# HTML-based Invoice Generator import io import os import zipfile import tempfile import shutil from typing import Dict, List import base64 import subprocess import sys import pandas as pd import streamlit as st from num2words import num2words # Try to import Playwright for PDF conversion PLAYWRIGHT_AVAILABLE = False try: from playwright.sync_api import sync_playwright PLAYWRIGHT_AVAILABLE = True except ImportError: pass # Install Playwright browsers at runtime (disabled by default for hosted envs) _playwright_flag = os.path.join(tempfile.gettempdir(), 'playwright_installed') _allow_runtime_install = os.environ.get('PLAYWRIGHT_RUNTIME_INSTALL') == '1' if PLAYWRIGHT_AVAILABLE and _allow_runtime_install and not os.path.exists(_playwright_flag): try: cmd = [sys.executable, "-m", "playwright", "install", "chromium"] subprocess.run(cmd, check=True) with open(_playwright_flag, 'w') as f: f.write('installed') print("✅ Playwright browsers installed!") except Exception as e: print(f"⚠️ Failed to install Playwright browsers: {e}") else: if not _allow_runtime_install: print("ℹ️ Skipping runtime Playwright install (build-time install expected).") # Try to import PyPDF for PDF page extraction PYPDF_AVAILABLE = False try: from pypdf import PdfReader, PdfWriter PYPDF_AVAILABLE = True except ImportError: pass # ------------------------- # Utility helpers # ------------------------- def safe_str(x): if pd.isna(x): return "" return str(x) def format_amount(x): """Format amount as Indian currency format""" try: num = float(x) if num == 0: return "0.00" return f"{num:,.2f}" except Exception: return "0.00" def to_words(value): """Convert number to words""" try: num = float(value) if num == 0: return "Zero Rupees Only" if num.is_integer(): num = int(num) return num2words(num, to="cardinal", lang="en").title() + " Only" except Exception: return "Zero Rupees Only" # ------------------------- # HTML Template Processing # ------------------------- def fill_html_template(template_path: str, invoice_data: dict, output_path: str): """Fill HTML template with invoice data and save""" # Read the HTML template with open(template_path, 'r', encoding='utf-8') as f: html_content = f.read() # Prepare data for injection data = { 'invoice_no': invoice_data.get('Invoice No', ''), 'invoice_date': invoice_data.get('Invoice Date', ''), 'customer_name': invoice_data.get('Customer Name', ''), 'buyer_gstin': invoice_data.get('Customer GSTIN', ''), 'buyer_pan': invoice_data.get('Customer PAN', ''), 'buyer_cin': invoice_data.get('Customer CIN', ''), 'po_no': invoice_data.get('PO No', ''), 'buyer_state': invoice_data.get('Customer State', ''), } # Handle customer address (split into multiple lines) address = invoice_data.get('Customer Address', '') if address: address_parts = [p.strip() for p in address.split(',')] data['customer_address_1'] = address_parts[0] if len(address_parts) > 0 else '' data['customer_address_2'] = address_parts[1] if len(address_parts) > 1 else '' data['customer_address_3'] = ', '.join(address_parts[2:]) if len(address_parts) > 2 else '' else: data['customer_address_1'] = data['customer_address_2'] = data['customer_address_3'] = '' # Calculate totals dynamically items = invoice_data.get('Items', []) total_taxable = 0 total_cgst = 0 total_sgst = 0 total_igst = 0 for item in items: taxable_value = float(item.get('Taxable Value', 0)) cgst_percentage = float(item.get('CGST %', 0)) sgst_percentage = float(item.get('SGST %', 0)) igst_percentage = float(item.get('IGST %', 0)) # Calculate tax amounts dynamically cgst_amount = round((taxable_value * cgst_percentage / 100), 2) sgst_amount = round((taxable_value * sgst_percentage / 100), 2) igst_amount = round((taxable_value * igst_percentage / 100), 2) # Add to totals total_taxable += taxable_value total_cgst += cgst_amount total_sgst += sgst_amount total_igst += igst_amount # Calculate grand total grand_total = total_taxable + total_cgst + total_sgst + total_igst # Add totals to data data.update({ 'total_taxable': format_amount(total_taxable), 'total_cgst': format_amount(total_cgst), 'total_sgst': format_amount(total_sgst), 'total_igst': format_amount(total_igst), 'grand_total': format_amount(grand_total), 'rounding': format_amount(0), # Can be calculated if needed 'net_amount': format_amount(grand_total), 'words_total': to_words(grand_total), 'words_cgst': to_words(total_cgst), 'words_sgst': to_words(total_sgst), 'words_igst': to_words(total_igst), }) # Prepare items data for JavaScript injection items_js = [] for i, item in enumerate(items): taxable_value = float(item.get('Taxable Value', 0)) cgst_percentage = float(item.get('CGST %', 0)) sgst_percentage = float(item.get('SGST %', 0)) igst_percentage = float(item.get('IGST %', 0)) # Calculate tax amounts dynamically from percentages cgst_amount = round((taxable_value * cgst_percentage / 100), 2) sgst_amount = round((taxable_value * sgst_percentage / 100), 2) igst_amount = round((taxable_value * igst_percentage / 100), 2) # Calculate total amount total_amount = taxable_value + cgst_amount + sgst_amount + igst_amount items_js.append({ 'sr': i + 1, 'desc': item.get('Service Details', ''), 'hsn': item.get('HSN', ''), 'tax': taxable_value, 'cgst_p': cgst_percentage, 'cgst_a': cgst_amount, # Dynamically calculated 'sgst_p': sgst_percentage, 'sgst_a': sgst_amount, # Dynamically calculated 'igst_p': igst_percentage, 'igst_a': igst_amount, # Dynamically calculated 'total': round(total_amount, 2), # Dynamically calculated }) # Create JavaScript injection code js_injection = f""" """ # Insert the injection script before the closing body tag html_content = html_content.replace('', f'{js_injection}\n') # Handle logo images (convert to base64 if exists) # Check for both company logos logo_paths = ['assets/inephos.png', 'assets/srestham.png'] for logo_path in logo_paths: if os.path.exists(logo_path): with open(logo_path, 'rb') as img_file: img_b64 = base64.b64encode(img_file.read()).decode() img_src = f"data:image/png;base64,{img_b64}" html_content = html_content.replace(f'src="{logo_path}"', f'src="{img_src}"') # Also handle any remaining generic image references if os.path.exists('image.png'): with open('image.png', 'rb') as img_file: img_b64 = base64.b64encode(img_file.read()).decode() img_src = f"data:image/png;base64,{img_b64}" html_content = html_content.replace('src="image.png"', f'src="{img_src}"') # Write the filled HTML with open(output_path, 'w', encoding='utf-8') as f: f.write(html_content) print(f"✅ Generated HTML invoice: {output_path}") return output_path def html_to_pdf_playwright(html_path: str, pdf_path: str) -> bool: """Convert HTML to PDF using Playwright with Windows compatibility""" import asyncio import sys import traceback async def create_pdf(): from playwright.async_api import async_playwright async with async_playwright() as p: browser = await p.chromium.launch(headless=True) page = await browser.new_page() # Load the HTML file file_url = f"file:///{os.path.abspath(html_path).replace(os.sep, '/')}" await page.goto(file_url, wait_until='networkidle') # Generate PDF with proper settings await page.pdf( path=pdf_path, format='A4', margin={ 'top': '16mm', 'bottom': '16mm', 'left': '10mm', 'right': '10mm' }, print_background=True, prefer_css_page_size=True ) await browser.close() def _try_generate() -> bool: try: # Set event loop policy for Windows compatibility if sys.platform == "win32": asyncio.set_event_loop_policy(asyncio.WindowsProactorEventLoopPolicy()) asyncio.run(create_pdf()) return True except Exception as ex: raise ex def _install_playwright_browser_once() -> bool: flag = os.path.join(tempfile.gettempdir(), 'playwright_browser_installed') if os.path.exists(flag): return True try: