mirror of
https://github.com/janeczku/calibre-web
synced 2024-10-31 23:26:20 +00:00
Merge branch 'pdf'
This commit is contained in:
commit
b9085129a7
@ -39,17 +39,20 @@ except (ImportError, RuntimeError) as e:
|
||||
|
||||
try:
|
||||
from pypdf import PdfReader
|
||||
from pypdf.generic import NullObject
|
||||
use_pdf_meta = True
|
||||
except ImportError as ex:
|
||||
log.debug('PyPDF is recommended for best performance in metadata extracting from pdf files: %s', ex)
|
||||
try:
|
||||
from PyPDF2 import PdfReader
|
||||
from pypdf.generic import NullObject
|
||||
use_pdf_meta = True
|
||||
except ImportError as ex:
|
||||
log.debug('PyPDF is recommended for best performance in metadata extracting from pdf files: %s', ex)
|
||||
log.debug('PyPdf2 is also possible for metadata extracting from pdf files, but not recommended anymore')
|
||||
try:
|
||||
from PyPDF3 import PdfFileReader as PdfReader
|
||||
from pypdf.generic import NullObject
|
||||
use_pdf_meta = True
|
||||
except ImportError as e:
|
||||
log.debug('Cannot import PyPDF3/PyPDF2, extracting pdf metadata will not work: %s / %s', e)
|
||||
@ -205,10 +208,12 @@ def pdf_meta(tmp_file_path, original_file_name, original_file_extension, no_cove
|
||||
if subject == '':
|
||||
subject = doc_info.subject or ""
|
||||
if tags == '' and '/Keywords' in doc_info:
|
||||
if isinstance(doc_info['/Keywords'], bytes):
|
||||
tags = doc_info['/Keywords'].decode('utf-8')
|
||||
else:
|
||||
tags = doc_info['/Keywords']
|
||||
keywords = doc_info['/Keywords']
|
||||
if not isinstance(keywords, NullObject):
|
||||
if isinstance(keywords, bytes):
|
||||
tags = keywords.decode('utf-8')
|
||||
else:
|
||||
tags = keywords
|
||||
else:
|
||||
title = original_file_name
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user