Update app.py

app.py

@@ -5,20 +5,63 @@ from selenium.webdriver.support.ui import WebDriverWait
 from selenium.webdriver.support import expected_conditions as EC
 import os
 import time
-import base64
 from datetime import datetime
+from werkzeug.utils import secure_filename
 
 app = Flask(__name__)
 PUBLIC_DIR = 'public'
+UPLOAD_DIR = 'uploads'
 os.makedirs(PUBLIC_DIR, exist_ok=True)
+os.makedirs(UPLOAD_DIR, exist_ok=True)
+
+ALLOWED_EXTENSIONS = {'txt', 'pdf', 'png', 'jpg', 'jpeg', 'gif', 'html', 'json', 'xml', 'csv'}
+MAX_FILE_SIZE = 16 * 1024 * 1024
+
+def allowed_file(filename):
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
 
 def get_driver():
     options = uc.ChromeOptions()
-    options.add_argument('--headless')
+    options.add_argument('--headless=new')
     options.add_argument('--no-sandbox')
     options.add_argument('--disable-dev-shm-usage')
     options.add_argument('--disable-gpu')
-    return uc.Chrome(options=options, use_subprocess=False)
+    options.add_argument('--disable-blink-features=AutomationControlled')
+    options.add_argument('--disable-features=IsolateOrigins,site-per-process')
+    options.add_argument('--user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36')
+    options.add_argument('--disable-web-security')
+    options.add_argument('--allow-running-insecure-content')
+    options.add_argument('--ignore-certificate-errors')
+    
+    prefs = {
+        'profile.default_content_setting_values.notifications': 2,
+        'credentials_enable_service': False,
+        'profile.password_manager_enabled': False
+    }
+    options.add_experimental_option('prefs', prefs)
+    options.add_experimental_option('excludeSwitches', ['enable-automation', 'enable-logging'])
+    options.add_experimental_option('useAutomationExtension', False)
+    
+    driver = uc.Chrome(options=options, use_subprocess=False)
+    
+    driver.execute_cdp_cmd('Page.addScriptToEvaluateOnNewDocument', {
+        'source': '''
+            Object.defineProperty(navigator, 'webdriver', {
+                get: () => undefined
+            });
+            Object.defineProperty(navigator, 'plugins', {
+                get: () => [1, 2, 3, 4, 5]
+            });
+            Object.defineProperty(navigator, 'languages', {
+                get: () => ['en-US', 'en']
+            });
+            window.chrome = {
+                runtime: {}
+            };
+        '''
+    })
+    
+    return driver
 
 @app.route('/')
 def index():
@@ -26,16 +69,105 @@ def index():
         'message': 'Undetected Chrome Scraper API is running',
         'endpoints': {
             'POST /api/scrape': 'Get HTML content from URL',
-            'POST /api/execute': 'Execute Python code with Selenium'
+            'POST /api/execute': 'Execute Python code with Selenium',
+            'POST /api/upload': 'Upload file to server',
+            'GET /api/files': 'List uploaded files',
+            'GET /uploads/<filename>': 'Download uploaded file'
         }
     })
 
+@app.route('/api/upload', methods=['POST'])
+def upload_file():
+    try:
+        if 'file' not in request.files:
+            return jsonify({
+                'success': False,
+                'error': 'No file part in request'
+            }), 400
+        
+        file = request.files['file']
+        
+        if file.filename == '':
+            return jsonify({
+                'success': False,
+                'error': 'No file selected'
+            }), 400
+        
+        if not allowed_file(file.filename):
+            return jsonify({
+                'success': False,
+                'error': f'File type not allowed. Allowed types: {", ".join(ALLOWED_EXTENSIONS)}'
+            }), 400
+        
+        filename = secure_filename(file.filename)
+        timestamp = int(time.time())
+        unique_filename = f"{timestamp}_{filename}"
+        filepath = os.path.join(UPLOAD_DIR, unique_filename)
+        
+        file.save(filepath)
+        
+        file_size = os.path.getsize(filepath)
+        
+        return jsonify({
+            'success': True,
+            'data': {
+                'filename': unique_filename,
+                'original_filename': filename,
+                'size': file_size,
+                'size_mb': round(file_size / (1024 * 1024), 2),
+                'url': f"{request.host_url}uploads/{unique_filename}",
+                'timestamp': datetime.now().isoformat()
+            }
+        })
+        
+    except Exception as e:
+        return jsonify({
+            'success': False,
+            'error': str(e)
+        }), 500
+
+@app.route('/api/files', methods=['GET'])
+def list_files():
+    try:
+        files = []
+        for filename in os.listdir(UPLOAD_DIR):
+            filepath = os.path.join(UPLOAD_DIR, filename)
+            if os.path.isfile(filepath):
+                file_stat = os.stat(filepath)
+                files.append({
+                    'filename': filename,
+                    'size': file_stat.st_size,
+                    'size_mb': round(file_stat.st_size / (1024 * 1024), 2),
+                    'url': f"{request.host_url}uploads/{filename}",
+                    'modified': datetime.fromtimestamp(file_stat.st_mtime).isoformat()
+                })
+        
+        return jsonify({
+            'success': True,
+            'data': {
+                'total': len(files),
+                'files': files
+            }
+        })
+        
+    except Exception as e:
+        return jsonify({
+            'success': False,
+            'error': str(e)
+        }), 500
+
+@app.route('/uploads/<path:filename>')
+def serve_upload(filename):
+    return send_from_directory(UPLOAD_DIR, filename)
+
 @app.route('/api/scrape', methods=['POST'])
 def scrape():
     data = request.get_json()
     url = data.get('url')
     wait_time = data.get('wait', 3)
     screenshot = data.get('screenshot', False)
+    html_only = data.get('html_only', False)
+    max_wait = data.get('max_wait', 30)
     
     if not url:
         return jsonify({'success': False, 'error': 'URL is required'}), 400
@@ -44,12 +176,33 @@ def scrape():
     try:
         driver = get_driver()
         driver.get(url)
+        
+        start_time = time.time()
+        while time.time() - start_time < max_wait:
+            html = driver.page_source
+            
+            if ("Just a moment" not in html and 
+                "Verifying you are human" not in html and
+                "cf-chl-widget" not in html):
+                break
+            
+            time.sleep(2)
+        
         time.sleep(wait_time)
         
         html = driver.page_source
         title = driver.title
         current_url = driver.current_url
         
+        if "Just a moment" in html or "Verifying you are human" in html:
+            return jsonify({
+                'success': False, 
+                'error': 'Cloudflare challenge not solved. Try increasing max_wait.'
+            }), 403
+        
+        if html_only:
+            return html, 200, {'Content-Type': 'text/html; charset=utf-8'}
+        
         result = {
             'success': True,
             'data': {