subprocess.run([sys.executable, "-m", "playwright", "install", "chromium"], check=True) with open(flag, 'w') as f: f.write('installed') print("✅ Playwright Chromium downloaded at runtime.") return True except Exception as ex: print(f"❌ Runtime Playwright browser install failed: {ex}") return False try: # Set event loop policy for Windows compatibility if sys.platform == "win32": asyncio.set_event_loop_policy(asyncio.WindowsProactorEventLoopPolicy()) # First attempt if _try_generate(): return True except Exception as e: print(f"Playwright conversion failed: {e}") err_text = f"{e}\n{traceback.format_exc()}" # If browsers are not downloaded, try to fetch them once and retry if "Executable doesn't exist" in err_text or "playwright install" in err_text: if _install_playwright_browser_once(): try: if _try_generate(): return True except Exception as e2: print(f"Retry after browser install failed: {e2}") # Additional debugging for Windows issues if "NotImplementedError" in str(e): print("Windows asyncio compatibility issue detected. Trying alternative approach...") try: # Alternative: Use subprocess to call playwright directly import subprocess import json # Create a simple script to run playwright script_content = f''' import asyncio import sys from playwright.async_api import async_playwright async def main(): async with async_playwright() as p: browser = await p.chromium.launch(headless=True) page = await browser.new_page() await page.goto("file:///{os.path.abspath(html_path).replace(os.sep, '/')}", wait_until='networkidle') await page.pdf( path="{pdf_path.replace(os.sep, '/')}", format='A4', margin={{"top": "16mm", "bottom": "16mm", "left": "10mm", "right": "10mm"}}, print_background=True, prefer_css_page_size=True ) await browser.close() if __name__ == "__main__": asyncio.run(main()) ''' # Write temporary script script_path = os.path.join(os.path.dirname(pdf_path), 'temp_pdf_script.py') with open(script_path, 'w', encoding='utf-8') as f: f.write(script_content) # Run script in subprocess result = subprocess.run([sys.executable, script_path], capture_output=True, text=True, timeout=30) # Clean up if os.path.exists(script_path): os.remove(script_path) if result.returncode == 0 and os.path.exists(pdf_path): return True else: print(f"Subprocess approach failed: {result.stderr}") except Exception as e2: print(f"Alternative approach also failed: {e2}") return False def html_to_pdf(html_path: str, pdf_path: str) -> bool: """Convert HTML to PDF using Playwright (mandatory)""" if PLAYWRIGHT_AVAILABLE: return html_to_pdf_playwright(html_path, pdf_path) else: print("❌ Playwright not available. PDF generation is mandatory!") print("Please install: pip install playwright && playwright install chromium") return False def extract_first_page_pdf(input_pdf_path: str, output_pdf_path: str) -> bool: """Extract only the first page from a PDF file""" if not PYPDF_AVAILABLE: print("⚠️ PyPDF not available. Keeping original PDF.") # Copy the original file if PyPDF is not available try: shutil.copy2(input_pdf_path, output_pdf_path) return True except Exception as e: print(f"❌ Failed to copy PDF: {e}") return False try: # Read the input PDF reader = PdfReader(input_pdf_path) # Create a new PDF writer writer = PdfWriter() # Add only the first page (if it exists) if len(reader.pages) > 0: writer.add_page(reader.pages[0]) # Write the first page to the output file with open(output_pdf_path, 'wb') as output_file: writer.write(output_file) print(f"✅ Extracted first page: {output_pdf_path}") return True else: print(f"⚠️ No pages found in PDF: {input_pdf_path}") return False except Exception as e: print(f"❌ Failed to extract first page from {input_pdf_path}: {e}") # Fallback: copy the original file try: shutil.copy2(input_pdf_path, output_pdf_path) return True except Exception as e2: print(f"❌ Failed to copy PDF as