merge cbr/cbz cover extraction

This commit is contained in:
j 2019-02-01 19:19:16 +05:30
parent 7ab27db0dd
commit 9ef5c01235
2 changed files with 45 additions and 37 deletions

View file

@ -1,19 +1,39 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
import logging import logging
import os import os
import zipfile
import ox import ox
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
IMAGE_EXTENSIONS = ['.jpg', '.png', '.gif'] IMAGE_EXTENSIONS = ['.jpg', '.png', '.gif']
def filter_images(files): def filter_images(files):
return [f for f in files if os.path.splitext(f)[-1] in IMAGE_EXTENSION] return [f for f in files if os.path.splitext(f)[-1].lower() in IMAGE_EXTENSIONS]
def detect_format(path):
with open(path, 'rb') as fd:
head = fd.read(10)
if head[:2] == b'PK':
return 'cbz'
if head[:3] == b'Rar':
return 'cbr'
logger.debug('unknown cbr/cbz file %s - %s', head, path)
return 'unknown'
def cover(path): def cover(path):
format = detect_format(path)
if format == 'cbz':
cover = cover_cbz(path)
elif format == 'cbr':
cover = cover_cbr(path)
else:
cover = None
return cover
def cover_cbr(path):
data = None data = None
#open rar file and extract first page here
try: try:
from unrar import rarfile from unrar import rarfile
rar = rarfile.RarFile(path) rar = rarfile.RarFile(path)
@ -23,9 +43,30 @@ def cover(path):
cover = ox.sorted_strings(files)[0] cover = ox.sorted_strings(files)[0]
data = rar.read(cover) data = rar.read(cover)
except: except:
logger.debug('invalid cbr file %s', path)
data = None data = None
return data return data
def cover_cbz(path):
data = None
logger.debug('cover %s', path)
data = None
try:
z = zipfile.ZipFile(path)
except zipfile.BadZipFile:
logger.debug('invalid cbz file %s', path)
return data
files = [f.filename for f in z.filelist]
files = filter_images(files)
if files:
cover = ox.sorted_strings(files)[0]
try:
data = z.read(cover)
except:
data = None
return data
def info(path): def info(path):
data = {} data = {}
data['title'] = os.path.splitext(os.path.basename(path))[0] data['title'] = os.path.splitext(os.path.basename(path))[0]

View file

@ -1,36 +1,3 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
import logging from .cbr import cover, info
import os
import zipfile
import ox
from .cbr import filter_images
logger = logging.getLogger(__name__)
def cover(path):
data = None
logger.debug('cover %s', path)
data = None
try:
z = zipfile.ZipFile(path)
except zipfile.BadZipFile:
logger.debug('invalid zbc file %s', path)
return data
files = [f.filename for f in z.filelist]
files = filter_images(files)
if files:
cover = ox.sorted_strings(files)[0]
try:
data = z.read(cover)
except:
data = None
return data
def info(path):
data = {}
data['title'] = os.path.splitext(os.path.basename(path))[0]
#data['pages'] = fixme read rar to count pages
return data