VIP PDF Splitter

from flask import Flask, request, jsonify, send_file, render_template_string from flask_cors import CORS from pypdf import PdfReader, PdfWriter import os import json import tempfile import zipfile from io import BytesIO app = Flask(__name__) CORS(app) UPLOAD_FOLDER = 'uploads' OUTPUT_FOLDER = 'output' os.makedirs(UPLOAD_FOLDER, exist_ok=True) os.makedirs(OUTPUT_FOLDER, exist_ok=True) ALLOWED_EXTENSIONS = {'pdf'} # HTML Frontend (embedded) - VIP PDF Splitter Design with Loader HTML_TEMPLATE = ''' VIP PDF Splitter

Processing Your PDF

Please wait while we split your document...

01 Select Your PDF Required

.pdf only

— place document on the tray —

Drop your PDF here

or click to browse your files

document.pdf 2.4 MB

02 Mark the Cuts 0 ranges

PDF Name	Page Range(s)	Discard

Processing...

0% Processing...

✓ Ready for Download

your files are stacked below

''' def allowed_file(filename): return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS @app.route('/') def index(): """Serve the frontend""" return render_template_string(HTML_TEMPLATE) @app.route('/process-pdf', methods=['POST']) def process_pdf(): try: # Check if file is present if 'pdf' not in request.files: return jsonify({'error': 'No PDF file uploaded'}), 400 file = request.files['pdf'] if file.filename == '': return jsonify({'error': 'No file selected'}), 400 if not allowed_file(file.filename): return jsonify({'error': 'Invalid file type. Please upload a PDF.'}), 400 # Get ranges from request ranges_data = request.form.get('ranges') if not ranges_data: return jsonify({'error': 'No ranges provided'}), 400 try: ranges = json.loads(ranges_data) except json.JSONDecodeError: return jsonify({'error': 'Invalid ranges format'}), 400 if not ranges: return jsonify({'error': 'No valid ranges provided'}), 400 # Save uploaded file temporarily with tempfile.NamedTemporaryFile(delete=False, suffix='.pdf') as tmp_file: file.save(tmp_file.name) temp_path = tmp_file.name try: # Read PDF reader = PdfReader(temp_path) total_pages = len(reader.pages) # Create output directory for this session session_dir = tempfile.mkdtemp() output_files = [] # Process each range for range_item in ranges: name = range_item.get('name', '').strip() range_list = range_item.get('ranges', []) if not name: continue # Validate ranges valid_ranges = [] for start, end in range_list: if start < 1 or end > total_pages or start > end: continue valid_ranges.append((start, end)) if not valid_ranges: continue # Create PDF for this range writer = PdfWriter() for start, end in valid_ranges: for page_num in range(start - 1, end): writer.add_page(reader.pages[page_num]) # Save file output_filename = f"{name}.pdf" output_path = os.path.join(session_dir, output_filename) with open(output_path, 'wb') as f: writer.write(f) output_files.append(output_filename) if not output_files: return jsonify({'error': 'No valid ranges processed'}), 400 # Create ZIP file in memory zip_buffer = BytesIO() with zipfile.ZipFile(zip_buffer, 'w', zipfile.ZIP_DEFLATED) as zip_file: for filename in output_files: file_path = os.path.join(session_dir, filename) zip_file.write(file_path, filename) zip_buffer.seek(0) # Clean up temp files os.unlink(temp_path) for filename in output_files: os.unlink(os.path.join(session_dir, filename)) os.rmdir(session_dir) # Send ZIP file return send_file( zip_buffer, mimetype='application/zip', as_attachment=True, download_name='split-pdfs.zip' ) except Exception as e: # Clean up on error if os.path.exists(temp_path): os.unlink(temp_path) raise e except Exception as e: return jsonify({'error': str(e)}), 500 @app.route('/health', methods=['GET']) def health(): return jsonify({'status': 'healthy'}) if __name__ == '__main__': app.run(debug=True, port=5000)