yt_dlp/extractor/instagram.py

@@ -10,7 +10,6 @@ from ..utils import (
     ExtractorError,
     decode_base_n,
     encode_base_n,
-    filter_dict,
     float_or_none,
     format_field,
     get_element_by_attribute,
@@ -704,31 +703,28 @@ class InstagramStoryIE(InstagramBaseIE):
         user_info = self._search_json(r'"user":', story_info, 'user info', story_id, fatal=False)
         if not user_info:
             self.raise_login_required('This content is unreachable')
+        user_id = user_info.get('id')
 
-        user_id = traverse_obj(user_info, 'pk', 'id', expected_type=str)
         story_info_url = user_id if username != 'highlights' else f'highlight:{story_id}'
-        if not story_info_url:  # user id is only mandatory for non-highlights
-            raise ExtractorError('Unable to extract user id')
-
         videos = traverse_obj(self._download_json(
             f'{self._API_BASE_URL}/feed/reels_media/?reel_ids={story_info_url}',
             story_id, errnote=False, fatal=False, headers=self._API_HEADERS), 'reels')
         if not videos:
             self.raise_login_required('You need to log in to access this content')
 
-        full_name = traverse_obj(videos, (f'highlight:{story_id}', 'user', 'full_name'), (user_id, 'user', 'full_name'))
+        full_name = traverse_obj(videos, (f'highlight:{story_id}', 'user', 'full_name'), (str(user_id), 'user', 'full_name'))
         story_title = traverse_obj(videos, (f'highlight:{story_id}', 'title'))
         if not story_title:
             story_title = f'Story by {username}'
 
-        highlights = traverse_obj(videos, (f'highlight:{story_id}', 'items'), (user_id, 'items'))
+        highlights = traverse_obj(videos, (f'highlight:{story_id}', 'items'), (str(user_id), 'items'))
         info_data = []
         for highlight in highlights:
             highlight_data = self._extract_product(highlight)
             if highlight_data.get('formats'):
                 info_data.append({
+                    **highlight_data,
                     'uploader': full_name,
                     'uploader_id': user_id,
-                    **filter_dict(highlight_data),
                 })
         return self.playlist_result(info_data, playlist_id=story_id, playlist_title=story_title)

yt_dlp/extractor/litv.py

@@ -6,7 +6,6 @@ from ..utils import (
     int_or_none,
     smuggle_url,
     traverse_obj,
-    try_call,
     unsmuggle_url,
 )
 
@@ -97,22 +96,13 @@ class LiTVIE(InfoExtractor):
             r'uiHlsUrl\s*=\s*testBackendData\(([^;]+)\);',
             webpage, 'video data', default='{}'), video_id)
         if not video_data:
-            payload = {'assetId': program_info['assetId']}
-            puid = try_call(lambda: self._get_cookies('https://www.litv.tv/')['PUID'].value)
-            if puid:
-                payload.update({
-                    'type': 'auth',
-                    'puid': puid,
-                })
-                endpoint = 'getUrl'
-            else:
-                payload.update({
+            payload = {
+                'assetId': program_info['assetId'],
                 'watchDevices': program_info['watchDevices'],
                 'contentType': program_info['contentType'],
-                })
-                endpoint = 'getMainUrlNoAuth'
+            }
             video_data = self._download_json(
-                f'https://www.litv.tv/vod/ajax/{endpoint}', video_id,
+                'https://www.litv.tv/vod/ajax/getMainUrlNoAuth', video_id,
                 data=json.dumps(payload).encode('utf-8'),
                 headers={'Content-Type': 'application/json'})
 

yt_dlp/extractor/twitter.py

@@ -10,7 +10,6 @@ from ..compat import (
     compat_urllib_parse_unquote,
     compat_urllib_parse_urlparse,
 )
-from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     dict_get,
@@ -1318,7 +1317,20 @@ class TwitterIE(TwitterBaseIE):
             }
         }
 
-    def _call_syndication_api(self, twid):
+    def _extract_status(self, twid):
+        if self.is_logged_in or self._selected_api == 'graphql':
+            status = self._graphql_to_legacy(self._call_graphql_api(self._GRAPHQL_ENDPOINT, twid), twid)
+
+        elif self._selected_api == 'legacy':
+            status = self._call_api(f'statuses/show/{twid}.json', twid, {
+                'cards_platform': 'Web-12',
+                'include_cards': 1,
+                'include_reply_count': 1,
+                'include_user_entities': 0,
+                'tweet_mode': 'extended',
+            })
+
+        elif self._selected_api == 'syndication':
             self.report_warning(
                 'Not all metadata or media is available via syndication endpoint', twid, only_once=True)
             status = self._download_json(
@@ -1338,31 +1350,8 @@ class TwitterIE(TwitterBaseIE):
                 media.append(detail)
             status['extended_entities'] = {'media': media}
 
-        return status
-
-    def _extract_status(self, twid):
-        if self._selected_api not in ('graphql', 'legacy', 'syndication'):
-            raise ExtractorError(f'{self._selected_api!r} is not a valid API selection', expected=True)
-
-        try:
-            if self.is_logged_in or self._selected_api == 'graphql':
-                status = self._graphql_to_legacy(self._call_graphql_api(self._GRAPHQL_ENDPOINT, twid), twid)
-            elif self._selected_api == 'legacy':
-                status = self._call_api(f'statuses/show/{twid}.json', twid, {
-                    'cards_platform': 'Web-12',
-                    'include_cards': 1,
-                    'include_reply_count': 1,
-                    'include_user_entities': 0,
-                    'tweet_mode': 'extended',
-                })
-        except ExtractorError as e:
-            if not isinstance(e.cause, HTTPError) or not e.cause.status == 429:
-                raise
-            self.report_warning('Rate-limit exceeded; falling back to syndication endpoint')
-            status = self._call_syndication_api(twid)
-
-        if self._selected_api == 'syndication':
-            status = self._call_syndication_api(twid)
+        else:
+            raise ExtractorError(f'"{self._selected_api}" is not a valid API selection', expected=True)
 
         return traverse_obj(status, 'retweeted_status', None, expected_type=dict) or {}
 
@@ -1427,8 +1416,8 @@ class TwitterIE(TwitterBaseIE):
                 'thumbnails': thumbnails,
                 'view_count': traverse_obj(media, ('mediaStats', 'viewCount', {int_or_none})),  # No longer available
                 'duration': float_or_none(traverse_obj(media, ('video_info', 'duration_millis')), 1000),
-                # Prioritize m3u8 formats for compat, see https://github.com/yt-dlp/yt-dlp/issues/8117
-                '_format_sort_fields': ('res', 'proto:m3u8', 'br', 'size'),  # http format codec is unknown
+                # The codec of http formats are unknown
+                '_format_sort_fields': ('res', 'br', 'size', 'proto'),
             }
 
         def extract_from_card_info(card):