aspirebunny/bank_statement

1import streamlit as st2import pandas as pd3import pdfplumber4import io5 6st.set_page_config(page_title="Bank PDF to Excel Converter", layout="centered")7 8st.title("🏦 Bank PDF to Excel Converter")9st.write("Upload your **bank statement PDF**, and I’ll extract useful transaction data for you.")10 11uploaded_file = st.file_uploader("Upload Bank Statement (PDF)", type=["pdf"])12 13if uploaded_file:14    with pdfplumber.open(uploaded_file) as pdf:15        text = ""16        for page in pdf.pages:17            text += page.extract_text() + "\n"18 19    # Example: Extract dummy structured data from PDF text (you can enhance later)20    rows = []21    for line in text.split("\n"):22        parts = line.split()23        if len(parts) >= 4:24            # Try to detect date-like text25            if any(char.isdigit() for char in parts[0]):26                date = parts[0]27                particulars = " ".join(parts[1:-3])28                debit = parts[-3] if parts[-3].replace('.', '', 1).isdigit() else ""29                credit = parts[-2] if parts[-2].replace('.', '', 1).isdigit() else ""30                balance = parts[-1] if parts[-1].replace('.', '', 1).isdigit() else ""31                rows.append([date, particulars, debit, credit, balance])32 33    df = pd.DataFrame(rows, columns=["Date", "Particular", "Debit", "Credit", "Balance"])34 35    # Format date properly if possible36    df["Date"] = pd.to_datetime(df["Date"], errors='coerce').dt.strftime("%d/%m/%Y")37 38    st.dataframe(df)39 40    # Download Excel41    output = io.BytesIO()42    with pd.ExcelWriter(output, engine="xlsxwriter") as writer:43        df.to_excel(writer, index=False, sheet_name="Statement")44    st.download_button("📥 Download Excel File", data=output.getvalue(), file_name="statement.xlsx")45 46else:47    st.info("Please upload a bank PDF to continue.")48