forked from acrcloud/acrcloud_scan_files_python
/
acrcloud_scan_files_libary.py
200 lines (171 loc) · 8.98 KB
/
acrcloud_scan_files_libary.py
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
#!/usr/bin/env python
#-*- coding:utf-8 -*-
import os
import sys
import time
import json
import codecs
import logging
from backports import csv
from openpyxl import Workbook
from acrcloud_filter_libary import FilterWorker
from acrcloud_logger import AcrcloudLogger
from acrcloud.recognizer import ACRCloudRecognizer
reload(sys)
sys.setdefaultencoding("utf8")
class ACRCloud_Scan_Files:
def __init__(self, config, debug=1):
self.config = config
self.debug = debug
self.init_log()
self.re_handler = ACRCloudRecognizer(self.config)
def init_log(self):
log_level = logging.ERROR
if self.debug == 1:
log_level = logging.DEBUG
shandler = logging.StreamHandler()
#shandler.setLevel(log_level)
self.log = logging.getLogger("ACRCloud_ScanFile")
self.log.setLevel(log_level)
self.log.addHandler(shandler)
def as_text(self, value):
if value is None:
return ""
return str(value)
def get_duration_by_file(self, filepath):
return int(ACRCloudRecognizer.get_duration_ms_by_file(filepath)/1000)
def export_to_xlsx(self, result_list, export_filename="ACRCloud_ScanFile_Results.xlsx", export_dir="./"):
try:
results = []
for item in result_list:
filename = item["file"]
timestamp = item["timestamp"]
jsoninfo = item["result"]
if "status" in jsoninfo and jsoninfo["status"]["code"] == 0:
row = self.parse_data(jsoninfo)
row = [filename, timestamp] + list(row)
results.append(row)
results = sorted(results, key=lambda x:x[1])
wb = Workbook()
sheet_music = wb.active
sheet_music.title = "ACRCloud_Scan_File"
header_row = ['filename', 'timestamp', 'custom_files_title', 'custom_acrid', 'title', 'artists', 'album',
'acrid', 'played_duration', 'label', 'isrc', 'upc', 'dezzer', 'spotify', 'itunes', 'youtube']
sheet_music.append(header_row)
for row in results:
sheet_music.append(row)
for column_cells in sheet_music.columns:
length = max(len(self.as_text(cell.value)) for cell in column_cells)
if length > 80:
length == 80
sheet_music.column_dimensions[column_cells[0].column].width = length
export_filepath = os.path.join(export_dir, export_filename)
wb.save(export_filepath)
if self.debug:
self.log.info("export_to_xlsx.Save Data to xlsx: {0}".format(export_filename))
except Exception as e:
self.log.error("Error@export_to_xlsx", exc_info=True)
def export_to_csv(self, result_list, export_filename="ACRCloud_ScanFile_Results.csv", export_dir="./"):
try:
results = []
for item in result_list:
filename = item["file"]
timestamp = item["timestamp"]
jsoninfo = item["result"]
if "status" in jsoninfo and jsoninfo["status"]["code"] == 0:
row = self.parse_data(jsoninfo)
row = [filename, timestamp] + list(row)
results.append(row)
results = sorted(results, key=lambda x:x[1])
export_filepath = os.path.join(export_dir, export_filename)
with codecs.open(export_filepath, 'w', 'utf-8-sig') as f:
head_row = ['filename', 'timestamp', 'custom_files_title', 'custom_acrid', 'title', 'artists', 'album',
'acrid', 'played_duration', 'label', 'isrc', 'upc', 'dezzer', 'spotify', 'itunes', 'youtube']
dw = csv.writer(f)
dw.writerow(head_row)
dw.writerows(results)
if self.debug:
self.log.info("export_to_csv.Save Data to csv: {0}".format(export_filename))
except Exception as e:
self.log.error("Error@export_to_csv", exc_info=True)
def parse_data(self, jsoninfo):
try:
title, played_duration, isrc, upc, acrid, label, album = [""]*7
artists, deezer, spotify, itunes, youtube, custom_files_title, audio_id, custom_acrid = [""]*8