fallback: {e2}") return False def process_invoices_html(data_file, template_path: str, company_name: str): """Process invoices using HTML template approach""" # Read customer data df = pd.read_excel(data_file, engine="openpyxl") df.columns = [str(c).strip().lower() for c in df.columns] # Create temporary directory for processing with tempfile.TemporaryDirectory() as temp_dir: invoices = [] html_files = [] pdf_files = [] # Process each row as a separate invoice for i, r in df.iterrows(): # Create invoice data structure invoice_data = { 'Invoice No': safe_str(r.get("invoice no", f"INV/{i+1}")), 'Invoice Date': safe_str(r.get("invoice date", "")), 'Customer Name': safe_str(r.get("customer name", "")), 'Customer Address': safe_str(r.get("customer address", "")), 'Customer GSTIN': safe_str(r.get("customer_gstin", "")), 'Customer PAN': safe_str(r.get("customer_pan", "")), 'Customer CIN': safe_str(r.get("customer_cin", "")), 'Customer State': safe_str(r.get("customer_state", "")), 'PO No': safe_str(r.get("po_no", "")), 'Total Amount': r.get("total amount", 0) or 0, 'Items': [{ 'Service Details': safe_str(r.get("service details", "")), 'HSN': safe_str(r.get("hsn", "")), 'Taxable Value': r.get("taxable value", 0) or 0, 'CGST %': r.get("cgst %", 0) or 0, 'SGST %': r.get("sgst %", 0) or 0, 'IGST %': r.get("igst %", 0) or 0, # Tax amounts and total will be calculated dynamically }] } # Generate HTML file html_filename = f"{invoice_data['Invoice No']}_{company_name}.html" html_path = os.path.join(temp_dir, html_filename) # Fill template fill_html_template(template_path, invoice_data, html_path) html_files.append((html_filename, html_path)) # Convert to PDF (mandatory with Playwright) pdf_filename = f"{invoice_data['Invoice No']}_{company_name}.pdf" pdf_path_temp = os.path.join(temp_dir, f"temp_{pdf_filename}") pdf_path_final = os.path.join(temp_dir, pdf_filename) if html_to_pdf(html_path, pdf_path_temp): # Extract only first page from the generated PDF if extract_first_page_pdf(pdf_path_temp, pdf_path_final): pdf_files.append((pdf_filename, pdf_path_final)) # Clean up temporary PDF if os.path.exists(pdf_path_temp): os.remove(pdf_path_temp) else: st.error(f"❌ Failed to extract first page for {invoice_data['Invoice No']}") print(f"❌ First page extraction failed for {invoice_data['Invoice No']}") else: st.error(f"❌ Failed to generate PDF for {invoice_data['Invoice No']}") print(f"❌ PDF generation failed for {invoice_data['Invoice No']}") invoices.append(invoice_data) # Create ZIP file with results zip_buffer = io.BytesIO() with zipfile.ZipFile(zip_buffer, "w", zipfile.ZIP_DEFLATED) as zf: # Add HTML files for filename, filepath in html_files: zf.write(filepath, filename) # Add PDF files if available for filename, filepath in pdf_files: if os.path.exists(filepath): zf.write(filepath, filename) zip_buffer.seek(0) return zip_buffer, len(invoices) # ------------------------- # Streamlit UI # ------------------------- st.set_page_config(page_title="HTML-Based Invoice Generator", layout="wide") st.title("🌐 HTML-Based Invoice Generator — Inephos & Srestham") st.markdown(""" Upload your customer data Excel file. The system will: 1. 📄 Generate individual HTML invoices using the template 2. 🎨 Apply beautiful styling and formatting 3. 📁 Convert to PDF (if weasyprint/playwright is available) 4. 