Spaces:
Running
Running
Delete utils.py
Browse files
utils.py
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
# utils.py
|
| 2 |
-
|
| 3 |
-
import pdfplumber
|
| 4 |
-
import re
|
| 5 |
-
|
| 6 |
-
def extract_text_from_pdf(pdf_path):
|
| 7 |
-
text = ""
|
| 8 |
-
with pdfplumber.open(pdf_path) as pdf:
|
| 9 |
-
for page in pdf.pages:
|
| 10 |
-
text += page.extract_text() + "\n"
|
| 11 |
-
return text
|
| 12 |
-
|
| 13 |
-
def parse_pdf_to_dict(text):
|
| 14 |
-
data = {}
|
| 15 |
-
|
| 16 |
-
# Example logic — customize based on actual data format
|
| 17 |
-
patterns = {
|
| 18 |
-
"Operator Name": r"Operator Name[:\s]+(.+)",
|
| 19 |
-
"Accreditation Modules": r"Accreditation Modules[:\s]+(.+)",
|
| 20 |
-
"Audit Date": r"Audit Date[:\s]+([\d\-\/]+)",
|
| 21 |
-
"Auditor Name": r"Auditor Name[:\s]+(.+)",
|
| 22 |
-
}
|
| 23 |
-
|
| 24 |
-
for key, pattern in patterns.items():
|
| 25 |
-
match = re.search(pattern, text, re.IGNORECASE)
|
| 26 |
-
if match:
|
| 27 |
-
data[key] = match.group(1).strip()
|
| 28 |
-
|
| 29 |
-
return data
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|