Extract subtitles from MKV/MP4 videos

extractSubtitles.sh

#!/bin/sh
# Extract subtitles from each MKV/MP4 file in the given directory
#   [updated 2024-01-09 by FurloSK]
#   Permanent gist address: https://gist.github.com/FurloSK/7f52303a10ab7478e3cddfe4bcc50881
#
# ===== Usage =====
# extractSubtitles.sh [-i] [<fileOrDirectory>]
#   -i
#     Supplying this option will skip extraction and only print information about subtitles in file
#   <fileOrDirectory>
#     If a directory is given, will process all MKV/MP4 files in this directory (and subdirectories)
#     If a file is given, will process this single file
#     If the parameter is skipped altogether, will process current directory (and subdirectories)
#
# ===== History =====
# Original version by ComputerNerdFromHell (site no longer working):
#   http://www.computernerdfromhell.com/blog/automatically-extract-subtitles-from-mkv
#   Archived here: https://web.archive.org/web/20181119144734/http://www.computernerdfromhell.com/blog/automatically-extract-subtitles-from-mkv/
# Resubmitted by nux:
#   https://askubuntu.com/questions/452268/extract-subtitle-from-mkv-files/452279#452279
# Completely rewritten and tweaked by FurloSK:
#   https://superuser.com/questions/1527829/extracting-subtitles-from-mkv-file/1649627#1649627
#   Permanent gist address: https://gist.github.com/FurloSK/7f52303a10ab7478e3cddfe4bcc50881
#
# =============================================================================
# Config part: this is the only thing you need to tweak

# MKVToolNix path - Leave empty if you have the tools added to $PATH.
#   This is needed e.g. on macOS, if you just downloaded MKVToolNix app and dragged it to Applications folder
toolPath='/Applications/+ Moje/MKVToolNix.app/Contents/MacOS/'

# =============================================================================
# Start of script

# by default, process all files in local dir
DIR="."
skipExtraction=false

# first parameter might be -i switch, which will only print subtitle tracks instead of extracting them
if [[ "$1" == "-i" ]] ; then
  skipExtraction=true
  # if also directory or file is given, print info about it instead of default local dir
  if [[ "$#" -eq 2  &&  "$1" == "-i" ]] ; then
    DIR="$2"
  fi
# otherwise if directory or file is given, extract subtitles from that one
elif [[ "$#" -eq 1 ]] ; then
  DIR="$1"
fi

# Get all the MKV/MP4 files in this dir and its subdirs
find "$DIR" -type f \( -iname '*.mkv' -o -iname '*.mp4' -o -iname '*.avi' -o -iname '*.ts' \) | while read filename
do
  echo "\nProcessing file $filename:"
  
  # Get base file name (without extension)
  fileBasename=${filename%.*}
  
  # Parse info about all subtitles tracks from file
  # This will output lines in this format, one line per subtitle track, fields delimited by tabulator:
  #   trackID <tab> trackLanguage <tab> trackCodecID <tab> trackCodec
  "${toolPath}mkvmerge" -J "$filename" | python -c "exec(\"import sys, json;\njs = json.load(sys.stdin);\nif not 'tracks' in js:\n\tprint('unsupported');\n\tsys.exit();\nfor track in js['tracks']:\n\tif track['type'] == 'subtitles':\n\t\tprint(str(track['id']) + '\t' + track['properties']['language'] + '\t' + (track['properties']['codec_id'] if 'codec_id' in track['properties'] else 'undefined') + '\t' + track['codec'])\")" | while IFS=$'\t' read -r trackNumber trackLanguage trackCodecID trackCodec;
  #"${toolPath}mkvmerge" -J "$filename" | python -c "exec(\"import sys, json;\nfor track in json.load(sys.stdin)['tracks']:\n\tif track['type'] == 'subtitles':\n\t\tprint(str(track['id']) + '\t' + track['properties']['language'] + '\t' + (track['properties']['codec_id'] if 'codec_id' in track['properties'] else track['codec']) + '\t' + track['codec'])\")" | while IFS=$'\t' read -r trackNumber trackLanguage trackCodecID trackCodec;
  do
    # if JSON tracks extraction failed, continue to next file
    if [ $trackNumber = 'unsupported' ] ; then
      echo "  Unsupported file, skipping..."
      continue;
    fi
    
    echo "  Found subtitle track #${trackNumber}: $trackLanguage ($trackCodec, $trackCodecID)"
    
