Last active
January 5, 2026 19:19
-
-
Save majora2007/724354d081627cfd96c24b8eefef4ec3 to your computer and use it in GitHub Desktop.
Remove foreign language audio and subtitle tracks from mkv files in bulk
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/python | |
| # Removes non-LANG audio tracks and subtitles from mkv files in a directory. | |
| # Original script by greenbender at https://forum.videohelp.com/threads/343271-BULK-remove-non-English-tracks-from-MKV-container | |
| # Modified by Joseph Milazzo for updated MkvMerge commands. | |
| # 12/3/2021: Updated to Python 3.9 | |
| import os | |
| import re | |
| import sys | |
| import subprocess | |
| import json | |
| # change this for other languages (3 character code) | |
| LANG = "eng" | |
| # set this to the path for mkvmerge | |
| MKVMERGE = "mkvmerge.exe" | |
| AUDIO_RE = re.compile( | |
| r"Track ID (\d+): audio \([A-Z0-9_/]+\) [number:\d+ uid:\d+ codec_id:[A-Z0-9_/]+ codec_private_length:\d+ language:([a-z]{3})") | |
| SUBTITLE_RE = re.compile( | |
| r"Track ID (\d+): subtitles \([A-Z0-9_/]+\) [number:\d+ uid:\d+ codec_id:[A-Z0-9_/]+ codec_private_length:\d+ language:([a-z]{3})(?: track_name:\w*)? default_track:[01]{1} forced_track:([01]{1})") | |
| if len(sys.argv) < 2: | |
| print("Please supply an input directory") | |
| sys.exit() | |
| in_dir = sys.argv[1] | |
| for root, dirs, files in os.walk(in_dir): | |
| for f in files: | |
| # filter out non mkv files | |
| if not f.endswith(".mkv"): | |
| continue | |
| # path to file | |
| path = os.path.join(root, f) | |
| # build command line | |
| cmd = [MKVMERGE, "-J", path] | |
| # get mkv info | |
| mkvmerge = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) | |
| stdout, stderr = mkvmerge.communicate() | |
| if mkvmerge.returncode != 0: | |
| print >> sys.stderr, "mkvmerge failed to identify", path | |
| continue | |
| # find audio and subtitle tracks | |
| audio = [] | |
| subtitle = [] | |
| info_json = json.loads(stdout) | |
| tracks = info_json['tracks'] | |
| for track in tracks: | |
| track['properties']['id'] = track['id'] | |
| if track['type'] == 'audio': | |
| audio.append(track) | |
| elif track['type'] == 'subtitles': | |
| subtitle.append(track) | |
| # filter out files that don't need processing | |
| if len(audio) < 2 and len(subtitle) < 2: | |
| print >> sys.stderr, "nothing to do for", path | |
| continue | |
| # filter out tracks that don't match the language | |
| audio_lang = filter(lambda a: a['properties']['language'] == LANG, audio) | |
| subtitle_lang = filter(lambda a: a['properties']['language'] == LANG, subtitle) | |
| # filter out files that don't need processing | |
| if len(audio_lang) == 0 and len(subtitle_lang) == 0: | |
| print >> sys.stderr, "no tracks with that language in", path | |
| continue | |
| # build command line | |
| cmd = [MKVMERGE, "-o", path + ".temp"] | |
| if len(audio_lang): | |
| cmd += ["--audio-tracks", ",".join([str(a['id']) for a in audio_lang])] | |
| for i in range(len(audio_lang)): | |
| cmd += ["--default-track", ":".join([str(audio_lang[i]['id']), "0" if i else "1"])] | |
| if len(subtitle_lang): | |
| cmd += ["--subtitle-tracks", ",".join([str(s['id']) for s in subtitle_lang])] | |
| for i in range(len(subtitle_lang)): | |
| cmd += ["--default-track", ":".join([str(subtitle_lang[i]['id']), "0"])] | |
| cmd += [path] | |
| # process file | |
| print >> sys.stderr, "Processing", path, "...", | |
| mkvmerge = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) | |
| stdout, stderr = mkvmerge.communicate() | |
| if mkvmerge.returncode != 0: | |
| print >> sys.stderr, "Failed" | |
| print(stdout) | |
| continue | |
| print >> sys.stderr, "Succeeded" | |
| # overwrite file | |
| os.remove(path) # Don't overwrite | |
| os.rename(path + ".temp", path) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
can this be updated to keep the default audio track and a list of languages, rather than just a list of languages?