Let `--match-filter` reject entries early

[yt-dlp.git] / yt_dlp / YoutubeDL.py

diff --git a/yt_dlp/YoutubeDL.py b/yt_dlp/YoutubeDL.py
index 7edae6fa246e38ef2bd3a0ce4f93ea3b136487f9..eef3f8b4ca42b2021cc0aa288b9eae6066fe62e6 100644 (file)
--- a/yt_dlp/YoutubeDL.py
+++ b/yt_dlp/YoutubeDL.py
@@ -1117,12 +1117,15 @@ def check_filter():
             if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')):
                 return 'Skipping "%s" because it is age restricted' % video_title
 
-            if not incomplete:
-                match_filter = self.params.get('match_filter')
-                if match_filter is not None:
-                    ret = match_filter(info_dict)
-                    if ret is not None:
-                        return ret
+            match_filter = self.params.get('match_filter')
+            if match_filter is not None:
+                try:
+                    ret = match_filter(info_dict, incomplete=incomplete)
+                except TypeError:
+                    # For backward compatibility
+                    ret = None if incomplete else match_filter(info_dict)
+                if ret is not None:
+                    return ret
             return None
 
         if self.in_download_archive(info_dict):
@@ -2231,7 +2234,7 @@ def is_wellformed(f):
         if self.params.get('list_thumbnails'):
             self.list_thumbnails(info_dict)
         if self.params.get('listformats'):
-            if not info_dict.get('formats'):
+            if not info_dict.get('formats') and not info_dict.get('url'):
                 raise ExtractorError('No video formats found', expected=True)
             self.list_formats(info_dict)
         if self.params.get('listsubtitles'):
@@ -2339,7 +2342,8 @@ def process_subtitles(self, video_id, normal_subtitles, automatic_captions):
             requested_langs = ['en']
         else:
             requested_langs = [list(all_sub_langs)[0]]
-        self.write_debug('Downloading subtitles: %s' % ', '.join(requested_langs))
+        if requested_langs:
+            self.write_debug('Downloading subtitles: %s' % ', '.join(requested_langs))
 
         formats_query = self.params.get('subtitlesformat', 'best')
         formats_preference = formats_query.split('/') if formats_query else []
@@ -2662,7 +2666,6 @@ def existing_file(*filepaths):
                             os.remove(encodeFilename(file))
                         return None
 
-                    self.report_file_already_downloaded(existing_files[0])
                     info_dict['ext'] = os.path.splitext(existing_files[0])[1][1:]
                     return existing_files[0]
 
@@ -2717,7 +2720,7 @@ def correct_ext(filename, ext=new_ext):
                         info_dict['protocol'] = _protocols.pop()
                     directly_mergable = FFmpegFD.can_merge_formats(info_dict)
                     if dl_filename is not None:
-                        pass
+                        self.report_file_already_downloaded(dl_filename)
                     elif (directly_mergable and get_suitable_downloader(
                             info_dict, self.params, to_stdout=(temp_filename == '-')) == FFmpegFD):
                         info_dict['url'] = '\n'.join(f['url'] for f in requested_formats)
@@ -2769,9 +2772,13 @@ def correct_ext(filename, ext=new_ext):
                 else:
                     # Just a single file
                     dl_filename = existing_file(full_filename, temp_filename)
-                    if dl_filename is None:
+                    if dl_filename is None or dl_filename == temp_filename:
+                        # dl_filename == temp_filename could mean that the file was partially downloaded with --no-part.
+                        # So we should try to resume the download
                         success, real_download = self.dl(temp_filename, info_dict)
                         info_dict['__real_download'] = real_download
+                    else:
+                        self.report_file_already_downloaded(dl_filename)
 
                 dl_filename = dl_filename or temp_filename
                 info_dict['__finaldir'] = os.path.dirname(os.path.abspath(encodeFilename(full_filename)))
@@ -2869,13 +2876,13 @@ def download(self, url_list):
             except UnavailableVideoError:
                 self.report_error('unable to download video')
             except MaxDownloadsReached:
-                self.to_screen('[info] Maximum number of downloaded files reached')
+                self.to_screen('[info] Maximum number of downloads reached')
                 raise
             except ExistingVideoReached:
-                self.to_screen('[info] Encountered a file that is already in the archive, stopping due to --break-on-existing')
+                self.to_screen('[info] Encountered a video that is already in the archive, stopping due to --break-on-existing')
                 raise
             except RejectedVideoReached:
-                self.to_screen('[info] Encountered a file that did not match filter, stopping due to --break-on-reject')
+                self.to_screen('[info] Encountered a video that did not match filter, stopping due to --break-on-reject')
                 raise
             else:
                 if self.params.get('dump_single_json', False):
@@ -2904,6 +2911,8 @@ def download_with_info_file(self, info_filename):
     @staticmethod
     def sanitize_info(info_dict, remove_private_keys=False):
         ''' Sanitize the infodict for converting to json '''
+        if info_dict is None:
+            return info_dict
         info_dict.setdefault('epoch', int(time.time()))
         remove_keys = {'__original_infodict'}  # Always remove this since this may contain a copy of the entire dict
         keep_keys = ['_type'],  # Always keep this to facilitate load-info-json
@@ -3256,13 +3265,13 @@ def python_implementation():
         from .postprocessor.embedthumbnail import has_mutagen
         from .cookies import SQLITE_AVAILABLE, KEYRING_AVAILABLE
 
-        lib_str = ', '.join(filter(None, (
+        lib_str = ', '.join(sorted(filter(None, (
             can_decrypt_frag and 'pycryptodome',
             has_websockets and 'websockets',
             has_mutagen and 'mutagen',
             SQLITE_AVAILABLE and 'sqlite',
             KEYRING_AVAILABLE and 'keyring',
-        ))) or 'none'
+        )))) or 'none'
         self._write_string('[debug] Optional libraries: %s\n' % lib_str)
 
         proxy_map = {}