summaryrefslogtreecommitdiff
path: root/jamos
blob: 8442eae04a330bd3fc02ac2fc88b6d9c5181cd35 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
#!/usr/bin/env python3
import argparse
import collections
import datetime
import glob
import json
import music_tag
import os
from pathlib import Path
import requests
import shutil
import sys
import youtube_dl
from ytmusicapi import YTMusic
# import musicpd

# TODO: set this to false to begin with. for now it's always gonna print
# debug information
DEBUG = True

# Includes the format characters
YOUTUBE_MUSIC_URL = "https://music.youtube.com/watch?v={}"

"""
How the albums will be formatted:
{
    'id': {
        'name': '',
        'tracks': [
            {
                'id': '',
                'name': ''
            }
        ],
    }
}
"""
ALBUMS = collections.defaultdict(lambda: None)


def get_command_line_options():
    parser = argparse.ArgumentParser(
        description="Download songs from YouTube Music")

    # NOTE: I'm not sure if this param is necessary anymore. If playlist
    # is public/unlisted, then it shouldn't need the cookies.
    parser.add_argument("--cookies",
                        metavar="cookiefile.txt",
                        # TODO: store this in a config file
                        default=os.path.join(os.path.expanduser("~"),
                                             "cookies.txt"),
                        type=str,
                        help="Cookie file to use.")

    parser.add_argument("--debug_location",
                        metavar="~/Music/jamos_debug",
                        default=None,
                        type=str,
                        help="Cookie file to use.")

    # NOTE: unlike cookies, this is required to get the library
    parser.add_argument("--headers",
                        metavar="header_path",
                        # TODO: store this in a config file
                        default='~/.config/jamos/headers.json',
                        type=str,
                        help="Header file to use.")

    parser.add_argument("-o",
                        "--output",
                        metavar="output_directory",
                        # TODO: store it in a config file
                        default=os.path.join(os.path.expanduser("~"), "Music"),
                        type=str,
                        help="Output directory to use")

    parser.add_argument("--playlist_id",
                        metavar='PLFsQleAWXsj_4yDeebiIADdH5FMayBiJo',
                        nargs='?',
                        type=str,
                        help="""Playlist id to download. Playlist MUST
                        be public or unlisted, but NOT private""")

    parser.add_argument("-r",
                        "--retry_file",
                        metavar="jamos_failed_urls.txt",
                        default=None,
                        type=str,
                        help="File to store songs that were not completed")

    parser.add_argument("--song_id",
                        metavar="lYBUbBu4W08",
                        nargs='?',
                        type=str,
                        help="Song id to download.")

    parser.add_argument("--song_limit",
                        metavar="5000",
                        default=5000,
                        type=int,
                        help="Number of songs to download")

    parser.add_argument("-t",
                        "--thumbnail_folder",
                        metavar="~/Music/jamos_thumbnails",
                        # TODO: store it in a config file
                        default=os.path.join(os.path.expanduser("~"), "Music",
                                             "jamos_thumbnails"),
                        type=str,
                        help="Directory to save thumbnails for albums")

    parser.add_argument("-v",
                        "--verbose",
                        action='store_true',
                        help="Directory to save thumbnails for albums")

    args = parser.parse_args()

    # Validate args
    if args.verbose:
        global DEBUG
        DEBUG = True

    if args.song_id and args.playlist_id:
        parser.error('--song_id and --playlist_id may not be passed together!')

    if args.song_id and args.retry_file:
        parser.error('--song_id and --retry_file may not be passed together!')

    if args.playlist_id and args.retry_file:
        parser.error(
            "--playlist_id and --retry_file may not be passed together!")

