Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -5,6 +5,14 @@ import fitz # PyMuPDF
|
|
| 5 |
import re
|
| 6 |
import json
|
| 7 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
def extract_pdf_text(pdf_path):
|
| 9 |
"""Extract text from a PDF file."""
|
| 10 |
with fitz.open(pdf_path) as pdf_document:
|
|
|
|
| 5 |
import re
|
| 6 |
import json
|
| 7 |
|
| 8 |
+
# LICENSE.numpy - https://github.com/numpy/numpy/blob/main/LICENSE.txt
|
| 9 |
+
# LICENSE.streamlit - https://github.com/streamlit/streamlit/blob/develop/LICENSE
|
| 10 |
+
# LICENSE.pandas - https://github.com/pandas-dev/pandas/blob/main/LICENSE
|
| 11 |
+
# LICENSE.sklearn - https://github.com/scikit-learn/scikit-learn/blob/main/COPYING
|
| 12 |
+
# LICENSE.pymupdf - https://github.com/pymupdf/PyMuPDF/blob/main/COPYING
|
| 13 |
+
# LICENSE.re -
|
| 14 |
+
# LICENSE.json - https://github.com/bradjasper/ImportJSON/blob/master/LICENSE
|
| 15 |
+
|
| 16 |
def extract_pdf_text(pdf_path):
|
| 17 |
"""Extract text from a PDF file."""
|
| 18 |
with fitz.open(pdf_path) as pdf_document:
|