apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-07-03 20:41:02 +02:00
Code Issues Projects Releases Packages Wiki Activity

Validate PDF parser CLI option

Browse source
This commit is contained in:
Ray 2026-05-13 02:16:55 +08:00
parent 966a6be4d6
commit e7715d8902
1 changed files with 3 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

5
run_pageindex.py
View file

@ -29,7 +29,8 @@ if __name__ == "__main__":
parser.add_argument('--if-add-node-text', type=str, default=None, parser.add_argument('--if-add-node-text', type=str, default=None,
help='Whether to add text to the node') help='Whether to add text to the node')
parser.add_argument('--pdf-parser', type=str, default=None, parser.add_argument('--pdf-parser', type=str, default=None,
help='PDF text extractor: PyPDF2 (default), pypdfium2 (requires `pip install pypdfium2`), or PyMuPDF') choices=pageindex_utils.SUPPORTED_PDF_PARSERS,
help='PDF text extractor to use')
# Markdown specific arguments # Markdown specific arguments
parser.add_argument('--if-thinning', type=str, default='no', parser.add_argument('--if-thinning', type=str, default='no',
@ -136,4 +137,4 @@ if __name__ == "__main__":
with open(output_file, 'w', encoding='utf-8') as f: with open(output_file, 'w', encoding='utf-8') as f:
json.dump(toc_with_page_number, f, indent=2, ensure_ascii=False) json.dump(toc_with_page_number, f, indent=2, ensure_ascii=False)
print(f'Tree structure saved to: {output_file}') print(f'Tree structure saved to: {output_file}')