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

Cleanup parsers

Browse Source
This commit is contained in:
BasioMeusPuga
2019-02-10 09:03:12 +05:30
parent c6e30b67ad
commit f6f9d01060
8 changed files with 271 additions and 316 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
lector/parsers/comicbooks.py
View File

@@ -21,6 +21,7 @@ import os
import time
import logging
import zipfile
import collections
from lector.rarfile import rarfile
@@ -35,54 +36,36 @@ class ParseCOMIC:
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() and is_image(i.filename)]
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() and is_image(i.filename)]
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() and is_image(i.filename)]
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() and is_image(i.filename)]
self.image_list.sort()
if not self.image_list:
return False
self.image_list.sort()
return True
except: # Specifying no exception here is warranted
return False
def get_title(self):
def generate_metadata(self):
title = os.path.basename(self.book_extension[0]).strip(' ')
return title
author = '<Unknown>'
isbn = None
tags = []
cover = self.book.read(self.image_list[0])
def get_author(self):
return 'Unknown'
def get_year(self):
creation_time = time.ctime(os.path.getctime(self.filename))
creation_year = creation_time.split()[-1]
return creation_year
year = creation_time.split()[-1]
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])
Metadata = collections.namedtuple(
'Metadata', ['title', 'author', 'year', 'isbn', 'tags', 'cover'])
return Metadata(title, author, year, isbn, tags, cover)
def get_isbn(self):
return None
def get_tags(self):
return None
def get_contents(self):
def generate_content(self):
image_number = len(self.image_list)
toc = [(1, f'Page {i + 1}', i + 1) for i in range(image_number)]

41
lector/parsers/epub.py
View File

@@ -14,6 +14,9 @@
# 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
# Maybe also include book description
import os
import zipfile
import logging
@@ -25,47 +28,27 @@ logger = logging.getLogger(__name__)
class ParseEPUB:
def __init__(self, filename, temp_dir, file_md5):
# TODO
# Maybe also include book description
self.book_ref = None
self.book = None
self.temp_dir = temp_dir
self.filename = filename
self.temp_dir = temp_dir
self.extract_path = os.path.join(temp_dir, file_md5)
def read_book(self):
self.book_ref = EPUB(self.filename, self.temp_dir)
self.book_ref.generate_metadata()
self.book = self.book_ref.book
return True
self.book = EPUB(self.filename, self.temp_dir)
def get_title(self):
return self.book['title']
def generate_metadata(self):
self.book.generate_metadata()
return self.book.metadata
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):
def generate_content(self):
zipfile.ZipFile(self.filename).extractall(self.extract_path)
self.book_ref.generate_toc()
self.book_ref.generate_content()
self.book.generate_toc()
self.book.generate_content()
toc = []
content = []
for count, i in enumerate(self.book['content']):
for count, i in enumerate(self.book.content):
toc.append((i[0], i[1], count + 1))
content.append(i[2])

39
lector/parsers/fb2.py
View File

@@ -14,6 +14,9 @@
# 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
# Maybe also include book description
import os
import logging
@@ -24,46 +27,24 @@ logger = logging.getLogger(__name__)
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:
return False
self.book = self.book_ref.book
return True
self.book = FB2(self.filename)
def get_title(self):
return self.book['title']
def generate_metadata(self):
self.book.generate_metadata()
return self.book.metadata
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):
def generate_content(self):
os.makedirs(self.extract_path, exist_ok=True) # Manual creation is required here
self.book_ref.parse_chapters(temp_dir=self.extract_path)
self.book.generate_content(temp_dir=self.extract_path)
toc = []
content = []
for count, i in enumerate(self.book['book_list']):
for count, i in enumerate(self.book.content):
toc.append((i[0], i[1], count + 1))
content.append(i[2])

33
lector/parsers/pdf.py
View File

@@ -14,11 +14,8 @@
# 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 os
import collections
import fitz
from PyQt5 import QtGui
@@ -36,43 +33,39 @@ class ParsePDF:
except RuntimeError:
return False
def get_title(self):
def generate_metadata(self):
title = self.book.metadata['title']
if not title:
title = os.path.splitext(os.path.basename(self.filename))[0]
return title
def get_author(self):
author = self.book.metadata['author']
if not author:
author = 'Unknown'
return author
def get_year(self):
creation_date = self.book.metadata['creationDate']
try:
year = creation_date.split(':')[1][:4]
except (ValueError, AttributeError):
year = 9999
return year
def get_cover_image(self):
isbn = None
tags = self.book.metadata['keywords']
if not tags:
tags = []
# This is a little roundabout for the cover
# and I'm sure it's taking a performance hit
# But it is simple. So there's that.
cover_page = self.book.loadPage(0)
# Disabling scaling gets the covers much faster
return render_pdf_page(cover_page, True)
cover = render_pdf_page(cover_page, True)
def get_isbn(self):
return None
Metadata = collections.namedtuple(
'Metadata', ['title', 'author', 'year', 'isbn', 'tags', 'cover'])
return Metadata(title, author, year, isbn, tags, cover)
def get_tags(self):
tags = self.book.metadata['keywords']
return tags # Fine if it returns None
def get_contents(self):
def generate_content(self):
content = list(range(self.book.pageCount))
toc = self.book.getToC()
if not toc: