From f25c204ed7bc1e1062b6a2d7e3583cee462756ea Mon Sep 17 00:00:00 2001
From: Adrian Heine <mail@adrianheine.de>
Date: Wed, 3 Feb 2021 23:42:51 +0100
Subject: [PATCH] [ArchiveOrg] Fix extractor

Closes #21330, closes #26780, closes #25277, closes #23586.
---
 youtube_dl/extractor/archiveorg.py | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/youtube_dl/extractor/archiveorg.py b/youtube_dl/extractor/archiveorg.py
index c79c58e8281..a0763514c01 100644
--- a/youtube_dl/extractor/archiveorg.py
+++ b/youtube_dl/extractor/archiveorg.py
@@ -16,7 +16,7 @@ class ArchiveOrgIE(InfoExtractor):
         'md5': '8af1d4cf447933ed3c7f4871162602db',
         'info_dict': {
             'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
-            'ext': 'ogg',
+            'ext': 'ogv',
             'title': '1968 Demo - FJCC Conference Presentation Reel #1',
             'description': 'md5:da45c349df039f1cc8075268eb1b5c25',
             'upload_date': '19681210',
@@ -24,12 +24,12 @@ class ArchiveOrgIE(InfoExtractor):
         }
     }, {
         'url': 'https://archive.org/details/Cops1922',
-        'md5': '0869000b4ce265e8ca62738b336b268a',
+        'md5': '9b865bfdb0ca6b955b93f4a446ddce82',
         'info_dict': {
             'id': 'Cops1922',
-            'ext': 'mp4',
+            'ext': 'ogv',
             'title': 'Buster Keaton\'s "Cops" (1922)',
-            'description': 'md5:89e7c77bf5d965dd5c0372cfb49470f6',
+            'description': 'md5:43a603fd6c5b4b90d12a96b921212b9c',
         }
     }, {
         'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
@@ -40,11 +40,16 @@ def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(
             'http://archive.org/embed/' + video_id, video_id)
-        jwplayer_playlist = self._parse_json(self._search_regex(
+        jwplayer_playlist_string = self._search_regex(
             r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\)",
-            webpage, 'jwplayer playlist'), video_id)
-        info = self._parse_jwplayer_data(
-            {'playlist': jwplayer_playlist}, video_id, base_url=url)
+            webpage, 'jwplayer playlist', default=None)
+        info = {}
+        if jwplayer_playlist_string:
+            jwplayer_playlist = self._parse_json(jwplayer_playlist_string, video_id)
+            info = self._parse_jwplayer_data({'playlist': jwplayer_playlist}, video_id, base_url=url)
+        else:
+            info['id'] = video_id
+            info.update(self._parse_html5_media_entries("https://archive.org", webpage, video_id)[0])
 
         def get_optional(metadata, field):
             return metadata.get(field, [None])[0]