metadata = jsoninfo.get('metadata', {})
played_duration = metadata.get("played_duration", "")
if "music" in metadata and len(metadata["music"]) > 0:
item = metadata["music"][0]
title = item.get("title", "")
offset = item.get("play_offset_ms", "")
isrc = item.get("external_ids", {"isrc":""}).get("isrc","")
upc = item.get("external_ids", {"upc":""}).get("upc","")
acrid = item.get("acrid","")
label = item.get("label", "")
album = item.get("album", {"name":""}).get("name", "")
artists = ",".join([ ar["name"] for ar in item.get('artists', [{"name":""}]) if ar.get("name") ])
deezer = item.get("external_metadata", {"deezer":{"track":{"id":""}}}).get("deezer", {"track":{"id":""}}).get("track", {"id":""}).get("id", "")
spotify = item.get("external_metadata", {"spotify":{"track":{"id":""}}}).get("spotify", {"track":{"id":""}}).get("track", {"id":""}).get("id", "")
itunes = item.get("external_metadata", {"itunes":{"track":{"id":""}}}).get("itunes", {"track":{"id":""}}).get("track", {"id":""}).get("id", "")
youtube = item.get("external_metadata", {"youtube":{"vid":""}}).get("youtube", {"vid":""}).get("vid", "")
if "custom_files" in metadata and len(metadata["custom_files"]) > 0:
custom_item = metadata["custom_files"][0]
custom_files_title = custom_item.get("title", "")
audio_id = custom_item.get("audio_id", "")
custom_acrid = custom_item.get("acrid", "")
except Exception as e:
self.log.error("Error@parse_data")
res = (custom_files_title, custom_acrid, title, artists, album, acrid,
played_duration, label, isrc, upc, deezer, spotify, itunes, youtube,)
return res
def apply_filter(self, results):
fworker = FilterWorker()
result_new = fworker.apply_filter(results)
return result_new
def do_recognize(self, filepath, start_time, rec_length):
current_time = time.strftime('%d %H:%M:%S', time.gmtime(start_time))
res_data = self.re_handler.recognize_by_file(filepath, start_time, rec_length)
return filepath, current_time, res_data
def for_recognize_file(self, filepath, start_time, stop_time, step, rec_length):
try:
for i in range(start_time, stop_time, step):
filep, current_time, res_data = self.do_recognize(filepath, i, rec_length)
if res_data:
jsoninfo = json.loads(res_data)
if "metadata" in jsoninfo and "timestamp_utc" in jsoninfo["metadata"]:
jsoninfo["metadata"]["timestamp_utc"] = current_time
else:
jsoninfo = {}
yield {"timestamp":current_time, "rec_length":rec_length, "result":jsoninfo, "file":filep}
except Exception as e:
self.log.error("Error@for_recognize_file", exc_info=True)
def recognize_file(self, filepath, start_time, stop_time, step, rec_length):
try:
result_list = []
for i in range(start_time, stop_time, step):
filep, current_time, res_data = self.do_recognize(filepath, i, rec_length)
if res_data:
jsoninfo = json.loads(res_data)
try:
if "metadata" in jsoninfo and "timestamp_utc" in jsoninfo["metadata"]:
jsoninfo["metadata"]["timestamp_utc"] = current_time
code = jsoninfo["status"]["code"]
msg = jsoninfo["status"]["msg"]
if jsoninfo["status"]["code"] not in [0, 1001]:
raise Exception("recognize_file.(timestamp: {0}, {1}, {2})".format(current_time, code, msg))
except Exception as e:
if self.debug:
self.log.error(e)
else:
print e
if code in [3001, 3003, 3013]:
break
else:
continue
result_list.append({"timestamp":current_time, "rec_length":rec_length, "result":jsoninfo, "file":filep})
if self.debug:
parse_info = self.parse_data(jsoninfo)
self.log.info('recognize_file.(timestamp: {0}, title: {1})'.format(current_time, parse_info[0]))
except Exception as e:
self.log.error("Error@recognize_file", exc_info=True)
return result_list