dnscope/core/scanner.py
2025-09-10 13:53:32 +02:00

461 lines
16 KiB
Python

"""
Main scanning orchestrator for DNSRecon.
Coordinates data gathering from multiple providers and builds the infrastructure graph.
"""
import threading
import time
import traceback
from typing import List, Set, Dict, Any, Optional
from concurrent.futures import ThreadPoolExecutor, as_completed
from core.graph_manager import GraphManager, NodeType, RelationshipType
from core.logger import get_forensic_logger, new_session
from providers.crtsh_provider import CrtShProvider
from config import config
class ScanStatus:
"""Enumeration of scan statuses."""
IDLE = "idle"
RUNNING = "running"
COMPLETED = "completed"
FAILED = "failed"
STOPPED = "stopped"
class Scanner:
"""
Main scanning orchestrator for DNSRecon passive reconnaissance.
Manages multi-provider data gathering and graph construction.
"""
def __init__(self):
"""Initialize scanner with default providers and empty graph."""
print("Initializing Scanner instance...")
try:
from providers.base_provider import BaseProvider
self.graph = GraphManager()
self.providers: List[BaseProvider] = []
self.status = ScanStatus.IDLE
self.current_target = None
self.current_depth = 0
self.max_depth = 2
self.stop_requested = False
self.scan_thread = None
# Scanning progress tracking
self.total_indicators_found = 0
self.indicators_processed = 0
self.current_indicator = ""
# Initialize providers
print("Calling _initialize_providers...")
self._initialize_providers()
# Initialize logger
print("Initializing forensic logger...")
self.logger = get_forensic_logger()
print("Scanner initialization complete")
except Exception as e:
print(f"ERROR: Scanner initialization failed: {e}")
traceback.print_exc()
raise
def _initialize_providers(self) -> None:
"""Initialize available providers based on configuration."""
self.providers = []
print("Initializing providers...")
# Always add free providers
if config.is_provider_enabled('crtsh'):
try:
crtsh_provider = CrtShProvider()
if crtsh_provider.is_available():
self.providers.append(crtsh_provider)
print("✓ CrtSh provider initialized successfully")
else:
print("✗ CrtSh provider is not available")
except Exception as e:
print(f"✗ Failed to initialize CrtSh provider: {e}")
traceback.print_exc()
print(f"Initialized {len(self.providers)} providers")
def _debug_threads(self):
"""Debug function to show current threads."""
print("=== THREAD DEBUG INFO ===")
for t in threading.enumerate():
print(f"Thread: {t.name} | Alive: {t.is_alive()} | Daemon: {t.daemon}")
print("=== END THREAD DEBUG ===")
def start_scan(self, target_domain: str, max_depth: int = 2) -> bool:
"""
Start a new reconnaissance scan.
Args:
target_domain: Initial domain to investigate
max_depth: Maximum recursion depth
Returns:
bool: True if scan started successfully
"""
print(f"Scanner.start_scan called with target='{target_domain}', depth={max_depth}")
try:
print("Checking current status...")
self._debug_threads()
if self.status == ScanStatus.RUNNING:
print("Scan already running, rejecting new scan")
return False
# Check if we have any providers
if not self.providers:
print("No providers available, cannot start scan")
return False
print(f"Current status: {self.status}, Providers: {len(self.providers)}")
# Stop any existing scan thread
if self.scan_thread and self.scan_thread.is_alive():
print("Stopping existing scan thread...")
self.stop_requested = True
self.scan_thread.join(timeout=2.0)
if self.scan_thread.is_alive():
print("WARNING: Could not stop existing thread")
return False
# Reset state
print("Resetting scanner state...")
#print("Running graph.clear()")
#self.graph.clear()
print("running self.current_target = target_domain.lower().strip()")
self.current_target = target_domain.lower().strip()
self.max_depth = max_depth
self.current_depth = 0
self.stop_requested = False
self.total_indicators_found = 0
self.indicators_processed = 0
self.current_indicator = self.current_target
# Start new forensic session
print("Starting new forensic session...")
self.logger = new_session()
# FOR DEBUGGING: Run scan synchronously instead of in thread
print("Running scan synchronously for debugging...")
self._execute_scan_sync(self.current_target, max_depth)
return True
except Exception as e:
print(f"ERROR: Exception in start_scan: {e}")
traceback.print_exc()
return False
def stop_scan(self) -> bool:
"""
Request scan termination.
Returns:
bool: True if stop request was accepted
"""
try:
if self.status == ScanStatus.RUNNING:
self.stop_requested = True
print("Scan stop requested")
return True
print("No active scan to stop")
return False
except Exception as e:
print(f"ERROR: Exception in stop_scan: {e}")
traceback.print_exc()
return False
def get_scan_status(self) -> Dict[str, Any]:
"""
Get current scan status and progress.
