user01/calibre-web
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'Develop'

Browse Source 
# Conflicts:
#	MANIFEST.in
#	README.md
#	cps/helper.py
#	cps/static/js/archive/archive.js
#	cps/translations/nl/LC_MESSAGES/messages.mo
#	cps/translations/nl/LC_MESSAGES/messages.po
#	cps/ub.py
#	cps/updater.py
#	cps/web.py
#	cps/worker.py
#	optional-requirements.txt
This commit is contained in:
Ozzieisaacs
2019-07-13 20:54:21 +02:00
parent 37736e11d5
commit 4708347c16
189 changed files with 33354 additions and 17681 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cps/uploader.py
+210 -9
View File
@@ -2,7 +2,7 @@
# -*- coding: utf-8 -*-
# This file is part of the Calibre-Web (https://github.com/janeczku/calibre-web)
# Copyright (C) 2012-2019 lemmsh, OzzieIsaacs
# Copyright (C) 2012-2019 lemmsh cervinko Kennyl matthazinski OzzieIsaacs
#
# 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
@@ -17,17 +17,218 @@
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
from __future__ import division, print_function, unicode_literals
import os
from tempfile import gettempdir
import hashlib
from collections import namedtuple
import book_formats
from tempfile import gettempdir
BookMeta = namedtuple('BookMeta', 'file_path, extension, title, author, cover, description, tags, series, series_id, languages')
from flask_babel import gettext as _
"""
:rtype: BookMeta
"""
from . import logger, comic
from .constants import BookMeta
log = logger.create()
try:
from lxml.etree import LXML_VERSION as lxmlversion
except ImportError:
lxmlversion = None
try:
from wand.image import Image
from wand import version as ImageVersion
from wand.exceptions import PolicyError
use_generic_pdf_cover = False
except (ImportError, RuntimeError) as e:
log.warning('cannot import Image, generating pdf covers for pdf uploads will not work: %s', e)
use_generic_pdf_cover = True
try:
from PyPDF2 import PdfFileReader
from PyPDF2 import __version__ as PyPdfVersion
use_pdf_meta = True
except ImportError as e:
log.warning('cannot import PyPDF2, extracting pdf metadata will not work: %s', e)
use_pdf_meta = False
try:
from . import epub
use_epub_meta = True
except ImportError as e:
log.warning('cannot import epub, extracting epub metadata will not work: %s', e)
use_epub_meta = False
try:
from . import fb2
use_fb2_meta = True
except ImportError as e:
log.warning('cannot import fb2, extracting fb2 metadata will not work: %s', e)
use_fb2_meta = False
try:
from PIL import Image
from PIL import __version__ as PILversion
use_PIL = True
except ImportError as e:
log.warning('cannot import Pillow, using png and webp images as cover will not work: %s', e)
use_generic_pdf_cover = True
use_PIL = False
__author__ = 'lemmsh'
def process(tmp_file_path, original_file_name, original_file_extension):
meta = None
try:
if ".PDF" == original_file_extension.upper():
meta = pdf_meta(tmp_file_path, original_file_name, original_file_extension)
if ".EPUB" == original_file_extension.upper() and use_epub_meta is True:
meta = epub.get_epub_info(tmp_file_path, original_file_name, original_file_extension)
if ".FB2" == original_file_extension.upper() and use_fb2_meta is True:
meta = fb2.get_fb2_info(tmp_file_path, original_file_extension)
if original_file_extension.upper() in ['.CBZ', '.CBT']:
meta = comic.get_comic_info(tmp_file_path, original_file_name, original_file_extension)
except Exception as ex:
log.warning('cannot parse metadata, using default: %s', ex)
if meta and meta.title.strip() and meta.author.strip():
return meta
else:
return default_meta(tmp_file_path, original_file_name, original_file_extension)
def default_meta(tmp_file_path, original_file_name, original_file_extension):
