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
|
import os
import requests
from requests.adapters import HTTPAdapter
from urllib3.util import Retry
from tqdm import tqdm
import pylrc
import json
from PIL import Image
from multiprocessing import Pool, Manager,Lock, Value
from mutagen.easyid3 import EasyID3
from mutagen.id3 import APIC, SYLT, Encoding, ID3
from mutagen.flac import Picture, FLAC
from pydub import AudioSegment
import time
import datetime
import sys
import random
def make_valid(filename):
# Make a filename valid in different OSs
f = filename.replace(':', '_')
f = f.replace('/', '_')
f = f.replace('<', '_')
f = f.replace('>', '_')
f = f.replace('\'', '_')
f = f.replace('\\', '_')
f = f.replace('|', '_')
f = f.replace('?', '_')
f = f.replace('*', '_')
return f
def lyric_file_to_text(filename):
lrc_file = open(filename, 'r', encoding='utf-8')
lrc_string = ''.join(lrc_file.readlines())
lrc_file.close()
subs = pylrc.parse(lrc_string)
ret = []
for sub in subs:
time = int(sub.time * 1000)
text = sub.text
ret.append((text, time))
return ret
def update_downloaded_albums(queue, directory):
while 1:
album_name = queue.get()
try:
with open(directory + 'completed_albums.json', 'r', encoding='utf8') as f:
completed_albums = json.load(f)
except:
completed_albums = []
completed_albums.append(album_name)
with open(directory + 'completed_albums.json', 'w+', encoding='utf8') as f:
json.dump(completed_albums, f)
def fill_metadata(filename, filetype, album, title, albumartist, artist, tracknumber, albumcover, songlyricpath):
if filetype == '.mp3':
file = EasyID3(filename)
else:
file = FLAC(filename)
file['album'] = album
file['title'] = title
file['albumartist'] = ''.join(albumartist)
file['artist'] = ''.join(artist)
file['tracknumber'] = str(tracknumber + 1)
file.save()
if filetype == '.mp3':
file = ID3(filename)
file.add(APIC(mime='image/png',type=3,desc='Cover',data=open(albumcover,'rb').read()))
# Read and add lyrics
if (songlyricpath != None):
sylt = lyric_file_to_text(songlyricpath)
file.setall('SYLT', [SYLT(encoding=Encoding.UTF8, lang='eng', format=2, type=1, text=sylt)])
file.save()
else:
image = Picture()
image.type = 3
image.desc = 'Cover'
image.mime = 'image/png'
with open(albumcover,'rb') as f:
image.data = f.read()
with Image.open(albumcover) as imagePil:
image.width, image.height = imagePil.size
image.depth = 24
file.add_picture(image)
# Read and add lyrics
if (songlyricpath != None):
musiclrc = open(songlyricpath, 'r', encoding='utf-8').read()
file['lyrics'] = musiclrc
file.save()
return
def download_song(session, directory, name, url, song_counter, lock):
# Set timeout and retry parameters
time.sleep(3)
timeout = 10
retries = 5
source = session.get(url, stream=True)
filename = directory + '/' + make_valid(name)
filetype = ''
if source.headers['content-type'] == 'audio/mpeg':
filename += '.mp3'
filetype = '.mp3'
else:
filename += '.wav'
# Download song with retries and timeout
total = int(source.headers.get('content-length', 0))
downloaded = 0
retry_count = 0
while downloaded < total:
try:
with open(filename, 'ab') as f, tqdm(
desc=name,
total=total,
initial=downloaded,
unit='iB',
unit_scale=True,
unit_divisor=1024,
) as bar:
f.seek(downloaded)
for data in source.iter_content(chunk_size = 1024):
size = f.write(data)
downloaded += size
bar.update(size)
if downloaded >= total:
break
if retry_count > 0:
print(f'Retry successful. Downloading {name}...')
