Application icon and .desktop file

Rearrange modules because of single-version-externally-managed

lector/parsers/comicbooks.py

@@ -0,0 +1,79 @@
+#!/usr/bin/env python3
+
+# This file is a part of Lector, a Qt based ebook reader
+# Copyright (C) 2017-18 BasioMeusPuga
+
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+# TODO
+# Account for files with passwords
+
+import os
+import time
+import zipfile
+from lector.rarfile import rarfile
+
+
+class ParseCOMIC:
+    def __init__(self, filename, *args):
+        self.filename = filename
+        self.book = None
+        self.image_list = None
+        self.book_extension = os.path.splitext(self.filename)
+
+    def read_book(self):
+        try:
+            if self.book_extension[1] == '.cbz':
+                self.book = zipfile.ZipFile(
+                    self.filename, mode='r', allowZip64=True)
+                self.image_list = [i.filename for i in self.book.infolist() if not i.is_dir()]
+
+            elif self.book_extension[1] == '.cbr':
+                self.book = rarfile.RarFile(self.filename)
+                self.image_list = [i.filename for i in self.book.infolist() if not i.isdir()]
+
+            self.image_list.sort()
+        except:  # Specifying no exception here is warranted
+            print('Cannot parse ' + self.filename)
+            return
+
+    def get_title(self):
+        title = os.path.basename(self.book_extension[0]).strip(' ')
+        return title
+
+    def get_author(self):
+        return None
+
+    def get_year(self):
+        creation_time = time.ctime(os.path.getctime(self.filename))
+        creation_year = creation_time.split()[-1]
+        return creation_year
+
+    def get_cover_image(self):
+        # The first image in the archive may not be the cover
+        # It is implied, however, that the first image in order
+        # will be the cover
+        return self.book.read(self.image_list[0])
+
+    def get_isbn(self):
+        return None
+
+    def get_tags(self):
+        return None
+
+    def get_contents(self):
+        file_settings = {'images_only': True}
+        contents = [(f'Page {count + 1}', i) for count, i in enumerate(self.image_list)]
+
+        return contents, file_settings

lector/parsers/epub.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+
+# This file is a part of Lector, a Qt based ebook reader
+# Copyright (C) 2017 BasioMeusPuga
+
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+import os
+import zipfile
+
+from lector.ePub.read_epub import EPUB
+
+
+class ParseEPUB:
+    def __init__(self, filename, temp_dir, file_md5):
+        # TODO
+        # Maybe also include book description
+        self.book_ref = None
+        self.book = None
+        self.filename = filename
+        self.extract_path = os.path.join(temp_dir, file_md5)
+
+    def read_book(self):
+        self.book_ref = EPUB(self.filename)
+        contents_found = self.book_ref.read_epub()
+        if not contents_found:
+            print('Cannot process: ' + self.filename)
+            return
+        self.book = self.book_ref.book
+
+    def get_title(self):
+        return self.book['title']
+
+    def get_author(self):
+        return self.book['author']
+
+    def get_year(self):
+        return self.book['year']
+
+    def get_cover_image(self):
+        return self.book['cover']
+
+    def get_isbn(self):
+        return self.book['isbn']
+
+    def get_tags(self):
+        return self.book['tags']
+
+    def get_contents(self):
+        zipfile.ZipFile(self.filename).extractall(self.extract_path)
+
+        self.book_ref.parse_chapters(temp_dir=self.extract_path)
+        file_settings = {
+            'images_only': False}
+        return self.book['book_list'], file_settings

