apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-07-18 21:21:05 +02:00
Code Issues Projects Releases Packages Wiki Activity

Centralize default parser as DEFAULT_PDF_PARSER constant

Browse source
This commit is contained in:
Ray 2026-05-11 16:24:01 +08:00
parent 1629ef4318
commit ec1aaca4c9
5 changed files with 12 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

4
run_pageindex.py
View file

@ -3,7 +3,7 @@ import os
import json
from pageindex import *
from pageindex.page_index_md import md_to_tree
from pageindex.utils import ConfigLoader
from pageindex.utils import ConfigLoader, DEFAULT_PDF_PARSER
if __name__ == "__main__":
# Set up argument parser
@ -67,7 +67,7 @@ if __name__ == "__main__":
opt = ConfigLoader().load({k: v for k, v in user_opt.items() if v is not None})
# Process the PDF
toc_with_page_number = page_index_main(args.pdf_path, opt, pdf_parser=args.pdf_parser or "PyPDF2")
toc_with_page_number = page_index_main(args.pdf_path, opt, pdf_parser=args.pdf_parser or DEFAULT_PDF_PARSER)
print('Parsing done, saving to file...')
# Save results