Merge pull request 'data-model' (#2) from data-model into main

Reviewed-on: mstoeck3/dnsrecon#2

.env.example

@@ -0,0 +1,34 @@
+# ===============================================
+# DNSRecon Environment Variables
+# ===============================================
+# Copy this file to .env and fill in your values.
+
+# --- API Keys ---
+# Add your Shodan API key for the Shodan provider to be enabled.
+SHODAN_API_KEY=
+
+# --- Flask & Session Settings ---
+# A strong, random secret key is crucial for session security.
+FLASK_SECRET_KEY=your-very-secret-and-random-key-here
+FLASK_HOST=127.0.0.1
+FLASK_PORT=5000
+FLASK_DEBUG=True
+# How long a user's session in the browser lasts (in hours).
+FLASK_PERMANENT_SESSION_LIFETIME_HOURS=2
+# How long inactive scanner data is stored in Redis (in minutes).
+SESSION_TIMEOUT_MINUTES=60
+
+
+# --- Application Core Settings ---
+# The default number of levels to recurse when scanning.
+DEFAULT_RECURSION_DEPTH=2
+# Default timeout for provider API requests in seconds.
+DEFAULT_TIMEOUT=30
+# The number of concurrent provider requests to make.
+MAX_CONCURRENT_REQUESTS=1
+# The number of results from a provider that triggers the "large entity" grouping.
+LARGE_ENTITY_THRESHOLD=100
+# The number of times to retry a target if a provider fails.
+MAX_RETRIES_PER_TARGET=8
+# How long cached provider responses are stored (in hours).
+CACHE_TIMEOUT_HOURS=12

.gitignore

@@ -169,3 +169,4 @@ cython_debug/
 #.idea/
 
 dump.rdb
+cache/

README.md

@@ -4,28 +4,32 @@ DNSRecon is an interactive, passive reconnaissance tool designed to map adversar
 
 **Current Status: Phase 2 Implementation**
 
-  - ✅ Core infrastructure and graph engine
-  - ✅ Multi-provider support (crt.sh, DNS, Shodan)
-  - ✅ Session-based multi-user support
-  - ✅ Real-time web interface with interactive visualization
-  - ✅ Forensic logging system and JSON export
+  * ✅ Core infrastructure and graph engine
+  * ✅ Multi-provider support (crt.sh, DNS, Shodan)
+  * ✅ Session-based multi-user support
+  * ✅ Real-time web interface with interactive visualization
+  * ✅ Forensic logging system and JSON export
+
+-----
 
 ## Features
 
-  - **Passive Reconnaissance**: Gathers data without direct contact with target infrastructure.
-  - **In-Memory Graph Analysis**: Uses NetworkX for efficient relationship mapping.
-  - **Real-Time Visualization**: The graph updates dynamically as the scan progresses.
-  - **Forensic Logging**: A complete audit trail of all reconnaissance activities is maintained.
-  - **Confidence Scoring**: Relationships are weighted based on the reliability of the data source.
-  - **Session Management**: Supports concurrent user sessions with isolated scanner instances.
+  * **Passive Reconnaissance**: Gathers data without direct contact with target infrastructure.
+  * **In-Memory Graph Analysis**: Uses NetworkX for efficient relationship mapping.
+  * **Real-Time Visualization**: The graph updates dynamically as the scan progresses.
+  * **Forensic Logging**: A complete audit trail of all reconnaissance activities is maintained.
+  * **Confidence Scoring**: Relationships are weighted based on the reliability of the data source.
+  * **Session Management**: Supports concurrent user sessions with isolated scanner instances.
+
+-----
 
 ## Installation
 
 ### Prerequisites
 
-  - Python 3.8 or higher
-  - A modern web browser with JavaScript enabled
-  - (Recommended) A Linux host for running the application and the optional DNS cache.
+  * Python 3.8 or higher
+  * A modern web browser with JavaScript enabled
+  * (Recommended) A Linux host for running the application and the optional DNS cache.
 
 ### 1\. Clone the Project
 
@@ -44,156 +48,50 @@ source venv/bin/activate
 pip install -r requirements.txt
 ```
 
-### 3\. (Optional but Recommended) Set up a Local DNS Caching Resolver
+The `requirements.txt` file contains the following dependencies:
 
-Running a local DNS caching resolver can significantly speed up DNS queries and reduce your network footprint. Here’s how to set up `unbound` on a Debian-based Linux distribution (like Ubuntu).
+  * Flask\>=2.3.3
+  * networkx\>=3.1
+  * requests\>=2.31.0
+  * python-dateutil\>=2.8.2
+  * Werkzeug\>=2.3.7
+  * urllib3\>=2.0.0
+  * dnspython\>=2.4.2
+  * gunicorn
+  * redis
+  * python-dotenv
 
-**a. Install Unbound:**
+-----
+
+## Configuration
+
+DNSRecon is configured using a `.env` file. You can copy the provided example file and edit it to suit your needs:
 
 ```bash
-sudo apt update
-sudo apt install unbound -y
+cp .env.example .env
 ```
 
-**b. Configure Unbound:**
-Create a new configuration file for DNSRecon:
+The following environment variables are available for configuration:
 
-```bash
-sudo nano /etc/unbound/unbound.conf.d/dnsrecon.conf
-```
+| Variable | Description | Default |
+| :--- | :--- | :--- |
+| `SHODAN_API_KEY` | Your Shodan API key. | |
+| `FLASK_SECRET_KEY`| A strong, random secret key for session security. | `your-very-secret-and-random-key-here` |
+| `FLASK_HOST` | The host address for the Flask application. | `127.0.0.1` |
+| `FLASK_PORT` | The port for the Flask application. | `5000` |
+| `FLASK_DEBUG` | Enable or disable Flask's debug mode. | `True` |
+| `FLASK_PERMANENT_SESSION_LIFETIME_HOURS`| How long a user's session in the browser lasts (in hours). | `2` |
+| `SESSION_TIMEOUT_MINUTES` | How long inactive scanner data is stored in Redis (in minutes). | `60` |
+| `DEFAULT_RECURSION_DEPTH` | The default number of levels to recurse when scanning. | `2` |
+| `DEFAULT_TIMEOUT` | Default timeout for provider API requests in seconds. | `30` |
+| `MAX_CONCURRENT_REQUESTS`| The number of concurrent provider requests to make. | `5` |
+| `LARGE_ENTITY_THRESHOLD`| The number of results from a provider that triggers the "large entity" grouping. | `100` |
+| `MAX_RETRIES_PER_TARGET`| The number of times to retry a target if a provider fails. | `8` |
+| `CACHE_EXPIRY_HOURS`| How long cached provider responses are stored (in hours). | `12` |
 
-Add the following content to the file:
+-----
 
-```
-server:
-    # Listen on localhost for all users
-    interface: 127.0.0.1
-    access-control: 0.0.0.0/0 refuse
-    access-control: 127.0.0.0/8 allow
-
-    # Enable prefetching of popular items
-    prefetch: yes
-```
-
-**c. Restart Unbound and set it as the default resolver:**
-
-```bash
-sudo systemctl restart unbound
-sudo systemctl enable unbound
-```
-
-To use this resolver for your system, you may need to update your network settings to point to `127.0.0.1` as your DNS server.
-
-**d. Update DNSProvider to use the local resolver:**
-In `dnsrecon/providers/dns_provider.py`, you can explicitly set the resolver's nameservers in the `__init__` method:
-
-```python
-# dnsrecon/providers/dns_provider.py
-
-class DNSProvider(BaseProvider):
-    def __init__(self, session_config=None):
-        """Initialize DNS provider with session-specific configuration."""
-        super().__init__(...)
-
-        # Configure DNS resolver
-        self.resolver = dns.resolver.Resolver()
-        self.resolver.nameservers = ['127.0.0.1'] # Use local caching resolver
-        self.resolver.timeout = 5
-        self.resolver.lifetime = 10
-```
-
-## Usage (Development)
-
-### 1\. Start the Application
-
-```bash
-python app.py
-```
-
-### 2\. Open Your Browser
-
-Navigate to `http://127.0.0.1:5000`.
-
-### 3\. Basic Reconnaissance Workflow
-
-1.  **Enter Target Domain**: Input a domain like `example.com`.
-2.  **Select Recursion Depth**: Depth 2 is recommended for most investigations.
-3.  **Start Reconnaissance**: Click "Start Reconnaissance" to begin.
-4.  **Monitor Progress**: Watch the real-time graph build as relationships are discovered.
-5.  **Analyze and Export**: Interact with the graph and download the results when the scan is complete.
-
-## Production Deployment
-
-To deploy DNSRecon in a production environment, follow these steps:
-
-### 1\. Use a Production WSGI Server
-
-Do not use the built-in Flask development server for production. Use a WSGI server like **Gunicorn**:
-
-```bash
-pip install gunicorn
-gunicorn --workers 4 --bind 0.0.0.0:5000 app:app
-```
-
-### 2\. Configure Environment Variables
-
-Set the following environment variables for a secure and configurable deployment:
-
-```bash
-# Generate a strong, random secret key
-export SECRET_KEY='your-super-secret-and-random-key'
-
-# Set Flask to production mode
-export FLASK_ENV='production'
-export FLASK_DEBUG=False
-
-# API keys (optional, but recommended for full functionality)
-export SHODAN_API_KEY="your_shodan_key"
-```
-
-### 3\. Use a Reverse Proxy
-
-Set up a reverse proxy like **Nginx** to sit in front of the Gunicorn server. This provides several benefits, including:
-
-  - **TLS/SSL Termination**: Securely handle HTTPS traffic.
-  - **Load Balancing**: Distribute traffic across multiple application instances.
-  - **Serving Static Files**: Efficiently serve CSS and JavaScript files.
-
-**Example Nginx Configuration:**
-
-```nginx
-server {
-    listen 80;
-    server_name your_domain.com;
-
-    location / {
-        return 301 https://$host$request_uri;
-    }
-}
-
-server {
-    listen 443 ssl;
-    server_name your_domain.com;
-
-    # SSL cert configuration
-    ssl_certificate /etc/letsencrypt/live/your_domain.com/fullchain.pem;
-    ssl_certificate_key /etc/letsencrypt/live/your_domain.com/privkey.pem;
-
-    location / {
-        proxy_pass http://127.0.0.1:5000;
-        proxy_set_header Host $host;
-        proxy_set_header X-Real-IP $remote_addr;
-        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-    }
-
-    location /static {
-        alias /path/to/your/dnsrecon/static;
-        expires 30d;
-    }
-}
-```
-
-## Autostart with systemd
+## Systemd Service
 
 To run DNSRecon as a service that starts automatically on boot, you can use `systemd`.
 
@@ -245,12 +143,18 @@ You can check the status of the service at any time with:
 sudo systemctl status dnsrecon.service
 ```
 
-## Security Considerations
-
-  - **API Keys**: API keys are stored in memory for the duration of a user session and are not written to disk.
-  - **Rate Limiting**: DNSRecon includes built-in rate limiting to be respectful to data sources.
-  - **Local Use**: The application is designed for local or trusted network use and does not have built-in authentication. **Do not expose it directly to the internet without proper security controls.**
+-----
 
 ## License
 
-This project is licensed under the terms of the license agreement found in the `LICENSE` file.
+This project is licensed under the terms of the **BSD-3-Clause** license.
+
+Copyright (c) 2025 mstoeck3.
+
+Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
+
+1.  Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
+2.  Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
+3.  Neither the name of the copyright holder nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

app.py

@@ -1,3 +1,5 @@
+# dnsrecon-reduced/app.py
+
 """
 Flask application entry point for DNSRecon web interface.
 Provides REST API endpoints and serves the web interface with user session support.
@@ -8,56 +10,63 @@ import traceback
 from flask import Flask, render_template, request, jsonify, send_file, session
 from datetime import datetime, timezone, timedelta
 import io
+import os
 
 from core.session_manager import session_manager
 from config import config
+from core.graph_manager import NodeType
+from utils.helpers import is_valid_target
+from decimal import Decimal
 
 
 app = Flask(__name__)
-app.config['SECRET_KEY'] = 'dnsrecon-dev-key-change-in-production'
-app.config['PERMANENT_SESSION_LIFETIME'] = timedelta(hours=2)  # 2 hour session lifetime
+app.config['SECRET_KEY'] = config.flask_secret_key
+app.config['PERMANENT_SESSION_LIFETIME'] = timedelta(hours=config.flask_permanent_session_lifetime_hours)
 
 def get_user_scanner():
     """
-    User scanner retrieval with better error handling and debugging.
+    Retrieves the scanner for the current session, or creates a new one if none exists.
     """
-    # Get current Flask session info for debugging
     current_flask_session_id = session.get('dnsrecon_session_id')
-    client_ip = request.remote_addr
-    user_agent = request.headers.get('User-Agent', '')[:100]  # Truncate for logging
     
-    # Try to get existing session
     if current_flask_session_id:
         existing_scanner = session_manager.get_session(current_flask_session_id)
         if existing_scanner:
-            # Ensure session ID is set
-            existing_scanner.session_id = current_flask_session_id
             return current_flask_session_id, existing_scanner
-        else:
-            print(f"Session {current_flask_session_id} not found in session manager")
     
-    # Create new session
-    print("Creating new session...")
     new_session_id = session_manager.create_session()
     new_scanner = session_manager.get_session(new_session_id)
     
     if not new_scanner:
-        print(f"ERROR: Failed to retrieve newly created session {new_session_id}")
         raise Exception("Failed to create new scanner session")
     
-    # Store in Flask session
     session['dnsrecon_session_id'] = new_session_id
     session.permanent = True
     
-    # Ensure session ID is set on scanner
-    new_scanner.session_id = new_session_id
-    
-    print(f"Created new session: {new_session_id}")
-    print(f"New scanner status: {new_scanner.status}")
-    print("=== END SESSION DEBUG ===")
-    
     return new_session_id, new_scanner
 
+class CustomJSONEncoder(json.JSONEncoder):
+    """Custom JSON encoder to handle non-serializable objects."""
+    
+    def default(self, obj):
+        if isinstance(obj, datetime):
+            return obj.isoformat()
+        elif isinstance(obj, set):
+            return list(obj)
+        elif isinstance(obj, Decimal):
+            return float(obj)
+        elif hasattr(obj, '__dict__'):
+            # For custom objects, try to serialize their dict representation
+            try:
+                return obj.__dict__
+            except:
+                return str(obj)
+        elif hasattr(obj, 'value') and hasattr(obj, 'name'):
+            # For enum objects
+            return obj.value
+        else:
+            # For any other non-serializable object, convert to string
+            return str(obj)
 @app.route('/')
 def index():
     """Serve the main web interface."""
@@ -67,285 +76,276 @@ def index():
 @app.route('/api/scan/start', methods=['POST'])
 def start_scan():
     """
-    Start a new reconnaissance scan with immediate GUI feedback.
+    Starts a new reconnaissance scan.
     """
-    print("=== API: /api/scan/start called ===")
-    
     try:
-        print("Getting JSON data from request...")
         data = request.get_json()
-        print(f"Request data: {data}")
+        if not data or 'target' not in data:
+            return jsonify({'success': False, 'error': 'Missing target in request'}), 400
         
-        if not data or 'target_domain' not in data:
-            print("ERROR: Missing target_domain in request")
-            return jsonify({
-                'success': False,
-                'error': 'Missing target_domain in request'
-            }), 400
-        
-        target_domain = data['target_domain'].strip()
+        target = data['target'].strip()
         max_depth = data.get('max_depth', config.default_recursion_depth)
         clear_graph = data.get('clear_graph', True)
+        force_rescan_target = data.get('force_rescan_target', None)
         
-        print(f"Parsed - target_domain: '{target_domain}', max_depth: {max_depth}")
+        if not target:
+            return jsonify({'success': False, 'error': 'Target cannot be empty'}), 400
+        if not is_valid_target(target):
+            return jsonify({'success': False, 'error': 'Invalid target format.'}), 400
+        if not isinstance(max_depth, int) or not 1 <= max_depth <= 5:
+            return jsonify({'success': False, 'error': 'Max depth must be an integer between 1 and 5'}), 400
         
-        # Validation
-        if not target_domain:
-            print("ERROR: Target domain cannot be empty")
-            return jsonify({
-                'success': False,
-                'error': 'Target domain cannot be empty'
-            }), 400
-        
-        if not isinstance(max_depth, int) or max_depth < 1 or max_depth > 5:
-            print(f"ERROR: Invalid max_depth: {max_depth}")
-            return jsonify({
-                'success': False,
-                'error': 'Max depth must be an integer between 1 and 5'
-            }), 400
-        
-        print("Validation passed, getting user scanner...")
-        
-        # Get user-specific scanner
         user_session_id, scanner = get_user_scanner()
         
-        # Ensure session ID is properly set
-        if not scanner.session_id:
-            scanner.session_id = user_session_id
+        if not scanner:
+            return jsonify({'success': False, 'error': 'Failed to get scanner instance.'}), 500
         
-        print(f"Using session: {user_session_id}")
-        print(f"Scanner object ID: {id(scanner)}")
-        
-        # Start scan
-        print(f"Calling start_scan on scanner {id(scanner)}...")
-        success = scanner.start_scan(target_domain, max_depth, clear_graph=clear_graph)
-        
-        # Immediately update session state regardless of success
-        session_manager.update_session_scanner(user_session_id, scanner)
+        success = scanner.start_scan(target, max_depth, clear_graph=clear_graph, force_rescan_target=force_rescan_target)
         
         if success:
-            scan_session_id = scanner.logger.session_id
-            print(f"Scan started successfully with scan session ID: {scan_session_id}")
             return jsonify({
                 'success': True,
                 'message': 'Scan started successfully',
-                'scan_id': scan_session_id,
-                'user_session_id': user_session_id,
-                'scanner_status': scanner.status,
-                'debug_info': {
-                    'scanner_object_id': id(scanner),
-                    'scanner_status': scanner.status
-                }
+                'scan_id': scanner.logger.session_id,
+                'user_session_id': user_session_id
             })
         else:
-            print("ERROR: Scanner returned False")
-            
-            # Provide more detailed error information
-            error_details = {
-                'scanner_status': scanner.status,
-                'scanner_object_id': id(scanner),
-                'session_id': user_session_id,
-                'providers_count': len(scanner.providers) if hasattr(scanner, 'providers') else 0
-            }
-            
             return jsonify({
                 'success': False,
                 'error': f'Failed to start scan (scanner status: {scanner.status})',
-                'debug_info': error_details
             }), 409
         
     except Exception as e:
-        print(f"ERROR: Exception in start_scan endpoint: {e}")
         traceback.print_exc()
-        return jsonify({
-            'success': False,
-            'error': f'Internal server error: {str(e)}'
-        }), 500
-
+        return jsonify({'success': False, 'error': f'Internal server error: {str(e)}'}), 500
 
 @app.route('/api/scan/stop', methods=['POST'])
 def stop_scan():
-    """Stop the current scan with immediate GUI feedback."""
-    print("=== API: /api/scan/stop called ===")
-    
+    """Stop the current scan."""
     try:
-        # Get user-specific scanner
         user_session_id, scanner = get_user_scanner()
-        print(f"Stopping scan for session: {user_session_id}")
         
         if not scanner:
-            return jsonify({
-                'success': False,
-                'error': 'No scanner found for session'
-            }), 404
+            return jsonify({'success': False, 'error': 'No scanner found for session'}), 404
         
-        # Ensure session ID is set
         if not scanner.session_id:
             scanner.session_id = user_session_id
         
-        # Use the stop mechanism
-        success = scanner.stop_scan()
-        
-        # Also set the Redis stop signal directly for extra reliability
+        scanner.stop_scan()
         session_manager.set_stop_signal(user_session_id)
-        
-        # Force immediate status update
         session_manager.update_scanner_status(user_session_id, 'stopped')
-        
-        # Update the full scanner state
         session_manager.update_session_scanner(user_session_id, scanner)
         
-        print(f"Stop scan completed. Success: {success}, Scanner status: {scanner.status}")
-        
         return jsonify({
             'success': True,
-            'message': 'Scan stop requested - termination initiated',
-            'user_session_id': user_session_id,
-            'scanner_status': scanner.status,
-            'stop_method': 'cross_process'
+            'message': 'Scan stop requested',
+            'user_session_id': user_session_id
         })
         
     except Exception as e:
-        print(f"ERROR: Exception in stop_scan endpoint: {e}")
         traceback.print_exc()
-        return jsonify({
-            'success': False,
-            'error': f'Internal server error: {str(e)}'
-        }), 500
+        return jsonify({'success': False, 'error': f'Internal server error: {str(e)}'}), 500
 
 
 @app.route('/api/scan/status', methods=['GET'])
 def get_scan_status():
-    """Get current scan status with error handling."""
+    """Get current scan status."""
     try:
-        # Get user-specific scanner
         user_session_id, scanner = get_user_scanner()
         
         if not scanner:
-            # Return default idle status if no scanner
             return jsonify({
                 'success': True,
                 'status': {
-                    'status': 'idle',
-                    'target_domain': None,
-                    'current_depth': 0,
-                    'max_depth': 0,
-                    'current_indicator': '',
-                    'total_indicators_found': 0,
-                    'indicators_processed': 0,
-                    'progress_percentage': 0.0,
-                    'enabled_providers': [],
-                    'graph_statistics': {},
+                    'status': 'idle', 'target_domain': None, 'current_depth': 0,
+                    'max_depth': 0, 'progress_percentage': 0.0,
                     'user_session_id': user_session_id
                 }
             })
         
-        # Ensure session ID is set
         if not scanner.session_id:
             scanner.session_id = user_session_id
         
         status = scanner.get_scan_status()
         status['user_session_id'] = user_session_id
         
-        # Additional debug info
-        status['debug_info'] = {
-            'scanner_object_id': id(scanner),
-            'session_id_set': bool(scanner.session_id),
-            'has_scan_thread': bool(scanner.scan_thread and scanner.scan_thread.is_alive())
-        }
-        
-        return jsonify({
-            'success': True,
-            'status': status
-        })
+        return jsonify({'success': True, 'status': status})
     
     except Exception as e:
-        print(f"ERROR: Exception in get_scan_status endpoint: {e}")
         traceback.print_exc()
         return jsonify({
-            'success': False,
-            'error': f'Internal server error: {str(e)}',
-            'fallback_status': {
-                'status': 'error',
-                'target_domain': None,
-                'current_depth': 0,
-                'max_depth': 0,
-                'progress_percentage': 0.0
-            }
+            'success': False, 'error': f'Internal server error: {str(e)}',
+            'fallback_status': {'status': 'error', 'progress_percentage': 0.0}
         }), 500
 
 
 
 @app.route('/api/graph', methods=['GET'])
 def get_graph_data():
-    """Get current graph data with error handling."""
+    """Get current graph data."""
     try:
-        # Get user-specific scanner
         user_session_id, scanner = get_user_scanner()
         
