[ie/mlbtv] Fix extraction (#10296)

[yt-dlp.git] / yt_dlp / extractor / nitter.py

diff --git a/yt_dlp/extractor/nitter.py b/yt_dlp/extractor/nitter.py
index 5d1ca1f5d0cf8b05b48cd42bbbe08ad613e05a4a..7609b4017861c0529075020020c1ff422420c8aa 100644 (file)
--- a/yt_dlp/extractor/nitter.py
+++ b/yt_dlp/extractor/nitter.py
@@ -1,13 +1,14 @@
+import random
+import re
+import urllib.parse
+
 from .common import InfoExtractor
-from ..compat import compat_urlparse
 from ..utils import (
+    determine_ext,
     parse_count,
-    unified_timestamp,
     remove_end,
-    determine_ext,
+    unified_timestamp,
 )
-import re
-import random
 
 
 class NitterIE(InfoExtractor):
@@ -264,13 +265,33 @@ class NitterIE(InfoExtractor):
                 'like_count': int,
                 'repost_count': int,
                 'comment_count': int,
-            }
-        }
+            },
+        }, {  # no OpenGraph title
+            'url': f'https://{current_instance}/LocalBateman/status/1678455464038735895#m',
+            'info_dict': {
+                'id': '1678455464038735895',
+                'ext': 'mp4',
+                'title': 'Your Typical Local Man - Local man, what did Romanians ever do to you?',
+                'description': 'Local man, what did Romanians ever do to you?',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'uploader': 'Your Typical Local Man',
+                'uploader_id': 'LocalBateman',
+                'uploader_url': f'https://{current_instance}/LocalBateman',
+                'upload_date': '20230710',
+                'timestamp': 1689009900,
+                'view_count': int,
+                'like_count': int,
+                'repost_count': int,
+                'comment_count': int,
+            },
+            'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
+            'params': {'skip_download': 'm3u8'},
+        },
     ]
 
     def _real_extract(self, url):
         video_id, uploader_id = self._match_valid_url(url).group('id', 'uploader_id')
-        parsed_url = compat_urlparse.urlparse(url)
+        parsed_url = urllib.parse.urlparse(url)
         base_url = f'{parsed_url.scheme}://{parsed_url.netloc}'
 
         self._set_cookie(parsed_url.netloc, 'hlsPlayback', 'on')
@@ -280,7 +301,7 @@ def _real_extract(self, url):
         if main_tweet_start > 0:
             webpage = full_webpage[main_tweet_start:]
 
-        video_url = '%s%s' % (base_url, self._html_search_regex(
+        video_url = '{}{}'.format(base_url, self._html_search_regex(
             r'(?:<video[^>]+data-url|<source[^>]+src)="([^"]+)"', webpage, 'video url'))
         ext = determine_ext(video_url)
 
@@ -289,10 +310,10 @@ def _real_extract(self, url):
         else:
             formats = [{
                 'url': video_url,
-                'ext': ext
+                'ext': ext,
             }]
 
-        title = description = self._og_search_description(full_webpage) or self._html_search_regex(
+        title = description = self._og_search_description(full_webpage, default=None) or self._html_search_regex(
             r'<div class="tweet-content[^>]+>([^<]+)</div>', webpage, 'title', fatal=False)
 
         uploader_id = self._html_search_regex(
@@ -313,12 +334,12 @@ def _real_extract(self, url):
 
         thumbnail = (
             self._html_search_meta('og:image', full_webpage, 'thumbnail url')
-            or remove_end('%s%s' % (base_url, self._html_search_regex(
+            or remove_end('{}{}'.format(base_url, self._html_search_regex(
                 r'<video[^>]+poster="([^"]+)"', webpage, 'thumbnail url', fatal=False)), '%3Asmall'))
 
         thumbnails = [
-            {'id': id, 'url': f'{thumbnail}%3A{id}'}
-            for id in ('thumb', 'small', 'large', 'medium', 'orig')
+            {'id': id_, 'url': f'{thumbnail}%3A{id_}'}
+            for id_ in ('thumb', 'small', 'large', 'medium', 'orig')
         ]
 
         date = self._html_search_regex(