    return args


def create_downloader(music_directory, cookies=None):
    audio_options = {
        'format': 'mp3/bestaudio/best',
        'cookiefile': cookies,
        'outtmpl': os.path.join(music_directory, '%(id)s.%(ext)s'),
        'postprocessors': [
            {
                'key': 'FFmpegExtractAudio',
                'preferredcodec': 'mp3',
                'preferredquality': '192',
            },
            {'key': 'FFmpegMetadata'},
        ],
        # 'writeinfojson': True,
        'quiet': not DEBUG
    }

    return youtube_dl.YoutubeDL(audio_options)


def remove_special_characters_for_filename(filename):
    special_chars = [
        ['-', ' '],
        ['(', ''],
        [')', ''],
        ['/', ' '],
        ['/', ' '],
        [' ', '_'],
        ["'", ''],
        ["&", 'and'],
        [chr(8217), ''],
        ['$', 's'],
        ['.', '']
    ]
    new_name = filename

    for char_set in special_chars:
        new_name = new_name.replace(char_set[0], char_set[1])

    return new_name.lower()


def create_youtube_music_api_object(header_path):
    return YTMusic(header_path)


def save_album(app, args, album_id):
    raw_album = app.get_album(album_id)

    # TODO: Add get_thumbnail function
    thumbnail_url = raw_album['thumbnails'][-1]['url']

    parsed_album = {
        'name': raw_album['title'],
        'tracks': [{'title': song['title'], 'id': song['videoId'],
                    'track_num': index + 1}
                   for index, song in enumerate(raw_album['tracks'])],
        'year': raw_album['year'],
        'thumbnail_url': thumbnail_url,
        'thumbnail_filepath': None
    }

    try:
        r = requests.get(thumbnail_url, stream=True)
        filename = os.path.join(args.thumbnail_folder, album_id + '.jpg')

        if not os.path.isfile(filename):
            # Check if the image was retrieved successfully
            if r.status_code == 200:
                # Set decode_content value to True,
                # otherwise the downloaded image file's size will be zero.
                r.raw.decode_content = True

                # Open a local file with wb ( write binary ) permission.
                with open(filename, 'wb') as f:
                    shutil.copyfileobj(r.raw, f)

                print('Image sucessfully Downloaded: ', filename)
            else:
                print('Image Couldn\'t be retreived')

        parsed_album['thumbnail_filepath'] = filename
    except Exception as ex:
        # NOTE: This is gonna be a pain to fix if a thumbnail doesn't download
        print("Could not download thumbnail")
        print(ex)

    ALBUMS[album_id] = parsed_album


def save_debug_data(filename, data, debug=True):
    if debug:
        with open(filename, 'w') as f:
            f.write(data)


# TODO: Good place for some fancy yield work?
def parse_songs(app, args, all_raw_song_data):
    all_parsed_songs = []
    for raw_song in all_raw_song_data:
        song_id = raw_song['videoId']

        album_id = raw_song['album']['id']
        if not ALBUMS[album_id]:
            save_album(app, args, album_id)

        album = ALBUMS[album_id]

        track_num = None
        for track in ALBUMS[album_id]['tracks']:
            if track['id'] == song_id:
                track_num = track['track_num']

        parsed_song = {
            'id': raw_song['videoId'],
            'title': raw_song['title'],
            'artists': [artist['name'] for artist in raw_song['artists']],
            'album': album['name'],
            'track': track_num,
            'url': YOUTUBE_MUSIC_URL.format(raw_song['videoId']),
            'year': album['year'],
            'thumbnail_filepath': album['thumbnail_filepath']
        }
        all_parsed_songs.append(parsed_song)

    if args.debug_location:
        save_debug_data('parsed_album_data.json', json.dumps(ALBUMS),
                        debug=DEBUG)
        save_debug_data('parsed_song_data.json', json.dumps(all_parsed_songs),
                        debug=DEBUG)

    return all_parsed_songs


def get_library_songs(app, args, order='a_to_z'):
    all_raw_song_data = app.get_library_songs(limit=args.song_limit,
                                              order=order)

    if args.debug_location:
        path = os.path.join(args.debug_location, 'raw_song_data.json')
        save_debug_data(path, json.dumps(all_raw_song_data),
                        debug=DEBUG)

    all_parsed_songs = parse_songs(app, args, all_raw_song_data)

    return all_parsed_songs


def stuff():
    # TODO: Can you use the cookies from YTMusic here
    # cookies = os.path.join(os.path.expanduser("~"), "cookies.txt")
    cookies = './cookies.txt'
    ytdl = create_downloader(music_directory, cookies)

    failed_songs = []
    for song in []:
        try:
            ytdl.extract_info(song['url'], download=True)
        except Exception as ex:
            print(ex)
            print("Could not download: {}".format((song)))
            failed_songs.append(song)

