertTrue(len(result['entries']) >= 48) + def test_khanacademy_topic(self): + dl = FakeYDL() + ie = KhanAcademyIE(dl) + result = ie.extract('https://www.khanacademy.org/math/applied-math/cryptography') + self.assertIsPlaylist(result) + self.assertEqual(result['id'], u'cryptography') + self.assertEqual(result['title'], u'Journey into cryptography') + self.assertEqual(result['description'], u'How have humans protected their secret messages through history? What has changed today?') + self.assertTrue(len(result['entries']) >= 3) + if __name__ == '__main__': unittest.main() diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 009d3b60f..99ba725d9 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -98,6 +98,7 @@ from .justintv import JustinTVIE from .jpopsukitv import JpopsukiIE from .kankan import KankanIE from .keezmovies import KeezMoviesIE +from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE from .keek import KeekIE from .liveleak import LiveLeakIE diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 2a5e8076c..0ec365eaa 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1,4 +1,5 @@ import base64 +import json import os import re import socket @@ -260,6 +261,15 @@ class InfoExtractor(object): xml_string = transform_source(xml_string) return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8')) + def _download_json(self, url_or_request, video_id, + note=u'Downloading JSON metadata', + errnote=u'Unable to download JSON metadata'): + json_string = self._download_webpage(url_or_request, video_id, note, errnote) + try: + return json.loads(json_string) + except ValueError as ve: + raise ExtractorError('Failed to download JSON', cause=ve) + def report_warning(self, msg, video_id=None): idstr = u'' if video_id is None else u'%s: ' % video_id self._downloader.report_warning( diff --git a/youtube_dl/extractor/khanacademy.py b/youtube_dl/extractor/khanacademy.py new file mode 100644 index 000000000..772bb5671 --- /dev/null +++ b/youtube_dl/extractor/khanacademy.py @@ -0,0 +1,71 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + unified_strdate, +) + + +class KhanAcademyIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?khanacademy\.org/(?P[^/]+)/(?:[^/]+/){,2}(?P[^?#/]+)(?:$|[?#])' + IE_NAME = 'KhanAcademy' + + _TEST = { + 'url': 'http://www.khanacademy.org/video/one-time-pad', + 'file': 'one-time-pad.mp4', + 'md5': '7021db7f2d47d4fff89b13177cb1e8f4', + 'info_dict': { + 'title': 'The one-time pad', + 'description': 'The perfect cipher', + 'duration': 176, + 'uploader': 'Brit Cruise', + 'upload_date': '20120411', + } + } + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('id') + + if m.group('key') == 'video': + data = self._download_json( + 'http://api.khanacademy.org/api/v1/videos/' + video_id, + video_id, 'Downloading video info') + + upload_date = unified_strdate(data['date_added']) + uploader = ', '.join(data['author_names']) + return { + '_type': 'url_transparent', + 'url': data['url'], + 'id': video_id, + 'title': data['title'], + 'thumbnail': data['image_url'], + 'duration': data['duration'], + 'description': data['description'], + 'uploader': uploader, + 'upload_date': upload_date, + } + else: + # topic + data = self._download_json( + 'http://api.khanacademy.org/api/v1/topic/' + video_id, + video_id, 'Downloading topic info') + + entries = [ + { + '_type': 'url', + 'url': c['url'], + 'id': c['id'], + 'title': c['title'], + } + for c in data['children'] if c['kind'] in ('Video', 'Topic')] + + return { + '_type': 'playlist', + 'id': video_id, + 'title': data['title'], + 'description': data['description'], + 'entries': entries, + }