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

Improved parsing of pdf files, bugfix for pypdf2 > V3.0

Browse Source
This commit is contained in:
Ozzie Isaacs 2023-01-22 11:25:24 +01:00
parent 2d6fe483ba
commit 791bc9621a
1 changed files with 8 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
cps/uploader.py
View File

@ -64,7 +64,7 @@ except ImportError as e:
def process(tmp_file_path, original_file_name, original_file_extension, rarExecutable): def process(tmp_file_path, original_file_name, original_file_extension, rarExecutable):
meta = None meta = default_meta(tmp_file_path, original_file_name, original_file_extension)
extension_upper = original_file_extension.upper() extension_upper = original_file_extension.upper()
try: try:
if ".PDF" == extension_upper: if ".PDF" == extension_upper:
@ -81,11 +81,11 @@ def process(tmp_file_path, original_file_name, original_file_extension, rarExecu
except Exception as ex: except Exception as ex:
log.warning('cannot parse metadata, using default: %s', ex) log.warning('cannot parse metadata, using default: %s', ex)
if meta and meta.title.strip() and meta.author.strip(): if not meta.title.strip():
if meta.author.lower() == 'unknown': meta = original_file_name
if not meta.author.strip() or meta.author.lower() == 'unknown':
meta = meta._replace(author=_('Unknown')) meta = meta._replace(author=_('Unknown'))
return meta return meta
return default_meta(tmp_file_path, original_file_name, original_file_extension)
def default_meta(tmp_file_path, original_file_name, original_file_extension): def default_meta(tmp_file_path, original_file_name, original_file_extension):
@ -111,7 +111,7 @@ def parse_xmp(pdf_file):
Parse XMP Metadata and prepare for BookMeta object Parse XMP Metadata and prepare for BookMeta object
""" """
try: try:
xmp_info = pdf_file.getXmpMetadata() xmp_info = pdf_file.xmp_metadata
except Exception as ex: except Exception as ex:
log.debug('Can not read PDF XMP metadata {}'.format(ex)) log.debug('Can not read PDF XMP metadata {}'.format(ex))
return None return None
@ -158,9 +158,8 @@ def pdf_meta(tmp_file_path, original_file_name, original_file_extension):
if use_pdf_meta: if use_pdf_meta:
with open(tmp_file_path, 'rb') as f: with open(tmp_file_path, 'rb') as f:
pdf_file = PdfReader(f) pdf_file = PdfReader(f)
doc_info = pdf_file.getDocumentInfo()
try: try:
doc_info = pdf_file.getDocumentInfo() doc_info = pdf_file.metadata
except Exception as exc: except Exception as exc:
log.debug('Can not read PDF DocumentInfo {}'.format(exc)) log.debug('Can not read PDF DocumentInfo {}'.format(exc))
xmp_info = parse_xmp(pdf_file) xmp_info = parse_xmp(pdf_file)