app.py

from flask import Flask, request, jsonify, send_file
from flask_cors import CORS
import os
import tempfile
from pdf2docx import Converter
from werkzeug.utils import secure_filename

app = Flask(__name__)
CORS(app)

# Use system temp directory for better cross-platform compatibility
UPLOAD_FOLDER = os.path.join(tempfile.gettempdir(), "pdf_uploads")
CONVERTED_FOLDER = os.path.join(tempfile.gettempdir(), "pdf_converted")

# Create directories
os.makedirs(UPLOAD_FOLDER, exist_ok=True)
os.makedirs(CONVERTED_FOLDER, exist_ok=True)

# Configuration
app.config['MAX_CONTENT_LENGTH'] = 16 * 1024 * 1024  # 16MB max file size
ALLOWED_EXTENSIONS = {'pdf'}

def allowed_file(filename):
    """Check if file has allowed extension"""
    return '.' in filename and \
           filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS

def cleanup_file(filepath):
    """Safely remove file if it exists"""
    try:
        if os.path.exists(filepath):
            os.remove(filepath)
    except Exception as e:
        print(f"Warning: Could not remove file {filepath}: {e}")

@app.route("/", methods=["GET"])
def index():
    return "✅ PDF to DOCX Converter is running!"

@app.route("/health", methods=["GET"])
def health_check():
    return jsonify({"status": "healthy", "service": "PDF to DOCX Converter"})

@app.route("/convert", methods=["POST"])
def convert_pdf_to_docx():
    # Check if file is present
    if "file" not in request.files:
        return jsonify({"error": "No file uploaded"}), 400
    
    pdf_file = request.files["file"]
    
    # Check if file is selected
    if pdf_file.filename == '':
        return jsonify({"error": "No file selected"}), 400
    
    # Validate file type
    if not allowed_file(pdf_file.filename):
        return jsonify({"error": "Only PDF files are allowed"}), 400
    
    # Secure the filename
    filename = secure_filename(pdf_file.filename)
    if not filename:
        return jsonify({"error": "Invalid filename"}), 400
    
    # Create unique paths to avoid conflicts
    import time
    timestamp = str(int(time.time()))
    pdf_path = os.path.join(UPLOAD_FOLDER, f"{timestamp}_{filename}")
    
    # Generate DOCX filename
    docx_filename = os.path.splitext(filename)[0] + ".docx"
    docx_path = os.path.join(CONVERTED_FOLDER, f"{timestamp}_{docx_filename}")
    
    try:
        # Save uploaded file
        pdf_file.save(pdf_path)
        
        # Convert PDF to DOCX
        cv = Converter(pdf_path)
        cv.convert(docx_path, start=0, end=None)
        cv.close()
        
        # Check if conversion was successful
        if not os.path.exists(docx_path):
            raise Exception("Conversion completed but output file not found")
        
        # Send file and cleanup in finally block
        return send_file(
            docx_path, 
            as_attachment=True,
            download_name=docx_filename,
            mimetype='application/vnd.openxmlformats-officedocument.wordprocessingml.document'
        )
        
    except Exception as e:
        # Cleanup on error
        cleanup_file(pdf_path)
        cleanup_file(docx_path)
        return jsonify({"error": f"Conversion failed: {str(e)}"}), 500
    
    finally:
        # Schedule cleanup of uploaded file (converted file cleaned up after send)
        try:
            cleanup_file(pdf_path)
        except:
            pass

@app.after_request
def cleanup_converted_files(response):
    """Clean up converted files after response is sent"""
    # This is a simple cleanup - in production you might want a more sophisticated approach
    return response

@app.errorhandler(413)
def too_large(e):
    return jsonify({"error": "File too large. Maximum size is 16MB"}), 413

@app.errorhandler(Exception)
def handle_exception(e):
    return jsonify({"error": f"An unexpected error occurred: {str(e)}"}), 500

if __name__ == "__main__":
    print(f"Upload folder: {UPLOAD_FOLDER}")
    print(f"Converted folder: {CONVERTED_FOLDER}")
    app.run(host="0.0.0.0", port=7860, debug=False)