📦 Package everything in a downloadable ZIP **Benefits of HTML approach:** - ✨ Perfect visual control and styling - ⚡ Faster processing than Excel manipulation - 🎯 Production-ready professional output - 🔧 Easy to customize and maintain """) # Upload section col1, col2 = st.columns(2) with col1: st.subheader("📊 Customer Data") data_file = st.file_uploader("Upload customer Excel (.xlsx/.xlsm)", type=["xlsx", "xlsm"]) if data_file: st.success("✅ Customer data uploaded") # Preview data try: preview_df = pd.read_excel(data_file, engine="openpyxl").head(3) st.write("**Data Preview:**") st.dataframe(preview_df) except Exception as e: st.error(f"Error reading file: {e}") with col2: st.subheader("🎨 Template Selection") # Check available templates inephos_available = os.path.exists('inephos.html') srestham_available = os.path.exists('srestham.html') if inephos_available and srestham_available: st.success("✅ Both templates found") # Radio button for template selection selected_template = st.radio( "Select Company Template:", options=["Inephos", "Srestham"], horizontal=True, help="Choose which company's invoice template to use" ) template_file = "inephos.html" if selected_template == "Inephos" else "srestham.html" st.info(f"Using: {template_file}") elif inephos_available: st.warning("⚠️ Only Inephos template found") selected_template = "Inephos" template_file = "inephos.html" elif srestham_available: st.warning("⚠️ Only Srestham template found") selected_template = "Srestham" template_file = "srestham.html" else: st.error("❌ No templates found") st.write("Make sure inephos.html and/or srestham.html are in the same directory") selected_template = None template_file = None # Processing section if template_file: st.markdown("---") st.subheader("🚀 Generate Invoices") col3, col4 = st.columns(2) with col3: # Enable Inephos button only when Inephos is selected inephos_enabled = (selected_template == "Inephos") if st.button("🏢 Generate Inephos Invoices", use_container_width=True, disabled=not inephos_enabled, help="Select Inephos template to enable this button"): if not data_file: st.error("Please upload customer data file.") else: with st.spinner("Generating Inephos invoices..."): try: zip_buffer, count = process_invoices_html(data_file, "inephos.html", "inephos") st.success(f"✅ Generated {count} Inephos invoices successfully!") file_types = "HTML files and PDFs" st.download_button( label=f"📥 Download ZIP ({file_types})", data=zip_buffer, file_name="inephos_invoices.zip", mime="application/zip" ) except Exception as e: st.error(f"Error generating invoices: {e}") st.exception(e) with col4: # Enable Srestham button only when Srestham is selected srestham_enabled = (selected_template == "Srestham") if st.button("🏢 Generate Srestham Invoices", use_container_width=True, disabled=not srestham_enabled, help="Select Srestham template to enable this button"): if not data_file: st.error("Please upload customer data file.") else: with st.spinner("Generating Srestham invoices..."): try: zip_buffer, count = process_invoices_html(data_file, "srestham.html", "srestham") st.success(f"✅ Generated {count} Srestham invoices successfully!") file_types = "HTML files and PDFs" st.download_button( label=f"📥 Download ZIP ({file_types})", data=zip_buffer, file_name="srestham_invoices.zip", mime="application/zip" ) except Exception as e: st.error(f"Error generating invoices: {e}") st.exception(e) # Information section st.markdown("---") st.subheader("ℹ️ Setup & Dependencies") col5, col6 = st.columns(2) with col5: st.markdown(""" **Installation for PDF conversion:** ```bash # Playwright (mandatory for PDF generation) pip install playwright playwright install chromium # PyPDF (recommended for first-page extraction) pip install pypdf ``` """) with col6: st.markdown(f""" **Current Status:** - Playwright: {'✅ Available' if PLAYWRIGHT_AVAILABLE else '❌ Not installed (REQUIRED)'} - PyPDF: {'✅ Available' if PYPDF_AVAILABLE else '⚠️ Not installed (recommended)'} - Inephos Template: {'✅ Found' if os.path.exists('inephos.html') else '❌ Missing'} - Srestham Template: {'✅ Found' if os.path.exists('srestham.html') else '❌ Missing'} **Output:** HTML invoices + First-page PDFs (mandatory) """) if not PLAYWRIGHT_AVAILABLE: st.error("🚨 **Playwright is required for PDF generation! Install it to continue.**") st.code("pip install playwright && playwright install chromium")