-        if not scanner:
-            # Return empty graph if no scanner
-            return jsonify({
-                'success': True,
-                'graph': {
-                    'nodes': [],
-                    'edges': [],
-                    'statistics': {
-                        'node_count': 0,
-                        'edge_count': 0,
-                        'creation_time': datetime.now(timezone.utc).isoformat(),
-                        'last_modified': datetime.now(timezone.utc).isoformat()
-                    }
-                },
-                'user_session_id': user_session_id
-            })
-        
-        graph_data = scanner.get_graph_data()
-        return jsonify({
-            'success': True,
-            'graph': graph_data,
-            'user_session_id': user_session_id
-        })
-    
-    except Exception as e:
-        print(f"ERROR: Exception in get_graph_data endpoint: {e}")
-        traceback.print_exc()
-        return jsonify({
-            'success': False,
-            'error': f'Internal server error: {str(e)}',
-            'fallback_graph': {
-                'nodes': [],
-                'edges': [],
+        empty_graph = {
+            'nodes': [], 'edges': [],
             'statistics': {'node_count': 0, 'edge_count': 0}
         }
+        
+        if not scanner:
+            return jsonify({'success': True, 'graph': empty_graph, 'user_session_id': user_session_id})
+        
+        graph_data = scanner.get_graph_data() or empty_graph
+        
+        return jsonify({'success': True, 'graph': graph_data, 'user_session_id': user_session_id})
+    
+    except Exception as e:
+        traceback.print_exc()
+        return jsonify({
+            'success': False, 'error': f'Internal server error: {str(e)}',
+            'fallback_graph': {'nodes': [], 'edges': [], 'statistics': {}}
         }), 500
 
+@app.route('/api/graph/large-entity/extract', methods=['POST'])
+def extract_from_large_entity():
+    """Extract a node from a large entity."""
+    try:
+        data = request.get_json()
+        large_entity_id = data.get('large_entity_id')
+        node_id = data.get('node_id')
+
+        if not large_entity_id or not node_id:
+            return jsonify({'success': False, 'error': 'Missing required parameters'}), 400
+
+        user_session_id, scanner = get_user_scanner()
+        if not scanner:
+            return jsonify({'success': False, 'error': 'No active session found'}), 404
+
+        success = scanner.extract_node_from_large_entity(large_entity_id, node_id)
+        
+        if success:
+            session_manager.update_session_scanner(user_session_id, scanner)
+            return jsonify({'success': True, 'message': f'Node {node_id} extracted successfully.'})
+        else:
+            return jsonify({'success': False, 'error': f'Failed to extract node {node_id}.'}), 500
+
+    except Exception as e:
+        traceback.print_exc()
+        return jsonify({'success': False, 'error': f'Internal server error: {str(e)}'}), 500
+
+@app.route('/api/graph/node/<node_id>', methods=['DELETE'])
+def delete_graph_node(node_id):
+    """Delete a node from the graph."""
+    try:
+        user_session_id, scanner = get_user_scanner()
+        if not scanner:
+            return jsonify({'success': False, 'error': 'No active session found'}), 404
+
+        success = scanner.graph.remove_node(node_id)
+        
+        if success:
+            session_manager.update_session_scanner(user_session_id, scanner)
+            return jsonify({'success': True, 'message': f'Node {node_id} deleted successfully.'})
+        else:
+            return jsonify({'success': False, 'error': f'Node {node_id} not found.'}), 404
+
+    except Exception as e:
+        traceback.print_exc()
+        return jsonify({'success': False, 'error': f'Internal server error: {str(e)}'}), 500
+
+
+@app.route('/api/graph/revert', methods=['POST'])
+def revert_graph_action():
+    """Reverts a graph action, such as re-adding a deleted node."""
+    try:
+        data = request.get_json()
+        if not data or 'type' not in data or 'data' not in data:
+            return jsonify({'success': False, 'error': 'Invalid revert request format'}), 400
+
+        user_session_id, scanner = get_user_scanner()
+        if not scanner:
+            return jsonify({'success': False, 'error': 'No active session found'}), 404
+
+        action_type = data['type']
+        action_data = data['data']
+        
+        if action_type == 'delete':
+            node_to_add = action_data.get('node')
+            if node_to_add:
+                scanner.graph.add_node(
+                    node_id=node_to_add['id'],
+                    node_type=NodeType(node_to_add['type']),
+                    attributes=node_to_add.get('attributes'),
+                    description=node_to_add.get('description'),
+                    metadata=node_to_add.get('metadata')
+                )
+            
+            edges_to_add = action_data.get('edges', [])
+            for edge in edges_to_add:
+                if scanner.graph.graph.has_node(edge['from']) and scanner.graph.graph.has_node(edge['to']):
+                    scanner.graph.add_edge(
+                        source_id=edge['from'], target_id=edge['to'],
+                        relationship_type=edge['metadata']['relationship_type'],
+                        confidence_score=edge['metadata']['confidence_score'],
+                        source_provider=edge['metadata']['source_provider'],
+                        raw_data=edge.get('raw_data', {})
+                    )
+            
+            session_manager.update_session_scanner(user_session_id, scanner)
+            return jsonify({'success': True, 'message': 'Delete action reverted successfully.'})
+
+        return jsonify({'success': False, 'error': f'Unknown revert action type: {action_type}'}), 400
+
+    except Exception as e:
+        traceback.print_exc()
+        return jsonify({'success': False, 'error': f'Internal server error: {str(e)}'}), 500
 
 
 @app.route('/api/export', methods=['GET'])
 def export_results():
-    """Export complete scan results as downloadable JSON for the user session."""
+    """Export scan results as a JSON file with improved error handling."""
     try:
-        # Get user-specific scanner
         user_session_id, scanner = get_user_scanner()
         
-        # Get complete results
-        results = scanner.export_results()
+        if not scanner:
+            return jsonify({'success': False, 'error': 'No active scanner session found'}), 404
         
-        # Add session information to export
+        # Get export data with error handling
+        try:
+            results = scanner.export_results()
+        except Exception as e:
+            return jsonify({'success': False, 'error': f'Failed to gather export data: {str(e)}'}), 500
+        
+        # Add export metadata
         results['export_metadata'] = {
             'user_session_id': user_session_id,
             'export_timestamp': datetime.now(timezone.utc).isoformat(),
-            'export_type': 'user_session_results'
+            'export_version': '1.0.0',
+            'forensic_integrity': 'maintained'
         }
         
-        # Create filename with timestamp
+        # Generate filename with forensic naming convention
         timestamp = datetime.now(timezone.utc).strftime('%Y%m%d_%H%M%S')
         target = scanner.current_target or 'unknown'
-        filename = f"dnsrecon_{target}_{timestamp}_{user_session_id[:8]}.json"
+        # Sanitize target for filename
+        safe_target = "".join(c for c in target if c.isalnum() or c in ('-', '_', '.')).rstrip()
+        filename = f"dnsrecon_{safe_target}_{timestamp}.json"
         
-        # Create in-memory file
-        json_data = json.dumps(results, indent=2, ensure_ascii=False)
+        # Serialize with custom encoder and error handling
+        try:
+            json_data = json.dumps(results, indent=2, cls=CustomJSONEncoder, ensure_ascii=False)
+        except Exception as e:
+            # If custom encoder fails, try a more aggressive approach
+            try:
+                # Convert problematic objects to strings recursively
+                cleaned_results = _clean_for_json(results)
+                json_data = json.dumps(cleaned_results, indent=2, ensure_ascii=False)
+            except Exception as e2:
+                return jsonify({
+                    'success': False, 
+                    'error': f'JSON serialization failed: {str(e2)}'
+                }), 500
+        
+        # Create file object
         file_obj = io.BytesIO(json_data.encode('utf-8'))
         
         return send_file(
@@ -356,64 +356,70 @@ def export_results():
         )
     
     except Exception as e:
-        print(f"ERROR: Exception in export_results endpoint: {e}")
         traceback.print_exc()
         return jsonify({
             'success': False, 
-            'error': f'Export failed: {str(e)}'
+            'error': f'Export failed: {str(e)}',
+            'error_type': type(e).__name__
         }), 500
 
+def _clean_for_json(obj, max_depth=10, current_depth=0):
+    """
+    Recursively clean an object to make it JSON serializable.
+    Handles circular references and problematic object types.
+    """
+    if current_depth > max_depth:
+        return f"<max_depth_exceeded_{type(obj).__name__}>"
     
-@app.route('/api/providers', methods=['GET'])
-def get_providers():
-    """Get information about available providers for the user session."""
-    print("=== API: /api/providers called ===")
-    
+    if obj is None or isinstance(obj, (bool, int, float, str)):
+        return obj
+    elif isinstance(obj, datetime):
+        return obj.isoformat()
+    elif isinstance(obj, (set, frozenset)):
+        return list(obj)
+    elif isinstance(obj, dict):
+        cleaned = {}
+        for key, value in obj.items():
             try:
-        # Get user-specific scanner
-        user_session_id, scanner = get_user_scanner()
-        
-        provider_info = scanner.get_provider_info()
-        
-        return jsonify({
-            'success': True,
-            'providers': provider_info,
-            'user_session_id': user_session_id
-        })
-    
-    except Exception as e:
-        print(f"ERROR: Exception in get_providers endpoint: {e}")
-        traceback.print_exc()
-        return jsonify({
-            'success': False,
-            'error': f'Internal server error: {str(e)}'
-        }), 500
-
+                # Ensure key is string
+                clean_key = str(key) if not isinstance(key, str) else key
+                cleaned[clean_key] = _clean_for_json(value, max_depth, current_depth + 1)
+            except Exception:
+                cleaned[str(key)] = f"<serialization_error_{type(value).__name__}>"
+        return cleaned
+    elif isinstance(obj, (list, tuple)):
+        cleaned = []
+        for item in obj:
+            try:
+                cleaned.append(_clean_for_json(item, max_depth, current_depth + 1))
+            except Exception:
+                cleaned.append(f"<serialization_error_{type(item).__name__}>")
+        return cleaned
+    elif hasattr(obj, '__dict__'):
+        try:
+            return _clean_for_json(obj.__dict__, max_depth, current_depth + 1)
+        except Exception:
+            return str(obj)
+    elif hasattr(obj, 'value'):
+        # For enum-like objects
+        return obj.value
+    else:
+        return str(obj)
 
 @app.route('/api/config/api-keys', methods=['POST'])
 def set_api_keys():
-    """
-    Set API keys for providers for the user session only.
-    """
+    """Set API keys for the current session."""
     try:
         data = request.get_json()
-        
         if data is None:
-            return jsonify({
-                'success': False,
-                'error': 'No API keys provided'
-            }), 400
+            return jsonify({'success': False, 'error': 'No API keys provided'}), 400
         
-        # Get user-specific scanner and config
         user_session_id, scanner = get_user_scanner()
         session_config = scanner.config
         
         updated_providers = []
         
-        # Iterate over the API keys provided in the request data
         for provider_name, api_key in data.items():
-            # This allows us to both set and clear keys. The config
-            # handles enabling/disabling based on if the key is empty.
             api_key_value = str(api_key or '').strip()
             success = session_config.set_api_key(provider_name.lower(), api_key_value)
             
@@ -421,167 +427,136 @@ def set_api_keys():
                 updated_providers.append(provider_name)
         
         if updated_providers:
-            # Reinitialize scanner providers to apply the new keys
             scanner._initialize_providers()
-            
-            # Persist the updated scanner object back to the user's session
             session_manager.update_session_scanner(user_session_id, scanner)
             
             return jsonify({
                 'success': True,
-                'message': f'API keys updated for session {user_session_id}: {", ".join(updated_providers)}',
-                'updated_providers': updated_providers,
+                'message': f'API keys updated for: {", ".join(updated_providers)}',
                 'user_session_id': user_session_id
             })
         else:
-            return jsonify({
-                'success': False,
-                'error': 'No valid API keys were provided or provider names were incorrect.'
-            }), 400
+            return jsonify({'success': False, 'error': 'No valid API keys were provided.'}), 400
     
     except Exception as e:
-        print(f"ERROR: Exception in set_api_keys endpoint: {e}")
         traceback.print_exc()
-        return jsonify({
-            'success': False,
-            'error': f'Internal server error: {str(e)}'
-        }), 500
+        return jsonify({'success': False, 'error': f'Internal server error: {str(e)}'}), 500
 
-
-@app.route('/api/session/info', methods=['GET'])
-def get_session_info():
-    """Get information about the current user session."""
+@app.route('/api/providers', methods=['GET'])
+def get_providers():
+    """Get enhanced information about available providers including API key sources."""
     try:
         user_session_id, scanner = get_user_scanner()
-        session_info = session_manager.get_session_info(user_session_id)
+        base_provider_info = scanner.get_provider_info()
         
-        return jsonify({
-            'success': True,
-            'session_info': session_info
+        # Enhance provider info with API key source information
+        enhanced_provider_info = {}
+        
+        for provider_name, info in base_provider_info.items():
+            enhanced_info = dict(info)  # Copy base info
+            
+            if info['requires_api_key']:
+                # Determine API key source and configuration status
+                api_key = scanner.config.get_api_key(provider_name)
+                backend_api_key = os.getenv(f'{provider_name.upper()}_API_KEY')
+                
+                if backend_api_key:
+                    # API key configured via backend/environment
+                    enhanced_info.update({
+                        'api_key_configured': True,
+                        'api_key_source': 'backend',
+                        'api_key_help': f'API key configured via environment variable {provider_name.upper()}_API_KEY'
                     })
-    
-    except Exception as e:
-        print(f"ERROR: Exception in get_session_info endpoint: {e}")
-        traceback.print_exc()
-        return jsonify({
-            'success': False,
-            'error': f'Internal server error: {str(e)}'
-        }), 500
-
-
-@app.route('/api/session/terminate', methods=['POST'])
-def terminate_session():
-    """Terminate the current user session."""
-    try:
-        user_session_id = session.get('dnsrecon_session_id')
-        
-        if user_session_id:
-            success = session_manager.terminate_session(user_session_id)
-            # Clear Flask session
-            session.pop('dnsrecon_session_id', None)
-            
-            return jsonify({
-                'success': success,
-                'message': 'Session terminated' if success else 'Session not found'
+                elif api_key:
+                    # API key configured via web interface
+                    enhanced_info.update({
+                        'api_key_configured': True,
+                        'api_key_source': 'frontend',
+                        'api_key_help': f'API key set via web interface (session-only)'
                     })
                 else:
-            return jsonify({
-                'success': False,
-                'error': 'No active session to terminate'
-            }), 400
+                    # No API key configured
+                    enhanced_info.update({
+                        'api_key_configured': False,
+                        'api_key_source': None,
+                        'api_key_help': f'Requires API key to enable {info["display_name"]} integration'
+                    })
+            else:
+                # Provider doesn't require API key
+                enhanced_info.update({
+                    'api_key_configured': True,  # Always "configured" for non-API providers
+                    'api_key_source': None,
+                    'api_key_help': None
+                })
             
-    except Exception as e:
-        print(f"ERROR: Exception in terminate_session endpoint: {e}")
-        traceback.print_exc()
-        return jsonify({
-            'success': False,
-            'error': f'Internal server error: {str(e)}'
-        }), 500
-
-
-@app.route('/api/admin/sessions', methods=['GET'])
-def list_sessions():
-    """Admin endpoint to list all active sessions."""
-    try:
-        sessions = session_manager.list_active_sessions()
-        stats = session_manager.get_statistics()
+            enhanced_provider_info[provider_name] = enhanced_info
         
         return jsonify({
             'success': True, 
-            'sessions': sessions,
-            'statistics': stats
+            'providers': enhanced_provider_info, 
+            'user_session_id': user_session_id
         })
     
     except Exception as e:
-        print(f"ERROR: Exception in list_sessions endpoint: {e}")
         traceback.print_exc()
-        return jsonify({
-            'success': False,
-            'error': f'Internal server error: {str(e)}'
-        }), 500
+        return jsonify({'success': False, 'error': f'Internal server error: {str(e)}'}), 500
 
 
-@app.route('/api/health', methods=['GET'])
-def health_check():
-    """Health check endpoint."""
+@app.route('/api/config/providers', methods=['POST'])
+def configure_providers():
+    """Configure provider settings (enable/disable)."""
     try:
-        # Get session stats
-        session_stats = session_manager.get_statistics()
+        data = request.get_json()
+        if data is None:
+            return jsonify({'success': False, 'error': 'No provider settings provided'}), 400
+        
+        user_session_id, scanner = get_user_scanner()
+        session_config = scanner.config
+        
+        updated_providers = []
+        
+        for provider_name, settings in data.items():
+            provider_name_clean = provider_name.lower().strip()
+            
+            if 'enabled' in settings:
+                # Update the enabled state in session config
+                session_config.enabled_providers[provider_name_clean] = settings['enabled']
+                updated_providers.append(provider_name_clean)
+        
+        if updated_providers:
+            # Reinitialize providers with new settings
+            scanner._initialize_providers()
+            session_manager.update_session_scanner(user_session_id, scanner)
             
             return jsonify({
                 'success': True,
-            'status': 'healthy',
-            'timestamp': datetime.now(timezone.utc).isoformat(),
-            'version': '1.0.0-phase2',
-            'phase': 2,
-            'features': {
-                'multi_provider': True,
-                'concurrent_processing': True,
-                'real_time_updates': True,
-                'api_key_management': True,
-                'visualization': True,
-                'retry_logic': True,
-                'user_sessions': True,
-                'session_isolation': True
-            },
-            'session_statistics': session_stats
+                'message': f'Provider settings updated for: {", ".join(updated_providers)}',
+                'user_session_id': user_session_id
             })
+        else:
+            return jsonify({'success': False, 'error': 'No valid provider settings were provided.'}), 400
+    
     except Exception as e:
-        print(f"ERROR: Exception in health_check endpoint: {e}")
-        return jsonify({
-            'success': False,
-            'error': f'Health check failed: {str(e)}'
-        }), 500
+        traceback.print_exc()
+        return jsonify({'success': False, 'error': f'Internal server error: {str(e)}'}), 500
+
 
 
 @app.errorhandler(404)
 def not_found(error):
     """Handle 404 errors."""
-    return jsonify({
-        'success': False,
-        'error': 'Endpoint not found'
-    }), 404
+    return jsonify({'success': False, 'error': 'Endpoint not found'}), 404
 
 
 @app.errorhandler(500)
 def internal_error(error):
     """Handle 500 errors."""
-    print(f"ERROR: 500 Internal Server Error: {error}")
     traceback.print_exc()
-    return jsonify({
-        'success': False,
-        'error': 'Internal server error'
-    }), 500
+    return jsonify({'success': False, 'error': 'Internal server error'}), 500
 
 
 if __name__ == '__main__':
-    print("Starting DNSRecon Flask application with user session support...")
-    
-    # Load configuration from environment
     config.load_from_env()
-    
-    # Start Flask application
-    print(f"Starting server on {config.flask_host}:{config.flask_port}")
     app.run(
         host=config.flask_host,
         port=config.flask_port,

config.py

@@ -1,3 +1,5 @@
+# dnsrecon-reduced/config.py
+
 """
 Configuration management for DNSRecon tool.
 Handles API key storage, rate limiting, and default settings.
@@ -5,110 +7,149 @@ Handles API key storage, rate limiting, and default settings.
 
 import os
 from typing import Dict, Optional
+from dotenv import load_dotenv
 
+# Load environment variables from .env file
+load_dotenv()
 
 class Config:
     """Configuration manager for DNSRecon application."""
     
     def __init__(self):
         """Initialize configuration with default values."""
-        self.api_keys: Dict[str, Optional[str]] = {
-            'shodan': None
-        }
+        self.api_keys: Dict[str, Optional[str]] = {}
         
-        # Default settings
+        # --- General Settings ---
         self.default_recursion_depth = 2
-        self.default_timeout = 10
-        self.max_concurrent_requests = 5
+        self.default_timeout = 60
+        self.max_concurrent_requests = 1
         self.large_entity_threshold = 100
+        self.max_retries_per_target = 8
         
-        # Rate limiting settings (requests per minute)
+        # --- Provider Caching Settings ---
+        self.cache_timeout_hours = 6  # Provider-specific cache timeout
+        
+        # --- Rate Limiting (requests per minute) ---
         self.rate_limits = {
-            'crtsh': 60,          # Free service, be respectful
-            'shodan': 60,         # API dependent
-            'dns': 100            # Local DNS queries
+            'crtsh': 5,
+            'shodan': 60,
+            'dns': 100
         }
         
-        # Provider settings
+        # --- Provider Settings ---
         self.enabled_providers = {
-            'crtsh': True,        # Always enabled (free)
-            'dns': True,          # Always enabled (free)
-            'shodan': False       # Requires API key
+            'crtsh': True,
+            'dns': True,
+            'shodan': False
         }
         
-        # Logging configuration
+        # --- Logging ---
         self.log_level = 'INFO'
         self.log_format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s'
         
-        # Flask configuration
+        # --- Flask & Session Settings ---
         self.flask_host = '127.0.0.1'
         self.flask_port = 5000
         self.flask_debug = True
+        self.flask_secret_key = 'default-secret-key-change-me'
+        self.flask_permanent_session_lifetime_hours = 2
+        self.session_timeout_minutes = 60
         
-    def set_api_key(self, provider: str, api_key: str) -> bool:
-        """
-        Set API key for a provider.
-        
-        Args:
-            provider: Provider name (shodan, etc)
-            api_key: API key string
-            
-        Returns:
-            bool: True if key was set successfully
-        """
-        if provider in self.api_keys:
-            self.api_keys[provider] = api_key
-            self.enabled_providers[provider] = True if api_key else False
-            return True
-        return False
-    
-    def get_api_key(self, provider: str) -> Optional[str]:
-        """
-        Get API key for a provider.
-        
-        Args:
-            provider: Provider name
-            
-        Returns:
-            API key or None if not set
-        """
-        return self.api_keys.get(provider)
-    
-    def is_provider_enabled(self, provider: str) -> bool:
-        """
-        Check if a provider is enabled.
-        
-        Args:
-            provider: Provider name
-            
-        Returns:
-            bool: True if provider is enabled
-        """
-        return self.enabled_providers.get(provider, False)
-    
-    def get_rate_limit(self, provider: str) -> int:
-        """
-        Get rate limit for a provider.
-        
-        Args:
-            provider: Provider name
-            
-        Returns:
-            Rate limit in requests per minute
-        """
-        return self.rate_limits.get(provider, 60)
+        # Load environment variables to override defaults
+        self.load_from_env()
         
     def load_from_env(self):
         """Load configuration from environment variables."""
-        if os.getenv('SHODAN_API_KEY'):
         self.set_api_key('shodan', os.getenv('SHODAN_API_KEY'))
 
-        # Override default settings from environment
-        self.default_recursion_depth = int(os.getenv('DEFAULT_RECURSION_DEPTH', '2'))
-        self.flask_debug = os.getenv('FLASK_DEBUG', 'True').lower() == 'true'
-        self.default_timeout = 30
-        self.max_concurrent_requests = 5
+        # Override settings from environment
+        self.default_recursion_depth = int(os.getenv('DEFAULT_RECURSION_DEPTH', self.default_recursion_depth))
+        self.default_timeout = int(os.getenv('DEFAULT_TIMEOUT', self.default_timeout))
+        self.max_concurrent_requests = int(os.getenv('MAX_CONCURRENT_REQUESTS', self.max_concurrent_requests))
+        self.large_entity_threshold = int(os.getenv('LARGE_ENTITY_THRESHOLD', self.large_entity_threshold))
+        self.max_retries_per_target = int(os.getenv('MAX_RETRIES_PER_TARGET', self.max_retries_per_target))
+        self.cache_timeout_hours = int(os.getenv('CACHE_TIMEOUT_HOURS', self.cache_timeout_hours))
         
