From 156c80bf0a22ba1241c8d46ae9c0e98654004439 Mon Sep 17 00:00:00 2001
From: flanter21 <flanter21@gmail.com>
Date: Thu, 13 Feb 2025 18:43:21 +0000
Subject: [PATCH] [ie/BlackboardCollaborate] Add support for subtitles, live
 chat, filesize and videos behind a login wall

---
 yt_dlp/extractor/blackboardcollaborate.py | 75 +++++++++++++++++++----
 1 file changed, 64 insertions(+), 11 deletions(-)

diff --git a/yt_dlp/extractor/blackboardcollaborate.py b/yt_dlp/extractor/blackboardcollaborate.py
index 535890979..a8832b288 100644
--- a/yt_dlp/extractor/blackboardcollaborate.py
+++ b/yt_dlp/extractor/blackboardcollaborate.py
@@ -1,16 +1,27 @@
+import base64
+import json
+
 from .common import InfoExtractor
-from ..utils import parse_iso8601
+from ..utils import (
+    mimetype2ext,
+    parse_iso8601,
+)
+from ..utils.traversal import traverse_obj
+
+'''APIs references - Blackboard Learn: https://developer.blackboard.com/portal/displayApi
+                   - Blackboard Collaborate: https://github.com/blackboard/BBDN-Collab-Postman-REST'''
 
 
 class BlackboardCollaborateIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                         https?://
-                        (?P<region>[a-z-]+)\.bbcollab\.com/
+                        (?P<region>[a-z]+)(?:-lti)?\.bbcollab\.com/
                         (?:
                             collab/ui/session/playback/load|
                             recording
                         )/
-                        (?P<id>[^/]+)'''
+                        (?P<id>[^/\?]+)
+                        \??(authToken=(?P<token>[\w\.\-]+))?'''
     _TESTS = [
         {
             'url': 'https://us-lti.bbcollab.com/collab/ui/session/playback/load/0a633b6a88824deb8c918f470b22b256',
@@ -43,21 +54,63 @@ class BlackboardCollaborateIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
+        # Prepare for requests
         mobj = self._match_valid_url(url)
         region = mobj.group('region')
         video_id = mobj.group('id')
-        info = self._download_json(
-            f'https://{region}.bbcollab.com/collab/api/csa/recordings/{video_id}/data', video_id)
-        duration = info.get('duration')
-        title = info['name']
-        upload_date = info.get('created')
-        streams = info['streams']
-        formats = [{'format_id': k, 'url': url} for k, url in streams.items()]
+        token = mobj.group('token')
+
+        headers = {'Authorization': f'Bearer {token}'}
+        base_url = f'https://{region}.bbcollab.com/collab/api/csa/recordings/{video_id}'
+
+        # Try request the way the player handles it when behind a login
+        if video_info := self._download_json(f'{base_url}/data/secure', video_id, 'Trying auth token',
+                                             headers=headers, fatal=False):
+            video_extra = self._download_json(f'{base_url}', video_id, 'Retrieving extra attributes',
+                                              headers=headers, fatal=False)
+
+        # Blackboard will allow redownloading from the same IP without authentication for a while, so if previous method fails, try this
+        else:
+            video_info = self._download_json(f'{base_url}/data', video_id, 'Trying fallback')
+            video_extra = 0
+
+        # Get metadata
+        duration = video_info.get('duration') / 1000
+        title = video_info.get('name')
+        upload_date = video_info.get('created')
+
+        # Get streams
+        stream_formats = []
+        streams = video_info.get('extStreams')  # Can also use video_info.get('streams') but I don't know its structure
+
+        for current_stream in streams:
+            stream_formats.append({
+                'url': current_stream['streamUrl'],
+                'container': mimetype2ext(current_stream.get('contentType')),
+                'filesize': video_extra.get('storageSize', None),
+                'aspect_ratio': video_info.get('aspectRatio', ''),
+            })
+
+        # Get subtitles
+        subtitles = {}
+        subs = video_info.get('subtitles')
+        for current_subs in subs:
+            lang_code = current_subs.get('lang')
+            subtitles.setdefault(lang_code, []).append({
+                'name': current_subs.get('label'),
+                'url': current_subs['url'],
+            })
+
+        # Get chat
+        chats = video_info.get('chats')
+        for current_chat in chats:
+            subtitles.setdefault('live_chat', []).append({'url': current_chat['url']})
 
         return {
             'duration': duration,
-            'formats': formats,
+            'formats': stream_formats,
             'id': video_id,
             'timestamp': parse_iso8601(upload_date),
+            'subtitles': subtitles,
             'title': title,
         }