saret/Lector
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Parser functional for initial epub details

Browse Source
This commit is contained in:
BasioMeusPuga
2017-11-06 14:43:01 +05:30
parent 8ec2b6e02c
commit ea399ff2c5
3 changed files with 84 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
__main__.py
View File

@@ -26,6 +26,7 @@ import sys
from PyQt5 import QtWidgets, QtGui, QtCore
import mainwindow
import database
import parser
class MainUI(QtWidgets.QMainWindow, mainwindow.Ui_MainWindow):
@@ -65,10 +66,13 @@ class MainUI(QtWidgets.QMainWindow, mainwindow.Ui_MainWindow):
def open_file(self):
# TODO
# Maybe expand this to traverse directories recursively
home_dir = os.path.expanduser('~')
my_file = QtWidgets.QFileDialog.getOpenFileNames(
self, 'Open file', home_dir, "eBooks (*.epub *.mobi *.txt)")
print(my_file[0])
self, 'Open file', self.last_open_path, "eBooks (*.epub *.mobi *.txt)")
if my_file[0]:
self.last_open_path = os.path.dirname(my_file[0][0])
print(self.last_open_path)
books = parser.BookSorter(my_file[0])
books.add_to_database()
def close_tab_class(self, tab_index):
this_tab = Tabs(self, None)
@@ -157,12 +161,22 @@ class Settings:
QtCore.QPoint(286, 141)))
self.settings.endGroup()
self.settings.beginGroup('path')
self.parent_window.last_open_path = self.settings.value(
'path', os.path.expanduser('~'))
print(self.parent_window.last_open_path)
self.settings.endGroup()
def save_settings(self):
self.settings.beginGroup('mainWindow')
self.settings.setValue('windowSize', self.parent_window.size())
self.settings.setValue('windowPosition', self.parent_window.pos())
self.settings.endGroup()
self.settings.beginGroup('lastOpen')
self.settings.setValue('path', self.parent_window.last_open_path)
self.settings.endGroup()
class Toolbars:
# TODO

4
database.py
View File

@@ -17,7 +17,7 @@ class DatabaseFunctions:
def create_database(self):
self.database.execute(
"CREATE TABLE books \
(id INTEGER PRIMARY KEY, Name TEXT, Path TEXT, ISBN TEXT, CoverImage BLOB)")
(id INTEGER PRIMARY KEY, Name TEXT, Path TEXT, ISBN TEXT, Tags TEXT, CoverImage BLOB)")
self.database.execute(
"CREATE TABLE cache \
(id INTEGER PRIMARY KEY, Name TEXT, Path TEXT, CachedDict BLOB)")
@@ -25,6 +25,6 @@ class DatabaseFunctions:
# database at time of closing
self.database.commit()
def add_to_database(self, book_data, image_data):
pass

99
parser.py
View File

@@ -6,59 +6,90 @@ import collections
import ebooklib.epub
def get_book_essentials(filename):
book = ebooklib.epub.read_epub(filename)
class ParseEPUB:
def __init__(self, filename):
self.filename = filename
self.book_title = None
try:
self.book = ebooklib.epub.read_epub(filename)
except (KeyError, AttributeError):
print('Cannot parse ' + self.filename)
return
# Get book title
title = book.title.strip()
def get_title(self):
return self.book.title.strip()
# Get cover image
# This seems hack-ish, but that's never stopped me before
image_path = None
try:
cover = book.metadata['http://www.idpf.org/2007/opf']['cover'][0][1]['content']
cover_item = book.get_item_with_id(cover)
def get_cover_image(self):
# Get cover image
# This seems hack-ish, but that's never stopped me before
image_path = None
try:
cover = self.book.metadata['http://www.idpf.org/2007/opf']['cover'][0][1]['content']
cover_item = self.book.get_item_with_id(cover)
if cover_item:
return cover_item.get_content()
# In case no cover_item is returned, we search the items
# in the book and get the first referenced image
if not cover_item:
for j in book.guide:
# In case no cover_item is returned,
# we look for a cover in the guide
for j in self.book.guide:
try:
if (j['title'].lower in ['cover', 'cover-image', 'coverimage'] or j['type'] == 'coverimagestandard'):
if (j['title'].lower in ['cover', 'cover-image', 'coverimage'] or
j['type'] == 'coverimagestandard'):
image_path = j['href']
break
except KeyError:
pass
# And if all else fails, we find
# the first image referenced in the book
# Fuck everything
if not image_path:
for j in book.items:
for j in self.book.items:
if j.media_type == 'application/xhtml+xml':
_regex = re.search(r"src=\"(.*)\"\/", j.content.decode('utf-8'))
if _regex:
image_path = _regex[1]
break
for k in book.get_items_of_type(ebooklib.ITEM_IMAGE):
for k in self.book.get_items_of_type(ebooklib.ITEM_IMAGE):
if os.path.basename(k.file_name) == os.path.basename(image_path):
image_content = k.get_content()
break
else:
image_content = cover_item.get_content()
return image_content
except KeyError:
print('Cannot parse ' + filename)
except KeyError:
print('Cannot parse ' + self.filename)
return
# Get ISBN ID
isbn_id = None
try:
identifier = book.metadata['http://purl.org/dc/elements/1.1/']['identifier']
for i in identifier:
identifier_provider = i[1]['{http://www.idpf.org/2007/opf}scheme']
if identifier_provider.lower() == 'isbn':
isbn_id = i[0]
break
except KeyError:
pass
def get_isbn(self):
try:
identifier = self.book.metadata['http://purl.org/dc/elements/1.1/']['identifier']
for i in identifier:
identifier_provider = i[1]['{http://www.idpf.org/2007/opf}scheme']
if identifier_provider.lower() == 'isbn':
isbn = i[0]
return isbn
except KeyError:
return
with open('/home/akhil/aa.jpg', 'bw') as myimg:
myimg.write(image_content)
class BookSorter:
def __init__(self, file_list):
# Have the GUI pass a list of files straight to here
# Then, on the basis of what is needed, pass the
# filenames to the requisite functions
# This includes getting file info for the database
# Parsing for the reader proper
# Caching upon closing
self.file_list = file_list
def add_to_database(self):
# Consider multithreading this
for i in self.file_list:
book_ref = ParseEPUB(i)
title = book_ref.get_title()
cover_image = book_ref.get_cover_image()
isbn = book_ref.get_isbn()
print(title, isbn)