+        # Override Flask and session settings
+        self.flask_host = os.getenv('FLASK_HOST', self.flask_host)
+        self.flask_port = int(os.getenv('FLASK_PORT', self.flask_port))
+        self.flask_debug = os.getenv('FLASK_DEBUG', str(self.flask_debug)).lower() == 'true'
+        self.flask_secret_key = os.getenv('FLASK_SECRET_KEY', self.flask_secret_key)
+        self.flask_permanent_session_lifetime_hours = int(os.getenv('FLASK_PERMANENT_SESSION_LIFETIME_HOURS', self.flask_permanent_session_lifetime_hours))
+        self.session_timeout_minutes = int(os.getenv('SESSION_TIMEOUT_MINUTES', self.session_timeout_minutes))
+
+    def set_api_key(self, provider: str, api_key: Optional[str]) -> bool:
+        """Set API key for a provider."""
+        self.api_keys[provider] = api_key
+        if api_key:
+            self.enabled_providers[provider] = True
+        return True
+    
+    def set_provider_enabled(self, provider: str, enabled: bool) -> bool:
+        """
+        Set provider enabled status for the session.
+        
+        Args:
+            provider: Provider name
+            enabled: Whether the provider should be enabled
+            
+        Returns:
+            True if the setting was applied successfully
+        """
+        provider_key = provider.lower()
+        self.enabled_providers[provider_key] = enabled
+        return True
+
+    def get_provider_enabled(self, provider: str) -> bool:
+        """
+        Get provider enabled status.
+        
+        Args:
+            provider: Provider name
+            
+        Returns:
+            True if the provider is enabled
+        """
+        provider_key = provider.lower()
+        return self.enabled_providers.get(provider_key, True)  # Default to enabled
+
+    def bulk_set_provider_settings(self, provider_settings: dict) -> dict:
+        """
+        Set multiple provider settings at once.
+        
+        Args:
+            provider_settings: Dict of provider_name -> {'enabled': bool, ...}
+            
+        Returns:
+            Dict with results for each provider
+        """
+        results = {}
+        
+        for provider_name, settings in provider_settings.items():
+            provider_key = provider_name.lower()
+            
+            try:
+                if 'enabled' in settings:
+                    self.enabled_providers[provider_key] = settings['enabled']
+                    results[provider_key] = {'success': True, 'enabled': settings['enabled']}
+                else:
+                    results[provider_key] = {'success': False, 'error': 'No enabled setting provided'}
+            except Exception as e:
+                results[provider_key] = {'success': False, 'error': str(e)}
+        
+        return results
+    
+    def get_api_key(self, provider: str) -> Optional[str]:
+        """Get API key for a provider."""
+        return self.api_keys.get(provider)
+    
+    def is_provider_enabled(self, provider: str) -> bool:
+        """Check if a provider is enabled."""
+        return self.enabled_providers.get(provider, False)
+    
+    def get_rate_limit(self, provider: str) -> int:
+        """Get rate limit for a provider."""
+        return self.rate_limits.get(provider, 60)
 
 # Global configuration instance
 config = Config()

core/graph_manager.py

@@ -1,6 +1,10 @@
+# dnsrecon-reduced/core/graph_manager.py
+
 """
 Graph data model for DNSRecon using NetworkX.
 Manages in-memory graph storage with confidence scoring and forensic metadata.
+Now fully compatible with the unified ProviderResult data model.
+UPDATED: Fixed correlation exclusion keys to match actual attribute names.
 """
 import re
 from datetime import datetime, timezone
@@ -14,7 +18,8 @@ class NodeType(Enum):
     """Enumeration of supported node types."""
     DOMAIN = "domain"
     IP = "ip"
-    ASN = "asn"
+    ISP = "isp"
+    CA = "ca"
     LARGE_ENTITY = "large_entity"
     CORRELATION_OBJECT = "correlation_object"
 
@@ -26,6 +31,7 @@ class GraphManager:
     """
     Thread-safe graph manager for DNSRecon infrastructure mapping.
     Uses NetworkX for in-memory graph storage with confidence scoring.
+    Compatible with unified ProviderResult data model.
     """
 
     def __init__(self):
@@ -37,6 +43,31 @@ class GraphManager:
         # Compile regex for date filtering for efficiency
         self.date_pattern = re.compile(r'^\d{4}-\d{2}-\d{2}[ T]\d{2}:\d{2}:\d{2}')
         
+        # FIXED: Exclude cert_issuer_name since we already create proper CA relationships
+        self.EXCLUDED_KEYS = [
+            # Certificate metadata that creates noise or has dedicated node types
+            'cert_source',                    # Always 'crtsh' for crtsh provider
+            'cert_common_name',
+            'cert_validity_period_days',      # Numerical, not useful for correlation
+            'cert_issuer_name',              # FIXED: Has dedicated CA nodes, don't correlate
+            #'cert_certificate_id',            # Unique per certificate
+            #'cert_serial_number',            # Unique per certificate
+            'cert_entry_timestamp',          # Timestamp, filtered by date regex anyway
+            'cert_not_before',               # Date, filtered by date regex anyway
+            'cert_not_after',                # Date, filtered by date regex anyway
+            # DNS metadata that creates noise
+            'dns_ttl',                       # TTL values are not meaningful for correlation
+            # Shodan metadata that might create noise
+            'timestamp',                     # Generic timestamp fields
+            'last_update',                   # Generic timestamp fields
+            #'org',                          # Too generic, causes false correlations
+            #'isp',                          # Too generic, causes false correlations
+            # Generic noisy attributes
+            'updated_timestamp',             # Any timestamp field
+            'discovery_timestamp',           # Any timestamp field
+            'query_timestamp',               # Any timestamp field
+        ]
+
     def __getstate__(self):
         """Prepare GraphManager for pickling, excluding compiled regex."""
         state = self.__dict__.copy()
@@ -50,178 +81,138 @@ class GraphManager:
         self.__dict__.update(state)
         self.date_pattern = re.compile(r'^\d{4}-\d{2}-\d{2}[ T]\d{2}:\d{2}:\d{2}')
 
-    def _update_correlation_index(self, node_id: str, data: Any, path: List[str] = None):
-        """Recursively traverse metadata and add hashable values to the index."""
-        if path is None:
-            path = []
-
-        if isinstance(data, dict):
-            for key, value in data.items():
-                self._update_correlation_index(node_id, value, path + [key])
-        elif isinstance(data, list):
-            for i, item in enumerate(data):
-                self._update_correlation_index(node_id, item, path + [f"[{i}]"])
-        else:
-            self._add_to_correlation_index(node_id, data, ".".join(path))
-
-    def _add_to_correlation_index(self, node_id: str, value: Any, path_str: str):
-        """Add a hashable value to the correlation index, filtering out noise."""
-        if not isinstance(value, (str, int, float, bool)) or value is None:
+    def process_correlations_for_node(self, node_id: str):
+        """
+        UPDATED: Process correlations for a given node with enhanced tracking.
+        Now properly tracks which attribute/provider created each correlation.
+        """
+        if not self.graph.has_node(node_id):
             return
 
-        # Ignore certain paths that contain noisy, non-unique identifiers
-        if any(keyword in path_str.lower() for keyword in ['count', 'total', 'timestamp', 'date']):
-            return
+        node_attributes = self.graph.nodes[node_id].get('attributes', [])
         
-        # Filter out common low-entropy values and date-like strings
-        if isinstance(value, str):
-            # FIXED: Prevent correlation on date/time strings.
-            if self.date_pattern.match(value):
-                return
-            if len(value) < 4 or value.lower() in ['true', 'false', 'unknown', 'none', 'crt.sh']:
-                return
-        elif isinstance(value, int) and abs(value) < 9999:
-            return  # Ignore small integers
-        elif isinstance(value, bool):
-            return  # Ignore boolean values
+        # Process each attribute for potential correlations
+        for attr in node_attributes:
+            attr_name = attr.get('name')
+            attr_value = attr.get('value')
+            attr_provider = attr.get('provider', 'unknown')
 
-        # Add the valuable correlation data to the index
-        if value not in self.correlation_index:
-            self.correlation_index[value] = {}
-        if node_id not in self.correlation_index[value]:
-            self.correlation_index[value][node_id] = []
-        if path_str not in self.correlation_index[value][node_id]:
-            self.correlation_index[value][node_id].append(path_str)
+            # IMPROVED: More comprehensive exclusion logic
+            should_exclude = (
+                # Check against excluded keys (exact match or substring)
+                any(excluded_key in attr_name or attr_name == excluded_key for excluded_key in self.EXCLUDED_KEYS) or
+                # Invalid value types
+                not isinstance(attr_value, (str, int, float, bool)) or 
+                attr_value is None or
+                # Boolean values are not useful for correlation
+                isinstance(attr_value, bool) or
+                # String values that are too short or are dates
+                (isinstance(attr_value, str) and (
+                    len(attr_value) < 4 or 
+                    self.date_pattern.match(attr_value) or
+                    # Exclude common generic values that create noise
+                    attr_value.lower() in ['unknown', 'none', 'null', 'n/a', 'true', 'false', '0', '1']
+                )) or
+                # Numerical values that are likely to be unique identifiers
+                (isinstance(attr_value, (int, float)) and (
+                    attr_value == 0 or  # Zero values are not meaningful
+                    attr_value == 1 or  # One values are too common
+                    abs(attr_value) > 1000000  # Very large numbers are likely IDs
+                ))
+            )
 
-    def _check_for_correlations(self, new_node_id: str, data: Any, path: List[str] = None) -> List[Dict]:
-        """Recursively traverse metadata to find correlations with existing data."""
-        if path is None:
-            path = []
-
-        all_correlations = []
-        if isinstance(data, dict):
-            for key, value in data.items():
-                if key == 'source':  # Avoid correlating on the provider name
+            if should_exclude:
                 continue
-                all_correlations.extend(self._check_for_correlations(new_node_id, value, path + [key]))
-        elif isinstance(data, list):
-            for i, item in enumerate(data):
-                all_correlations.extend(self._check_for_correlations(new_node_id, item, path + [f"[{i}]"]))
-        else:
-            value = data
-            if value in self.correlation_index:
-                existing_nodes_with_paths = self.correlation_index[value]
-                unique_nodes = set(existing_nodes_with_paths.keys())
-                unique_nodes.add(new_node_id)
 
-                if len(unique_nodes) < 2:
-                    return all_correlations # Correlation must involve at least two distinct nodes
+            # Initialize correlation tracking for this value
+            if attr_value not in self.correlation_index:
+                self.correlation_index[attr_value] = {
+                    'nodes': set(),
+                    'sources': []  # Track which provider/attribute combinations contributed
+                }
 
-                new_source = {'node_id': new_node_id, 'path': ".".join(path)}
-                all_sources = [new_source]
-                for node_id, paths in existing_nodes_with_paths.items():
-                    for p_str in paths:
-                        all_sources.append({'node_id': node_id, 'path': p_str})
+            # Add this node and source information
+            self.correlation_index[attr_value]['nodes'].add(node_id)
             
-                all_correlations.append({
+            # Track the source of this correlation value
+            source_info = {
+                'node_id': node_id,
+                'provider': attr_provider,
+                'attribute': attr_name,
+                'path': f"{attr_provider}_{attr_name}"
+            }
+            
+            # Add source if not already present (avoid duplicates)
+            existing_sources = [s for s in self.correlation_index[attr_value]['sources'] 
+                              if s['node_id'] == node_id and s['path'] == source_info['path']]
+            if not existing_sources:
+                self.correlation_index[attr_value]['sources'].append(source_info)
+
+            # Create correlation node if we have multiple nodes with this value
+            if len(self.correlation_index[attr_value]['nodes']) > 1:
+                self._create_enhanced_correlation_node_and_edges(attr_value, self.correlation_index[attr_value])
+
+    def _create_enhanced_correlation_node_and_edges(self, value, correlation_data):
+        """
+        UPDATED: Create correlation node and edges with raw provider data (no formatting).
+        """
+        correlation_node_id = f"corr_{hash(str(value)) & 0x7FFFFFFF}"
+        nodes = correlation_data['nodes']
+        sources = correlation_data['sources']
+        
+        # Create or update correlation node
+        if not self.graph.has_node(correlation_node_id):
+            # Use raw provider/attribute data - no formatting
+            provider_counts = {}
+            for source in sources:
+                # Keep original provider and attribute names
+                key = f"{source['provider']}_{source['attribute']}"
+                provider_counts[key] = provider_counts.get(key, 0) + 1
+            
+            # Use the most common provider/attribute as the primary label (raw)
+            primary_source = max(provider_counts.items(), key=lambda x: x[1])[0] if provider_counts else "unknown_correlation"
+            
+            metadata = {
                 'value': value,
-                    'sources': all_sources,
-                    'nodes': list(unique_nodes)
-                })
-        return all_correlations
+                'correlated_nodes': list(nodes),
+                'sources': sources,
+                'primary_source': primary_source,
+                'correlation_count': len(nodes)
+            }
             
-    def add_node(self, node_id: str, node_type: NodeType, attributes: Optional[Dict[str, Any]] = None,
-                description: str = "", metadata: Optional[Dict[str, Any]] = None) -> bool:
-        """Add a node to the graph, update attributes, and process correlations."""
-        is_new_node = not self.graph.has_node(node_id)
-        if is_new_node:
-            self.graph.add_node(node_id, type=node_type.value,
-                                added_timestamp=datetime.now(timezone.utc).isoformat(),
-                                attributes=attributes or {},
-                                description=description,
-                                metadata=metadata or {})
-        else:
-            # Safely merge new attributes into existing attributes
-            if attributes:
-                existing_attributes = self.graph.nodes[node_id].get('attributes', {})
-                existing_attributes.update(attributes)
-                self.graph.nodes[node_id]['attributes'] = existing_attributes
-            if description:
-                self.graph.nodes[node_id]['description'] = description
-            if metadata:
-                existing_metadata = self.graph.nodes[node_id].get('metadata', {})
-                existing_metadata.update(metadata)
-                self.graph.nodes[node_id]['metadata'] = existing_metadata
+            self.add_node(correlation_node_id, NodeType.CORRELATION_OBJECT, metadata=metadata)
+            #print(f"Created correlation node {correlation_node_id} for value '{value}' with {len(nodes)} nodes")
 
-        if attributes and node_type != NodeType.CORRELATION_OBJECT:
-            correlations = self._check_for_correlations(node_id, attributes)
-            for corr in correlations:
-                value = corr['value']
+        # Create edges from each node to the correlation node
+        for source in sources:
+            node_id = source['node_id']
+            provider = source['provider']
+            attribute = source['attribute']
             
-                # STEP 1: Substring check against all existing nodes
-                if self._correlation_value_matches_existing_node(value):
-                    # Skip creating correlation node - would be redundant
-                    continue
+            if self.graph.has_node(node_id) and not self.graph.has_edge(node_id, correlation_node_id):
+                # Format relationship label as "corr_provider_attribute"
+                relationship_label = f"corr_{provider}_{attribute}"
                 
-                # STEP 2: Filter out node pairs that already have direct edges
-                eligible_nodes = self._filter_nodes_without_direct_edges(set(corr['nodes']))
+                self.add_edge(
+                    source_id=node_id,
+                    target_id=correlation_node_id,
+                    relationship_type=relationship_label,
+                    confidence_score=0.9,
+                    source_provider=provider,
+                    raw_data={
+                        'correlation_value': value,
+                        'original_attribute': attribute,
+                        'correlation_type': 'attribute_matching'
+                    }
+                )
                 
-                if len(eligible_nodes) < 2:
-                    # Need at least 2 nodes to create a correlation
-                    continue
+                #print(f"Added correlation edge: {node_id} -> {correlation_node_id} ({relationship_label})")
 
-                # STEP 3: Check for existing correlation node with same connection pattern
-                correlation_nodes_with_pattern = self._find_correlation_nodes_with_same_pattern(eligible_nodes)
-                
-                if correlation_nodes_with_pattern:
-                    # STEP 4: Merge with existing correlation node
-                    target_correlation_node = correlation_nodes_with_pattern[0]
-                    self._merge_correlation_values(target_correlation_node, value, corr)
-                else:
-                    # STEP 5: Create new correlation node for eligible nodes only
-                    correlation_node_id = f"corr_{abs(hash(str(sorted(eligible_nodes))))}"
-                    self.add_node(correlation_node_id, NodeType.CORRELATION_OBJECT,
-                                metadata={'values': [value], 'sources': corr['sources'],
-                                            'correlated_nodes': list(eligible_nodes)})
-                    
-                    # Create edges from eligible nodes to this correlation node
-                    for c_node_id in eligible_nodes:
-                        if self.graph.has_node(c_node_id):
-                            attribute = corr['sources'][0]['path'].split('.')[-1]
-                            relationship_type = f"c_{attribute}"
-                            self.add_edge(c_node_id, correlation_node_id, relationship_type, confidence_score=0.9)
-
-            self._update_correlation_index(node_id, attributes)
-
-        self.last_modified = datetime.now(timezone.utc).isoformat()
-        return is_new_node
-
-    def _filter_nodes_without_direct_edges(self, node_set: set) -> set:
-        """
-        Filter out nodes that already have direct edges between them.
-        Returns set of nodes that should be included in correlation.
-        """
-        nodes_list = list(node_set)
-        eligible_nodes = set(node_set)  # Start with all nodes
-        
-        # Check all pairs of nodes
-        for i in range(len(nodes_list)):
-            for j in range(i + 1, len(nodes_list)):
-                node_a = nodes_list[i]
-                node_b = nodes_list[j]
-                
-                # Check if direct edge exists in either direction
-                if self._has_direct_edge_bidirectional(node_a, node_b):
-                    # Remove both nodes from eligible set since they're already connected
-                    eligible_nodes.discard(node_a)
-                    eligible_nodes.discard(node_b)
-        
-        return eligible_nodes
 
     def _has_direct_edge_bidirectional(self, node_a: str, node_b: str) -> bool:
         """
         Check if there's a direct edge between two nodes in either direction.
-        Returns True if node_a→node_b OR node_b→node_a exists.
+        Returns True if node_aâ†'node_b OR node_bâ†'node_a exists.
         """
         return (self.graph.has_edge(node_a, node_b) or 
                 self.graph.has_edge(node_b, node_a))
@@ -290,7 +281,7 @@ class GraphManager:
         # Create set of unique sources based on (node_id, path) tuples
         source_set = set()
         for source in existing_sources + new_sources:
-            source_tuple = (source['node_id'], source['path'])
+            source_tuple = (source['node_id'], source.get('path', ''))
             source_set.add(source_tuple)
         
         # Convert back to list of dictionaries
@@ -313,19 +304,60 @@ class GraphManager:
             f"across {node_count} nodes"
         )
         
+    def add_node(self, node_id: str, node_type: NodeType, attributes: Optional[List[Dict[str, Any]]] = None,
+                description: str = "", metadata: Optional[Dict[str, Any]] = None) -> bool:
+        """
+        Add a node to the graph, update attributes, and process correlations.
+        Now compatible with unified data model - attributes are dictionaries from converted StandardAttribute objects.
+        """
+        is_new_node = not self.graph.has_node(node_id)
+        if is_new_node:
+            self.graph.add_node(node_id, type=node_type.value,
+                                added_timestamp=datetime.now(timezone.utc).isoformat(),
+                                attributes=attributes or [],  # Store as a list from the start
+                                description=description,
+                                metadata=metadata or {})
+        else:
+            # Safely merge new attributes into the existing list of attributes
+            if attributes:
+                existing_attributes = self.graph.nodes[node_id].get('attributes', [])
+                
+                # Handle cases where old data might still be in dictionary format
+                if not isinstance(existing_attributes, list):
+                    existing_attributes = []
+
+                # Create a set of existing attribute names for efficient duplicate checking
+                existing_attr_names = {attr['name'] for attr in existing_attributes}
+
+                for new_attr in attributes:
+                    if new_attr['name'] not in existing_attr_names:
+                        existing_attributes.append(new_attr)
+                        existing_attr_names.add(new_attr['name'])
+                
+                self.graph.nodes[node_id]['attributes'] = existing_attributes
+            if description:
+                self.graph.nodes[node_id]['description'] = description
+            if metadata:
+                existing_metadata = self.graph.nodes[node_id].get('metadata', {})
+                existing_metadata.update(metadata)
+                self.graph.nodes[node_id]['metadata'] = existing_metadata
+
+        self.last_modified = datetime.now(timezone.utc).isoformat()
+        return is_new_node
+
     def add_edge(self, source_id: str, target_id: str, relationship_type: str,
                 confidence_score: float = 0.5, source_provider: str = "unknown",
                 raw_data: Optional[Dict[str, Any]] = None) -> bool:
-        """Add or update an edge between two nodes, ensuring nodes exist."""
+        """
+        UPDATED: Add or update an edge between two nodes with raw relationship labels.
+        """
         if not self.graph.has_node(source_id) or not self.graph.has_node(target_id):
             return False
 
         new_confidence = confidence_score
         
-        if relationship_type.startswith("c_"):
+        # UPDATED: Use raw relationship type - no formatting
         edge_label = relationship_type
-        else:
-            edge_label = f"{source_provider}_{relationship_type}"
         
         if self.graph.has_edge(source_id, target_id):
             # If edge exists, update confidence if the new score is higher.
@@ -335,7 +367,7 @@ class GraphManager:
                 self.graph.edges[source_id, target_id]['updated_by'] = source_provider
             return False
 
-        # Add a new edge with all attributes.
+        # Add a new edge with raw attributes
         self.graph.add_edge(source_id, target_id,
                             relationship_type=edge_label,
                             confidence_score=new_confidence,
@@ -345,6 +377,69 @@ class GraphManager:
         self.last_modified = datetime.now(timezone.utc).isoformat()
         return True
 
+    def extract_node_from_large_entity(self, large_entity_id: str, node_id_to_extract: str) -> bool:
+        """
+        Removes a node from a large entity's internal lists and updates its count.
+        This prepares the large entity for the node's promotion to a regular node.
+        """
+        if not self.graph.has_node(large_entity_id):
+            return False
+            
+        node_data = self.graph.nodes[large_entity_id]
+        attributes = node_data.get('attributes', [])
+        
+        # Find the 'nodes' attribute dictionary in the list
+        nodes_attr = next((attr for attr in attributes if attr.get('name') == 'nodes'), None)
+        
+        # Remove from the list of member nodes
+        if nodes_attr and 'value' in nodes_attr and isinstance(nodes_attr['value'], list) and node_id_to_extract in nodes_attr['value']:
+            nodes_attr['value'].remove(node_id_to_extract)
+            
+            # Find the 'count' attribute and update it
+            count_attr = next((attr for attr in attributes if attr.get('name') == 'count'), None)
+            if count_attr:
+                count_attr['value'] = len(nodes_attr['value'])
+        else:
+            # This can happen if the node was already extracted, which is not an error.
+            print(f"Warning: Node {node_id_to_extract} not found in the 'nodes' list of {large_entity_id}.")
+            return True # Proceed as if successful
+            
+        self.last_modified = datetime.now(timezone.utc).isoformat()
+        return True
+
+    def remove_node(self, node_id: str) -> bool:
+        """Remove a node and its connected edges from the graph."""
+        if not self.graph.has_node(node_id):
+            return False
+
+        # Remove node from the graph (NetworkX handles removing connected edges)
+        self.graph.remove_node(node_id)
+
+        # Clean up the correlation index
+        keys_to_delete = []
+        for value, data in self.correlation_index.items():
+            if isinstance(data, dict) and 'nodes' in data:
+                # Updated correlation structure
+                if node_id in data['nodes']:
+                    data['nodes'].discard(node_id)
+                    # Remove sources for this node
+                    data['sources'] = [s for s in data['sources'] if s['node_id'] != node_id]
+                if not data['nodes']:  # If no other nodes are associated, remove it
+                    keys_to_delete.append(value)
+            else:
+                # Legacy correlation structure (fallback)
+                if isinstance(data, set) and node_id in data:
+                    data.discard(node_id)
+                if not data:
+                    keys_to_delete.append(value)
+        
+        for key in keys_to_delete:
+            if key in self.correlation_index:
+                del self.correlation_index[key]
+
+        self.last_modified = datetime.now(timezone.utc).isoformat()
+        return True
+
     def get_node_count(self) -> int:
         """Get total number of nodes in the graph."""
         return self.graph.number_of_nodes()
@@ -357,54 +452,59 @@ class GraphManager:
         """Get all nodes of a specific type."""
         return [n for n, d in self.graph.nodes(data=True) if d.get('type') == node_type.value]
 
