2014-05-04 17:26:43 +00:00
|
|
|
# -*- coding: utf-8 -*-
|
2014-09-02 22:32:44 +00:00
|
|
|
|
2014-05-04 17:26:43 +00:00
|
|
|
|
|
|
|
import os
|
|
|
|
from utils import find_isbns
|
2014-05-19 18:12:02 +00:00
|
|
|
import tempfile
|
|
|
|
import subprocess
|
2014-05-04 17:26:43 +00:00
|
|
|
|
|
|
|
def cover(path):
|
2024-06-10 13:57:12 +00:00
|
|
|
import settings
|
2014-05-19 18:12:02 +00:00
|
|
|
image = tempfile.mkstemp('.jpg')[1]
|
2024-06-10 13:57:12 +00:00
|
|
|
cmd = ['python3', os.path.join(settings.top_dir, 'reader/txt.js/txt.py'), '-i', path, '-o', image]
|
2014-08-22 16:49:11 +00:00
|
|
|
p = subprocess.Popen(cmd, close_fds=True)
|
2014-05-19 18:12:02 +00:00
|
|
|
p.wait()
|
|
|
|
with open(image, 'rb') as fd:
|
|
|
|
data = fd.read()
|
|
|
|
os.unlink(image)
|
2014-05-04 17:26:43 +00:00
|
|
|
return data
|
|
|
|
|
|
|
|
def info(path):
|
|
|
|
data = {}
|
|
|
|
data['title'] = os.path.splitext(os.path.basename(path))[0]
|
|
|
|
text = extract_text(path)
|
|
|
|
isbn = extract_isbn(text)
|
|
|
|
if isbn:
|
2016-01-11 13:43:54 +00:00
|
|
|
data['isbn'] = isbn
|
2014-05-04 17:26:43 +00:00
|
|
|
data['textsize'] = len(text)
|
|
|
|
return data
|
|
|
|
|
|
|
|
def extract_text(path):
|
2014-10-31 14:41:46 +00:00
|
|
|
with open(path, 'rb') as fd:
|
|
|
|
data = fd.read().decode('utf-8', errors='replace')
|
2014-05-04 17:26:43 +00:00
|
|
|
return data
|
|
|
|
|
|
|
|
def extract_isbn(text):
|
|
|
|
isbns = find_isbns(text)
|
|
|
|
if isbns:
|
|
|
|
return isbns[0]
|