Spaces:
Sleeping
Sleeping
Create pdf_parser.py
Browse files- pdf_parser.py +11 -0
pdf_parser.py
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import pdfplumber
|
| 2 |
+
|
| 3 |
+
def extract_text_from_pdf(file_path: str) -> str:
|
| 4 |
+
if file_path is None:
|
| 5 |
+
return ""
|
| 6 |
+
try:
|
| 7 |
+
with pdfplumber.open(file_path) as pdf:
|
| 8 |
+
pages = [page.extract_text() or "" for page in pdf.pages]
|
| 9 |
+
return "\n".join(pages).strip()
|
| 10 |
+
except Exception as e:
|
| 11 |
+
return f"Chyba při čtení PDF: {str(e)}"
|