-    def get_neighbors(self, node_id: str) -> List[str]:
-        """Get all unique neighbors (predecessors and successors) for a node."""
-        if not self.graph.has_node(node_id):
-            return []
-        return list(set(self.graph.predecessors(node_id)) | set(self.graph.successors(node_id)))
-
     def get_high_confidence_edges(self, min_confidence: float = 0.8) -> List[Tuple[str, str, Dict]]:
         """Get edges with confidence score above a given threshold."""
         return [(u, v, d) for u, v, d in self.graph.edges(data=True)
                 if d.get('confidence_score', 0) >= min_confidence]
 
     def get_graph_data(self) -> Dict[str, Any]:
-        """Export graph data formatted for frontend visualization."""
+        """
+        Export graph data formatted for frontend visualization.
+        SIMPLIFIED: No certificate styling - frontend handles all visual styling.
+        """
         nodes = []
         for node_id, attrs in self.graph.nodes(data=True):
-            node_data = {'id': node_id, 'label': node_id, 'type': attrs.get('type', 'unknown'),
-                         'attributes': attrs.get('attributes', {}),
+            node_data = {
+                'id': node_id, 
+                'label': node_id, 
+                'type': attrs.get('type', 'unknown'),
+                'attributes': attrs.get('attributes', []), # Raw attributes list
                 'description': attrs.get('description', ''),
                 'metadata': attrs.get('metadata', {}),
-                         'added_timestamp': attrs.get('added_timestamp')}
-            # Customize node appearance based on type and attributes
-            node_type = node_data['type']
-            attributes = node_data['attributes']
-            if node_type == 'domain' and attributes.get('certificates', {}).get('has_valid_cert') is False:
-                node_data['color'] = {'background': '#c7c7c7', 'border': '#999'} # Gray for invalid cert
+                'added_timestamp': attrs.get('added_timestamp')
+            }
             
             # Add incoming and outgoing edges to node data
             if self.graph.has_node(node_id):
-                node_data['incoming_edges'] = [{'from': u, 'data': d} for u, _, d in self.graph.in_edges(node_id, data=True)]
-                node_data['outgoing_edges'] = [{'to': v, 'data': d} for _, v, d in self.graph.out_edges(node_id, data=True)]
+                node_data['incoming_edges'] = [
+                    {'from': u, 'data': d} for u, _, d in self.graph.in_edges(node_id, data=True)
+                ]
+                node_data['outgoing_edges'] = [
+                    {'to': v, 'data': d} for _, v, d in self.graph.out_edges(node_id, data=True)
+                ]
             
             nodes.append(node_data)
 
         edges = []
         for source, target, attrs in self.graph.edges(data=True):
-            edges.append({'from': source, 'to': target,
+            edges.append({
+                'from': source, 
+                'to': target,
                 'label': attrs.get('relationship_type', ''),
                 'confidence_score': attrs.get('confidence_score', 0),
                 'source_provider': attrs.get('source_provider', ''),
-                          'discovery_timestamp': attrs.get('discovery_timestamp')})
+                'discovery_timestamp': attrs.get('discovery_timestamp')
+            })
+        
         return {
-            'nodes': nodes, 'edges': edges,
+            'nodes': nodes, 
+            'edges': edges,
             'statistics': self.get_statistics()['basic_metrics']
         }
 
     def export_json(self) -> Dict[str, Any]:
         """Export complete graph data as a JSON-serializable dictionary."""
-        graph_data = nx.node_link_data(self.graph) # Use NetworkX's built-in robust serializer
+        graph_data = nx.node_link_data(self.graph, edges="edges")
         return {
             'export_metadata': {
                 'export_timestamp': datetime.now(timezone.utc).isoformat(),
@@ -412,37 +512,67 @@ class GraphManager:
                 'last_modified': self.last_modified,
                 'total_nodes': self.get_node_count(),
                 'total_edges': self.get_edge_count(),
-                'graph_format': 'dnsrecon_v1_nodeling'
+                'graph_format': 'dnsrecon_v1_unified_model'
             },
             'graph': graph_data,
             'statistics': self.get_statistics()
         }
 
     def _get_confidence_distribution(self) -> Dict[str, int]:
-        """Get distribution of edge confidence scores."""
+        """Get distribution of edge confidence scores with empty graph handling."""
         distribution = {'high': 0, 'medium': 0, 'low': 0}
-        for _, _, confidence in self.graph.edges(data='confidence_score', default=0):
-            if confidence >= 0.8: distribution['high'] += 1
-            elif confidence >= 0.6: distribution['medium'] += 1
-            else: distribution['low'] += 1
+        
+        # FIXED: Handle empty graph case
+        if self.get_edge_count() == 0:
+            return distribution
+            
+        for _, _, data in self.graph.edges(data=True):
+            confidence = data.get('confidence_score', 0)
+            if confidence >= 0.8:
+                distribution['high'] += 1
+            elif confidence >= 0.6:
+                distribution['medium'] += 1
+            else:
+                distribution['low'] += 1
         return distribution
 
     def get_statistics(self) -> Dict[str, Any]:
-        """Get comprehensive statistics about the graph."""
-        stats = {'basic_metrics': {'total_nodes': self.get_node_count(),
-                                   'total_edges': self.get_edge_count(),
+        """Get comprehensive statistics about the graph with proper empty graph handling."""
+        
+        # FIXED: Handle empty graph case properly
+        node_count = self.get_node_count()
+        edge_count = self.get_edge_count()
+        
+        stats = {
+            'basic_metrics': {
+                'total_nodes': node_count,
+                'total_edges': edge_count,
                 'creation_time': self.creation_time,
-                                   'last_modified': self.last_modified},
-                 'node_type_distribution': {}, 'relationship_type_distribution': {},
+                'last_modified': self.last_modified
+            },
+            'node_type_distribution': {}, 
+            'relationship_type_distribution': {},
             'confidence_distribution': self._get_confidence_distribution(),
-                 'provider_distribution': {}}
-        # Calculate distributions
+            'provider_distribution': {}
+        }
+        
+        # FIXED: Only calculate distributions if we have data
+        if node_count > 0:
+            # Calculate node type distributions
             for node_type in NodeType:
-            stats['node_type_distribution'][node_type.value] = self.get_nodes_by_type(node_type).__len__()
-        for _, _, rel_type in self.graph.edges(data='relationship_type', default='unknown'):
+                count = len(self.get_nodes_by_type(node_type))
+                if count > 0:  # Only include types that exist
+                    stats['node_type_distribution'][node_type.value] = count
+        
+        if edge_count > 0:
+            # Calculate edge distributions
+            for _, _, data in self.graph.edges(data=True):
+                rel_type = data.get('relationship_type', 'unknown')
                 stats['relationship_type_distribution'][rel_type] = stats['relationship_type_distribution'].get(rel_type, 0) + 1
-        for _, _, provider in self.graph.edges(data='source_provider', default='unknown'):
+                
+                provider = data.get('source_provider', 'unknown')
                 stats['provider_distribution'][provider] = stats['provider_distribution'].get(provider, 0) + 1
+        
         return stats
 
     def clear(self) -> None:

core/logger.py

@@ -42,7 +42,7 @@ class ForensicLogger:
     Maintains detailed audit trail of all reconnaissance activities.
     """
     
-    def __init__(self, session_id: str = None):
+    def __init__(self, session_id: str = ""):
         """
         Initialize forensic logger.
         
@@ -50,7 +50,7 @@ class ForensicLogger:
             session_id: Unique identifier for this reconnaissance session
         """
         self.session_id = session_id or self._generate_session_id()
-        #self.lock = threading.Lock()
+        self.lock = threading.Lock()
         
         # Initialize audit trail storage
         self.api_requests: List[APIRequest] = []
@@ -86,6 +86,8 @@ class ForensicLogger:
         # Remove the unpickleable 'logger' attribute
         if 'logger' in state:
             del state['logger']
+        if 'lock' in state:
+            del state['lock']
         return state
 
     def __setstate__(self, state):
@@ -101,6 +103,7 @@ class ForensicLogger:
             console_handler = logging.StreamHandler()
             console_handler.setFormatter(formatter)
             self.logger.addHandler(console_handler)
+        self.lock = threading.Lock()
 
     def _generate_session_id(self) -> str:
         """Generate unique session identifier."""
@@ -149,7 +152,7 @@ class ForensicLogger:
         
         # Log to standard logger
         if error:
-            self.logger.error(f"API Request Failed - {provider}: {url} - {error}")
+            self.logger.error(f"API Request Failed.")
         else:
             self.logger.info(f"API Request - {provider}: {url} - Status: {status_code}")
     
@@ -194,7 +197,7 @@ class ForensicLogger:
         self.logger.info(f"Scan Started - Target: {target_domain}, Depth: {recursion_depth}")
         self.logger.info(f"Enabled Providers: {', '.join(enabled_providers)}")
         
-        self.session_metadata['target_domains'].add(target_domain)
+        self.session_metadata['target_domains'].update(target_domain)
     
     def log_scan_complete(self) -> None:
         """Log the completion of a reconnaissance scan."""
@@ -203,8 +206,6 @@ class ForensicLogger:
         self.session_metadata['target_domains'] = list(self.session_metadata['target_domains'])
         
         self.logger.info(f"Scan Complete - Session: {self.session_id}")
-        self.logger.info(f"Total API Requests: {self.session_metadata['total_requests']}")
-        self.logger.info(f"Total Relationships: {self.session_metadata['total_relationships']}")
     
     def export_audit_trail(self) -> Dict[str, Any]:
         """

core/provider_result.py

@@ -0,0 +1,107 @@
+# dnsrecon-reduced/core/provider_result.py
+
+"""
+Unified data model for DNSRecon passive reconnaissance.
+Standardizes the data structure across all providers to ensure consistent processing.
+"""
+
+from typing import Any, Optional, List, Dict
+from dataclasses import dataclass, field
+from datetime import datetime, timezone
+
+
+@dataclass
+class StandardAttribute:
+    """A unified data structure for a single piece of information about a node."""
+    target_node: str
+    name: str
+    value: Any
+    type: str
+    provider: str
+    confidence: float
+    timestamp: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
+    metadata: Optional[Dict[str, Any]] = field(default_factory=dict)
+
+    def __post_init__(self):
+        """Validate the attribute after initialization."""
+        if not isinstance(self.confidence, (int, float)) or not 0.0 <= self.confidence <= 1.0:
+            raise ValueError(f"Confidence must be between 0.0 and 1.0, got {self.confidence}")
+
+
+@dataclass
+class Relationship:
+    """A unified data structure for a directional link between two nodes."""
+    source_node: str
+    target_node: str
+    relationship_type: str
+    confidence: float
+    provider: str
+    timestamp: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
+    raw_data: Optional[Dict[str, Any]] = field(default_factory=dict)
+
+    def __post_init__(self):
+        """Validate the relationship after initialization."""
+        if not isinstance(self.confidence, (int, float)) or not 0.0 <= self.confidence <= 1.0:
+            raise ValueError(f"Confidence must be between 0.0 and 1.0, got {self.confidence}")
+
+
+@dataclass
+class ProviderResult:
+    """A container for all data returned by a provider from a single query."""
+    attributes: List[StandardAttribute] = field(default_factory=list)
+    relationships: List[Relationship] = field(default_factory=list)
+
+    def add_attribute(self, target_node: str, name: str, value: Any, attr_type: str, 
+                     provider: str, confidence: float = 0.8, 
+                     metadata: Optional[Dict[str, Any]] = None) -> None:
+        """Helper method to add an attribute to the result."""
+        self.attributes.append(StandardAttribute(
+            target_node=target_node,
+            name=name,
+            value=value,
+            type=attr_type,
+            provider=provider,
+            confidence=confidence,
+            metadata=metadata or {}
+        ))
+
+    def add_relationship(self, source_node: str, target_node: str, relationship_type: str,
+                        provider: str, confidence: float = 0.8, 
+                        raw_data: Optional[Dict[str, Any]] = None) -> None:
+        """Helper method to add a relationship to the result."""
+        self.relationships.append(Relationship(
+            source_node=source_node,
+            target_node=target_node,
+            relationship_type=relationship_type,
+            confidence=confidence,
+            provider=provider,
+            raw_data=raw_data or {}
+        ))
+
+    def get_discovered_nodes(self) -> set:
+        """Get all unique node identifiers discovered in this result."""
+        nodes = set()
+        
+        # Add nodes from relationships
+        for rel in self.relationships:
+            nodes.add(rel.source_node)
+            nodes.add(rel.target_node)
+            
+        # Add nodes from attributes
+        for attr in self.attributes:
+            nodes.add(attr.target_node)
+            
+        return nodes
+
+    def get_relationship_count(self) -> int:
+        """Get the total number of relationships in this result."""
+        return len(self.relationships)
+
+    def get_attribute_count(self) -> int:
+        """Get the total number of attributes in this result."""
+        return len(self.attributes)
+
+    ##TODO
+    #def is_large_entity(self, threshold: int) -> bool:
+    #    """Check if this result qualifies as a large entity based on relationship count."""
+    #    return self.get_relationship_count() > threshold

core/rate_limiter.py

@@ -0,0 +1,28 @@
+# dnsrecon-reduced/core/rate_limiter.py
+
+import time
+
+class GlobalRateLimiter:
+    def __init__(self, redis_client):
+        self.redis = redis_client
+
+    def is_rate_limited(self, key, limit, period):
+        """
+        Check if a key is rate-limited.
+        """
+        now = time.time()
+        key = f"rate_limit:{key}"
+
+        # Remove old timestamps
+        self.redis.zremrangebyscore(key, 0, now - period)
+
+        # Check the count
+        count = self.redis.zcard(key)
+        if count >= limit:
+            return True
+
+        # Add new timestamp
+        self.redis.zadd(key, {now: now})
+        self.redis.expire(key, period)
+
+        return False

core/session_config.py

@@ -3,11 +3,9 @@ Per-session configuration management for DNSRecon.
 Provides isolated configuration instances for each user session.
 """
 
-import os
-from typing import Dict, Optional
+from config import Config
 
-
-class SessionConfig:
+class SessionConfig(Config):
     """
     Session-specific configuration that inherits from global config
     but maintains isolated API keys and provider settings.
@@ -15,106 +13,8 @@ class SessionConfig:
     
     def __init__(self):
         """Initialize session config with global defaults."""
-        # Copy all attributes from global config
-        self.api_keys: Dict[str, Optional[str]] = {
-            'shodan': None
-        }
+        super().__init__()
 
-        # Default settings (copied from global config)
-        self.default_recursion_depth = 2
-        self.default_timeout = 30
-        self.max_concurrent_requests = 5
-        self.large_entity_threshold = 100
-        
-        # Rate limiting settings (per session)
-        self.rate_limits = {
-            'crtsh': 60,
-            'shodan': 60,
-            'dns': 100
-        }
-        
-        # Provider settings (per session)
-        self.enabled_providers = {
-            'crtsh': True,
-            'dns': True,
-            'shodan': False
-        }
-        
-        # Logging configuration
-        self.log_level = 'INFO'
-        self.log_format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s'
-        
-        # Flask configuration (shared)
-        self.flask_host = '127.0.0.1'
-        self.flask_port = 5000
-        self.flask_debug = True
-    
-    def set_api_key(self, provider: str, api_key: str) -> bool:
-        """
-        Set API key for a provider in this session.
-        
-        Args:
-            provider: Provider name (shodan, etc)
-            api_key: API key string
-            
-        Returns:
-            bool: True if key was set successfully
-        """
-        if provider in self.api_keys:
-            self.api_keys[provider] = api_key
-            self.enabled_providers[provider] = True if api_key else False
-            return True
-        return False
-    
-    def get_api_key(self, provider: str) -> Optional[str]:
-        """
-        Get API key for a provider in this session.
-        
-        Args:
-            provider: Provider name
-            
-        Returns:
-            API key or None if not set
-        """
-        return self.api_keys.get(provider)
-    
-    def is_provider_enabled(self, provider: str) -> bool:
-        """
-        Check if a provider is enabled in this session.
-        
-        Args:
-            provider: Provider name
-            
-        Returns:
-            bool: True if provider is enabled
-        """
-        return self.enabled_providers.get(provider, False)
-    
-    def get_rate_limit(self, provider: str) -> int:
-        """
-        Get rate limit for a provider in this session.
-        
-        Args:
-            provider: Provider name
-            
-        Returns:
-            Rate limit in requests per minute
-        """
-        return self.rate_limits.get(provider, 60)
-    
-    def load_from_env(self):
-        """Load configuration from environment variables (only if not already set)."""
-        if os.getenv('SHODAN_API_KEY') and not self.api_keys['shodan']:
-            self.set_api_key('shodan', os.getenv('SHODAN_API_KEY'))
-        
-        # Override default settings from environment
-        self.default_recursion_depth = int(os.getenv('DEFAULT_RECURSION_DEPTH', '2'))
-        self.default_timeout = 30
-        self.max_concurrent_requests = 5
-
-
-def create_session_config() -> SessionConfig:
+def create_session_config() -> 'SessionConfig':
     """Create a new session configuration instance."""
-    session_config = SessionConfig()
-    session_config.load_from_env()
-    return session_config
+    return SessionConfig()

core/session_manager.py

@@ -5,26 +5,30 @@ import time
 import uuid
 import redis
 import pickle
-from typing import Dict, Optional, Any, List
+from typing import Dict, Optional, Any
 
 from core.scanner import Scanner
-
-# WARNING: Using pickle can be a security risk if the data source is not trusted.
-# In this case, we are only serializing/deserializing our own trusted Scanner objects,
-# which is generally safe. Do not unpickle data from untrusted sources.
+from config import config
 
 class SessionManager:
     """
-    Manages multiple scanner instances for concurrent user sessions using Redis.
+    FIXED: Manages multiple scanner instances for concurrent user sessions using Redis.
+    Now more conservative about session creation to preserve API keys and configuration.
     """
     
-    def __init__(self, session_timeout_minutes: int = 60):
+    def __init__(self, session_timeout_minutes: int = 0):
         """
         Initialize session manager with a Redis backend.
         """
+        if session_timeout_minutes is None:
+            session_timeout_minutes = config.session_timeout_minutes
+
         self.redis_client = redis.StrictRedis(db=0, decode_responses=False)
         self.session_timeout = session_timeout_minutes * 60  # Convert to seconds
-        self.lock = threading.Lock() # Lock for local operations, Redis handles atomic ops
+        self.lock = threading.Lock()
+        
+        # FIXED: Add a creation lock to prevent race conditions
+        self.creation_lock = threading.Lock()
         
         # Start cleanup thread
         self.cleanup_thread = threading.Thread(target=self._cleanup_loop, daemon=True)
@@ -36,7 +40,7 @@ class SessionManager:
         """Prepare SessionManager for pickling."""
         state = self.__dict__.copy()
         # Exclude unpickleable attributes - Redis client and threading objects
-        unpicklable_attrs = ['lock', 'cleanup_thread', 'redis_client']
+        unpicklable_attrs = ['lock', 'cleanup_thread', 'redis_client', 'creation_lock']
         for attr in unpicklable_attrs:
             if attr in state:
                 del state[attr]
@@ -46,9 +50,9 @@ class SessionManager:
         """Restore SessionManager after unpickling."""
         self.__dict__.update(state)
         # Re-initialize unpickleable attributes
-        import redis
         self.redis_client = redis.StrictRedis(db=0, decode_responses=False)
         self.lock = threading.Lock()
+        self.creation_lock = threading.Lock()
         self.cleanup_thread = threading.Thread(target=self._cleanup_loop, daemon=True)
         self.cleanup_thread.start()
 
@@ -62,8 +66,10 @@ class SessionManager:
 
     def create_session(self) -> str:
         """
-        Create a new user session and store it in Redis.
+        FIXED: Create a new user session with thread-safe creation to prevent duplicates.
         """
+        # FIXED: Use creation lock to prevent race conditions
+        with self.creation_lock:
             session_id = str(uuid.uuid4())
             print(f"=== CREATING SESSION {session_id} IN REDIS ===")
             
@@ -95,6 +101,7 @@ class SessionManager:
                 self.redis_client.setex(stop_key, self.session_timeout, b'0')
                 
                 print(f"Session {session_id} stored in Redis with stop signal initialized")
+                print(f"Session has {len(scanner_instance.providers)} providers: {[p.get_name() for p in scanner_instance.providers]}")
                 return session_id
                 
             except Exception as e:
@@ -208,7 +215,14 @@ class SessionManager:
                 # Immediately save to Redis for GUI updates
                 success = self._save_session_data(session_id, session_data)
                 if success:
-                    print(f"Scanner state updated for session {session_id} (status: {scanner.status})")
+                    # Only log occasionally to reduce noise
+                    if hasattr(self, '_last_update_log'):
+                        if time.time() - self._last_update_log > 5:  # Log every 5 seconds max
+                            #print(f"Scanner state updated for session {session_id} (status: {scanner.status})")
+                            self._last_update_log = time.time()
+                    else:
+                        #print(f"Scanner state updated for session {session_id} (status: {scanner.status})")
+                        self._last_update_log = time.time()
                 else:
                     print(f"WARNING: Failed to save scanner state for session {session_id}")
                 return success
@@ -355,31 +369,6 @@ class SessionManager:
             
             time.sleep(300)  # Sleep for 5 minutes
 
-    def list_active_sessions(self) -> List[Dict[str, Any]]:
-        """List all active sessions for admin purposes."""
-        try:
-            session_keys = self.redis_client.keys("dnsrecon:session:*")
-            sessions = []
-            
-            for session_key in session_keys:
-                session_id = session_key.decode('utf-8').split(':')[-1]
-                session_data = self._get_session_data(session_id)
-                
-                if session_data:
-                    scanner = session_data.get('scanner')
-                    sessions.append({
-                        'session_id': session_id,
-                        'created_at': session_data.get('created_at'),
-                        'last_activity': session_data.get('last_activity'),
-                        'scanner_status': scanner.status if scanner else 'unknown',
-                        'current_target': scanner.current_target if scanner else None
-                    })
-            
-            return sessions
-        except Exception as e:
-            print(f"ERROR: Failed to list active sessions: {e}")
-            return []
-
     def get_statistics(self) -> Dict[str, Any]:
         """Get session manager statistics."""
         try:

providers/__init__.py

@@ -3,14 +3,15 @@ Data provider modules for DNSRecon.
 Contains implementations for various reconnaissance data sources.
 """
 
-from .base_provider import BaseProvider, RateLimiter
+from .base_provider import BaseProvider
 from .crtsh_provider import CrtShProvider
 from .dns_provider import DNSProvider
 from .shodan_provider import ShodanProvider
+from core.rate_limiter import GlobalRateLimiter
 
 __all__ = [
     'BaseProvider',
-    'RateLimiter', 
+    'GlobalRateLimiter', 
     'CrtShProvider',
     'DNSProvider',
     'ShodanProvider'

providers/base_provider.py

@@ -3,52 +3,18 @@
 import time
 import requests
 import threading
-import os
-import json
 from abc import ABC, abstractmethod
-from typing import List, Dict, Any, Optional, Tuple
+from typing import Dict, Any, Optional
 
 from core.logger import get_forensic_logger
-
-
-class RateLimiter:
-    """Simple rate limiter for API calls."""
-
-    def __init__(self, requests_per_minute: int):
-        """
-        Initialize rate limiter.
-
-        Args:
-            requests_per_minute: Maximum requests allowed per minute
-        """
-        self.requests_per_minute = requests_per_minute
-        self.min_interval = 60.0 / requests_per_minute
-        self.last_request_time = 0
-
-    def __getstate__(self):
-        """RateLimiter is fully picklable, return full state."""
-        return self.__dict__.copy()
-
-    def __setstate__(self, state):
-        """Restore RateLimiter state."""
-        self.__dict__.update(state)
-
-    def wait_if_needed(self) -> None:
-        """Wait if necessary to respect rate limits."""
-        current_time = time.time()
-        time_since_last = current_time - self.last_request_time
-
-        if time_since_last < self.min_interval:
-            sleep_time = self.min_interval - time_since_last
-            time.sleep(sleep_time)
-
-        self.last_request_time = time.time()
+from core.rate_limiter import GlobalRateLimiter
+from core.provider_result import ProviderResult
 
 
 class BaseProvider(ABC):
     """
     Abstract base class for all DNSRecon data providers.
-    Now supports session-specific configuration.
+    Now supports session-specific configuration and returns standardized ProviderResult objects.
     """
 
     def __init__(self, name: str, rate_limit: int = 60, timeout: int = 30, session_config=None):
@@ -70,30 +36,20 @@ class BaseProvider(ABC):
             # Fallback to global config for backwards compatibility
             from config import config as global_config
             self.config = global_config
-            actual_rate_limit = rate_limit
             actual_timeout = timeout
 
         self.name = name
-        self.rate_limiter = RateLimiter(actual_rate_limit)
         self.timeout = actual_timeout
         self._local = threading.local()
         self.logger = get_forensic_logger()
         self._stop_event = None
 
-        # Caching configuration (per session)
-        self.cache_dir = f'.cache/{id(self.config)}'  # Unique cache per session config
-        self.cache_expiry = 12 * 3600  # 12 hours in seconds
-        if not os.path.exists(self.cache_dir):
-            os.makedirs(self.cache_dir)
-
         # Statistics (per provider instance)
         self.total_requests = 0
         self.successful_requests = 0
         self.failed_requests = 0
         self.total_relationships_found = 0
 
-        print(f"Initialized {name} provider with session-specific config (rate: {actual_rate_limit}/min)")
-
     def __getstate__(self):
         """Prepare BaseProvider for pickling by excluding unpicklable objects."""
         state = self.__dict__.copy()
@@ -146,7 +102,7 @@ class BaseProvider(ABC):
         pass
 
     @abstractmethod
-    def query_domain(self, domain: str) -> List[Tuple[str, str, str, float, Dict[str, Any]]]:
+    def query_domain(self, domain: str) -> ProviderResult:
         """
         Query the provider for information about a domain.
 