retry_count = 0
except (requests.exceptions.RequestException, IOError) as e:
if retry_count >= retries:
raise e
else:
retry_count += 1
print(f"Download of {name} failed. Retrying in 3 seconds ({retry_count}/{retries})", file=sys.stderr)
time.sleep(3)
source = session.get(url, stream=True, timeout=timeout)
total = int(source.headers.get('content-length', 0))
downloaded = f.tell()
if downloaded < total:
print(f'Download of {name} was incomplete. Retrying...', file=sys.stderr)
os.remove(filename)
# If file is .wav then export to .flac
if source.headers['content-type'] != 'audio/mpeg':
AudioSegment.from_wav(filename).export(directory + '/' + make_valid(name) + '.flac', format='flac')
os.remove(filename)
filename = directory + '/' + make_valid(name) + '.flac'
filetype = '.flac'
# Increase song counter
with lock:
song_counter.value += 1
return filename, filetype
def download_album( args, pass_counter, song_counter, album_counter,lock):
directory = args['directory']
session = args['session']
queue = args['queue']
album_cid = args['cid']
album_name = args['name']
album_coverUrl = args['coverUrl']
album_artistes = args['artistes']
album_url = 'https://monster-siren.hypergryph.com/api/album/' + album_cid + '/detail'
try:
with open(directory + 'completed_albums.json', 'r', encoding='utf8') as f:
completed_albums = json.load(f)
except:
completed_albums = []
# fix the album name which have space in last word in Windows
album_name = album_name.rstrip().split()
if len(album_name) > 0 and album_name[-1].endswith(' '):
album_name[-1] = album_name[-1][:-1]
album_name = ' '.join(album_name)
if album_name in completed_albums:
# If album is completed then skip
print(f'Skipping downloaded album {album_name}')
with lock:
pass_counter.value += 1
return
try:
os.mkdir(directory + album_name)
except:
pass
# Download album art
with open(directory + album_name + '/cover.jpg', 'w+b') as f:
f.write(session.get(album_coverUrl).content)
# Change album art from .jpg to .png
cover = Image.open(directory + album_name + '/cover.jpg')
cover.save(directory + album_name + '/cover.png')
os.remove(directory + album_name + '/cover.jpg')
songs = session.get(album_url, headers={'Accept': 'application/json'}).json()['data']['songs']
for song_track_number, song in enumerate(songs):
# Get song details
time.sleep(3) # add 3-second delay
song_cid = song['cid']
song_name = song['name']
song_artists = song['artistes']
song_url = 'https://monster-siren.hypergryph.com/api/song/' + song_cid
headers = read_agent()
song_detail = session.get(song_url, headers=headers).json()['data']
song_lyricUrl = song_detail['lyricUrl']
song_sourceUrl = song_detail['sourceUrl']
# Download lyric
if (song_lyricUrl != None):
songlyricpath = directory + album_name + '/' + make_valid(song_name) + '.lrc'
with open(songlyricpath, 'w+b') as f:
f.write(session.get(song_lyricUrl).content)
else:
songlyricpath = None
# Download song and fill out metadata
filename, filetype = download_song(session=session, directory=directory + album_name, name=song_name, url=song_sourceUrl,song_counter=song_counter,lock=lock)
fill_metadata(filename=filename,
filetype=filetype,
album=album_name,
title=song_name,
albumartist=album_artistes,
artist=song_artists,
tracknumber=song_track_number,
albumcover=directory + album_name + '/cover.png',
songlyricpath=songlyricpath)
# Increase album counter
with lock:
album_counter.value += 1
# Mark album as finished
queue.put(album_name)
return
def read_agent():
# Read user agent strings from file
with open('user_agent.txt', 'r') as f:
user_agent_list = [line.strip() for line in f]
# Choose a random user agent
user_agent = random.choice(user_agent_list)
# Set headers with Accept and User-Agent
headers = {
'Accept': 'application/json',
'User-Agent': user_agent
}
return headers
def main():
directory = './MonsterSiren/'
session = requests.Session()
manager = Manager()
queue = manager.Queue()
lock = manager.Lock()
pass_counter = manager.Value('i', 0)
song_counter = manager.Value('i', 0)
album_counter = manager.Value('i', 0)
try:
os.mkdir(directory)
except:
pass
headers = read_agent()
# Get all albums
albums = session.get('https://monster-siren.hypergryph.com/api/albums', headers=headers).json()['data']
for album in albums:
album['directory'] = directory
album['session'] = session
album['queue'] = queue
# Download all albums
num_workers = os.cpu_count() - 3 # leave one CPU core free
with Pool(num_workers) as pool:
# with Pool(maxtasksperchild=1) as pool:
pool.apply_async(update_downloaded_albums, (queue, directory))
results = pool.starmap(download_album, [(album, pass_counter, song_counter, album_counter, lock) for album in albums])
queue.put('kill')
pass_total = pass_counter.value
song_total = song_counter.value
album_total = album_counter.value
# Write counter to file
with open("counter.txt", "a") as f:
timestamp = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
f.write(f'Finish Time: {timestamp}\n')
f.write(f'Total albums skipped: {pass_total}\n')
f.write(f"Downloaded {song_total} songs from {album_total} albums.\n")
f.write(f"-----------------------------\n")
print(f'Total albums skipped: {pass_total}')
print(f"Downloaded {song_total} songs from {album_total} albums.")
return
if __name__ == '__main__':
main()
|