From c7bab7c39fd51c0812f70020172766303191bc01 Mon Sep 17 00:00:00 2001
From: Daniel Baumann <daniel.baumann@progress-linux.org>
Date: Sun, 5 May 2024 19:37:42 +0200
Subject: Adding upstream version 2023.03.04.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
---
 yt_dlp/extractor/khanacademy.py | 110 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 110 insertions(+)
 create mode 100644 yt_dlp/extractor/khanacademy.py

(limited to 'yt_dlp/extractor/khanacademy.py')

diff --git a/yt_dlp/extractor/khanacademy.py b/yt_dlp/extractor/khanacademy.py
new file mode 100644
index 0000000..5333036
--- /dev/null
+++ b/yt_dlp/extractor/khanacademy.py
@@ -0,0 +1,110 @@
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+    try_get,
+)
+
+
+class KhanAcademyBaseIE(InfoExtractor):
+    _VALID_URL_TEMPL = r'https?://(?:www\.)?khanacademy\.org/(?P<id>(?:[^/]+/){%s}%s[^?#/&]+)'
+
+    def _parse_video(self, video):
+        return {
+            '_type': 'url_transparent',
+            'url': video['youtubeId'],
+            'id': video.get('slug'),
+            'title': video.get('title'),
+            'thumbnail': video.get('imageUrl') or video.get('thumbnailUrl'),
+            'duration': int_or_none(video.get('duration')),
+            'description': video.get('description'),
+            'ie_key': 'Youtube',
+        }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        content = self._download_json(
+            'https://www.khanacademy.org/api/internal/graphql/FetchContentData',
+            display_id, query={
+                'fastly_cacheable': 'persist_until_publish',
+                'hash': '4134764944',
+                'lang': 'en',
+                'variables': json.dumps({
+                    'path': display_id,
+                    'queryParams': 'lang=en',
+                    'isModal': False,
+                    'followRedirects': True,
+                    'countryCode': 'US',
+                }),
+            })['data']['contentJson']
+        return self._parse_component_props(self._parse_json(content, display_id)['componentProps'])
+
+
+class KhanAcademyIE(KhanAcademyBaseIE):
+    IE_NAME = 'khanacademy'
+    _VALID_URL = KhanAcademyBaseIE._VALID_URL_TEMPL % ('4', 'v/')
+    _TEST = {
+        'url': 'https://www.khanacademy.org/computing/computer-science/cryptography/crypt/v/one-time-pad',
+        'md5': '9c84b7b06f9ebb80d22a5c8dedefb9a0',
+        'info_dict': {
+            'id': 'FlIG3TvQCBQ',
+            'ext': 'mp4',
+            'title': 'The one-time pad',
+            'description': 'The perfect cipher',
+            'duration': 176,
+            'uploader': 'Brit Cruise',
+            'uploader_id': 'khanacademy',
+            'upload_date': '20120411',
+            'timestamp': 1334170113,
+            'license': 'cc-by-nc-sa',
+        },
+        'add_ie': ['Youtube'],
+    }
+
+    def _parse_component_props(self, component_props):
+        video = component_props['tutorialPageData']['contentModel']
+        info = self._parse_video(video)
+        author_names = video.get('authorNames')
+        info.update({
+            'uploader': ', '.join(author_names) if author_names else None,
+            'timestamp': parse_iso8601(video.get('dateAdded')),
+            'license': video.get('kaUserLicense'),
+        })
+        return info
+
+
+class KhanAcademyUnitIE(KhanAcademyBaseIE):
+    IE_NAME = 'khanacademy:unit'
+    _VALID_URL = (KhanAcademyBaseIE._VALID_URL_TEMPL % ('2', '')) + '/?(?:[?#&]|$)'
+    _TEST = {
+        'url': 'https://www.khanacademy.org/computing/computer-science/cryptography',
+        'info_dict': {
+            'id': 'cryptography',
+            'title': 'Cryptography',
+            'description': 'How have humans protected their secret messages through history? What has changed today?',
+        },
+        'playlist_mincount': 31,
+    }
+
+    def _parse_component_props(self, component_props):
+        curation = component_props['curation']
+
+        entries = []
+        tutorials = try_get(curation, lambda x: x['tabs'][0]['modules'][0]['tutorials'], list) or []
+        for tutorial_number, tutorial in enumerate(tutorials, 1):
+            chapter_info = {
+                'chapter': tutorial.get('title'),
+                'chapter_number': tutorial_number,
+                'chapter_id': tutorial.get('id'),
+            }
+            for content_item in (tutorial.get('contentItems') or []):
+                if content_item.get('kind') == 'Video':
+                    info = self._parse_video(content_item)
+                    info.update(chapter_info)
+                    entries.append(info)
+
+        return self.playlist_result(
+            entries, curation.get('unit'), curation.get('title'),
+            curation.get('description'))
-- 
cgit v1.2.3