@@ -154,12 +110,12 @@ class BaseProvider(ABC):
             domain: Domain to investigate
 
         Returns:
-            List of tuples: (source_node, target_node, relationship_type, confidence, raw_data)
+            ProviderResult containing standardized attributes and relationships
         """
         pass
 
     @abstractmethod
-    def query_ip(self, ip: str) -> List[Tuple[str, str, str, float, Dict[str, Any]]]:
+    def query_ip(self, ip: str) -> ProviderResult:
         """
         Query the provider for information about an IP address.
 
@@ -167,61 +123,23 @@ class BaseProvider(ABC):
             ip: IP address to investigate
 
         Returns:
-            List of tuples: (source_node, target_node, relationship_type, confidence, raw_data)
+            ProviderResult containing standardized attributes and relationships
         """
         pass
 
     def make_request(self, url: str, method: str = "GET",
                     params: Optional[Dict[str, Any]] = None,
                     headers: Optional[Dict[str, str]] = None,
-                    target_indicator: str = "",
-                    max_retries: int = 3) -> Optional[requests.Response]:
+                    target_indicator: str = "") -> Optional[requests.Response]:
         """
-        Make a rate-limited HTTP request with aggressive stop signal handling.
-        Terminates immediately when stop is requested, including during retries.
+        Make a rate-limited HTTP request.
+        FIXED: Returns response without automatically raising HTTPError exceptions.
+        Individual providers should handle status codes appropriately.
         """
-        # Check for cancellation before starting
         if self._is_stop_requested():
             print(f"Request cancelled before start: {url}")
             return None
 
-        # Create a unique cache key
-        cache_key = f"{self.name}_{hash(f'{method}:{url}:{json.dumps(params, sort_keys=True)}')}.json"
-        cache_path = os.path.join(self.cache_dir, cache_key)
-
-        # Check cache
-        if os.path.exists(cache_path):
-            cache_age = time.time() - os.path.getmtime(cache_path)
-            if cache_age < self.cache_expiry:
-                print(f"Returning cached response for: {url}")
-                with open(cache_path, 'r') as f:
-                    cached_data = json.load(f)
-                    response = requests.Response()
-                    response.status_code = cached_data['status_code']
-                    response._content = cached_data['content'].encode('utf-8')
-                    response.headers = cached_data['headers']
-                    return response
-
-        # Determine effective max_retries based on stop signal
-        effective_max_retries = 0 if self._is_stop_requested() else max_retries
-        last_exception = None
-
-        for attempt in range(effective_max_retries + 1):
-            # AGGRESSIVE: Check for cancellation before each attempt
-            if self._is_stop_requested():
-                print(f"Request cancelled during attempt {attempt + 1}: {url}")
-                return None
-
-            # Apply rate limiting with cancellation awareness
-            if not self._wait_with_cancellation_check():
-                print(f"Request cancelled during rate limiting: {url}")
-                return None
-
-            # AGGRESSIVE: Final check before making HTTP request
-            if self._is_stop_requested():
-                print(f"Request cancelled before HTTP call: {url}")
-                return None
-
         start_time = time.time()
         response = None
         error = None
@@ -229,42 +147,39 @@ class BaseProvider(ABC):
         try:
             self.total_requests += 1
 
-                # Prepare request
-                request_headers = self.session.headers.copy()
+            request_headers = dict(self.session.headers).copy()
             if headers:
                 request_headers.update(headers)
 
-                print(f"Making {method} request to: {url} (attempt {attempt + 1})")
+            print(f"Making {method} request to: {url}")
 
-                # AGGRESSIVE: Use much shorter timeout if termination is requested
-                request_timeout = self.timeout
-                if self._is_stop_requested():
-                    request_timeout = 2  # Max 2 seconds if termination requested
-                    print(f"Stop requested - using short timeout: {request_timeout}s")
-
-                # Make request
             if method.upper() == "GET":
                 response = self.session.get(
                     url,
                     params=params,
                     headers=request_headers,
-                        timeout=request_timeout
+                    timeout=self.timeout
                 )
             elif method.upper() == "POST":
                 response = self.session.post(
                     url,
                     json=params,
                     headers=request_headers,
-                        timeout=request_timeout
+                    timeout=self.timeout
                 )
             else:
                 raise ValueError(f"Unsupported HTTP method: {method}")
 
             print(f"Response status: {response.status_code}")
-                response.raise_for_status()
-                self.successful_requests += 1
             
-                # Success - log, cache, and return
+            # FIXED: Don't automatically raise for HTTP error status codes
+            # Let individual providers handle status codes appropriately
+            # Only count 2xx responses as successful
+            if 200 <= response.status_code < 300:
+                self.successful_requests += 1
+            else:
+                self.failed_requests += 1
+            
             duration_ms = (time.time() - start_time) * 1000
             self.logger.log_api_request(
                 provider=self.name,
@@ -276,53 +191,12 @@ class BaseProvider(ABC):
                 error=None,
                 target_indicator=target_indicator
             )
-                # Cache the successful response to disk
-                with open(cache_path, 'w') as f:
-                    json.dump({
-                        'status_code': response.status_code,
-                        'content': response.text,
-                        'headers': dict(response.headers)
-                    }, f)
+            
             return response
 
         except requests.exceptions.RequestException as e:
             error = str(e)
             self.failed_requests += 1
-                print(f"Request failed (attempt {attempt + 1}): {error}")
-                last_exception = e
-                
-                # AGGRESSIVE: Immediately abort retries if stop requested
-                if self._is_stop_requested():
-                    print(f"Stop requested - aborting retries for: {url}")
-                    break
-                
-                # Check if we should retry (but only if stop not requested)
-                if attempt < effective_max_retries and self._should_retry(e):
-                    # Use a longer, more respectful backoff for 429 errors
-                    if isinstance(e, requests.exceptions.HTTPError) and e.response and e.response.status_code == 429:
-                        # Start with a 10-second backoff and increase exponentially
-                        backoff_time = 10 * (2 ** attempt)
-                        print(f"Rate limit hit. Retrying in {backoff_time} seconds...")
-                    else:
-                        backoff_time = min(1.0, (2 ** attempt) * 0.5)  # Shorter backoff for other errors
-                        print(f"Retrying in {backoff_time} seconds...")
-                    
-                    # AGGRESSIVE: Much shorter backoff and more frequent checking
-                    if not self._sleep_with_cancellation_check(backoff_time):
-                        print(f"Stop requested during backoff - aborting: {url}")
-                        return None
-                    continue
-                else:
-                    break
-
-            except Exception as e:
-                error = f"Unexpected error: {str(e)}"
-                self.failed_requests += 1
-                print(f"Unexpected error: {error}")
-                last_exception = e
-                break
-
-        # All attempts failed - log and return None
             duration_ms = (time.time() - start_time) * 1000
             self.logger.log_api_request(
                 provider=self.name,
@@ -334,11 +208,7 @@ class BaseProvider(ABC):
                 error=error,
                 target_indicator=target_indicator
             )
-        
-        if error and last_exception:
-            raise last_exception
-        
-        return None
+            raise e
 
     def _is_stop_requested(self) -> bool:
         """
@@ -348,44 +218,6 @@ class BaseProvider(ABC):
             return True
         return False
 
-
-    def _wait_with_cancellation_check(self) -> bool:
-        """
-        Wait for rate limiting while aggressively checking for cancellation.
-        Returns False if cancelled during wait.
-        """
-        current_time = time.time()
-        time_since_last = current_time - self.rate_limiter.last_request_time
-
-        if time_since_last < self.rate_limiter.min_interval:
-            sleep_time = self.rate_limiter.min_interval - time_since_last
-            if not self._sleep_with_cancellation_check(sleep_time):
-                return False
-
-        self.rate_limiter.last_request_time = time.time()
-        return True
-
-    def _sleep_with_cancellation_check(self, sleep_time: float) -> bool:
-        """
-        Sleep for the specified time while aggressively checking for cancellation.
-        
-        Args:
-            sleep_time: Time to sleep in seconds
-            
-        Returns:
-            bool: True if sleep completed, False if cancelled
-        """
-        sleep_start = time.time()
-        check_interval = 0.05  # Check every 50ms for aggressive responsiveness
-        
-        while time.time() - sleep_start < sleep_time:
-            if self._is_stop_requested():
-                return False
-            remaining_time = sleep_time - (time.time() - sleep_start)
-            time.sleep(min(check_interval, remaining_time))
-        
-        return True
-
     def set_stop_event(self, stop_event: threading.Event) -> None:
         """
         Set the stop event for this provider to enable cancellation.
@@ -395,28 +227,6 @@ class BaseProvider(ABC):
         """
         self._stop_event = stop_event
 
-    def _should_retry(self, exception: requests.exceptions.RequestException) -> bool:
-        """
-        Determine if a request should be retried based on the exception.
-        
-        Args:
-            exception: The request exception that occurred
-            
-        Returns:
-            True if the request should be retried
-        """
-        # Retry on connection errors and timeouts
-        if isinstance(exception, (requests.exceptions.ConnectionError, 
-                                requests.exceptions.Timeout)):
-            return True
-        
-        if isinstance(exception, requests.exceptions.HTTPError):
-            if hasattr(exception, 'response') and exception.response:
-                # Retry on server errors (5xx) AND on rate-limiting errors (429)
-                return exception.response.status_code >= 500 or exception.response.status_code == 429
-        
-        return False
-
     def log_relationship_discovery(self, source_node: str, target_node: str,
                                  relationship_type: str,
                                  confidence_score: float,
@@ -459,5 +269,5 @@ class BaseProvider(ABC):
             'failed_requests': self.failed_requests,
             'success_rate': (self.successful_requests / self.total_requests * 100) if self.total_requests > 0 else 0,
             'relationships_found': self.total_relationships_found,
-            'rate_limit': self.rate_limiter.requests_per_minute
+            'rate_limit': self.config.get_rate_limit(self.name)
         }

providers/crtsh_provider.py

@@ -1,27 +1,26 @@
-"""
-Certificate Transparency provider using crt.sh.
-Discovers domain relationships through certificate SAN analysis with comprehensive certificate tracking.
-Stores certificates as metadata on domain nodes rather than creating certificate nodes.
-"""
+# dnsrecon/providers/crtsh_provider.py
 
 import json
 import re
-from typing import List, Dict, Any, Tuple, Set
+from pathlib import Path
+from typing import List, Dict, Any, Set
 from urllib.parse import quote
 from datetime import datetime, timezone
 import requests
 
 from .base_provider import BaseProvider
+from core.provider_result import ProviderResult
 from utils.helpers import _is_valid_domain
 
 
 class CrtShProvider(BaseProvider):
     """
     Provider for querying crt.sh certificate transparency database.
-    Now uses session-specific configuration and caching.
+    FIXED: Now properly creates domain and CA nodes instead of large entities.
+    Returns standardized ProviderResult objects with caching support.
     """
     
-    def __init__(self, session_config=None):
+    def __init__(self, name=None, session_config=None):
         """Initialize CrtSh provider with session-specific configuration."""
         super().__init__(
             name="crtsh",
@@ -32,6 +31,13 @@ class CrtShProvider(BaseProvider):
         self.base_url = "https://crt.sh/"
         self._stop_event = None
         
+        # Initialize cache directory (separate from BaseProvider's HTTP cache)
+        self.domain_cache_dir = Path('cache') / 'crtsh'
+        self.domain_cache_dir.mkdir(parents=True, exist_ok=True)
+        
+        # Compile regex for date filtering for efficiency
+        self.date_pattern = re.compile(r'^\d{4}-\d{2}-\d{2}[ T]\d{2}:\d{2}:\d{2}')
+    
     def get_name(self) -> str:
         """Return the provider name."""
         return "crtsh"
@@ -49,100 +55,359 @@ class CrtShProvider(BaseProvider):
         return {'domains': True, 'ips': False}
 
     def is_available(self) -> bool:
-        """
-        Check if the provider is configured to be used.
-        This method is intentionally simple and does not perform a network request
-        to avoid blocking application startup.
-        """
+        """Check if the provider is configured to be used."""
         return True
     
-    def _parse_certificate_date(self, date_string: str) -> datetime:
-        """
-        Parse certificate date from crt.sh format.
+    def _get_cache_file_path(self, domain: str) -> Path:
+        """Generate cache file path for a domain."""
+        safe_domain = domain.replace('.', '_').replace('/', '_').replace('\\', '_')
+        return self.domain_cache_dir / f"{safe_domain}.json"
     
-        Args:
-            date_string: Date string from crt.sh API
-
-        Returns:
-            Parsed datetime object in UTC
+    def _get_cache_status(self, cache_file_path: Path) -> str:
         """
-        if not date_string:
-            raise ValueError("Empty date string")
+        Check cache status for a domain.
+        Returns: 'not_found', 'fresh', or 'stale'
+        """
+        if not cache_file_path.exists():
+            return "not_found"
         
         try:
-            # Handle various possible formats from crt.sh
-            if date_string.endswith('Z'):
-                return datetime.fromisoformat(date_string[:-1]).replace(tzinfo=timezone.utc)
-            elif '+' in date_string or date_string.endswith('UTC'):
-                # Handle timezone-aware strings
-                date_string = date_string.replace('UTC', '').strip()
-                if '+' in date_string:
-                    date_string = date_string.split('+')[0]
-                return datetime.fromisoformat(date_string).replace(tzinfo=timezone.utc)
+            with open(cache_file_path, 'r') as f:
+                cache_data = json.load(f)
+            
+            last_query_str = cache_data.get("last_upstream_query")
+            if not last_query_str:
+                return "stale"
+            
+            last_query = datetime.fromisoformat(last_query_str.replace('Z', '+00:00'))
+            hours_since_query = (datetime.now(timezone.utc) - last_query).total_seconds() / 3600
+            
+            cache_timeout = self.config.cache_timeout_hours
+            if hours_since_query < cache_timeout:
+                return "fresh"
             else:
-                # Assume UTC if no timezone specified
-                return datetime.fromisoformat(date_string).replace(tzinfo=timezone.utc)
-        except Exception as e:
-            # Fallback: try parsing without timezone info and assume UTC
-            try:
-                return datetime.strptime(date_string[:19], "%Y-%m-%dT%H:%M:%S").replace(tzinfo=timezone.utc)
-            except Exception:
-                raise ValueError(f"Unable to parse date: {date_string}") from e
+                return "stale"
                 
-    def _is_cert_valid(self, cert_data: Dict[str, Any]) -> bool:
+        except (json.JSONDecodeError, ValueError, KeyError) as e:
+            self.logger.logger.warning(f"Invalid cache file format for {cache_file_path}: {e}")
+            return "stale"
+
+    def query_domain(self, domain: str) -> ProviderResult:
         """
-        Check if a certificate is currently valid based on its expiry date.
+        FIXED: Query crt.sh for certificates containing the domain.
+        Now properly creates domain and CA nodes instead of large entities.
         
         Args:
-            cert_data: Certificate data from crt.sh
+            domain: Domain to investigate
             
         Returns:
-            True if certificate is currently valid (not expired)
+            ProviderResult containing discovered relationships and attributes
         """
+        if not _is_valid_domain(domain):
+            return ProviderResult()
+        
+        if self._stop_event and self._stop_event.is_set():
+            return ProviderResult()
+
+        cache_file = self._get_cache_file_path(domain)
+        cache_status = self._get_cache_status(cache_file)
+        
+        result = ProviderResult()
+
         try:
-            not_after_str = cert_data.get('not_after')
-            if not not_after_str:
-                return False
+            if cache_status == "fresh":
+                result = self._load_from_cache(cache_file)
+                self.logger.logger.info(f"Using fresh cached crt.sh data for {domain}")
             
-            not_after_date = self._parse_certificate_date(not_after_str)
-            not_before_str = cert_data.get('not_before')
+            else:  # "stale" or "not_found"
+                # Query the API for the latest certificates
+                new_raw_certs = self._query_crtsh_api(domain)
                 
-            now = datetime.now(timezone.utc)
+                if self._stop_event and self._stop_event.is_set():
+                    return ProviderResult()
 
-            # Check if certificate is within valid date range
-            is_not_expired = not_after_date > now
+                # Combine with old data if cache is stale
+                if cache_status == "stale":
+                    old_raw_certs = self._load_raw_data_from_cache(cache_file)
+                    combined_certs = old_raw_certs + new_raw_certs
                     
-            if not_before_str:
-                not_before_date = self._parse_certificate_date(not_before_str)
-                is_not_before_valid = not_before_date <= now
-                return is_not_expired and is_not_before_valid
+                    # Deduplicate the combined list
+                    seen_ids = set()
+                    unique_certs = []
+                    for cert in combined_certs:
+                        cert_id = cert.get('id')
+                        if cert_id not in seen_ids:
+                            unique_certs.append(cert)
+                            seen_ids.add(cert_id)
                     
-            return is_not_expired
+                    raw_certificates_to_process = unique_certs
+                    self.logger.logger.info(f"Refreshed and merged cache for {domain}. Total unique certs: {len(raw_certificates_to_process)}")
+                else:  # "not_found"
+                    raw_certificates_to_process = new_raw_certs
                 
