Jafner/calibre-web
1
0
Fork 0
Code Issues 2 Pull Requests Packages Projects Releases Wiki Activity

Bugfixes pdf xmp parsing

Browse Source
This commit is contained in:
Ozzie Isaacs 2021-03-21 07:28:35 +01:00
parent fcaa232967
commit 9c842f1895
1 changed files with 9 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
cps/uploader.py
View File

@ -22,7 +22,7 @@ import hashlib
from tempfile import gettempdir
from flask_babel import gettext as _
from . import logger, comic, isoLanguages, get_locale
from . import logger, comic, isoLanguages
from .constants import BookMeta
from .helper import split_authors
@ -53,7 +53,7 @@ except ImportError as ex:
from PyPDF2 import __version__ as PyPdfVersion
use_pdf_meta = True
except ImportError as e:
log.debug('Cannot import PyPDF3/PyPDF2, extracting pdf metadata will not work: %s / %s', e)
log.debug('Cannot import PyPDF3/PyPDF2, extracting pdf metadata will not work: %s / %s', ex, e)
use_pdf_meta = False
try:
@ -118,7 +118,7 @@ def parse_xmp(pdf_file):
try:
xmp_info = pdf_file.getXmpMetadata()
except Exception as e:
log.debug('Can not read XMP metadata', e)
log.debug('Can not read XMP metadata %e', e)
return None
if xmp_info:
@ -142,7 +142,7 @@ def parse_xmp(pdf_file):
for i in xmp_info.dc_language:
#calibre-web currently only takes one language.
languages.append(isoLanguages.get_lang3(i))
except:
except AttributeError:
languages.append('')
xmp_tags = ', '.join(xmp_info.dc_subject)
@ -156,51 +156,6 @@ def parse_xmp(pdf_file):
}
def parse_xmp(pdf_file):
"""
Parse XMP Metadata and prepare for BookMeta object
"""
try:
xmp_info = pdf_file.getXmpMetadata()
except Exception as e:
log.debug('Can not read XMP metadata', e)
return None
if xmp_info:
try:
xmp_author = xmp_info.dc_creator # list
except:
xmp_author = ['']
if xmp_info.dc_title:
xmp_title = xmp_info.dc_title['x-default']
else:
xmp_title = ''
if xmp_info.dc_description:
xmp_description = xmp_info.dc_description['x-default']
else:
xmp_description = ''
languages = []
try:
for i in xmp_info.dc_language:
languages.append(isoLanguages.get_lang3(i))
except AttributeError:
languages= [""]
xmp_tags = ', '.join(xmp_info.dc_subject)
xmp_publisher = ', '.join(xmp_info.dc_publisher)
return {'author': xmp_author,
'title': xmp_title,
'subject': xmp_description,
'tags': xmp_tags,
'languages': languages,
'publisher': xmp_publisher
}
def parse_xmp(pdf_file):
"""
Parse XMP Metadata and prepare for BookMeta object