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
|
#!/usr/bin/env python3
import datetime
import hashlib
import json
import math
import os
from datetime import timedelta
from flask import Flask
from lib.tinytag import TinyTag
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')
class Books:
def __init__(self):
'''
Book-related handlers (r/w cache) and track discovery
'''
if os.path.exists(JSON_PATH):
self._cache = self._read_cache()
else:
self._cache = {}
def _get_dirs(self, path):
'''
Return list of directories recursively discovered in :path:
'''
s = os.scandir(path)
ret = [x.path for x in s if not x.name.startswith('.') and x.is_dir()]
s.close()
return ret
def _get_path_hash_dict(self):
'''
Return dict of book paths and their hash from cache, used to check paths
against existing cache
'/home/user/audiobooks/book': d815c7a3cc11f08558b4d91ca93de023
'''
ret = {}
for k, _ in self._cache.items():
path = self._cache[k]['path']
if os.path.exists(path):
ret[path] = k
return ret
def write_cache(self):
'''
Dump contents of :books: to :json_path:
'''
if not os.path.exists(CACHE_PATH):
os.mkdir(CACHE_PATH)
with open(JSON_PATH, 'w') as cache:
json.dump(self.books, cache, indent=4)
def _read_cache(self):
'''
Return dict of existing cache
'''
with open(JSON_PATH, 'r') as cache:
data = json.load(cache)
return data
def _validate(self, v, b):
'''
Returns :v: if :v: and v.isspace(), otherwise :b:
'''
if v and not v.isspace():
return v
return b
def _log(self, msg):
'''
Prints :msg: with formatted ISO-8601 date
'''
now = datetime.datetime.now().strftime("%Y-%m-%dT%H:%M:%S")
print('%s %s' % (now, msg))
def scan_books(self, audiobook_path=None):
'''
Discover audiobooks under :root_path: and populate books object
:cache: existing JSON cache, used to determine which content is new
(existing content is not re-hashed)
'''
ex = self._get_path_hash_dict()
dirs = self._get_dirs(audiobook_path)
books = dict()
for path in dirs:
if path in ex:
_hash = ex[path]
books[_hash] = self._cache[_hash]
continue
book = self._check_dir(path)
if book:
books[book[0]] = book[1]
self.books = books
def _check_dir(self, path):
'''
Determine if :path: contains (supported) audio files; return populated
book dict or None
'''
ext = ['mp3'] # m4b seems to be unsupported by Apple
is_book = False
# book attributes to be populated
book = {
'author': None,
'duration': 0,
'duration_str': None,
'files': dict(),
'path': path,
'size_bytes': 0,
'size_str': None,
'title': None
}
# hash of each supported track in directory path
folder_hash = hashlib.md5()
for f in sorted(os.listdir(path)):
# must be a file and have a supported extension
file_path = os.path.join(path, f)
if not os.path.isfile(file_path) or not f.split('.')[-1].lower() in ext:
continue
# tracks at minimum must have a duration tag (required by podcast
# apps)
tag = TinyTag.get(file_path)
if not tag.duration:
continue
# previous conditions met, we've found at least one track
is_book = True
self._log(os.path.join(path, f))
# hash track (used as a key) and update folder hash
file_hash = hashlib.md5()
with open(file_path, 'rb') as f:
while True:
data = f.read(1024)
if not data:
break
folder_hash.update(data)
file_hash.update(data)
# 1 day, 10:59:58
duration_str = str(timedelta(seconds=tag.duration))
# per-file atributes, some values are populated conditionally
track = {
'album': self._validate(tag.album, os.path.split(path)[1]),
'author': self._validate(tag.artist, 'Unknown'),
'duration': tag.duration,
'duration_str': duration_str.split('.')[0],
'filename': os.path.split(file_path)[1],
'path': file_path,
'size_bytes': tag.filesize,
'title': self._validate(tag.title, os.path.split(file_path)[1]),
'track': tag.track
}
# we assume author and album attributes are unchanged between tracks
book['author'] = track['author']
book['title'] = track['album']
# increment book total size/duration
book['duration'] += tag.duration
book['size_bytes'] += tag.filesize
# hexdigest: track dict
book['files'][file_hash.hexdigest()] = track
# final book processing routine; update total size, duration
if is_book:
folder_hash = folder_hash.hexdigest()
total_size = book['size_bytes']
# bytes -> readable file size, used in audiobook index
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
SIZES = ('B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB')
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]
return (folder_hash, book)
return None
|
