mirror of
https://github.com/th3r00t/pyShelf.git
synced 2026-04-28 01:59:35 -04:00
96 lines
3.4 KiB
Python
Executable File
96 lines
3.4 KiB
Python
Executable File
#!/usr/bin/python
|
|
import json
|
|
import os
|
|
import re
|
|
import zipfile
|
|
from bs4 import BeautifulSoup
|
|
from config import Config
|
|
config = Config()
|
|
|
|
|
|
class Catalogue:
|
|
"""Decodes and stores book information"""
|
|
"""Step One: filter_books"""
|
|
def __init__(self):
|
|
self.file_list = []
|
|
with open(config.book_shelf, 'r') as f:
|
|
try:
|
|
self.catalogue = json.load(f)
|
|
self.current_files = self.scan_folder()
|
|
except Exception:
|
|
self.filter_books()
|
|
|
|
def scan_folder(self, folder=config.book_path):
|
|
for f in os.listdir(folder):
|
|
_path = os.path.abspath(folder+'/'+f)
|
|
#_path = os.path.abspath('.')+'/'+folder+f+'/'
|
|
_is_dir = os.path.isdir(_path.strip()+'/')
|
|
if _is_dir:
|
|
self.file_list.append(self.scan_folder(_path))
|
|
self.file_list.append(_path)
|
|
|
|
def scan_book(self, book):
|
|
"""REMOVE ME?"""
|
|
_epub = zipfile.ZipFile(book)
|
|
with _epub as _epub_open:
|
|
try: _epub_open.open('content.opf'); return True
|
|
except Exception as e: print(e); return False
|
|
|
|
def filter_books(self):
|
|
"""
|
|
Scan book folder recursively for epub files
|
|
filter_books(0) -> Catalogue.books
|
|
filter_books(1) -> self.books[]
|
|
:param ret: 0 -> create class property -> dump json
|
|
:param ret: 1 -> create & return class property
|
|
"""
|
|
self.scan_folder()
|
|
regx = re.compile(r"\.epub")
|
|
self.books = list(filter(regx.search, filter(None, self.file_list)))
|
|
_book_list_expanded = {}
|
|
with open(config.book_shelf, 'w') as f:
|
|
for book in self.books:
|
|
_book_list_expanded[book] = self.process_book(book)
|
|
json.dump(_book_list_expanded, f)
|
|
return _book_list_expanded
|
|
|
|
def process_book(self, book):
|
|
"""Return dictionary of epub file contents"""
|
|
f_name = 'content.opf'
|
|
book = zipfile.ZipFile(book, 'r')
|
|
details = {}
|
|
with book as book_zip:
|
|
details['files'] = []
|
|
details['path'] = book.filename
|
|
expanded = book_zip.infolist()
|
|
regx = re.compile(r'\.opf|cover')
|
|
for i in expanded:
|
|
match = re.search(regx, i.filename)
|
|
if match:
|
|
# Returns zip file location of requested files
|
|
details['files'].append(match.string)
|
|
return details
|
|
|
|
def extract_metadata(self, book):
|
|
"""
|
|
Return extracted metadata and cover picture
|
|
book['path'] == Full path to ebook file
|
|
book['files'] == list of files from self.process_book(book)
|
|
"""
|
|
book_zip = zipfile.ZipFile(book['path'], 'r')
|
|
opf_regx, cover_regx = re.compile(r'\.opf'), re.compile(r'\.jpg|\.png|\.bmp|\.gif')
|
|
with book_zip as f:
|
|
content = list(filter(opf_regx.search, book['files']))
|
|
content = book_zip.open(content[0])
|
|
soup = BeautifulSoup(content, "xml")
|
|
title = soup.find("dc:title")
|
|
author = soup.find("dc:creator")
|
|
cover = soup.find("meta", attrs={"name" : "cover"})
|
|
return title
|
|
def compare_shelf_current(self):
|
|
try:
|
|
self.books
|
|
except Exception:
|
|
self.filter_books()
|
|
unique = set(self.books) - set(self.catalogue)
|
|
return unique |