Jonathan/calibre-web
1
0
Fork 0
mirror of https://github.com/JonathanHerrewijnen/calibre-web.git synced 2024-11-10 21:24:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make pyPDF2 again to the favorite pdf metadata extractor

Browse Source
This commit is contained in:
Ozzie Isaacs 2022-08-27 15:44:21 +02:00
parent e5c8a7ce50
commit ec8844c7d4
2 changed files with 10 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
cps/uploader.py
View File

@ -37,16 +37,15 @@ except (ImportError, RuntimeError) as e:
use_generic_pdf_cover = True use_generic_pdf_cover = True
try: try:
from PyPDF3 import PdfFileReader from PyPDF2 import PdfFileReader
from PyPDF3 import __version__ as PyPdfVersion
use_pdf_meta = True use_pdf_meta = True
except ImportError as ex: except ImportError as ex:
log.debug('PyPDF2 is recommended for best performance in metadata extracting from pdf files: %s', ex)
try: try:
from PyPDF2 import PdfFileReader from PyPDF3 import PdfFileReader
from PyPDF2 import __version__ as PyPdfVersion
use_pdf_meta = True use_pdf_meta = True
except ImportError as e: except ImportError as e:
log.debug('Cannot import PyPDF3/PyPDF2, extracting pdf metadata will not work: %s / %s', ex, e) log.debug('Cannot import PyPDF3/PyPDF2, extracting pdf metadata will not work: %s / %s', e)
use_pdf_meta = False use_pdf_meta = False
try: try:
@ -114,7 +113,7 @@ def parse_xmp(pdf_file):
try: try:
xmp_info = pdf_file.getXmpMetadata() xmp_info = pdf_file.getXmpMetadata()
except Exception as ex: except Exception as ex:
log.debug('Can not read XMP metadata {}'.format(ex)) log.debug('Can not read PDF XMP metadata {}'.format(ex))
return None return None
if xmp_info: if xmp_info:
@ -160,6 +159,10 @@ def pdf_meta(tmp_file_path, original_file_name, original_file_extension):
with open(tmp_file_path, 'rb') as f: with open(tmp_file_path, 'rb') as f:
pdf_file = PdfFileReader(f) pdf_file = PdfFileReader(f)
doc_info = pdf_file.getDocumentInfo() doc_info = pdf_file.getDocumentInfo()
try:
doc_info = pdf_file.getDocumentInfo()
except Exception as exc:
log.debug('Can not read PDF DocumentInfo {}'.format(exc))
xmp_info = parse_xmp(pdf_file) xmp_info = parse_xmp(pdf_file)
if xmp_info: if xmp_info:

2
requirements.txt
View File

@ -7,7 +7,7 @@ Flask-Principal>=0.3.2,<0.5.1
backports_abc>=0.4 backports_abc>=0.4
Flask>=1.0.2,<2.1.0 Flask>=1.0.2,<2.1.0
iso-639>=0.4.5,<0.5.0 iso-639>=0.4.5,<0.5.0
PyPDF3>=1.0.0,<1.0.7 PyPDF2>=1.20,<2.11.0
pytz>=2016.10 pytz>=2016.10
requests>=2.11.1,<2.28.0 requests>=2.11.1,<2.28.0
SQLAlchemy>=1.3.0,<1.5.0 SQLAlchemy>=1.3.0,<1.5.0