lector/parsers/mobi.py

@@ -0,0 +1,98 @@
+#!/usr/bin/env python3
+
+# This file is a part of Lector, a Qt based ebook reader
+# Copyright (C) 2017 BasioMeusPuga
+
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+# This module parses Amazon ebooks using KindleUnpack to first create an
+# epub that is then read the usual way
+
+import os
+import sys
+import shutil
+import zipfile
+
+from lector.ePub.read_epub import EPUB
+import lector.KindleUnpack.kindleunpack as KindleUnpack
+
+
+class ParseMOBI:
+    def __init__(self, filename, temp_dir, file_md5):
+        self.book_ref = None
+        self.book = None
+        self.filename = filename
+        self.epub_filepath = None
+        self.split_large_xml = False
+        self.temp_dir = temp_dir
+        self.extract_dir = os.path.join(temp_dir, file_md5)
+
+    def read_book(self):
+        with HidePrinting():
+            KindleUnpack.unpackBook(self.filename, self.extract_dir)
+
+        epub_filename = os.path.splitext(
+            os.path.basename(self.filename))[0] + '.epub'
+
+        self.epub_filepath = os.path.join(
+            self.extract_dir, 'mobi8', epub_filename)
+        if not os.path.exists(self.epub_filepath):
+            zip_dir = os.path.join(self.extract_dir, 'mobi7')
+            zip_file = os.path.join(
+                self.extract_dir, epub_filename)
+            self.epub_filepath = shutil.make_archive(zip_file, 'zip', zip_dir)
+            self.split_large_xml = True
+
+        self.book_ref = EPUB(self.epub_filepath)
+        contents_found = self.book_ref.read_epub()
+        if not contents_found:
+            print('Cannot process: ' + self.filename)
+            return
+        self.book = self.book_ref.book
+
+    def get_title(self):
+        return self.book['title']
+
+    def get_author(self):
+        return self.book['author']
+
+    def get_year(self):
+        return self.book['year']
+
+    def get_cover_image(self):
+        return self.book['cover']
+
+    def get_isbn(self):
+        return self.book['isbn']
+
+    def get_tags(self):
+        return self.book['tags']
+
+    def get_contents(self):
+        extract_path = os.path.join(self.extract_dir)
+        zipfile.ZipFile(self.epub_filepath).extractall(extract_path)
+
+        self.book_ref.parse_chapters(
+            temp_dir=self.temp_dir, split_large_xml=self.split_large_xml)
+        file_settings = {
+            'images_only': False}
+        return self.book['book_list'], file_settings
+
+class HidePrinting:
+    def __enter__(self):
+        self._original_stdout = sys.stdout
+        sys.stdout = None
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        sys.stdout = self._original_stdout

lector/parsers/pdf.py

@@ -0,0 +1,105 @@
+#!/usr/bin/env python3
+
+# This file is a part of Lector, a Qt based ebook reader
+# Copyright (C) 2018 BasioMeusPuga
+
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+import io
+import os
+from PyQt5 import QtCore
+from bs4 import BeautifulSoup
+
+proceed = True
+try:
+    import popplerqt5
+except ImportError:
+    print('python-poppler-qt5 is not installed. Pdf files will not work.')
+    proceed = False
+
+class ParsePDF:
+    def __init__(self, filename, *args):
+        self.filename = filename
+        self.book = None
+        self.metadata = None
+
+    def read_book(self):
+        if not proceed:
+            return
+
+        self.book = popplerqt5.Poppler.Document.load(self.filename)
+        if not self.book:
+            return
+
+        self.metadata = BeautifulSoup(self.book.metadata(), 'xml')
+
+    def get_title(self):
+        try:
+            title = self.metadata.find('title').text
+            return title.replace('\n', '')
+        except AttributeError:
+            return os.path.splitext(os.path.basename(self.filename))[0]
+
+    def get_author(self):
+        try:
+            author = self.metadata.find('creator').text
+            return author.replace('\n', '')
+        except AttributeError:
+            return 'Unknown'
+
+    def get_year(self):
+        try:
+            year = self.metadata.find('MetadataDate').text
+            return year.replace('\n', '')
+        except AttributeError:
+            return 9999
+
+    def get_cover_image(self):
+        self.book.setRenderHint(
+            popplerqt5.Poppler.Document.Antialiasing
+            and popplerqt5.Poppler.Document.TextAntialiasing)
+
+        cover_page = self.book.page(0)
+        cover_image = cover_page.renderToImage(300, 300)
+        return resize_image(cover_image)
+
+    def get_isbn(self):
+        return None
+
+    def get_tags(self):
+        try:
+            tags = self.metadata.find('Keywords').text
+            return tags.replace('\n', '')
+        except AttributeError:
+            return None
+
+    def get_contents(self):
+        file_settings = {'images_only': True}
+        contents = [(f'Page {i + 1}', i) for i in range(self.book.numPages())]
+
+        return contents, file_settings
+
+
+def resize_image(cover_image):
+    cover_image = cover_image.scaled(
+        420, 600, QtCore.Qt.IgnoreAspectRatio)
+
+    byte_array = QtCore.QByteArray()
+    buffer = QtCore.QBuffer(byte_array)
+    buffer.open(QtCore.QIODevice.WriteOnly)
+    cover_image.save(buffer, 'jpg', 75)
+
+    cover_image_final = io.BytesIO(byte_array)
+    cover_image_final.seek(0)
+    return cover_image_final.getvalue()