+                # FIXED: Process certificates to create proper domain and CA nodes
+                result = self._process_certificates_to_result_fixed(domain, raw_certificates_to_process)
+                self.logger.logger.info(f"Created fresh result for {domain} ({result.get_relationship_count()} relationships)")
+
+                # Save the new result and the raw data to the cache
+                self._save_result_to_cache(cache_file, result, raw_certificates_to_process, domain)
+
+        except requests.exceptions.RequestException as e:
+            self.logger.logger.error(f"API query failed for {domain}: {e}")
+            if cache_status != "not_found":
+                result = self._load_from_cache(cache_file)
+                self.logger.logger.warning(f"Using stale cache for {domain} due to API failure.")
+            else:
+                raise e  # Re-raise if there's no cache to fall back on
+
+        return result
+
+    def query_ip(self, ip: str) -> ProviderResult:
+        """
+        Query crt.sh for certificates containing the IP address.
+        Note: crt.sh doesn't typically index by IP, so this returns empty results.
+        
+        Args:
+            ip: IP address to investigate
+            
+        Returns:
+            Empty ProviderResult (crt.sh doesn't support IP-based certificate queries effectively)
+        """
+        return ProviderResult()
+
+    def _load_from_cache(self, cache_file_path: Path) -> ProviderResult:
+        """Load processed crt.sh data from a cache file."""
+        try:
+            with open(cache_file_path, 'r') as f:
+                cache_content = json.load(f)
+            
+            result = ProviderResult()
+            
+            # Reconstruct relationships
+            for rel_data in cache_content.get("relationships", []):
+                result.add_relationship(
+                    source_node=rel_data["source_node"],
+                    target_node=rel_data["target_node"],
+                    relationship_type=rel_data["relationship_type"],
+                    provider=rel_data["provider"],
+                    confidence=rel_data["confidence"],
+                    raw_data=rel_data.get("raw_data", {})
+                )
+            
+            # Reconstruct attributes
+            for attr_data in cache_content.get("attributes", []):
+                result.add_attribute(
+                    target_node=attr_data["target_node"],
+                    name=attr_data["name"],
+                    value=attr_data["value"],
+                    attr_type=attr_data["type"],
+                    provider=attr_data["provider"],
+                    confidence=attr_data["confidence"],
+                    metadata=attr_data.get("metadata", {})
+                )
+            
+            return result
+            
+        except (json.JSONDecodeError, FileNotFoundError, KeyError) as e:
+            self.logger.logger.error(f"Failed to load cached certificates from {cache_file_path}: {e}")
+            return ProviderResult()
+
+    def _load_raw_data_from_cache(self, cache_file_path: Path) -> List[Dict[str, Any]]:
+        """Load only the raw certificate data from a cache file."""
+        try:
+            with open(cache_file_path, 'r') as f:
+                cache_content = json.load(f)
+            return cache_content.get("raw_certificates", [])
+        except (json.JSONDecodeError, FileNotFoundError):
+            return []
+
+    def _save_result_to_cache(self, cache_file_path: Path, result: ProviderResult, raw_certificates: List[Dict[str, Any]], domain: str) -> None:
+        """Save processed crt.sh result and raw data to a cache file."""
+        try:
+            cache_data = {
+                "domain": domain,
+                "last_upstream_query": datetime.now(timezone.utc).isoformat(),
+                "raw_certificates": raw_certificates, # Store the raw data for deduplication
+                "relationships": [
+                    {
+                        "source_node": rel.source_node,
+                        "target_node": rel.target_node,
+                        "relationship_type": rel.relationship_type,
+                        "confidence": rel.confidence,
+                        "provider": rel.provider,
+                        "raw_data": rel.raw_data
+                    } for rel in result.relationships
+                ],
+                "attributes": [
+                    {
+                        "target_node": attr.target_node,
+                        "name": attr.name,
+                        "value": attr.value,
+                        "type": attr.type,
+                        "provider": attr.provider,
+                        "confidence": attr.confidence,
+                        "metadata": attr.metadata
+                    } for attr in result.attributes
+                ]
+            }
+            cache_file_path.parent.mkdir(parents=True, exist_ok=True)
+            with open(cache_file_path, 'w') as f:
+                json.dump(cache_data, f, separators=(',', ':'), default=str)
         except Exception as e:
-            self.logger.logger.debug(f"Certificate validity check failed: {e}")
+            self.logger.logger.warning(f"Failed to save cache file for {domain}: {e}")
+
+    def _query_crtsh_api(self, domain: str) -> List[Dict[str, Any]]:
+        """Query crt.sh API for raw certificate data."""
+        url = f"{self.base_url}?q={quote(domain)}&output=json"
+        response = self.make_request(url, target_indicator=domain)
+        
+        if not response or response.status_code != 200:
+            raise requests.exceptions.RequestException(f"crt.sh API returned status {response.status_code if response else 'None'}")
+        
+        try:
+            certificates = response.json()
+        except json.JSONDecodeError:
+            self.logger.logger.error(f"crt.sh returned invalid JSON for {domain}")
+            return []
+
+        if not certificates:
+            return []
+        
+        return certificates
+
+    def _process_certificates_to_result_fixed(self, query_domain: str, certificates: List[Dict[str, Any]]) -> ProviderResult:
+        """
+        FIXED: Process certificates to create proper domain and CA nodes.
+        Now creates individual domain nodes instead of large entities.
+        """
+        result = ProviderResult()
+
+        if self._stop_event and self._stop_event.is_set():
+            self.logger.logger.info(f"CrtSh processing cancelled before processing for domain: {query_domain}")
+            return result
+
+        all_discovered_domains = set()
+        processed_issuers = set()
+
+        for i, cert_data in enumerate(certificates):
+            if i % 10 == 0 and self._stop_event and self._stop_event.is_set():
+                self.logger.logger.info(f"CrtSh processing cancelled at certificate {i} for domain: {query_domain}")
+                break
+
+            # Extract all domains from this certificate
+            cert_domains = self._extract_domains_from_certificate(cert_data)
+            all_discovered_domains.update(cert_domains)
+
+            # FIXED: Create CA nodes for certificate issuers (not as domain metadata)
+            issuer_name = self._parse_issuer_organization(cert_data.get('issuer_name', ''))
+            if issuer_name and issuer_name not in processed_issuers:
+                # Create relationship from query domain to CA
+                result.add_relationship(
+                    source_node=query_domain,
+                    target_node=issuer_name,
+                    relationship_type='crtsh_cert_issuer',
+                    provider=self.name,
+                    confidence=0.95,
+                    raw_data={'issuer_dn': cert_data.get('issuer_name', '')}
+                )
+                processed_issuers.add(issuer_name)
+
+            # Add certificate metadata to each domain in this certificate
+            cert_metadata = self._extract_certificate_metadata(cert_data)
+            for cert_domain in cert_domains:
+                if not _is_valid_domain(cert_domain):
+                    continue
+
+                # Add certificate attributes to the domain
+                for key, value in cert_metadata.items():
+                    if value is not None:
+                        result.add_attribute(
+                            target_node=cert_domain,
+                            name=f"cert_{key}",
+                            value=value,
+                            attr_type='certificate_data',
+                            provider=self.name,
+                            confidence=0.9,
+                            metadata={'certificate_id': cert_data.get('id')}
+                        )
+
+        if self._stop_event and self._stop_event.is_set():
+            self.logger.logger.info(f"CrtSh query cancelled before relationship creation for domain: {query_domain}")
+            return result
+
+        # FIXED: Create selective relationships to avoid large entities
+        # Only create relationships to domains that are closely related
+        for discovered_domain in all_discovered_domains:
+            if discovered_domain == query_domain:
+                continue
+
+            if not _is_valid_domain(discovered_domain):
+                continue
+
+            # FIXED: Only create relationships for domains that share a meaningful connection
+            # This prevents creating too many relationships that trigger large entity creation
+            if self._should_create_relationship(query_domain, discovered_domain):
+                confidence = self._calculate_domain_relationship_confidence(
+                    query_domain, discovered_domain, [], all_discovered_domains
+                )
+
+                result.add_relationship(
+                    source_node=query_domain,
+                    target_node=discovered_domain,
+                    relationship_type='crtsh_san_certificate',
+                    provider=self.name,
+                    confidence=confidence,
+                    raw_data={'relationship_type': 'certificate_discovery'}
+                )
+
+                self.log_relationship_discovery(
+                    source_node=query_domain,
+                    target_node=discovered_domain,
+                    relationship_type='crtsh_san_certificate',
+                    confidence_score=confidence,
+                    raw_data={'relationship_type': 'certificate_discovery'},
+                    discovery_method="certificate_transparency_analysis"
+                )
+
+        self.logger.logger.info(f"CrtSh processing completed for {query_domain}: {len(all_discovered_domains)} domains, {result.get_relationship_count()} relationships")
+        return result
+
+    def _should_create_relationship(self, source_domain: str, target_domain: str) -> bool:
+        """
+        FIXED: Determine if a relationship should be created between two domains.
+        This helps avoid creating too many relationships that trigger large entity creation.
+        """
+        # Always create relationships for subdomains
+        if target_domain.endswith(f'.{source_domain}') or source_domain.endswith(f'.{target_domain}'):
+            return True
+        
+        # Create relationships for domains that share a common parent (up to 2 levels)
+        source_parts = source_domain.split('.')
+        target_parts = target_domain.split('.')
+        
+        # Check if they share the same root domain (last 2 parts)
+        if len(source_parts) >= 2 and len(target_parts) >= 2:
+            source_root = '.'.join(source_parts[-2:])
+            target_root = '.'.join(target_parts[-2:])
+            return source_root == target_root
+        
         return False
 
     def _extract_certificate_metadata(self, cert_data: Dict[str, Any]) -> Dict[str, Any]:
-        """
-        Extract comprehensive metadata from certificate data.
+        """Extract comprehensive metadata from certificate data."""
+        raw_issuer_name = cert_data.get('issuer_name', '')
+        parsed_issuer_name = self._parse_issuer_organization(raw_issuer_name)
         
-        Args:
-            cert_data: Raw certificate data from crt.sh
-            
-        Returns:
-            Comprehensive certificate metadata dictionary
-        """
         metadata = {
             'certificate_id': cert_data.get('id'),
             'serial_number': cert_data.get('serial_number'),
-            'issuer_name': cert_data.get('issuer_name'),
+            'issuer_name': parsed_issuer_name,
             'issuer_ca_id': cert_data.get('issuer_ca_id'),
             'common_name': cert_data.get('common_name'),
             'not_before': cert_data.get('not_before'),
             'not_after': cert_data.get('not_after'),
             'entry_timestamp': cert_data.get('entry_timestamp'),
-            'source': 'crt.sh'
+            'source': 'crtsh'
         }
         
         try:
@@ -154,9 +419,9 @@ class CrtShProvider(BaseProvider):
                 metadata['is_currently_valid'] = self._is_cert_valid(cert_data)
                 metadata['expires_soon'] = (not_after - datetime.now(timezone.utc)).days <= 30
                 
-                # Add human-readable dates
-                metadata['not_before'] = not_before.strftime('%Y-%m-%d %H:%M:%S UTC')
-                metadata['not_after'] = not_after.strftime('%Y-%m-%d %H:%M:%S UTC')
+                # Keep raw date format or convert to standard format
+                metadata['not_before'] = not_before.isoformat()
+                metadata['not_after'] = not_after.isoformat()
                 
         except Exception as e:
             self.logger.logger.debug(f"Error computing certificate metadata: {e}")
@@ -165,328 +430,73 @@ class CrtShProvider(BaseProvider):
         
         return metadata
 
-    def query_domain(self, domain: str) -> List[Tuple[str, str, str, float, Dict[str, Any]]]:
-        """
-        Query crt.sh for certificates containing the domain.
-        """
-        if not _is_valid_domain(domain):
-            return []
-        
-        # Check for cancellation before starting
-        if self._stop_event and self._stop_event.is_set():
-            print(f"CrtSh query cancelled before start for domain: {domain}")
-            return []
-        
-        relationships = []
+    def _parse_issuer_organization(self, issuer_dn: str) -> str:
+        """Parse the issuer Distinguished Name to extract just the organization name."""
+        if not issuer_dn:
+            return issuer_dn
         
         try:
-            # Query crt.sh for certificates
-            url = f"{self.base_url}?q={quote(domain)}&output=json"
-            response = self.make_request(url, target_indicator=domain, max_retries=3)
+            components = [comp.strip() for comp in issuer_dn.split(',')]
             
-            if not response or response.status_code != 200:
-                return []
+            for component in components:
+                if component.startswith('O='):
+                    org_name = component[2:].strip()
+                    if org_name.startswith('"') and org_name.endswith('"'):
+                        org_name = org_name[1:-1]
+                    return org_name
             
-            # Check for cancellation after request
-            if self._stop_event and self._stop_event.is_set():
-                print(f"CrtSh query cancelled after request for domain: {domain}")
-                return []
+            return issuer_dn
             
-            certificates = response.json()
+        except Exception as e:
+            self.logger.logger.debug(f"Failed to parse issuer DN '{issuer_dn}': {e}")
+            return issuer_dn
 
-            if not certificates:
-                return []
+    def _parse_certificate_date(self, date_string: str) -> datetime:
+        """Parse certificate date from crt.sh format."""
+        if not date_string:
+            raise ValueError("Empty date string")
 
-            # Check for cancellation before processing
-            if self._stop_event and self._stop_event.is_set():
-                print(f"CrtSh query cancelled before processing for domain: {domain}")
-                return []
-
-            # Aggregate certificate data by domain
-            domain_certificates = {}
-            all_discovered_domains = set()
-            
-            # Process certificates with cancellation checking
-            for i, cert_data in enumerate(certificates):
-                # Check for cancellation every 5 certificates instead of 10 for faster response
-                if i % 5 == 0 and self._stop_event and self._stop_event.is_set():
-                    print(f"CrtSh processing cancelled at certificate {i} for domain: {domain}")
-                    break
-                    
-                cert_metadata = self._extract_certificate_metadata(cert_data)
-                cert_domains = self._extract_domains_from_certificate(cert_data)
-                
-                # Add all domains from this certificate to our tracking
-                for cert_domain in cert_domains:
-                    # Additional stop check during domain processing
-                    if i % 20 == 0 and self._stop_event and self._stop_event.is_set():
-                        print(f"CrtSh domain processing cancelled for domain: {domain}")
-                        break
-                        
-                    if not _is_valid_domain(cert_domain):
-                        continue
-                    
-                    all_discovered_domains.add(cert_domain)
-                    
-                    # Initialize domain certificate list if needed
-                    if cert_domain not in domain_certificates:
-                        domain_certificates[cert_domain] = []
-                    
-                    # Add this certificate to the domain's certificate list
-                    domain_certificates[cert_domain].append(cert_metadata)
-            
-            # Final cancellation check before creating relationships
-            if self._stop_event and self._stop_event.is_set():
-                print(f"CrtSh query cancelled before relationship creation for domain: {domain}")
-                return []
-
-            # Create relationships from query domain to ALL discovered domains with stop checking
-            for i, discovered_domain in enumerate(all_discovered_domains):
-                if discovered_domain == domain:
-                    continue  # Skip self-relationships
-                
-                # Check for cancellation every 10 relationships
-                if i % 10 == 0 and self._stop_event and self._stop_event.is_set():
-                    print(f"CrtSh relationship creation cancelled for domain: {domain}")
-                    break
-
-                if not _is_valid_domain(discovered_domain):
-                    continue
-                
-                # Get certificates for both domains
-                query_domain_certs = domain_certificates.get(domain, [])
-                discovered_domain_certs = domain_certificates.get(discovered_domain, [])
-                
-                # Find shared certificates (for metadata purposes)
-                shared_certificates = self._find_shared_certificates(query_domain_certs, discovered_domain_certs)
-                
-                # Calculate confidence based on relationship type and shared certificates
-                confidence = self._calculate_domain_relationship_confidence(
-                    domain, discovered_domain, shared_certificates, all_discovered_domains
-                )
-                
-                # Create comprehensive raw data for the relationship
-                relationship_raw_data = {
-                    'relationship_type': 'certificate_discovery',
-                    'shared_certificates': shared_certificates,
-                    'total_shared_certs': len(shared_certificates),
-                    'discovery_context': self._determine_relationship_context(discovered_domain, domain),
-                    'domain_certificates': {
-                        domain: self._summarize_certificates(query_domain_certs),
-                        discovered_domain: self._summarize_certificates(discovered_domain_certs)
-                    }
-                }
-                
-                # Create domain -> domain relationship
-                relationships.append((
-                    domain,
-                    discovered_domain,
-                    'san_certificate',
-                    confidence,
-                    relationship_raw_data
-                ))
-                
-                # Log the relationship discovery
-                self.log_relationship_discovery(
-                    source_node=domain,
-                    target_node=discovered_domain,
-                    relationship_type='san_certificate',
-                    confidence_score=confidence,
-                    raw_data=relationship_raw_data,
-                    discovery_method="certificate_transparency_analysis"
-                )
-
-        except json.JSONDecodeError as e:
-            self.logger.logger.error(f"Failed to parse JSON response from crt.sh: {e}")
-        except requests.exceptions.RequestException as e:
-            self.logger.logger.error(f"HTTP request to crt.sh failed: {e}")
-
-        
-        return relationships
-
-    def _find_shared_certificates(self, certs1: List[Dict[str, Any]], certs2: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
-        """
-        Find certificates that are shared between two domain certificate lists.
-        
-        Args:
-            certs1: First domain's certificates
-            certs2: Second domain's certificates
-            
-        Returns:
-            List of shared certificate metadata
-        """
-        shared = []
-        
-        # Create a set of certificate IDs from the first list for quick lookup
-        cert1_ids = {cert.get('certificate_id') for cert in certs1 if cert.get('certificate_id')}
-        
-        # Find certificates in the second list that match
-        for cert in certs2:
-            if cert.get('certificate_id') in cert1_ids:
-                shared.append(cert)
-        
-        return shared
-
-    def _summarize_certificates(self, certificates: List[Dict[str, Any]]) -> Dict[str, Any]:
-        """
-        Create a summary of certificates for a domain.
-        
-        Args:
-            certificates: List of certificate metadata
-            
-        Returns:
-            Summary dictionary with aggregate statistics
-        """
-        if not certificates:
-            return {
-                'total_certificates': 0,
-                'valid_certificates': 0,
-                'expired_certificates': 0,
-                'expires_soon_count': 0,
-                'unique_issuers': [],
-                'latest_certificate': None,
-                'has_valid_cert': False
-            }
-        
-        valid_count = sum(1 for cert in certificates if cert.get('is_currently_valid'))
-        expired_count = len(certificates) - valid_count
-        expires_soon_count = sum(1 for cert in certificates if cert.get('expires_soon'))
-        
-        # Get unique issuers
-        unique_issuers = list(set(cert.get('issuer_name') for cert in certificates if cert.get('issuer_name')))
-        
-        # Find the most recent certificate
-        latest_cert = None
-        latest_date = None
-        
-        for cert in certificates:
         try:
-                if cert.get('not_before'):
-                    cert_date = self._parse_certificate_date(cert['not_before'])
-                    if latest_date is None or cert_date > latest_date:
-                        latest_date = cert_date
-                        latest_cert = cert
+            if date_string.endswith('Z'):
+                return datetime.fromisoformat(date_string[:-1]).replace(tzinfo=timezone.utc)
+            elif '+' in date_string or date_string.endswith('UTC'):
+                date_string = date_string.replace('UTC', '').strip()
+                if '+' in date_string:
+                    date_string = date_string.split('+')[0]
+                return datetime.fromisoformat(date_string).replace(tzinfo=timezone.utc)
+            else:
+                return datetime.fromisoformat(date_string).replace(tzinfo=timezone.utc)
+        except Exception as e:
+            try:
+                return datetime.strptime(date_string[:19], "%Y-%m-%dT%H:%M:%S").replace(tzinfo=timezone.utc)
             except Exception:
-                continue
+                raise ValueError(f"Unable to parse date: {date_string}") from e
 
-        return {
-            'total_certificates': len(certificates),
-            'valid_certificates': valid_count,
-            'expired_certificates': expired_count,
-            'expires_soon_count': expires_soon_count,
-            'unique_issuers': unique_issuers,
-            'latest_certificate': latest_cert,
-            'has_valid_cert': valid_count > 0,
-            'certificate_details': certificates  # Full details for forensic analysis
-        }
+    def _is_cert_valid(self, cert_data: Dict[str, Any]) -> bool:
+        """Check if a certificate is currently valid based on its expiry date."""
+        try:
+            not_after_str = cert_data.get('not_after')
+            if not not_after_str:
+                return False
 
-    def _calculate_domain_relationship_confidence(self, domain1: str, domain2: str, 
-                                                shared_certificates: List[Dict[str, Any]],
-                                                all_discovered_domains: Set[str]) -> float:
-        """
-        Calculate confidence score for domain relationship based on various factors.
+            not_after_date = self._parse_certificate_date(not_after_str)
+            not_before_str = cert_data.get('not_before')
 
-        Args:
-            domain1: Source domain (query domain)
-            domain2: Target domain (discovered domain)
-            shared_certificates: List of shared certificate metadata
-            all_discovered_domains: All domains discovered in this query
+            now = datetime.now(timezone.utc)
+            is_not_expired = not_after_date > now
 
-        Returns:
-            Confidence score between 0.0 and 1.0
-        """
-        base_confidence = 0.9
+            if not_before_str:
+                not_before_date = self._parse_certificate_date(not_before_str)
+                is_not_before_valid = not_before_date <= now
+                return is_not_expired and is_not_before_valid
 
-        # Adjust confidence based on domain relationship context
-        relationship_context = self._determine_relationship_context(domain2, domain1)
+            return is_not_expired
 
-        if relationship_context == 'exact_match':
-            context_bonus = 0.0  # This shouldn't happen, but just in case
-        elif relationship_context == 'subdomain':
-            context_bonus = 0.1  # High confidence for subdomains
-        elif relationship_context == 'parent_domain':
-            context_bonus = 0.05  # Medium confidence for parent domains
-        else:
-            context_bonus = 0.0  # Related domains get base confidence
-        
-        # Adjust confidence based on shared certificates
-        if shared_certificates:
-            shared_count = len(shared_certificates)
-            if shared_count >= 3:
-                shared_bonus = 0.1
-            elif shared_count >= 2:
-                shared_bonus = 0.05
-            else:
-                shared_bonus = 0.02
-            
-            # Additional bonus for valid shared certificates
-            valid_shared = sum(1 for cert in shared_certificates if cert.get('is_currently_valid'))
-            if valid_shared > 0:
-                validity_bonus = 0.05
-            else:
-                validity_bonus = 0.0
-        else:
-            # Even without shared certificates, domains found in the same query have some relationship
-            shared_bonus = 0.0
-            validity_bonus = 0.0
-        
-        # Adjust confidence based on certificate issuer reputation (if shared certificates exist)
-        issuer_bonus = 0.0
-        if shared_certificates:
-            for cert in shared_certificates:
-                issuer = cert.get('issuer_name', '').lower()
-                if any(trusted_ca in issuer for trusted_ca in ['let\'s encrypt', 'digicert', 'sectigo', 'globalsign']):
-                    issuer_bonus = max(issuer_bonus, 0.03)
-                    break
-        
-        # Calculate final confidence
-        final_confidence = base_confidence + context_bonus + shared_bonus + validity_bonus + issuer_bonus
-        return max(0.1, min(1.0, final_confidence))  # Clamp between 0.1 and 1.0
-
-    def _determine_relationship_context(self, cert_domain: str, query_domain: str) -> str:
-        """
-        Determine the context of the relationship between certificate domain and query domain.
-        
-        Args:
-            cert_domain: Domain found in certificate
-            query_domain: Original query domain
-            
-        Returns:
-            String describing the relationship context
-        """
-        if cert_domain == query_domain:
-            return 'exact_match'
-        elif cert_domain.endswith(f'.{query_domain}'):
-            return 'subdomain'
-        elif query_domain.endswith(f'.{cert_domain}'):
-            return 'parent_domain'
-        else:
-            return 'related_domain'
-    
-    def query_ip(self, ip: str) -> List[Tuple[str, str, str, float, Dict[str, Any]]]:
-        """
-        Query crt.sh for certificates containing the IP address.
-        Note: crt.sh doesn't typically index by IP, so this returns empty results.
-        
-        Args:
-            ip: IP address to investigate
-            
-        Returns:
-            Empty list (crt.sh doesn't support IP-based certificate queries effectively)
-        """
-        # crt.sh doesn't effectively support IP-based certificate queries
-        return []
+        except Exception as e:
+            return False
 
     def _extract_domains_from_certificate(self, cert_data: Dict[str, Any]) -> Set[str]:
-        """
-        Extract all domains from certificate data.
-        
-        Args:
-            cert_data: Certificate data from crt.sh API
-            
-        Returns:
-            Set of unique domain names found in the certificate
-        """
+        """Extract all domains from certificate data."""
         domains = set()
         
         # Extract from common name
@@ -499,7 +509,6 @@ class CrtShProvider(BaseProvider):
         # Extract from name_value field (contains SANs)
         name_value = cert_data.get('name_value', '')
         if name_value:
-            # Split by newlines and clean each domain
             for line in name_value.split('\n'):
                 cleaned_domains = self._clean_domain_name(line.strip())
                 if cleaned_domains:
@@ -508,37 +517,28 @@ class CrtShProvider(BaseProvider):
         return domains
 
     def _clean_domain_name(self, domain_name: str) -> List[str]:
-        """
-        Clean and normalize domain name from certificate data.
-        Now returns a list to handle wildcards correctly.
-        """
+        """Clean and normalize domain name from certificate data."""
         if not domain_name:
             return []
 
         domain = domain_name.strip().lower()
 
-        # Remove protocol if present
         if domain.startswith(('http://', 'https://')):
             domain = domain.split('://', 1)[1]
 
-        # Remove path if present
         if '/' in domain:
             domain = domain.split('/', 1)[0]
 
-        # Remove port if present
-        if ':' in domain and not domain.count(':') > 1:  # Avoid breaking IPv6
+        if ':' in domain and not domain.count(':') > 1:
             domain = domain.split(':', 1)[0]
 
-        # Handle wildcard domains
         cleaned_domains = []
         if domain.startswith('*.'):
-            # Add both the wildcard and the base domain
             cleaned_domains.append(domain)
             cleaned_domains.append(domain[2:])
         else:
             cleaned_domains.append(domain)
 
-        # Remove any remaining invalid characters and validate
         final_domains = []
         for d in cleaned_domains:
             d = re.sub(r'[^\w\-\.]', '', d)
@@ -546,3 +546,35 @@ class CrtShProvider(BaseProvider):
                 final_domains.append(d)
 
         return [d for d in final_domains if _is_valid_domain(d)]
+
+    def _calculate_domain_relationship_confidence(self, domain1: str, domain2: str, 
+                                                shared_certificates: List[Dict[str, Any]],
+                                                all_discovered_domains: Set[str]) -> float:
+        """Calculate confidence score for domain relationship based on various factors."""
+        base_confidence = 0.9
+        
+        # Adjust confidence based on domain relationship context
+        relationship_context = self._determine_relationship_context(domain2, domain1)
+        
+        if relationship_context == 'exact_match':
+            context_bonus = 0.0
+        elif relationship_context == 'subdomain':
+            context_bonus = 0.1
+        elif relationship_context == 'parent_domain':
+            context_bonus = 0.05
+        else:
+            context_bonus = 0.0
+        
+        final_confidence = base_confidence + context_bonus
+        return max(0.1, min(1.0, final_confidence))
+
+    def _determine_relationship_context(self, cert_domain: str, query_domain: str) -> str:
+        """Determine the context of the relationship between certificate domain and query domain."""
+        if cert_domain == query_domain:
+            return 'exact_match'
+        elif cert_domain.endswith(f'.{query_domain}'):
+            return 'subdomain'
+        elif query_domain.endswith(f'.{cert_domain}'):
+            return 'parent_domain'
+        else:
+            return 'related_domain'

providers/dns_provider.py

@@ -1,19 +1,19 @@
 # dnsrecon/providers/dns_provider.py
 
-import dns.resolver
-import dns.reversename
-from typing import List, Dict, Any, Tuple
+from dns import resolver, reversename
+from typing import Dict
 from .base_provider import BaseProvider
-from utils.helpers import _is_valid_ip, _is_valid_domain
+from core.provider_result import ProviderResult
+from utils.helpers import _is_valid_ip, _is_valid_domain, get_ip_version
 
 
 class DNSProvider(BaseProvider):
     """
     Provider for standard DNS resolution and reverse DNS lookups.
-    Now uses session-specific configuration.
+    Now returns standardized ProviderResult objects with IPv4 and IPv6 support.
     """
 
-    def __init__(self, session_config=None):
+    def __init__(self, name=None, session_config=None):
         """Initialize DNS provider with session-specific configuration."""
         super().__init__(
             name="dns",
@@ -23,10 +23,9 @@ class DNSProvider(BaseProvider):
         )
 
         # Configure DNS resolver
-        self.resolver = dns.resolver.Resolver()
+        self.resolver = resolver.Resolver()
         self.resolver.timeout = 5
         self.resolver.lifetime = 10
-        #self.resolver.nameservers = ['127.0.0.1']
 
     def get_name(self) -> str:
         """Return the provider name."""
@@ -48,97 +47,149 @@ class DNSProvider(BaseProvider):
         """DNS is always available - no API key required."""
         return True
 
-    def query_domain(self, domain: str) -> List[Tuple[str, str, str, float, Dict[str, Any]]]:
+    def query_domain(self, domain: str) -> ProviderResult:
         """
-        Query DNS records for the domain to discover relationships.
+        Query DNS records for the domain to discover relationships and attributes.
+        FIXED: Now creates separate attributes for each DNS record type.
         
