Tool to extract one or many tracks from one or many mkv

mkv-track-extractor.py

#!/usr/bin/env python3

''' BSD 3-Clause License — but if it was useful to you, you may tell me :)
Copyright (c) 2016-2017, Alexandre Levavasseur
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
    * Redistributions of source code must retain the above copyright
      notice, this list of conditions and the following disclaimer.
    * Redistributions in binary form must reproduce the above copyright
      notice, this list of conditions and the following disclaimer in the
      documentation and/or other materials provided with the distribution.
    * Neither the name of the copyright holder nor the names of its
      contributors may be used to endorse or promote products
      derived from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
'''

# To set
extract_types = { # Types as in reported by mkvmerge
    'video': None,
    'audio': ['fre'],
    'subtitles': [], # empty = all, None = none
    'button': None # ?
}
mkvtoolnix_basepath = r'C:\path\to\mkvtoolnix'
mkvmerge = mkvtoolnix_basepath+'\mkvmerge.exe'
mkvextract = mkvtoolnix_basepath+'\mkvextract.exe'

###

import sys, os, glob, subprocess, json
from collections import OrderedDict

# https://mkvtoolnix.download/doc/mkvextract.html#mkvextract.output_file_formats
# https://github.com/mbunkus/mkvtoolnix/blob/release-15.0.0/src/extract/xtr_base.cpp#L139
# https://github.com/mbunkus/mkvtoolnix/blob/release-15.0.0/src/common/codec.h#L27
# https://github.com/mbunkus/mkvtoolnix/blob/release-15.0.0/src/common/codec.cpp#L26
# https://github.com/mbunkus/mkvtoolnix/blob/release-15.0.0/src/common/file_types.cpp#L25
codec_to_extension = {
    'A_AC3': 'ac3',
    'A_EAC3': 'eac3',
    'A_MPEG/L2': 'mp2',
    'A_MPEG/L3': 'mp3',
    'A_DTS': 'dts',
    'A_PCM/INT/': 'wav',
    'A_FLAC': 'flac',
    'A_ALAC': 'caf',
    'A_VORBIS': 'oga',
    'A_OPUS': 'opus',
    'A_AAC': 'aac',
    'A_REAL/': 'ra',
    'A_MLP': 'mlp',
    'A_TRUEHD': 'thd',
    'A_TTA1': 'tta',
    'A_WAVPACK4': 'wv',
    'V_MS/VFW/FOURCC': 'avi',
    'V_MPEG4/ISO/AVC': 'h264',
    'V_MPEGH/ISO/HEVC': 'h265',
    'V_REAL/': 'rv',
    'V_MPEG1': 'm1v',
    'V_MPEG2': 'm2v',
    'V_THEORA': 'ogv',
    'V_VP8': 'ivf',
    'V_VP9': 'ivf',
    'S_TEXT/UTF8': 'srt',
    'S_TEXT/ASCII': 'srt',
    'S_TEXT/SSA': 'ssa',
    'S_TEXT/ASS': 'ass',
    'S_SSA': 'ssa',
    'S_ASS': 'ass',
    'S_VOBSUB': 'sub', # Will be overwrited to .sub and .idx
    'S_TEXT/USF': 'usf',
    'S_KATE': 'ogx',
    'S_HDMV/PGS': 'sup',
    'S_HDMV/TEXTST': 'textst',
    'S_TEXT/WEBVTT': 'vtt',
}
def extension_lookup(codec_id):
    for codec, extension in codec_to_extension.items():
        if codec_id.lower().startswith(codec.lower()):
            return extension
    #return 'unk'
    return codec_id[2:].lower().replace('/', '-')

files = glob.glob(sys.argv[1])
for fileno, file in enumerate(files):
    log_prefix = '[{}/{}] File {}'.format(fileno+1, len(files), os.path.basename(file))
    try:
        # https://docs.python.org/3/library/subprocess.html
        json_infos = subprocess.check_output((mkvmerge, '-i', '-F', 'json', file))
        infos = json.loads(json_infos.decode())
    except Exception as e:
        print(log_prefix+', error while retrieiving informations: {}'.format(e), file=sys.stderr)
        continue
    
    to_extract = OrderedDict() # Keep tracks in order ..
    for track in infos['tracks']:
        if track['type'] in extract_types.keys() and extract_types[track['type']] is not None:
            try: 
                lang = track['properties']['language'] if 'language' in track['properties'] else 'eng' # Or '---' ?
                if (not len(extract_types[track['type']])) or (lang in extract_types[track['type']]):
                    to_extract[track['id']] = '.'.join((
                        os.path.splitext(file)[0],
                        track['type'],
                        str(track['id']),
                        lang,
                        extension_lookup(track['properties']['codec_id'])
                    ))
            except Exception as e:
                print(log_prefix+', track {}, error while creating output list: {}'.format(track['id'], e), file=sys.stderr)
    
    if not len(to_extract):
        print(log_prefix+': no track marked for extraction', file=sys.stderr)
        continue
    
    try:
        args = [mkvextract, 'tracks', file]
        for track_id, outfile in to_extract.items():
            args.append(str(track_id)+':'+outfile)
        
        print(log_prefix+': executing '+' '.join(('"'+arg+'"' if " " in arg else arg for arg in args)))
        subprocess.check_call(args)
    except Exception as e:
        print(log_prefix+', error executing extraction command: {}'.format(e), file=sys.stderr)

'''
> py .\extract_subs.py *.mkv
[1/1] MyFile.mkv: executing C:\path\to\mkvtoolnix\mkvextract.exe tracks MyFile.mkv 2:MyFile.audio.2.fre.ac3 3:MyFile.subtitles.3.eng.sub 4:MyFile.subtitles.4.fre.sub 5:MyFile.subtitles.5.ger.sub 6:MyFile.subtitles.6.fre.sub
Extracting track 2 with the CodecID 'A_AC3' to the file 'MyFile.audio.2.fre.ac3'. Container format: Dolby Digital (AC-3)
Extracting track 3 with the CodecID 'S_VOBSUB' to the file 'MyFile.subtitles.3.eng.sub'. Container format: VobSubs
Extracting track 4 with the CodecID 'S_VOBSUB' to the file 'MyFile.subtitles.4.fre.sub'. Container format: VobSubs
Extracting track 5 with the CodecID 'S_VOBSUB' to the file 'MyFile.subtitles.5.ger.sub'. Container format: VobSubs
Extracting track 6 with the CodecID 'S_VOBSUB' to the file 'MyFile.subtitles.6.fre.sub'. Container format: VobSubs
Writing the VobSub index file 'MyFile.subtitles.3.eng.idx'.
Writing the VobSub index file 'MyFile.subtitles.4.fre.idx'.
Writing the VobSub index file 'MyFile.subtitles.5.ger.idx'.
Writing the VobSub index file 'MyFile.subtitles.6.fre.idx'.
Progress: 100%
'''