openmedialibrary/oml/media/__init__.py

85 lines
2.5 KiB
Python
Raw Normal View History

2014-05-12 23:43:27 +00:00
# -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4
from __future__ import division
import base64
import hashlib
import os
import ox
2014-05-04 17:26:43 +00:00
import pdf
import epub
import txt
import opf
2014-05-04 17:26:43 +00:00
2014-05-12 23:43:27 +00:00
def get_id(f=None, data=None):
if data:
return base64.b32encode(hashlib.sha1(data).digest())
else:
2014-05-26 09:27:20 +00:00
return base64.b32encode(ox.sha1sum(f, cached=True).decode('hex'))
2014-05-12 23:43:27 +00:00
2014-05-04 17:26:43 +00:00
def metadata(f, from_=None):
2014-05-04 17:26:43 +00:00
ext = f.split('.')[-1]
data = {}
2014-05-18 23:24:04 +00:00
data['extension'] = ext
data['size'] = os.stat(f).st_size
2014-05-04 17:26:43 +00:00
if ext == 'pdf':
info = pdf.info(f)
elif ext == 'epub':
info = epub.info(f)
elif ext == 'txt':
info = txt.info(f)
opf_info = {}
metadata_opf = os.path.join(os.path.dirname(from_ or f), 'metadata.opf')
if os.path.exists(metadata_opf):
opf_info = opf.info(metadata_opf)
for key in (
'title', 'author', 'date', 'publisher',
'language', 'textsize', 'pages',
'isbn', 'asin'
):
2014-05-04 17:26:43 +00:00
if key in info:
value = info[key]
if isinstance(value, str):
try:
value = value.decode('utf-8')
except:
value = None
if value:
data[key] = info[key]
if key in opf_info:
data[key] = opf_info[key]
2014-05-28 15:36:26 +00:00
if key in data:
2014-05-28 11:36:44 +00:00
if isinstance(data[key], basestring):
data[key] = data[key].replace('\x00', '')
elif isinstance(data[key], list):
data[key] = [e.replace('\x00', '') if isinstance(e, basestring) else e for e in data[key]]
2014-05-04 17:26:43 +00:00
if 'isbn' in data:
2014-05-21 00:02:21 +00:00
data['primaryid'] = ['isbn', data['isbn'][0]]
elif 'asin' in data:
data['primaryid'] = ['asin', data['asin'][0]]
2014-05-26 08:23:10 +00:00
if 'author' in data:
if isinstance(data['author'], basestring):
2014-05-27 18:10:55 +00:00
if data['author'].strip():
data['author'] = data['author'].strip().split('; ')
else:
del data['author']
2014-05-26 08:23:10 +00:00
if data['author'] in (['Administrator'], ['Default'], ['user']):
del data['author']
2014-05-04 17:26:43 +00:00
if not 'title' in data:
data['title'] = os.path.splitext(os.path.basename(f))[0]
2014-05-26 08:23:10 +00:00
if data['title'].startswith('Microsoft Word - '):
data['title'] = data['title'][len('Microsoft Word - '):]
2014-05-26 09:27:20 +00:00
for postfix in ('.doc', 'docx', '.qxd', '.indd', '.tex'):
2014-05-26 08:23:10 +00:00
if data['title'].endswith(postfix):
data['title'] = data['title'][:-len(postfix)]
if not data['title'].strip():
del data['title']
2014-05-04 17:26:43 +00:00
return data