         Args:
             domain: Domain to investigate
             
         Returns:
-            List of relationships discovered from DNS analysis
+            ProviderResult containing discovered relationships and attributes
         """
         if not _is_valid_domain(domain):
-            return []
+            return ProviderResult()
 
-        relationships = []
+        result = ProviderResult()
 
-        # Query all record types
+        # Query all record types - each gets its own attribute
         for record_type in ['A', 'AAAA', 'CNAME', 'MX', 'NS', 'SOA', 'TXT', 'SRV', 'CAA']:
-            relationships.extend(self._query_record(domain, record_type))
+            try:
+                self._query_record(domain, record_type, result)
+            #except resolver.NoAnswer:
+                # This is not an error, just a confirmation that the record doesn't exist.
+                #self.logger.logger.debug(f"No {record_type} record found for {domain}")
+            except Exception as e:
+                self.failed_requests += 1
+                self.logger.logger.debug(f"{record_type} record query failed for {domain}: {e}")
 
-        return relationships
+        return result
 
-    def query_ip(self, ip: str) -> List[Tuple[str, str, str, float, Dict[str, Any]]]:
+    def query_ip(self, ip: str) -> ProviderResult:
         """
-        Query reverse DNS for the IP address.
+        Query reverse DNS for the IP address (supports both IPv4 and IPv6).
 
         Args:
-            ip: IP address to investigate
+            ip: IP address to investigate (IPv4 or IPv6)
 
         Returns:
-            List of relationships discovered from reverse DNS
+            ProviderResult containing discovered relationships and attributes
         """
         if not _is_valid_ip(ip):
-            return []
+            return ProviderResult()
 
-        relationships = []
+        result = ProviderResult()
+        ip_version = get_ip_version(ip)
 
         try:
-            # Perform reverse DNS lookup
+            # Perform reverse DNS lookup (works for both IPv4 and IPv6)
             self.total_requests += 1
-            reverse_name = dns.reversename.from_address(ip)
+            reverse_name = reversename.from_address(ip)
             response = self.resolver.resolve(reverse_name, 'PTR')
             self.successful_requests += 1
 
+            ptr_records = []
             for ptr_record in response:
                 hostname = str(ptr_record).rstrip('.')
 
                 if _is_valid_domain(hostname):
+                    # Determine appropriate forward relationship type based on IP version
+                    if ip_version == 6:
+                        relationship_type = 'dns_aaaa_record'
+                        record_prefix = 'AAAA'
+                    else:
+                        relationship_type = 'dns_a_record'
+                        record_prefix = 'A'
+                    
+                    # Add the relationship
+                    result.add_relationship(
+                        source_node=ip,
+                        target_node=hostname,
+                        relationship_type='dns_ptr_record',
+                        provider=self.name,
+                        confidence=0.8,
                         raw_data={
                             'query_type': 'PTR',
                             'ip_address': ip,
+                            'ip_version': ip_version,
                             'hostname': hostname,
                             'ttl': response.ttl
                         }
+                    )
 
-                    relationships.append((
-                        ip,
-                        hostname,
-                        'ptr_record',
-                        0.8,
-                        raw_data
-                    ))
+                    # Add to PTR records list
+                    ptr_records.append(f"PTR: {hostname}")
 
+                    # Log the relationship discovery
                     self.log_relationship_discovery(
                         source_node=ip,
                         target_node=hostname,
-                        relationship_type='ptr_record',
+                        relationship_type='dns_ptr_record',
                         confidence_score=0.8,
-                        raw_data=raw_data,
-                        discovery_method="reverse_dns_lookup"
+                        raw_data={
+                            'query_type': 'PTR',
+                            'ip_address': ip,
+                            'ip_version': ip_version,
+                            'hostname': hostname,
+                            'ttl': response.ttl
+                        },
+                        discovery_method=f"reverse_dns_lookup_ipv{ip_version}"
                     )
 
+            # Add PTR records as separate attribute
+            if ptr_records:
+                result.add_attribute(
+                    target_node=ip,
+                    name='ptr_records',  # Specific name for PTR records
+                    value=ptr_records,
+                    attr_type='dns_record',
+                    provider=self.name,
+                    confidence=0.8,
+                    metadata={'ttl': response.ttl, 'ip_version': ip_version}
+                )
+
+        except resolver.NXDOMAIN:
+            self.failed_requests += 1
+            self.logger.logger.debug(f"Reverse DNS lookup failed for {ip}: NXDOMAIN")
         except Exception as e:
             self.failed_requests += 1
             self.logger.logger.debug(f"Reverse DNS lookup failed for {ip}: {e}")
+            # Re-raise the exception so the scanner can handle the failure
+            raise e
 
-        return relationships
+        return result
 
-    def _query_record(self, domain: str, record_type: str) -> List[Tuple[str, str, str, float, Dict[str, Any]]]:
+    def _query_record(self, domain: str, record_type: str, result: ProviderResult) -> None:
         """
-        Query a specific type of DNS record for the domain.
+        FIXED: Query DNS records with unique attribute names for each record type.
+        Enhanced to better handle IPv6 AAAA records.
         """
-        relationships = []
         try:
             self.total_requests += 1
             response = self.resolver.resolve(domain, record_type)
             self.successful_requests += 1
 
+            dns_records = []
+            
             for record in response:
                 target = ""
                 if record_type in ['A', 'AAAA']:
                     target = str(record)
+                    # Validate that the IP address is properly formed
+                    if not _is_valid_ip(target):
+                        self.logger.logger.debug(f"Invalid IP address in {record_type} record: {target}")
+                        continue
                 elif record_type in ['CNAME', 'NS', 'PTR']:
                     target = str(record.target).rstrip('.')
                 elif record_type == 'MX':
@@ -146,32 +197,56 @@ class DNSProvider(BaseProvider):
                 elif record_type == 'SOA':
                     target = str(record.mname).rstrip('.')
                 elif record_type in ['TXT']:
-                    # TXT records are treated as metadata, not relationships.
+                    # Keep raw TXT record value
+                    txt_value = str(record).strip('"')
+                    dns_records.append(txt_value)  # Just the value for TXT
                     continue
                 elif record_type == 'SRV':
                     target = str(record.target).rstrip('.')
                 elif record_type == 'CAA':
-                    target = f"{record.flags} {record.tag.decode('utf-8')} \"{record.value.decode('utf-8')}\""
+                    # Keep raw CAA record format
+                    caa_value = f"{record.flags} {record.tag.decode('utf-8')} \"{record.value.decode('utf-8')}\""
+                    dns_records.append(caa_value)  # Just the value for CAA
+                    continue
                 else:
                     target = str(record)
 
                 if target:
+                    # Determine IP version for metadata if this is an IP record
+                    ip_version = None
+                    if record_type in ['A', 'AAAA'] and _is_valid_ip(target):
+                        ip_version = get_ip_version(target)
+                    
                     raw_data = {
                         'query_type': record_type,
                         'domain': domain,
                         'value': target,
                         'ttl': response.ttl
                     }
-                    relationship_type = f"{record_type.lower()}_record"
-                    confidence = 0.8  # Default confidence for DNS records
                     
-                    relationships.append((
-                        domain,
-                        target,
-                        relationship_type,
-                        confidence,
-                        raw_data
-                    ))
+                    if ip_version:
+                        raw_data['ip_version'] = ip_version
+                    
+                    relationship_type = f"dns_{record_type.lower()}_record"
+                    confidence = 0.8
+
+                    # Add relationship
+                    result.add_relationship(
+                        source_node=domain,
+                        target_node=target,
+                        relationship_type=relationship_type,
+                        provider=self.name,
+                        confidence=confidence,
+                        raw_data=raw_data
+                    )
+
+                    # Add target to records list
+                    dns_records.append(target)
+
+                    # Log relationship discovery with IP version info
+                    discovery_method = f"dns_{record_type.lower()}_record"
+                    if ip_version:
+                        discovery_method += f"_ipv{ip_version}"
                     
                     self.log_relationship_discovery(
                         source_node=domain,
@@ -179,11 +254,33 @@ class DNSProvider(BaseProvider):
                         relationship_type=relationship_type,
                         confidence_score=confidence,
                         raw_data=raw_data,
-                        discovery_method=f"dns_{record_type.lower()}_record"
+                        discovery_method=discovery_method
+                    )
+
+            # FIXED: Create attribute with specific name for each record type
+            if dns_records:
+                # Use record type specific attribute name (e.g., 'a_records', 'mx_records', etc.)
+                attribute_name = f"{record_type.lower()}_records"
+                
+                metadata = {'record_type': record_type, 'ttl': response.ttl}
+                
+                # Add IP version info for A/AAAA records
+                if record_type in ['A', 'AAAA'] and dns_records:
+                    first_ip_version = get_ip_version(dns_records[0])
+                    if first_ip_version:
+                        metadata['ip_version'] = first_ip_version
+                
+                result.add_attribute(
+                    target_node=domain,
+                    name=attribute_name,  # UNIQUE name for each record type!
+                    value=dns_records,
+                    attr_type='dns_record_list',
+                    provider=self.name,
+                    confidence=0.8,
+                    metadata=metadata
                 )
 
         except Exception as e:
             self.failed_requests += 1
             self.logger.logger.debug(f"{record_type} record query failed for {domain}: {e}")
-
-        return relationships
+            raise e

providers/shodan_provider.py

@@ -1,21 +1,23 @@
-"""
-Shodan provider for DNSRecon.
-Discovers IP relationships and infrastructure context through Shodan API.
-"""
+# dnsrecon/providers/shodan_provider.py
 
 import json
-from typing import List, Dict, Any, Tuple
+from pathlib import Path
+from typing import Dict, Any
+from datetime import datetime, timezone
+import requests
+
 from .base_provider import BaseProvider
-from utils.helpers import _is_valid_ip, _is_valid_domain
+from core.provider_result import ProviderResult
+from utils.helpers import _is_valid_ip, _is_valid_domain, get_ip_version, normalize_ip
 
 
 class ShodanProvider(BaseProvider):
     """
-    Provider for querying Shodan API for IP address and hostname information.
-    Now uses session-specific API keys.
+    Provider for querying Shodan API for IP address information.
+    Now returns standardized ProviderResult objects with caching support for IPv4 and IPv6.
     """
 
-    def __init__(self, session_config=None):
+    def __init__(self, name=None, session_config=None):
         """Initialize Shodan provider with session-specific configuration."""
         super().__init__(
             name="shodan",
@@ -26,6 +28,10 @@ class ShodanProvider(BaseProvider):
         self.base_url = "https://api.shodan.io"
         self.api_key = self.config.get_api_key('shodan')
         
+        # Initialize cache directory
+        self.cache_dir = Path('cache') / 'shodan'
+        self.cache_dir.mkdir(parents=True, exist_ok=True)
+
     def is_available(self) -> bool:
         """Check if Shodan provider is available (has valid API key in this session)."""
         return self.api_key is not None and len(self.api_key.strip()) > 0
@@ -36,7 +42,7 @@ class ShodanProvider(BaseProvider):
 
     def get_display_name(self) -> str:
         """Return the provider display name for the UI."""
-        return "shodan"
+        return "Shodan"
 
     def requires_api_key(self) -> bool:
         """Return True if the provider requires an API key."""
@@ -44,267 +50,300 @@ class ShodanProvider(BaseProvider):
 
     def get_eligibility(self) -> Dict[str, bool]:
         """Return a dictionary indicating if the provider can query domains and/or IPs."""
-        return {'domains': True, 'ips': True}
+        return {'domains': False, 'ips': True}
 
-    def query_domain(self, domain: str) -> List[Tuple[str, str, str, float, Dict[str, Any]]]:
+    def _get_cache_file_path(self, ip: str) -> Path:
         """
-        Query Shodan for information about a domain.
-        Uses Shodan's hostname search to find associated IPs.
+        Generate cache file path for an IP address (IPv4 or IPv6).
+        IPv6 addresses contain colons which are replaced with underscores for filesystem safety.
+        """
+        # Normalize the IP address first to ensure consistent caching
+        normalized_ip = normalize_ip(ip)
+        if not normalized_ip:
+            # Fallback for invalid IPs
+            safe_ip = ip.replace('.', '_').replace(':', '_')
+        else:
+            # Replace problematic characters for both IPv4 and IPv6
+            safe_ip = normalized_ip.replace('.', '_').replace(':', '_')
+        
+        return self.cache_dir / f"{safe_ip}.json"
+
+    def _get_cache_status(self, cache_file_path: Path) -> str:
+        """
+        Check cache status for an IP.
+        Returns: 'not_found', 'fresh', or 'stale'
+        """
+        if not cache_file_path.exists():
+            return "not_found"
+        
+        try:
+            with open(cache_file_path, 'r') as f:
+                cache_data = json.load(f)
+            
+            last_query_str = cache_data.get("last_upstream_query")
+            if not last_query_str:
+                return "stale"
+            
+            last_query = datetime.fromisoformat(last_query_str.replace('Z', '+00:00'))
+            hours_since_query = (datetime.now(timezone.utc) - last_query).total_seconds() / 3600
+            
+            cache_timeout = self.config.cache_timeout_hours
+            if hours_since_query < cache_timeout:
+                return "fresh"
+            else:
+                return "stale"
+                
+        except (json.JSONDecodeError, ValueError, KeyError):
+            return "stale"
+
+    def query_domain(self, domain: str) -> ProviderResult:
+        """
+        Domain queries are no longer supported for the Shodan provider.
         
         Args:
             domain: Domain to investigate
             
         Returns:
-            List of relationships discovered from Shodan data
+            Empty ProviderResult
         """
-        if not _is_valid_domain(domain) or not self.is_available():
-            return []
+        return ProviderResult()
 
-        relationships = []
-
-        try:
-            # Search for hostname in Shodan
-            search_query = f"hostname:{domain}"
-            url = f"{self.base_url}/shodan/host/search"
-            params = {
-                'key': self.api_key,
-                'query': search_query,
-                'minify': True  # Get minimal data to reduce bandwidth
-            }
-
-            response = self.make_request(url, method="GET", params=params, target_indicator=domain)
-
-            if not response or response.status_code != 200:
-                return []
-
-            data = response.json()
-
-            if 'matches' not in data:
-                return []
-
-            # Process search results
-            for match in data['matches']:
-                ip_address = match.get('ip_str')
-                hostnames = match.get('hostnames', [])
-
-                if ip_address and domain in hostnames:
-                    raw_data = {
-                        'ip_address': ip_address,
-                        'hostnames': hostnames,
-                        'country': match.get('location', {}).get('country_name', ''),
-                        'city': match.get('location', {}).get('city', ''),
-                        'isp': match.get('isp', ''),
-                        'org': match.get('org', ''),
-                        'ports': match.get('ports', []),
-                        'last_update': match.get('last_update', '')
-                    }
-
-                    relationships.append((
-                        domain,
-                        ip_address,
-                        'a_record',  # Domain resolves to IP
-                        0.8,
-                        raw_data
-                    ))
-
-                    self.log_relationship_discovery(
-                        source_node=domain,
-                        target_node=ip_address,
-                        relationship_type='a_record',
-                        confidence_score=0.8,
-                        raw_data=raw_data,
-                        discovery_method="shodan_hostname_search"
-                    )
-
-                    # Also create relationships to other hostnames on the same IP
-                    for hostname in hostnames:
-                        if hostname != domain and _is_valid_domain(hostname):
-                            hostname_raw_data = {
-                                'shared_ip': ip_address,
-                                'all_hostnames': hostnames,
-                                'discovery_context': 'shared_hosting'
-                            }
-
-                            relationships.append((
-                                domain,
-                                hostname,
-                                'passive_dns',  # Shared hosting relationship
-                                0.6,  # Lower confidence for shared hosting
-                                hostname_raw_data
-                            ))
-
-                            self.log_relationship_discovery(
-                                source_node=domain,
-                                target_node=hostname,
-                                relationship_type='passive_dns',
-                                confidence_score=0.6,
-                                raw_data=hostname_raw_data,
-                                discovery_method="shodan_shared_hosting"
-                            )
-
-        except json.JSONDecodeError as e:
-            self.logger.logger.error(f"Failed to parse JSON response from Shodan: {e}")
-
-        return relationships
-
-    def query_ip(self, ip: str) -> List[Tuple[str, str, str, float, Dict[str, Any]]]:
+    def query_ip(self, ip: str) -> ProviderResult:
         """
-        Query Shodan for information about an IP address.
+        Query Shodan for information about an IP address (IPv4 or IPv6), with caching of processed data.
         
         Args:
-            ip: IP address to investigate
+            ip: IP address to investigate (IPv4 or IPv6)
             
         Returns:
-            List of relationships discovered from Shodan IP data
+            ProviderResult containing discovered relationships and attributes
         """
         if not _is_valid_ip(ip) or not self.is_available():
-            return []
+            return ProviderResult()
         
-        relationships = []
+        # Normalize IP address for consistent processing
+        normalized_ip = normalize_ip(ip)
+        if not normalized_ip:
+            return ProviderResult()
+        
+        cache_file = self._get_cache_file_path(normalized_ip)
+        cache_status = self._get_cache_status(cache_file)
+        
+        result = ProviderResult()
         
         try:
-            # Query Shodan host information
-            url = f"{self.base_url}/shodan/host/{ip}"
+            if cache_status == "fresh":
+                result = self._load_from_cache(cache_file)
+                self.logger.logger.info(f"Using cached Shodan data for {normalized_ip}")
+            else:  # "stale" or "not_found"
+                url = f"{self.base_url}/shodan/host/{normalized_ip}"
                 params = {'key': self.api_key}
+                response = self.make_request(url, method="GET", params=params, target_indicator=normalized_ip)
                 
-            response = self.make_request(url, method="GET", params=params, target_indicator=ip)
-
-            if not response or response.status_code != 200:
-                return []
-
+                if response and response.status_code == 200:
                     data = response.json()
-
-            # Extract hostname relationships
-            hostnames = data.get('hostnames', [])
-            for hostname in hostnames:
-                if _is_valid_domain(hostname):
-                    raw_data = {
-                        'ip_address': ip,
-                        'hostname': hostname,
-                        'country': data.get('country_name', ''),
-                        'city': data.get('city', ''),
-                        'isp': data.get('isp', ''),
-                        'org': data.get('org', ''),
-                        'asn': data.get('asn', ''),
-                        'ports': data.get('ports', []),
-                        'last_update': data.get('last_update', ''),
-                        'os': data.get('os', '')
-                    }
-
-                    relationships.append((
-                        ip,
-                        hostname,
-                        'a_record',  # IP resolves to hostname
-                        0.8,
-                        raw_data
-                    ))
-
-                    self.log_relationship_discovery(
-                        source_node=ip,
-                        target_node=hostname,
-                        relationship_type='a_record',
-                        confidence_score=0.8,
-                        raw_data=raw_data,
-                        discovery_method="shodan_host_lookup"
-                    )
-
-            # Extract ASN relationship if available
-            asn = data.get('asn')
-            if asn:
-                # Ensure the ASN starts with "AS"
-                if isinstance(asn, str) and asn.startswith('AS'):
-                    asn_name = asn
-                    asn_number = asn[2:]
+                    # Process the data into ProviderResult BEFORE caching
+                    result = self._process_shodan_data(normalized_ip, data)
+                    self._save_to_cache(cache_file, result, data)  # Save both result and raw data
+                elif response and response.status_code == 404:
+                    # Handle 404 "No information available" as successful empty result
+                    try:
+                        error_data = response.json()
+                        if "No information available" in error_data.get('error', ''):
+                            # This is a successful query - Shodan just has no data
+                            self.logger.logger.debug(f"Shodan has no information for {normalized_ip}")
+                            result = ProviderResult()  # Empty but successful result
+                            # Cache the empty result to avoid repeated queries
+                            self._save_to_cache(cache_file, result, {'error': 'No information available'})
                         else:
-                    asn_name = f"AS{asn}"
-                    asn_number = str(asn)
+                            # Some other 404 error - treat as failure
+                            raise requests.exceptions.RequestException(f"Shodan API returned 404: {error_data}")
+                    except (ValueError, KeyError):
+                        # Could not parse JSON response - treat as failure
+                        raise requests.exceptions.RequestException(f"Shodan API returned 404 with unparseable response")
+                elif cache_status == "stale":
+                    # If API fails on a stale cache, use the old data
+                    result = self._load_from_cache(cache_file)
+                else:
+                    # Other HTTP error codes should be treated as failures
+                    status_code = response.status_code if response else "No response"
+                    raise requests.exceptions.RequestException(f"Shodan API returned HTTP {status_code}")
 
