Begin fb2 support

Fix Chinese translation

lector/parsers/comicbooks.py

@@ -1,5 +1,3 @@
-#!/usr/bin/env python3
-
 # This file is a part of Lector, a Qt based ebook reader
 # Copyright (C) 2017-18 BasioMeusPuga
 

lector/parsers/epub.py

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # This file is a part of Lector, a Qt based ebook reader
-# Copyright (C) 2017 BasioMeusPuga
+# Copyright (C) 2017-2018 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
@@ -19,7 +17,7 @@
 import os
 import zipfile
 
-from lector.ePub.read_epub import EPUB
+from lector.readers.read_epub import EPUB
 
 
 class ParseEPUB:

lector/parsers/fb2.py

@@ -0,0 +1,67 @@
+# This file is a part of Lector, a Qt based ebook reader
+# Copyright (C) 2017-2018 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 os
+import zipfile
+
+from lector.readers.read_fb2 import FB2
+
+
+class ParseFB2:
+    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 = FB2(self.filename)
+        contents_found = self.book_ref.read_fb2()
+        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):
+        # TODO
+        # Make this save images to the temp path
+        # Relative file paths should then point there
+        # 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

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # This file is a part of Lector, a Qt based ebook reader
-# Copyright (C) 2017 BasioMeusPuga
+# Copyright (C) 2017-2018 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
@@ -24,7 +22,7 @@ import sys
 import shutil
 import zipfile
 
-from lector.ePub.read_epub import EPUB
+from lector.readers.read_epub import EPUB
 import lector.KindleUnpack.kindleunpack as KindleUnpack
 
 

lector/parsers/pdf.py

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # This file is a part of Lector, a Qt based ebook reader
-# Copyright (C) 2018 BasioMeusPuga
+# Copyright (C) 2017-2018 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
@@ -16,6 +14,10 @@
 # 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
+# Error handling
+# TOC parsing
+
 import io
 import os
 

lector/readers/read_epub.py

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # This file is a part of Lector, a Qt based ebook reader
-# Copyright (C) 2017 BasioMeusPuga
+# Copyright (C) 2017-2018 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
@@ -33,15 +31,18 @@ class EPUB:
     def read_epub(self):
         # This is the function that should error out in
         # case the module cannot process the file
-        self.load_zip()
-        contents_path = self.get_file_path(
-            None, True)
+        try:
+            self.load_zip()
+            contents_path = self.get_file_path(
+                None, True)
 
-        if not contents_path:
-            return False  # No (valid) opf was found so processing cannot continue
+            if not contents_path:
+                return False  # No (valid) opf was found so processing cannot continue
 
-        self.generate_book_metadata(contents_path)
-        self.parse_toc()
+            self.generate_book_metadata(contents_path)
+            self.parse_toc()
+        except:  # Not specifying an exception type here may be justified
+            return False
 
         return True
 

lector/readers/read_fb2.py

@@ -0,0 +1,82 @@
+# This file is a part of Lector, a Qt based ebook reader
+# Copyright (C) 2017-2018 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 os
+import base64
+import zipfile
+
+from bs4 import BeautifulSoup
+
+
+class FB2:
+    def __init__(self, filename):
+        self.filename = filename
+        self.zip_file = None
+        self.book = {}
+        self.xml = None
+
+    def read_fb2(self):
+        try:
+            if self.filename.endswith('.fb2.zip'):
+                this_book = zipfile.ZipFile(self.filename, mode='r', allowZip64=True)
+                for i in this_book.filelist:
+                    if os.path.splitext(i.filename)[1] == '.fb2':
+                        book_text = this_book.read(i.filename)
+                        break
+            else:
+                with open(self.filename, 'r') as book_file:
+                    book_text = book_file.read()
+
+            self.xml = BeautifulSoup(book_text, 'lxml')
+            self.generate_book_metadata()
+        except:  # Not specifying an exception type here may be justified
+            return False
+
+        return True
+
+    def generate_book_metadata(self):
+        self.book['title'] = os.path.splitext(
+            os.path.basename(self.filename))[0]
+        self.book['author'] = 'Unknown'
+        self.book['isbn'] = None
+        self.book['tags'] = None
+        self.book['cover'] = None
+        self.book['year'] = 9999
+        self.book['book_list'] = []
+
+        # TODO
+        # Look for other components of book metadata here
+        for i in self.xml.find_all():
+
+            if i.name == 'section':
+                for j in i:
+                    if j.name == 'title':
+                        this_title = j.text
+                self.book['book_list'].append(
+                    (this_title, str(i)))
+
+        # Cover Image
+        cover_image_xml = self.xml.find('coverpage')
+        for i in cover_image_xml:
+            cover_image_name = i.get('l:href')
+
+        cover_image_data = self.xml.find_all('binary')
+        for i in cover_image_data:
+
+            # TODO
+            # Account for other images as well
+            if cover_image_name.endswith(i.get('id')):
+                self.book['cover'] = base64.decodebytes(i.text.encode())

lector/resources/translations/Lector_zh.ts

@@ -406,7 +406,7 @@ Reopen book to see changes</source>
     <message>
         <location filename="../../library.py" line="292"/>
         <source>manually added</source>
-        <translation>手动添加</translation>
+        <translation>手动添加的</translation>
     </message>
     <message>
         <location filename="../../library.py" line="215"/>

lector/sorter.py

@@ -50,6 +50,7 @@ from lector import database
 
 from lector.parsers.epub import ParseEPUB
 from lector.parsers.mobi import ParseMOBI
+from lector.parsers.fb2 import ParseFB2
 from lector.parsers.comicbooks import ParseCOMIC
 
 sorter = {
@@ -59,6 +60,8 @@ sorter = {
     'azw3': ParseMOBI,
     'azw4': ParseMOBI,
     'prc': ParseMOBI,
+    'fb2': ParseFB2,
+    'fb2.zip': ParseFB2,
     'cbz': ParseCOMIC,
     'cbr': ParseCOMIC}
 
@@ -172,7 +175,8 @@ class BookSorter:
                     print(f'{os.path.basename(filename)} is already in database')
                 return
 
-        file_extension = os.path.splitext(filename)[1][1:]
+        # Using os.extsep like so allows for file extensions with multiple dots
+        file_extension = os.path.basename(filename).split(os.extsep, 1)[1]
         try:
             # Get the requisite parser from the sorter dict
             book_ref = sorter[file_extension](filename, self.temp_dir, file_md5)