return BookMeta(
file_path=tmp_file_path,
extension=original_file_extension,
title=original_file_name,
author=u"Unknown",
cover=None,
description="",
tags="",
series="",
series_id="",
languages="")
def pdf_meta(tmp_file_path, original_file_name, original_file_extension):
if use_pdf_meta:
pdf = PdfFileReader(open(tmp_file_path, 'rb'))
doc_info = pdf.getDocumentInfo()
else:
doc_info = None
if doc_info is not None:
author = doc_info.author if doc_info.author else u"Unknown"
title = doc_info.title if doc_info.title else original_file_name
subject = doc_info.subject
else:
author = u"Unknown"
title = original_file_name
subject = ""
return BookMeta(
file_path=tmp_file_path,
extension=original_file_extension,
title=title,
author=author,
cover=pdf_preview(tmp_file_path, original_file_name),
description=subject,
tags="",
series="",
series_id="",
languages="")
def pdf_preview(tmp_file_path, tmp_dir):
if use_generic_pdf_cover:
return None
else:
if use_PIL:
try:
input1 = PdfFileReader(open(tmp_file_path, 'rb'), strict=False)
page0 = input1.getPage(0)
xObject = page0['/Resources']['/XObject'].getObject()
for obj in xObject:
if xObject[obj]['/Subtype'] == '/Image':
size = (xObject[obj]['/Width'], xObject[obj]['/Height'])
data = xObject[obj]._data # xObject[obj].getData()
if xObject[obj]['/ColorSpace'] == '/DeviceRGB':
mode = "RGB"
else:
mode = "P"
if '/Filter' in xObject[obj]:
if xObject[obj]['/Filter'] == '/FlateDecode':
img = Image.frombytes(mode, size, data)
cover_file_name = os.path.splitext(tmp_file_path)[0] + ".cover.png"
img.save(filename=os.path.join(tmp_dir, cover_file_name))
return cover_file_name
# img.save(obj[1:] + ".png")
elif xObject[obj]['/Filter'] == '/DCTDecode':
cover_file_name = os.path.splitext(tmp_file_path)[0] + ".cover.jpg"
img = open(cover_file_name, "wb")
img.write(data)
img.close()
return cover_file_name
elif xObject[obj]['/Filter'] == '/JPXDecode':
cover_file_name = os.path.splitext(tmp_file_path)[0] + ".cover.jp2"
img = open(cover_file_name, "wb")
img.write(data)
img.close()
return cover_file_name
else:
img = Image.frombytes(mode, size, data)
cover_file_name = os.path.splitext(tmp_file_path)[0] + ".cover.png"
img.save(filename=os.path.join(tmp_dir, cover_file_name))
return cover_file_name
# img.save(obj[1:] + ".png")
except Exception as ex:
print(ex)
try:
cover_file_name = os.path.splitext(tmp_file_path)[0] + ".cover.jpg"
with Image(filename=tmp_file_path + "[0]", resolution=150) as img:
img.compression_quality = 88
img.save(filename=os.path.join(tmp_dir, cover_file_name))
return cover_file_name
except PolicyError as ex:
log.warning('Pdf extraction forbidden by Imagemagick policy: %s', ex)
return None
except Exception as ex:
log.warning('Cannot extract cover image, using default: %s', ex)
return None
def get_versions():
if not use_generic_pdf_cover:
IVersion = ImageVersion.MAGICK_VERSION
WVersion = ImageVersion.VERSION
else:
IVersion = _(u'not installed')
WVersion = _(u'not installed')
if use_pdf_meta:
PVersion='v'+PyPdfVersion
else:
PVersion=_(u'not installed')
if lxmlversion:
XVersion = 'v'+'.'.join(map(str, lxmlversion))
else:
XVersion = _(u'not installed')
if use_PIL:
PILVersion = 'v' + PILversion
else:
PILVersion = _(u'not installed')
return {'Image Magick': IVersion,
'PyPdf': PVersion,
'lxml':XVersion,
'Wand': WVersion,
'Pillow': PILVersion}
def upload(uploadfile):
@@ -42,5 +243,5 @@ def upload(uploadfile):
md5.update(filename.encode('utf-8'))
tmp_file_path = os.path.join(tmp_dir, md5.hexdigest())
uploadfile.save(tmp_file_path)
meta = book_formats.process(tmp_file_path, filename_root, file_extension)
meta = process(tmp_file_path, filename_root, file_extension)
return meta