    # address missing ['properties']['codec_id'] in JSON
    if [ $trackCodecID = 'undefined' ] ; then
      # fix DVBSUB codec automatically
      if [ $trackCodec = 'DVBSUB' ] ; then
        trackCodecID='S_DVBSUB'
        echo "    Warning: missing codec_id for $trackCodec track => corrected to $trackCodecID."
      else
        echo "    Error: missing codec_id for $trackCodec track!"
      fi
    fi
    
    # if we are only printing tracks, not extracting them, print track and continue
    if [ $skipExtraction = true ] ; then
      continue;
    fi
    
    # optional: process only some types of subtitle tracks (according to $trackCodecID)
    #   See codec types here (under header Subtitle Codec Mappings):
    #   https://datatracker.ietf.org/doc/html/draft-ietf-cellar-codec/#name-subtitle-codec-mappings
    #   E.g. to skip DVD subtitles, add S_VOBSUB
    if [[ $trackCodecID == 'unwantedCodecID_#1' || $trackCodecID == 'unwantedCodecID_#2' ]] ; then
      echo "    Unwanted codec ID $trackCodecID, skipping track..."
      continue;
    fi
    
    # determine proper extension
    if [ $trackCodecID = 'S_TEXT/SSA' ] ; then
      extension='ssa'
    elif [ $trackCodecID = 'S_TEXT/ASS' ] ; then
      extension='ass'
    elif [ $trackCodecID = 'S_TEXT/USF' ] ; then
      extension='usf'
    elif [ $trackCodecID = 'S_TEXT/WEBVTT' ] ; then
      extension='vtt'
    elif [ $trackCodecID = 'S_DVBSUB' ] ; then
      extension='dvb'
    else # fallback to standard .srt file (S_VOBSUB files will still get their proper extension)
      extension='srt'
    fi
    
    # prepare output filename
    #   (adding . [dot] between filename and language, so VLC will properly recognize the language)
    outFilename="${fileBasename} [#${trackNumber}].${trackLanguage}.${extension}"
    
    # extract track with language and track id
    echo "    Extracting track to file ${outFilename}"
    echo "    Executing command \"${toolPath}mkvextract\" tracks \"${filename}\" ${trackNumber}:\"${outFilename}\""
    result=`"${toolPath}mkvextract" tracks "${filename}" ${trackNumber}:"${outFilename}"`
    echo "    > $result"
    #`"${toolPath}mkvextract" tracks "${filename}" ${trackNumber}:"${outFilename}" > /dev/null 2>&1`
    
    #==========================================================================
    # Lines below are from the original source by ComputerNerdFromHell.
    # They are now all obsolete and redundant (kept just for reference)
    
    # Extract the track to a .tmp file
    #`"${toolPath}mkvextract" tracks "$filename" $trackNumber:"$subtitlename.srt.tmp" > /dev/null 2>&1`
    #`chmod g+rw "$subtitlename.srt.tmp"`

    # # Do a super-primitive language guess: ENGLISH
    # langtest=`egrep -ic ' you | to | the ' "$subtitlename".srt.tmp`
    # trimregex=""
    #
    # # Check if subtitle passes our language filter (10 or more matches)
    # if [ $langtest -ge 10 ]; then
    #   # Regex to remove credits at the end of subtitles (read my reason why!)
    #   `sed 's/\r//g' < "$subtitlename.srt.tmp" \
    #     | sed 's/%/%%/g' \
    #     | awk '{if (a){printf("\t")};printf $0; a=1; } /^$/{print ""; a=0;}' \
    #     | grep -iv "$trimregex" \
    #     | sed 's/\t/\r\n/g' > "$subtitlename.srt"`
    #   `rm "$subtitlename.srt.tmp"`
    #   `chmod g+rw "$subtitlename.srt"`
    # else
    #   # Not our desired language: add a number to the filename and keep anyway, just in case
    #   `mv "$subtitlename.srt.tmp" "$subtitlename.$tracknumber.srt" > /dev/null 2>&1`
    # fi
    
    echo ""
  done
done

Nice, thanks.

echo "\nProcessing file $filename:" should be echo -e "\nProcessing file $filename:".

Nice scripting Thnx!
For MacOs users there are 3 things to check to make this script work for you:

1 - Make sure the path to MKVToolnix is correct. In my case this worked(line30):

toolPath='/Applications/MKVToolNix-79.0.app/Contents/MacOS/'

2 - Make sure python can be found. In my case I had to add the version number after python (line62):

"${toolPath}mkvmerge" -J "$filename" | python3 -c

3 - When downloading the script there was (in my case) a line-break that produced a python 'syntax error' (line 62).
Make sure that the line-break is after ' trackCodec; '

Then everything worked just fine !)

For use with Ubuntu, change first line to #!/bin/bash, comment the toolPath line, and add the -e option to the first echo command.