Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -5,13 +5,19 @@ import fitz # PyMuPDF
|
|
| 5 |
import re
|
| 6 |
import json
|
| 7 |
|
| 8 |
-
# LICENSE.numpy - https://github.com/numpy/numpy/blob/main/LICENSE.txt
|
| 9 |
-
|
| 10 |
-
# LICENSE.
|
| 11 |
-
|
| 12 |
-
# LICENSE.
|
| 13 |
-
|
| 14 |
-
# LICENSE.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
def extract_pdf_text(pdf_path):
|
| 17 |
"""Extract text from a PDF file."""
|
|
|
|
| 5 |
import re
|
| 6 |
import json
|
| 7 |
|
| 8 |
+
# LICENSE.numpy.BSD-3 - Copyright (c) 2005-2024, NumPy Developers (https://github.com/numpy/numpy/blob/main/LICENSE.txt)
|
| 9 |
+
|
| 10 |
+
# LICENSE.streamlit.Apachev2 - Copyright (c) Streamlit Inc. (2018-2022) Snowflake Inc. (2022-2024) (https://github.com/streamlit/streamlit/blob/develop/LICENSE)
|
| 11 |
+
|
| 12 |
+
# LICENSE.pandas.BSD-3 - Copyright (c) 2008-2011, AQR Capital Management, LLC, Lambda Foundry, Inc. and PyData Development Team (https://github.com/pandas-dev/pandas/blob/main/LICENSE)
|
| 13 |
+
|
| 14 |
+
# LICENSE.re.CNRI - Copyright (c) 1998-2001 by Secret Labs AB. All rights reserved. (https://www.handle.net/python_licenses/python1.6_9-5-00.html)
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
# LICENSE.json.LGPL - Copyright: (c) 2017-2019 by Brad Jasper (c) 2012-2017 by Trevor Lohrbeer (https://github.com/bradjasper/ImportJSON/blob/master/LICENSE)
|
| 18 |
+
|
| 19 |
+
# LICENSE.pymupdf.AGPL - Copyright (C) 2023 Artifex Software, Inc. (https://github.com/pymupdf/PyMuPDF/blob/main/COPYING)
|
| 20 |
+
|
| 21 |
|
| 22 |
def extract_pdf_text(pdf_path):
|
| 23 |
"""Extract text from a PDF file."""
|