44 lines
1.1 KiB
Python
44 lines
1.1 KiB
Python
# -*- coding: utf-8 -*-
|
|
# vi:si:et:sw=4:sts=4:ts=4
|
|
|
|
|
|
import re
|
|
import stdnum.isbn
|
|
|
|
import ox
|
|
import ox.iso
|
|
|
|
def to_isbn13(isbn):
|
|
try:
|
|
isbn = stdnum.isbn.validate(isbn, True)
|
|
if isbn[:2] != '97':
|
|
isbn = None
|
|
except:
|
|
isbn = None
|
|
return isbn
|
|
|
|
def normalize_isbn(value):
|
|
return ''.join([s for s in value if s.isdigit() or s == 'X'])
|
|
|
|
def find_isbns(text):
|
|
if isinstance(text, bytes):
|
|
text = text.decode()
|
|
matches = re.compile('\d[\d\-X\u2013\ ]+').findall(text)
|
|
matches = [normalize_isbn(value) for value in matches]
|
|
matches = [to_isbn13(value) for value in matches]
|
|
matches = list(set([value for value in matches if value]))
|
|
return matches
|
|
|
|
def get_language(lang):
|
|
return ox.iso.codeToLang(lang.split('-')[0]) or lang
|
|
|
|
def decode_html_data(data):
|
|
if isinstance(data, dict):
|
|
for key in data:
|
|
data[key] = decode_html_data(data[key])
|
|
elif isinstance(data, list):
|
|
data = [decode_html_data(v) for v in data]
|
|
elif isinstance(data, str):
|
|
data = ox.decode_html(data)
|
|
return data
|