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
|
#!/usr/bin/env python3
import hashlib
import json
import math
import os
from datetime import timedelta
from flask import Flask
from lib.tinytag import TinyTag
def get_books(root_path):
'''
Discover audiobooks under :root_path: and populate books object
'''
if not os.path.exists(root_path):
raise ValueError('root path does not exist: %s' % root_path)
SIZES = ('B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB')
_books = dict()
book_dirs = list()
for root, dirs, _ in os.walk(root_path):
for d in dirs:
book_dirs.append(os.path.join(root, d))
for book_path in book_dirs:
print('[+] processing: %s' % book_path)
# initial set of attributes to be populated
book = {
'duration': 0,
'path': book_path,
'files': dict(),
'size_bytes': 0,
'size_str': None,
}
# hash of each file in directory w/ MP3 extension
folder_hash = hashlib.md5()
is_book = False
# a book_path is only a book if it contains at least one MP3
for f in os.listdir(book_path):
file_path = os.path.join(book_path, f)
if not os.path.isfile(file_path) or not f.endswith('.mp3'):
continue
# update folder hash with MD5 of current file
BLOCK = 1024
file_hash = hashlib.md5()
with open(file_path, 'rb') as f:
while True:
data = f.read(BLOCK)
if not data:
break
folder_hash.update(data)
file_hash.update(data)
# skip if no duration attribute (required)
tag = TinyTag.get(file_path)
if not tag.duration:
continue
is_book = True
# populate file-specific attributes
attr = dict()
attr['path'] = file_path
attr['duration'] = tag.duration
if tag.title:
attr['title'] = tag.title
else:
attr['title'] = file_path.split('/')[-1]
if tag.album:
attr['album'] = tag.album
book['title'] = tag.album
else:
attr['album'] = book_path.split('/')[-1]
book['title'] = book_path.split('/')[-1]
if tag.artist:
attr['author'] = tag.artist
book['author'] = tag.artist
else:
attr['author'] = 'Unknown'
book['author'] = 'Unknown'
attr['duration'] = tag.duration
attr['track'] = tag.track
attr['size_bytes'] = tag.filesize
duration_str = str(timedelta(seconds=attr['duration']))
attr['duration_str'] = duration_str.split('.')[0]
book['duration'] += tag.duration
book['files'][file_hash.hexdigest()] = attr
book['size_bytes'] += tag.filesize
if is_book:
folder_hash = folder_hash.hexdigest()
total_size = book['size_bytes']
try:
_i = int(math.floor(math.log(total_size, 1024)))
_p = math.pow(1024, _i)
_s = round(total_size / _p, 2)
except:
_i = 1
_s = 0
# e.g. 1.48 GB
book['size_str'] = '%s %s' % (str(_s), SIZES[_i])
# e.g. 2 days, 5:47:47
duration_str = str(timedelta(seconds=book['duration']))
book['duration_str'] = duration_str.split('.')[0]
_books[folder_hash] = book
return _books
def write_cache(books, json_path):
'''
Dump contents of :books: to :json_path:
'''
cache_path = os.path.dirname(json_path)
if not os.path.exists(cache_path):
os.mkdir(cache_path)
with open(json_path, 'w') as f:
json.dump(books, f, indent=4)
if __name__ == '__main__':
ABS_PATH = os.path.dirname(os.path.abspath(__file__))
CACHE_PATH = os.path.join(ABS_PATH, 'cache')
JSON_PATH = os.path.join(CACHE_PATH, 'audiobooks.json')
# use Flask's config parser, configparser would be hacky
APP = Flask(__name__)
APP.config.from_pyfile(os.path.join(ABS_PATH, 'app.cfg'))
BOOKS = get_books(APP.config['ROOT_PATH'])
write_cache(BOOKS, JSON_PATH)
|
