Spaces:
Sleeping
Sleeping
Delete extract.py
Browse files- extract.py +0 -19
extract.py
DELETED
@@ -1,19 +0,0 @@
|
|
1 |
-
import pdfplumber
|
2 |
-
import pandas as pd
|
3 |
-
import re
|
4 |
-
|
5 |
-
def extract_upi_transactions(pdf_path):
|
6 |
-
transactions = []
|
7 |
-
|
8 |
-
with pdfplumber.open(pdf_path) as pdf:
|
9 |
-
for page in pdf.pages:
|
10 |
-
text = page.extract_text()
|
11 |
-
if text:
|
12 |
-
lines = text.split("\n")
|
13 |
-
for line in lines:
|
14 |
-
match = re.search(r'(\d{2}-\d{2}-\d{4})\s+([\w\s]+)\s+₹([\d,.]+)', line)
|
15 |
-
if match:
|
16 |
-
date, description, amount = match.groups()
|
17 |
-
transactions.append({"Date": date, "Description": description, "Amount": float(amount.replace(",", ""))})
|
18 |
-
|
19 |
-
return pd.DataFrame(transactions)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|