0x2620/openmedialibrary
1
0
Fork 0
Code Issues 131 Pull requests Releases Wiki Activity

store metadata per user. remove primaryid. only store isbn13

Browse source
This commit is contained in:
j 2016-01-11 19:13:54 +05:30
commit 02e040d9f5
16 changed files with 245 additions and 192 deletions
Download patch file Download diff file Expand all files Collapse all files

25
oml/media/epub.py
View file

@ -5,14 +5,13 @@
import os
import xml.etree.ElementTree as ET
import zipfile
from io import BytesIO
import re
from urllib.parse import unquote
import lxml.html
import stdnum.isbn
from ox import strip_tags, decode_html
from utils import normalize_isbn, find_isbns, get_language
from utils import find_isbns, get_language, to_isbn13
import logging
logger = logging.getLogger(__name__)
@ -104,13 +103,24 @@ def info(epub):
}.get(key, key)
value = e.text.strip()
if key == 'identifier':
value = normalize_isbn(value)
if stdnum.isbn.is_valid(value):
data['isbn'] = [value]
value = to_isbn13(value)
if value:
data['isbn'] = value
elif key == 'author':
data[key] = value.split(', ')
else:
data[key] = value
guide = info.findall('{http://www.idpf.org/2007/opf}guide')
if guide:
for ref in guide[0].findall('{http://www.idpf.org/2007/opf}reference'):
if ref.attrib.get('type') == 'toc':
filename = unquote(ref.attrib['href'])
filename = os.path.normpath(os.path.join(os.path.dirname(opf[0]), filename))
toc = z.read(filename)
if toc:
doc = lxml.html.document_fromstring(toc)
data['tableofcontents'] = '\n'.join([a.text_content() for a in doc.xpath('//a')])
if 'description' in data:
data['description'] = strip_tags(decode_html(data['description']))
text = extract_text(epub)
@ -118,7 +128,7 @@ def info(epub):
if not 'isbn' in data:
isbn = extract_isbn(text)
if isbn:
data['isbn'] = [isbn]
data['isbn'] = isbn
if 'date' in data and 'T' in data['date']:
data['date'] = data['date'].split('T')[0]
if 'language' in data and isinstance(data['language'], str):
@ -139,4 +149,3 @@ def extract_isbn(data):
isbns = find_isbns(data)
if isbns:
return isbns[0]