Code Editor for app.py

import streamlit as st
import pandas as pd
import pdfplumber
import re
from datetime import datetime
import io
from dateutil.parser import parse
import xlsxwriter

st.set_page_config(page_title="Receipt Processor", page_icon="🧾", layout="wide")

st.title("🧾 Accounting Receipt Processor")
st.markdown("Upload PDF receipts and convert them to Excel format for accounting purposes")

# Initialize session state
if 'receipts_data' not in st.session_state:
    st.session_state.receipts_data = []

def extract_text_from_pdf(pdf_file):
    """Extract text from uploaded PDF file"""
    try:
        with pdfplumber.open(pdf_file) as pdf:
            text = ""
            for page in pdf.pages:
                text += page.extract_text() or ""
        return text
    except Exception as e:
        st.error(f"Error reading PDF: {str(e)}")
        return ""

def parse_receipt_data(text, filename):
    """Parse receipt text and extract relevant information"""
    # Initialize data structure
    receipt_data = {
        'filename': filename,
        'date': None,
        'vendor': None,
        'total_amount': None,
        'tax_amount': None,
        'items': [],
        'category': 'General',
        'payment_method': 'Unknown',
        'raw_text': text
    }
    
    # Extract date patterns
    date_patterns = [
        r'\b(\d{1,2}[/-]\d{1,2}[/-]\d{2,4})\b',
        r'\b(\d{4}[/-]\d{1,2}[/-]\d{1,2})\b',
        r'\b(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\s+\d{1,2},?\s+\d{4}\b'
    ]
    
    for pattern in date_patterns:
        matches = re.findall(pattern, text, re.IGNORECASE)
        if matches:
            try:
                receipt_data['date'] = parse(matches[0]).strftime('%Y-%m-%d')
                break
            except:
                continue
    
    # Extract total amount
    amount_patterns = [
        r'total[:\s]*\$?(\d+\.?\d*)',
        r'amount[:\s]*\$?(\d+\.?\d*)',
        r'\$(\d+\.\d{2})\s*$'
    ]
    
    for pattern in amount_patterns:
        matches = re.findall(pattern, text, re.IGNORECASE)
        if matches:
            try:
                receipt_data['total_amount'] = float(matches[-1])
                break
            except:
                continue
    
    # Extract tax amount
    tax_patterns = [
        r'tax[:\s]*\$?(\d+\.?\d*)',
        r'gst[:\s]*\$?(\d+\.?\d*)',
        r'hst[:\s]*\$?(\d+\.?\d*)'
    ]
    
    for pattern in tax_patterns:
        matches = re.findall(pattern, text, re.IGNORECASE)
        if matches:
            try:
                receipt_data['tax_amount'] = float(matches[0])
                break
            except:
                continue
    
    # Extract vendor name (first few lines often contain vendor info)
    lines = text.split('\n')
    for i, line in enumerate(lines[:5]):
        line = line.strip()
        if len(line) > 3 and not re.match(r'^\d+', line):
            receipt_data['vendor'] = line
            break
    
    # Determine category based on vendor name or content
    if receipt_data['vendor']:
        vendor_lower = receipt_data['vendor'].lower()
        if any(word in vendor_lower for word in ['gas', 'shell', 'esso', 'petro']):
            receipt_data['category'] = 'Fuel'
        elif any(word in vendor_lower for word in ['restaurant', 'cafe', 'coffee', 'food']):
            receipt_data['category'] = 'Meals'
        elif any(word in vendor_lower for word in ['office', 'supply', 'staples']):
            receipt_data['category'] = 'Office Supplies'
        elif any(word in vendor_lower for word in ['hotel', 'inn', 'lodge']):
            receipt_data['category'] = 'Accommodation'
    
    return receipt_data

# File upload section
st.header("📤 Upload Receipts")
uploaded_files = st.file_uploader(
    "Choose PDF files", 
    type=['pdf'], 
    accept_multiple_files=True,
    help="Upload one or more PDF receipts"
)

if uploaded_files:
    progress_bar = st.progress(0)
    status_text = st.empty()
    
    for i, uploaded_file in enumerate(uploaded_files):
        status_text.text(f"Processing {uploaded_file.name}...")
        
        # Extract text from PDF
        text = extract_text_from_pdf(uploaded_file)
        
        if text:
            # Parse receipt data
            receipt_data = parse_receipt_data(text, uploaded_file.name)
            
            # Check if this receipt is already processed
            existing_receipt = next((r for r in st.session_state.receipts_data if r['filename'] == uploaded_file.name), None)
            if not existing_receipt:
                st.session_state.receipts_data.append(receipt_data)
        
        progress_bar.progress((i + 1) / len(uploaded_files))
    
    status_text.text("✅ Processing complete!")
    st.success(f"Processed {len(uploaded_files)} receipt(s)")

# Display and edit receipt data
if st.session_state.receipts_data:
    st.header("📊 Receipt Data")
    
    # Convert to DataFrame for display
    df_display = pd.DataFrame([
        {
            'Filename': r['filename'],
            'Date': r['date'] or 'Not found',
            'Vendor': r['vendor'] or 'Not found',
            'Total Amount': f"${r['total_amount']:.2f}" if r['total_amount'] else 'Not found',
            'Tax Amount': f"${r['tax_amount']:.2f}" if r['tax_amount'] else 'Not found',
            'Category': r['category'],
            'Payment Method': r['payment_method']
        }
        for r in st.session_state.receipts_data
    ])
    
    st.dataframe(df_display, use_container_width=True)
    