    failed_songs = []

    for song in all_songs:
        try:
            print("Downloading: {} - {} - {} from {}...".format(
                song['title'], song['artist'], song['album'], song['url']),
                  end='')
            ytdl.extract_info(song['url'], download=True)
            sys.exit()
            print("Done.")
        except Exception as ex:
            print(ex)
            print("Could not download: {}".format((song['url'])))
            failed_songs.append(song)

    files = get_all_files(music_directory)

    counter = 1
    for f in files:
        try:
            print("Adding metadata to {} ...".format(f), end="")
            with open(f.replace('.mp3', '.info.json')) as json_file:
                json_data = json.load(json_file)
                metadata = get_song_metadata_from_json(json_data, counter)
                write_metadata_to_song_file(f, metadata)
                print("Done")
            print("Moving file...", end="")
            move_file(f, metadata, music_directory)
            print("Done")
            counter += 1
        except Exception as e:
            # just gonna print this and move on to the next file.
            print(e)

    print("Cleaning up JSON files...", end='')
    cleanup_metadata_files(music_directory)
    print("Done.")


# TODO: Implement
def retry_downloading_songs():
    # try:
    #     if len(failed_urls) > 1:
    #         print("Saving failed urls to txt file.")
    #         save_urls_from_playlist_to_file(
    #             os.path.join(music_directory, "jamos_failed_urls.txt"),
    #             failed_urls)
    #     elif args.retry_file:
    #        # Just because we don't have any failed urls in this run, doesn't
    #        # mean that we can get rid of the retry file. We'll only remove it
    #         # if it's been explicitly tried and we have no failed urls.

    #        # We've successfully downloaded all of the previously failed urls.
    #         # Delete the file
    #         os.remove(args.retry_file)
    # except Exception as ex:
    #     print(ex)
    #     print("Saving failed urls to file failed! Printing failed urls:")
    #     for url in failed_urls:
    #         print(url)
    print("Not Implemented Yet!")
    sys.exit()


# TODO: Implement
def handle_downloading_playlist():
    print("Not Implemented Yet!")
    sys.exit()
    pass


# def sanitize_for_filename(filename):
#     new_filename = filename.replace(' ', '_')
#     new_filename = (''.join(
#             [s for s in new_filename if s.isalnum() or s == '_'])).lower()
#     return new_filename


if __name__ == "__main__":
    try:
        args = get_command_line_options()
    except Exception as ex:
        print(ex)
        sys.exit()

    music_directory = args.output

    app = create_youtube_music_api_object(args.headers)

    all_songs = get_library_songs(app, args)

    ytdl = create_downloader(music_directory)

    for song in all_songs:
        # download song
        ytdl.extract_info(song['url'], download=True)

        # get filename song was downloaded to
        filenames = glob.glob(os.path.join(music_directory, song['id'] + '.*'))
        filename = filenames[0]

        # tag basic data
        file = music_tag.load_file(filename)
        file['name'] = song['title']
        file['artist'] = song['artists'][0]
        file['albumartist'] = song['artists'][0]
        file['album'] = song['album']
        file['tracknumber'] = song['track']
        file['year'] = song['year']

        # include album cover
        try:
            # NOTE: this will be at least None
            if song['thumbnail_filepath']:
                with open(song['thumbnail_filepath'], 'rb') as img_in:
                    file['artwork'] = img_in.read()
        except Exception as ex:
            print(ex)

        # save music tag data
        file.save()

        # move song to music_directory/artist/album/artist_album_title.ext
        # excluding non filesafe characters

        artist_for_filename = remove_special_characters_for_filename(
            song['artists'][0])
        album_for_filename = remove_special_characters_for_filename(
            song['album'])
        title_for_filename = remove_special_characters_for_filename(
            song['title'])
        song_output_dir = os.path.join(music_directory,
                                       artist_for_filename,
                                       album_for_filename)

        Path(song_output_dir).mkdir(parents=True, exist_ok=True)

        new_filename = '{}_{}_{}.mp3'.format(artist_for_filename,
                                             album_for_filename,
                                             title_for_filename)

        shutil.move(filename, os.path.join(song_output_dir, new_filename))
    print("done")