Start epub parser

This commit is contained in:
BasioMeusPuga
2017-11-04 12:20:18 +05:30
parent e49fefd19d
commit db52b413ad

View File

@@ -2,9 +2,29 @@
import os
import zipfile
import xml.etree.ElementTree as ET
import tempfile
import xmltodict
class ePUB:
def __init__(self, filename):
pass
self.filename = filename
self.tmpdir = None
def extract(self):
self.tmpdir = tempfile.TemporaryDirectory()
with zipfile.ZipFile(self.filename, 'r') as zip_ref:
zip_ref.extractall(self.tmpdir.name)
def parse(self):
with open(self.tmpdir.name + os.sep + 'content.opf') as fd:
xml_dict = xmltodict.parse(fd.read())
metadata = xml_dict['package']['metadata']
book_title = metadata['dc:title']
book_description = metadata['dc:description']
book_author = metadata['dc:creator']['#text']
print(book_author)
print(book_title)
print(book_description)