[extractor/generic] Remove HEAD request

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

diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py
index 1a9c88f35e3c39071fdc8542e9aca42bbc7b0ad3..90d2435de96673506d2b72bd033b178620c62f9d 100644 (file)
--- a/yt_dlp/extractor/youtube.py
+++ b/yt_dlp/extractor/youtube.py
@@ -2467,6 +2467,7 @@ def _extract_signature_function(self, video_id, player_url, example_sig):
         func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
         assert os.path.basename(func_id) == func_id
 
+        self.write_debug(f'Extracting signature function {func_id}')
         cache_spec = self.cache.load('youtube-sigfuncs', func_id)
         if cache_spec is not None:
             return lambda s: ''.join(s[i] for i in cache_spec)
@@ -2714,10 +2715,10 @@ def _extract_url(webpage):
 
     @classmethod
     def extract_id(cls, url):
-        mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
-        if mobj is None:
-            raise ExtractorError('Invalid URL: %s' % url)
-        return mobj.group('id')
+        video_id = cls.get_temp_id(url)
+        if not video_id:
+            raise ExtractorError(f'Invalid URL: {url}')
+        return video_id
 
     def _extract_chapters_from_json(self, data, duration):
         chapter_list = traverse_obj(
@@ -2763,17 +2764,15 @@ def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration,
         if not strict:
             chapter_list.sort(key=lambda c: c['start_time'] or 0)
 
-        chapters = [{'start_time': 0, 'title': '<Untitled>'}]
+        chapters = [{'start_time': 0}]
         for idx, chapter in enumerate(chapter_list):
-            if chapter['start_time'] is None or not chapter['title']:
+            if chapter['start_time'] is None:
                 self.report_warning(f'Incomplete chapter {idx}')
             elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
-                chapters[-1]['end_time'] = chapter['start_time']
                 chapters.append(chapter)
             else:
                 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}"')
-        chapters[-1]['end_time'] = duration
-        return chapters if len(chapters) > 1 and chapters[1]['start_time'] else chapters[1:]
+        return chapters[1:]
 
     def _extract_comment(self, comment_renderer, parent=None):
         comment_id = comment_renderer.get('commentId')