    # Edit section
    st.subheader("✏️ Edit Receipt Data")
    
    if st.session_state.receipts_data:
        selected_receipt = st.selectbox(
            "Select receipt to edit:",
            options=range(len(st.session_state.receipts_data)),
            format_func=lambda x: st.session_state.receipts_data[x]['filename']
        )
        
        receipt = st.session_state.receipts_data[selected_receipt]
        
        col1, col2 = st.columns(2)
        
        with col1:
            new_date = st.date_input(
                "Date:",
                value=datetime.strptime(receipt['date'], '%Y-%m-%d').date() if receipt['date'] else datetime.now().date()
            )
            new_vendor = st.text_input("Vendor:", value=receipt['vendor'] or "")
            new_total = st.number_input("Total Amount:", value=receipt['total_amount'] or 0.0, min_value=0.0, step=0.01)
        
        with col2:
            new_tax = st.number_input("Tax Amount:", value=receipt['tax_amount'] or 0.0, min_value=0.0, step=0.01)
            new_category = st.selectbox(
                "Category:",
                options=['General', 'Meals', 'Fuel', 'Office Supplies', 'Accommodation', 'Travel', 'Equipment', 'Professional Services'],
                index=['General', 'Meals', 'Fuel', 'Office Supplies', 'Accommodation', 'Travel', 'Equipment', 'Professional Services'].index(receipt['category'])
            )
            new_payment = st.selectbox(
                "Payment Method:",
                options=['Credit Card', 'Cash', 'Debit Card', 'Bank Transfer', 'Unknown'],
                index=['Credit Card', 'Cash', 'Debit Card', 'Bank Transfer', 'Unknown'].index(receipt['payment_method'])
            )
        
        if st.button("Update Receipt"):
            st.session_state.receipts_data[selected_receipt].update({
                'date': new_date.strftime('%Y-%m-%d'),
                'vendor': new_vendor,
                'total_amount': new_total,
                'tax_amount': new_tax,
                'category': new_category,
                'payment_method': new_payment
            })
            st.success("Receipt updated successfully!")
            st.rerun()

# Export to Excel
if st.session_state.receipts_data:
    st.header("📥 Export to Excel")
    
    col1, col2 = st.columns(2)
    
    with col1:
        if st.button("Generate Excel File", type="primary"):
            # Create DataFrame for export
            export_data = []
            for receipt in st.session_state.receipts_data:
                export_data.append({
                    'Date': receipt['date'],
                    'Vendor': receipt['vendor'],
                    'Category': receipt['category'],
                    'Total Amount': receipt['total_amount'],
                    'Tax Amount': receipt['tax_amount'],
                    'Net Amount': (receipt['total_amount'] or 0) - (receipt['tax_amount'] or 0),
                    'Payment Method': receipt['payment_method'],
                    'Filename': receipt['filename']
                })
            
            df_export = pd.DataFrame(export_data)
            
            # Create Excel file in memory
            output = io.BytesIO()
            with pd.ExcelWriter(output, engine='xlsxwriter') as writer:
                df_export.to_excel(writer, sheet_name='Receipts', index=False)
                
                # Get workbook and worksheet
                workbook = writer.book
                worksheet = writer.sheets['Receipts']
                
                # Add formatting
                money_format = workbook.add_format({'num_format': '$#,##0.00'})
                date_format = workbook.add_format({'num_format': 'yyyy-mm-dd'})
                
                # Apply formats
                worksheet.set_column('A:A', 12, date_format)  # Date column
                worksheet.set_column('B:B', 25)  # Vendor column
                worksheet.set_column('C:C', 15)  # Category column
                worksheet.set_column('D:F', 12, money_format)  # Amount columns
                worksheet.set_column('G:G', 15)  # Payment method column
                worksheet.set_column('H:H', 30)  # Filename column
            
            output.seek(0)
            
            st.download_button(
                label="📄 Download Excel File",
                data=output.getvalue(),
                file_name=f"receipts_{datetime.now().strftime('%Y%m%d_%H%M%S')}.xlsx",
                mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
            )
    
    with col2:
        # Summary statistics
        st.subheader("📈 Summary")
        total_receipts = len(st.session_state.receipts_data)
        total_amount = sum(r['total_amount'] or 0 for r in st.session_state.receipts_data)
        total_tax = sum(r['tax_amount'] or 0 for r in st.session_state.receipts_data)
        
        st.metric("Total Receipts", total_receipts)
        st.metric("Total Amount", f"${total_amount:.2f}")
        st.metric("Total Tax", f"${total_tax:.2f}")

# Clear data button
if st.session_state.receipts_data:
    st.header("🗑️ Clear Data")
    if st.button("Clear All Receipt Data", type="secondary"):
        st.session_state.receipts_data = []
        st.success("All receipt data cleared!")
        st.rerun()

# Instructions
with st.expander("ℹ️ How to use this application"):
    st.markdown("""
    1. **Upload PDF Receipts**: Click the file uploader and select one or more PDF receipt files
    2. **Review Extracted Data**: The application will automatically extract information like date, vendor, amounts, etc.
    3. **Edit Data**: Select individual receipts to correct or add missing information
    4. **Export to Excel**: Generate an Excel file with all your processed receipts
    5. **Categories**: Receipts are automatically categorized based on vendor names
    
    **Supported Information**:
    - Date of transaction
    - Vendor/merchant name
    - Total amount
    - Tax amount
    - Payment method
    - Expense category
    
    **Note**: OCR accuracy depends on the quality of the PDF. You may need to manually correct some extracted data.
    """)