CUE splitter using ffmpeg (to flac)

cue_to_flac_cmd.py

#! /usr/bin/env python3
import sys


def unquote(s):
    if len(s) < 2:
        return s
    if s[0] == '"' and s[-1] == '"':
        return s[1:-1]
    return s


def shellescape(s):
    return "'" + s.replace("'", "'\\''") + "'"


d = sys.stdin.read().splitlines()

general = {}

tracks = []

current_file = None

for line in d:
    if line.startswith('REM GENRE '):
        general['genre'] = unquote(' '.join(line.split(' ')[2:]))
    if line.startswith('REM DATE '):
        general['date'] = unquote(' '.join(line.split(' ')[2:]))
    if line.startswith('PERFORMER '):
        general['artist'] = unquote(' '.join(line.split(' ')[1:]))
    if line.startswith('TITLE '):
        general['album'] = unquote(' '.join(line.split(' ')[1:]))
    if line.startswith('FILE '):
        current_file = unquote(' '.join(line.split(' ')[1:-1]))

    if line.startswith(' '):
        line = line.strip()  # we want to try our best at handling files with different indentations

        if line.startswith('TRACK '):
            track = general.copy()
            track['track'] = int(line.strip().split(' ')[1], 10)

            tracks.append(track)

        if line.startswith('TITLE '):
            tracks[-1]['title'] = unquote(' '.join(line.strip().split(' ')[1:]))
        if line.startswith('PERFORMER '):
            tracks[-1]['artist'] = unquote(' '.join(line.strip().split(' ')[1:]))
        if line.startswith('INDEX 01 '):
            t = tuple(map(int, unquote(' '.join(line.strip().split(' ')[2:])).split(':')))
            tracks[-1]['start'] = 60 * t[0] + t[1] + t[2] / 100.0

for i in range(len(tracks)):
    if i != len(tracks) - 1:
        tracks[i]['duration'] = tracks[i + 1]['start'] - tracks[i]['start']

for track in tracks:
    metadata = {
        'artist': track['artist'],
        'title': track['title'],
        'album': track['album'],
        'track': str(track['track']) + '/' + str(len(tracks))
    }

    if 'genre' in track:
        metadata['genre'] = track['genre']
    if 'date' in track:
        metadata['date'] = track['date']

    cmd = 'ffmpeg'
    cmd += ' -i "%s"' % current_file
    cmd += ' -ss ' + shellescape('%.2d:%.2d:%.2d' % (track['start'] / 60 / 60, track['start'] / 60 % 60, int(track['start'] % 60)))

    if 'duration' in track:
        cmd += ' -t ' + shellescape('%.2d:%.2d:%.2d' % (track['duration'] / 60 / 60, track['duration'] / 60 % 60, int(track['duration'] % 60)))

    cmd += ' ' + ' '.join('-metadata ' + shellescape('%s=%s' % (k, v)) for (k, v) in metadata.items())
    cmd += ' ' + shellescape('%.2d. %s - %s.flac' % (track['track'], track['artist'], track['title']))

    print(cmd)

Example invocation for russian windows encoding:

iconv -f CP1251 < file.cue | cue_to_flac_cmd.py | tee to-tracks.sh
sh ./to-tracks.sh