-                asn_raw_data = {
-                    'ip_address': ip,
-                    'asn': asn_number,
-                    'isp': data.get('isp', ''),
-                    'org': data.get('org', '')
-                }
+        except requests.exceptions.RequestException as e:
+            self.logger.logger.info(f"Shodan API query returned no info for {normalized_ip}: {e}")
+            if cache_status == "stale":
+                result = self._load_from_cache(cache_file)
+            else:
+                # Re-raise for retry scheduling - but only for actual failures
+                raise e
         
-                relationships.append((
-                    ip,
-                    asn_name,
-                    'asn_membership',
-                    0.7,
-                    asn_raw_data
-                ))
+        return result
 
-                self.log_relationship_discovery(
-                    source_node=ip,
-                    target_node=asn_name,
-                    relationship_type='asn_membership',
-                    confidence_score=0.7,
-                    raw_data=asn_raw_data,
-                    discovery_method="shodan_asn_lookup"
+    def _load_from_cache(self, cache_file_path: Path) -> ProviderResult:
+        """Load processed Shodan data from a cache file."""
+        try:
+            with open(cache_file_path, 'r') as f:
+                cache_content = json.load(f)
+            
+            result = ProviderResult()
+            
+            # Reconstruct relationships
+            for rel_data in cache_content.get("relationships", []):
+                result.add_relationship(
+                    source_node=rel_data["source_node"],
+                    target_node=rel_data["target_node"],
+                    relationship_type=rel_data["relationship_type"],
+                    provider=rel_data["provider"],
+                    confidence=rel_data["confidence"],
+                    raw_data=rel_data.get("raw_data", {})
                 )
             
-        except json.JSONDecodeError as e:
-            self.logger.logger.error(f"Failed to parse JSON response from Shodan: {e}")
+            # Reconstruct attributes
+            for attr_data in cache_content.get("attributes", []):
+                result.add_attribute(
+                    target_node=attr_data["target_node"],
+                    name=attr_data["name"],
+                    value=attr_data["value"],
+                    attr_type=attr_data["type"],
+                    provider=attr_data["provider"],
+                    confidence=attr_data["confidence"],
+                    metadata=attr_data.get("metadata", {})
+                )
             
-        return relationships
+            return result
             
-    def search_by_organization(self, org_name: str) -> List[Dict[str, Any]]:
-        """
-        Search Shodan for hosts belonging to a specific organization.
-
-        Args:
-            org_name: Organization name to search for
-
-        Returns:
-            List of host information dictionaries
-        """
-        if not self.is_available():
-            return []
+        except (json.JSONDecodeError, FileNotFoundError, KeyError):
+            return ProviderResult()
 
+    def _save_to_cache(self, cache_file_path: Path, result: ProviderResult, raw_data: Dict[str, Any]) -> None:
+        """Save processed Shodan data to a cache file."""
         try:
-            search_query = f"org:\"{org_name}\""
-            url = f"{self.base_url}/shodan/host/search"
-            params = {
-                'key': self.api_key,
-                'query': search_query,
-                'minify': True
+            cache_data = {
+                "last_upstream_query": datetime.now(timezone.utc).isoformat(),
+                "raw_data": raw_data,  # Preserve original for forensic purposes
+                "relationships": [
+                    {
+                        "source_node": rel.source_node,
+                        "target_node": rel.target_node,
+                        "relationship_type": rel.relationship_type,
+                        "confidence": rel.confidence,
+                        "provider": rel.provider,
+                        "raw_data": rel.raw_data
+                    } for rel in result.relationships
+                ],
+                "attributes": [
+                    {
+                        "target_node": attr.target_node,
+                        "name": attr.name,
+                        "value": attr.value,
+                        "type": attr.type,
+                        "provider": attr.provider,
+                        "confidence": attr.confidence,
+                        "metadata": attr.metadata
+                    } for attr in result.attributes
+                ]
             }
-
-            response = self.make_request(url, method="GET", params=params, target_indicator=org_name)
-
-            if response and response.status_code == 200:
-                data = response.json()
-                return data.get('matches', [])
-
+            with open(cache_file_path, 'w') as f:
+                json.dump(cache_data, f, separators=(',', ':'), default=str)
         except Exception as e:
-            self.logger.logger.error(f"Error searching Shodan by organization {org_name}: {e}")
+            self.logger.logger.warning(f"Failed to save Shodan cache for {cache_file_path.name}: {e}")
 
-        return []
-
-    def get_host_services(self, ip: str) -> List[Dict[str, Any]]:
+    def _process_shodan_data(self, ip: str, data: Dict[str, Any]) -> ProviderResult:
         """
-        Get service information for a specific IP address.
-
-        Args:
-            ip: IP address to query
-
-        Returns:
-            List of service information dictionaries
+        VERIFIED: Process Shodan data creating ISP nodes with ASN attributes and proper relationships.
+        Enhanced to include IP version information for IPv6 addresses.
         """
-        if not _is_valid_ip(ip) or not self.is_available():
-            return []
+        result = ProviderResult()
         
-        try:
-            url = f"{self.base_url}/shodan/host/{ip}"
-            params = {'key': self.api_key}
+        # Determine IP version for metadata
+        ip_version = get_ip_version(ip)
 
-            response = self.make_request(url, method="GET", params=params, target_indicator=ip)
+        # VERIFIED: Extract ISP information and create proper ISP node with ASN
+        isp_name = data.get('org')
+        asn_value = data.get('asn')
 
-            if response and response.status_code == 200:
-                data = response.json()
-                return data.get('data', [])  # Service banners
+        if isp_name and asn_value:
+            # Create relationship from IP to ISP
+            result.add_relationship(
+                source_node=ip,
+                target_node=isp_name,
+                relationship_type='shodan_isp',
+                provider=self.name,
+                confidence=0.9,
+                raw_data={'asn': asn_value, 'shodan_org': isp_name, 'ip_version': ip_version}
+            )
             
-        except Exception as e:
-            self.logger.logger.error(f"Error getting Shodan services for IP {ip}: {e}")
+            # Add ASN as attribute to the ISP node
+            result.add_attribute(
+                target_node=isp_name,
+                name='asn',
+                value=asn_value,
+                attr_type='isp_info',
+                provider=self.name,
+                confidence=0.9,
+                metadata={'description': 'Autonomous System Number from Shodan', 'ip_version': ip_version}
+            )
             
-        return []
+            # Also add organization name as attribute to ISP node for completeness
+            result.add_attribute(
+                target_node=isp_name,
+                name='organization_name',
+                value=isp_name,
+                attr_type='isp_info',
+                provider=self.name,
+                confidence=0.9,
+                metadata={'description': 'Organization name from Shodan', 'ip_version': ip_version}
+            )
+
+        # Process hostnames (reverse DNS)
+        for key, value in data.items():
+            if key == 'hostnames':
+                for hostname in value:
+                    if _is_valid_domain(hostname):
+                        # Use appropriate relationship type based on IP version
+                        if ip_version == 6:
+                            relationship_type = 'shodan_aaaa_record'
+                        else:
+                            relationship_type = 'shodan_a_record'
+                        
+                        result.add_relationship(
+                            source_node=ip,
+                            target_node=hostname,
+                            relationship_type=relationship_type,
+                            provider=self.name,
+                            confidence=0.8,
+                            raw_data={**data, 'ip_version': ip_version}
+                        )
+                        self.log_relationship_discovery(
+                            source_node=ip,
+                            target_node=hostname,
+                            relationship_type=relationship_type,
+                            confidence_score=0.8,
+                            raw_data={**data, 'ip_version': ip_version},
+                            discovery_method=f"shodan_host_lookup_ipv{ip_version}"
+                        )
+            elif key == 'ports':
+                # Add open ports as attributes to the IP
+                for port in value:
+                    result.add_attribute(
+                        target_node=ip,
+                        name='shodan_open_port',
+                        value=port,
+                        attr_type='shodan_network_info',
+                        provider=self.name,
+                        confidence=0.9,
+                        metadata={'ip_version': ip_version}
+                    )
+            elif isinstance(value, (str, int, float, bool)) and value is not None:
+                # Add other Shodan fields as IP attributes (keep raw field names)
+                result.add_attribute(
+                    target_node=ip,
+                    name=key,  # Raw field name from Shodan API
+                    value=value,
+                    attr_type='shodan_info',
+                    provider=self.name,
+                    confidence=0.9,
+                    metadata={'ip_version': ip_version}
+                )
+
+        return result

requirements.txt

@@ -1,9 +1,10 @@
-Flask>=2.3.3
-networkx>=3.1
-requests>=2.31.0
-python-dateutil>=2.8.2
-Werkzeug>=2.3.7
-urllib3>=2.0.0
-dnspython>=2.4.2
+Flask
+networkx
+requests
+python-dateutil
+Werkzeug
+urllib3
+dnspython
 gunicorn
 redis
+python-dotenv

templates/index.html

@@ -1,5 +1,6 @@
 <!DOCTYPE html>
 <html lang="en">
+
 <head>
     <meta charset="UTF-8">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
@@ -7,8 +8,11 @@
     <link rel="stylesheet" href="{{ url_for('static', filename='css/main.css') }}">
     <script src="https://cdnjs.cloudflare.com/ajax/libs/vis/4.21.0/vis.min.js"></script>
     <link href="https://cdnjs.cloudflare.com/ajax/libs/vis/4.21.0/vis.min.css" rel="stylesheet" type="text/css">
-    <link href="https://fonts.googleapis.com/css2?family=Roboto+Mono:wght@300;400;500;700&family=Special+Elite&display=swap" rel="stylesheet">
+    <link
+        href="https://fonts.googleapis.com/css2?family=Roboto+Mono:wght@300;400;500;700&family=Special+Elite&display=swap"
+        rel="stylesheet">
 </head>
+
 <body>
     <div class="container">
         <header class="header">
@@ -32,19 +36,8 @@
 
                 <div class="form-container">
                     <div class="input-group">
-                        <label for="target-domain">Target Domain</label>
-                        <input type="text" id="target-domain" placeholder="example.com" autocomplete="off">
-                    </div>
-                    
-                    <div class="input-group">
-                        <label for="max-depth">Recursion Depth</label>
-                        <select id="max-depth">
-                            <option value="1">Depth 1 - Direct relationships</option>
-                            <option value="2" selected>Depth 2 - Recommended</option>
-                            <option value="3">Depth 3 - Extended analysis</option>
-                            <option value="4">Depth 4 - Deep reconnaissance</option>
-                            <option value="5">Depth 5 - Maximum depth</option>
-                        </select>
+                        <label for="target-input">Target Domain or IP</label>
+                        <input type="text" id="target-input" placeholder="example.com or 8.8.8.8" autocomplete="off">
                     </div>
 
                     <div class="button-group">
@@ -60,13 +53,13 @@
                             <span class="btn-icon">[STOP]</span>
                             <span>Terminate Scan</span>
                         </button>
-                        <button id="export-results" class="btn btn-secondary">
+                        <button id="export-options" class="btn btn-secondary">
                             <span class="btn-icon">[EXPORT]</span>
-                            <span>Download Results</span>
+                            <span>Export Options</span>
                         </button>
-                        <button id="configure-api-keys" class="btn btn-secondary">
+                        <button id="configure-settings" class="btn btn-secondary">
                             <span class="btn-icon">[API]</span>
-                            <span>Configure API Keys</span>
+                            <span>Settings</span>
                         </button>
                     </div>
                 </div>
@@ -90,54 +83,47 @@
                         <span class="status-label">Depth:</span>
                         <span id="depth-display" class="status-value">0/0</span>
                     </div>
-                    <div class="status-row">
-                        <span class="status-label">Progress:</span>
-                        <span id="progress-display" class="status-value">0%</span>
-                    </div>
-                    <div class="status-row">
-                        <span class="status-label">Indicators:</span>
-                        <span id="indicators-display" class="status-value">0</span>
-                    </div>
                     <div class="status-row">
                         <span class="status-label">Relationships:</span>
                         <span id="relationships-display" class="status-value">0</span>
                     </div>
                 </div>
 
+                <div class="progress-container">
+                    <div class="progress-info">
+                        <span id="progress-label">Progress:</span>
+                        <span id="progress-compact">0/0</span>
+                    </div>
                     <div class="progress-bar">
                         <div id="progress-fill" class="progress-fill"></div>
                     </div>
+                    <div class="progress-placeholder">
+                        <span class="status-label">
+                            ⚠️ <strong>Important:</strong> Scanning large public services (e.g., Google, Cloudflare,
+                            AWS) is
+                            <strong>discouraged</strong> due to rate limits (e.g., crt.sh).
+                            <br><br>
+                            Our task scheduler operates on a <strong>priority-based queue</strong>:
+                            Short, targeted tasks like DNS are processed first, while resource-intensive requests (e.g.,
+                            crt.sh)
+                            are <strong>automatically deprioritized</strong> and may be processed later.
+                        </span>
+                    </div>
+                </div>
             </section>
 
             <section class="visualization-panel">
                 <div class="panel-header">
                     <h2>Infrastructure Map</h2>
-                    <div class="view-controls">
-                        <div class="filter-group">
-                            <label for="node-type-filter">Node Type:</label>
-                            <select id="node-type-filter">
-                                <option value="all">All</option>
-                                <option value="domain">Domain</option>
-                                <option value="ip">IP</option>
-                                <option value="asn">ASN</option>
-                                <option value="correlation_object">Correlation Object</option>
-                                <option value="large_entity">Large Entity</option>
-                            </select>
-                        </div>
-                        <div class="filter-group">
-                            <label for="confidence-filter">Min Confidence:</label>
-                            <input type="range" id="confidence-filter" min="0" max="1" step="0.1" value="0">
-                            <span id="confidence-value">0</span>
-                        </div>
-                    </div>
                 </div>
 
                 <div id="network-graph" class="graph-container">
                     <div class="graph-placeholder">
                         <div class="placeholder-content">
-                            <div class="placeholder-icon">[○]</div>
+                            <div class="placeholder-icon">[◯]</div>
                             <div class="placeholder-text">Infrastructure map will appear here</div>
-                            <div class="placeholder-subtext">Start a reconnaissance scan to visualize relationships</div>
+                            <div class="placeholder-subtext">Start a reconnaissance scan to visualize relationships
+                            </div>
                         </div>
                     </div>
                 </div>
@@ -147,29 +133,30 @@
                         <div class="legend-color" style="background-color: #00ff41;"></div>
                         <span>Domains</span>
                     </div>
+                    <div class="legend-item">
+                        <div class="legend-color" style="background-color: #c92f2f;"></div>
+                        <span>Domain (no valid cert)</span>
+                    </div>
+                    <div class="legend-item">
+                        <div class="legend-color" style="background-color: #c7c7c7;"></div>
+                        <span>Domain (never had cert)</span>
+                    </div>
                     <div class="legend-item">
                         <div class="legend-color" style="background-color: #ff9900;"></div>
                         <span>IP Addresses</span>
                     </div>
                     <div class="legend-item">
-                        <div class="legend-color" style="background-color: #c7c7c7;"></div>
-                        <span>Domain (invalid cert)</span>
-                    </div>
-                    <div class="legend-item">
-                        <div class="legend-color" style="background-color: #9d4edd;"></div>
-                        <span>Correlation Objects</span>
-                    </div>
-                    <div class="legend-item">
-                        <div class="legend-edge high-confidence"></div>
-                        <span>High Confidence</span>
-                    </div>
-                    <div class="legend-item">
-                        <div class="legend-edge medium-confidence"></div>
-                        <span>Medium Confidence</span>
+                        <div class="legend-color" style="background-color: #00aaff;"></div>
+                        <span>ISPs</span>
                     </div>
                     <div class="legend-item">
                         <div class="legend-color" style="background-color: #ff6b6b;"></div>
-                        <span>Large Entity</span>
+                        <span>Certificate Authorities</span>
+                    </div>
+
+                    <div class="legend-item">
+                        <div class="legend-color" style="background-color: #9d4edd;"></div>
+                        <span>Correlation Objects</span>
                     </div>
                 </div>
             </section>
@@ -207,24 +194,79 @@
             </div>
         </div>
 
-        <div id="api-key-modal" class="modal">
+        <!-- Settings Modal -->
+        <div id="settings-modal" class="modal">
             <div class="modal-content">
                 <div class="modal-header">
-                    <h3>Configure API Keys</h3>
-                    <button id="api-key-modal-close" class="modal-close">[×]</button>
+                    <h3>Scanner Configuration</h3>
+                    <button id="settings-modal-close" class="modal-close">[×]</button>
                 </div>
                 <div class="modal-body">
-                    <p class="modal-description">
-                        Enter your API keys for enhanced data providers. Keys are stored in memory for the current session only and are never saved to disk.
+                    <div class="modal-details">
+                        <!-- Scan Settings Section -->
+                        <section class="modal-section">
+                            <details open>
+                                <summary>
+                                    <span>⚙️ Scan Settings</span>
+                                </summary>
+                                <div class="modal-section-content">
+                                    <div class="input-group">
+                                        <label for="max-depth">Recursion Depth</label>
+                                        <select id="max-depth">
+                                            <option value="1">Depth 1 - Direct relationships</option>
+                                            <option value="2" selected>Depth 2 - Recommended</option>
+                                            <option value="3">Depth 3 - Extended analysis</option>
+                                            <option value="4">Depth 4 - Deep reconnaissance</option>
+                                            <option value="5">Depth 5 - Maximum depth</option>
+                                        </select>
+                                    </div>
+                                </div>
+                            </details>
+                        </section>
+
+                        <!-- Provider Configuration Section -->
+                        <section class="modal-section">
+                            <details open>
+                                <summary>
+                                    <span>🔧 Provider Configuration</span>
+                                    <span class="merge-badge" id="provider-count">0</span>
+                                </summary>
+                                <div class="modal-section-content">
+                                    <div id="provider-config-list">
+                                        <!-- Dynamically populated -->
+                                    </div>
+                                </div>
+                            </details>
+                        </section>
+
+                        <!-- API Keys Section -->
+                        <section class="modal-section">
+                            <details>
+                                <summary>
+                                    <span>🔑 API Keys</span>
+                                    <span class="merge-badge" id="api-key-count">0</span>
+                                </summary>
+                                <div class="modal-section-content">
+                                    <p class="placeholder-subtext" style="margin-bottom: 1rem;">
+                                        ⚠️ API keys are stored in memory for the current session only.
+                                        Only provide API keys you don't use for anything else.
                                     </p>
                                     <div id="api-key-inputs">
+                                        <!-- Dynamically populated -->
                                     </div>
-                    <div class="button-group" style="flex-direction: row; justify-content: flex-end;">
-                        <button id="reset-api-keys" class="btn btn-secondary">
-                            <span>Reset</span>
+                                </div>
+                            </details>
+                        </section>
+
+                        <!-- Action Buttons -->
+                        <div class="button-group" style="margin-top: 1.5rem;">
+                            <button id="save-settings" class="btn btn-primary">
+                                <span class="btn-icon">[SAVE]</span>
+                                <span>Save Configuration</span>
                             </button>
-                        <button id="save-api-keys" class="btn btn-primary">
-                            <span>Save Keys</span>
+                            <button id="reset-settings" class="btn btn-secondary">
+                                <span class="btn-icon">[RESET]</span>
+                                <span>Reset to Defaults</span>
                             </button>
                         </div>
                     </div>
@@ -232,19 +274,42 @@
             </div>
         </div>
 
-    <script>
-        function copyToClipboard(elementId) {
-            const element = document.getElementById(elementId);
-            const textToCopy = element.innerText;
-            navigator.clipboard.writeText(textToCopy).then(() => {
-                // Optional: Show a success message
-                console.log('Copied to clipboard');
-            }).catch(err => {
-                console.error('Failed to copy: ', err);
-            });
-        }
-    </script>
+        <!-- Export Modal -->
+        <div id="export-modal" class="modal">
+            <div class="modal-content">
+                <div class="modal-header">
+                    <h3>Export Options</h3>
+                    <button id="export-modal-close" class="modal-close">[×]</button>
+                </div>
+                <div class="modal-body">
+                    <div class="modal-details">
+                        <section class="modal-section">
+                            <details open>
+                                <summary>
+                                    <span>📊 Available Exports</span>
+                                </summary>
+                                <div class="modal-section-content">
+                                    <div class="button-group" style="margin-top: 1rem;">
+                                        <button id="export-graph-json" class="btn btn-primary">
+                                            <span class="btn-icon">[JSON]</span>
+                                            <span>Export Graph Data</span>
+                                        </button>
+                                        <div class="status-row" style="margin-top: 0.5rem;">
+                                            <span class="status-label">Complete graph data with forensic audit trail,
+                                                provider statistics, and scan metadata in JSON format for analysis and
+                                                archival.</span>
+                                        </div>
+                                    </div>
+                                </div>
+                            </details>
+                        </section>
+                    </div>
+                </div>
+            </div>
+        </div>
+    </div>
     <script src="{{ url_for('static', filename='js/graph.js') }}"></script>
     <script src="{{ url_for('static', filename='js/main.js') }}"></script>
 </body>
+
 </html>

utils/helpers.py

@@ -1,3 +1,8 @@
+# dnsrecon-reduced/utils/helpers.py
+
+import ipaddress
+from typing import Union
+
 def _is_valid_domain(domain: str) -> bool:
     """
     Basic domain validation.
@@ -26,25 +31,64 @@ def _is_valid_domain(domain: str) -> bool:
 
 def _is_valid_ip(ip: str) -> bool:
     """
-    Basic IP address validation.
+    IP address validation supporting both IPv4 and IPv6.
 
     Args:
         ip: IP address string to validate
 
     Returns:
-        True if IP appears valid
+        True if IP appears valid (IPv4 or IPv6)
     """
+    if not ip:
+        return False
+    
     try:
-        parts = ip.split('.')
-        if len(parts) != 4:
-            return False
-
-        for part in parts:
-            num = int(part)
-            if not 0 <= num <= 255:
-                return False
-
+        # This handles both IPv4 and IPv6 validation
+        ipaddress.ip_address(ip.strip())
         return True
-
     except (ValueError, AttributeError):
         return False
+
+def is_valid_target(target: str) -> bool:
+    """
+    Checks if the target is a valid domain or IP address (IPv4/IPv6).
+
+    Args:
+        target: The target string to validate.
+
+    Returns:
+        True if the target is a valid domain or IP, False otherwise.
+    """
+    return _is_valid_domain(target) or _is_valid_ip(target)
+
+def get_ip_version(ip: str) -> Union[int, None]:
+    """
+    Get the IP version (4 or 6) of a valid IP address.
+    
+    Args:
+        ip: IP address string
+        
+    Returns:
+        4 for IPv4, 6 for IPv6, None if invalid
+    """
+    try:
+        addr = ipaddress.ip_address(ip.strip())
+        return addr.version
+    except (ValueError, AttributeError):
+        return None
+
+def normalize_ip(ip: str) -> Union[str, None]:
+    """
+    Normalize an IP address to its canonical form.
+    
+    Args:
+        ip: IP address string
+        
+    Returns:
+        Normalized IP address string, None if invalid
+    """
+    try:
+        addr = ipaddress.ip_address(ip.strip())
+        return str(addr)
+    except (ValueError, AttributeError):
+        return None