apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-04-24 23:56:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

fix pdf name

Browse source
This commit is contained in:
Ray 2025-04-09 19:37:00 +08:00
parent 8a7f8132cf
commit 4ba12cf3ce
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
pageindex/utils.py
View file

@ -254,7 +254,7 @@ def extract_text_from_pdf(pdf_path):
def get_pdf_title(pdf_path): def get_pdf_title(pdf_path):
pdf_reader = PyPDF2.PdfReader(pdf_path) pdf_reader = PyPDF2.PdfReader(pdf_path)
meta = pdf_reader.metadata meta = pdf_reader.metadata
title = meta.title title = meta.title if meta and meta.title else 'Untitled'
return title return title
def get_text_of_pages(pdf_path, start_page, end_page, tag=True): def get_text_of_pages(pdf_path, start_page, end_page, tag=True):
@ -299,7 +299,7 @@ def get_pdf_name(pdf_path):
elif isinstance(pdf_path, BytesIO): elif isinstance(pdf_path, BytesIO):
pdf_reader = PyPDF2.PdfReader(pdf_path) pdf_reader = PyPDF2.PdfReader(pdf_path)
meta = pdf_reader.metadata meta = pdf_reader.metadata
pdf_name = meta.title if meta.title else 'Untitled' pdf_name = meta.title if meta and meta.title else 'Untitled'
pdf_name = sanitize_filename(pdf_name) pdf_name = sanitize_filename(pdf_name)
return pdf_name return pdf_name