Returns:
Dictionary containing scan status information
"""
try:
return {
'status': self.status,
'target_domain': self.current_target,
'current_depth': self.current_depth,
'max_depth': self.max_depth,
'current_indicator': self.current_indicator,
'total_indicators_found': self.total_indicators_found,
'indicators_processed': self.indicators_processed,
'progress_percentage': self._calculate_progress(),
'enabled_providers': [provider.get_name() for provider in self.providers],
'graph_statistics': self.graph.get_statistics()
}
except Exception as e:
print(f"ERROR: Exception in get_scan_status: {e}")
traceback.print_exc()
return {
'status': 'error',
'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': {}
}
def _calculate_progress(self) -> float:
"""Calculate scan progress percentage."""
if self.total_indicators_found == 0:
return 0.0
return min(100.0, (self.indicators_processed / self.total_indicators_found) * 100)
def _execute_scan_sync(self, target_domain: str, max_depth: int) -> None:
"""
Execute the reconnaissance scan synchronously (for debugging).
Args:
target_domain: Target domain to investigate
max_depth: Maximum recursion depth
"""
print(f"_execute_scan_sync started for {target_domain} with depth {max_depth}")
try:
print("Setting status to RUNNING")
self.status = ScanStatus.RUNNING
# Log scan start
enabled_providers = [provider.get_name() for provider in self.providers]
self.logger.log_scan_start(target_domain, max_depth, enabled_providers)
print(f"Logged scan start with providers: {enabled_providers}")
# Initialize with target domain
print(f"Adding target domain '{target_domain}' as initial node")
self.graph.add_node(target_domain, NodeType.DOMAIN)
# BFS-style exploration with depth limiting
current_level_domains = {target_domain}
processed_domains = set()
print(f"Starting BFS exploration...")
for depth in range(max_depth + 1):
if self.stop_requested:
print(f"Stop requested at depth {depth}")
break
self.current_depth = depth
print(f"Processing depth level {depth} with {len(current_level_domains)} domains")
if not current_level_domains:
print("No domains to process at this level")
break
# Update progress tracking
self.total_indicators_found += len(current_level_domains)
next_level_domains = set()
# Process domains at current depth level
for domain in current_level_domains:
if self.stop_requested:
print(f"Stop requested while processing domain {domain}")
break
if domain in processed_domains:
print(f"Domain {domain} already processed, skipping")
continue
print(f"Processing domain: {domain}")
self.current_indicator = domain
self.indicators_processed += 1
# Query all providers for this domain
discovered_domains = self._query_providers_for_domain(domain)
print(f"Discovered {len(discovered_domains)} new domains from {domain}")
# Add discovered domains to next level if not at max depth
if depth < max_depth:
for discovered_domain in discovered_domains:
if discovered_domain not in processed_domains:
next_level_domains.add(discovered_domain)
print(f"Adding {discovered_domain} to next level")
processed_domains.add(domain)
current_level_domains = next_level_domains
print(f"Completed depth {depth}, {len(next_level_domains)} domains for next level")
# Finalize scan
if self.stop_requested:
self.status = ScanStatus.STOPPED
print("Scan completed with STOPPED status")
else:
self.status = ScanStatus.COMPLETED
print("Scan completed with COMPLETED status")
self.logger.log_scan_complete()
# Print final statistics
stats = self.graph.get_statistics()
print(f"Final scan statistics:")
print(f" - Total nodes: {stats['basic_metrics']['total_nodes']}")
print(f" - Total edges: {stats['basic_metrics']['total_edges']}")
print(f" - Domains processed: {len(processed_domains)}")
except Exception as e:
print(f"ERROR: Scan execution failed with error: {e}")
traceback.print_exc()
self.status = ScanStatus.FAILED
self.logger.logger.error(f"Scan failed: {e}")
def _query_providers_for_domain(self, domain: str) -> Set[str]:
"""
Query all enabled providers for information about a domain.
Args:
domain: Domain to investigate
Returns:
Set of newly discovered domains
"""
print(f"Querying {len(self.providers)} providers for domain: {domain}")
discovered_domains = set()
if not self.providers:
print("No providers available")
return discovered_domains
# Query providers sequentially for debugging
for provider in self.providers:
if self.stop_requested:
print("Stop requested, cancelling provider queries")
break
try:
print(f"Querying provider: {provider.get_name()}")
relationships = provider.query_domain(domain)
print(f"Provider {provider.get_name()} returned {len(relationships)} relationships")
for source, target, rel_type, confidence, raw_data in relationships:
print(f"Processing relationship: {source} -> {target} ({rel_type.relationship_name})")
# Add target node to graph if it doesn't exist
self.graph.add_node(target, NodeType.DOMAIN)
# Add relationship
success = self.graph.add_edge(
source, target, rel_type, confidence,
provider.get_name(), raw_data
)
if success:
print(f"Added new relationship: {source} -> {target}")
else:
print(f"Relationship already exists or failed to add: {source} -> {target}")
discovered_domains.add(target)
except Exception as e:
print(f"Provider {provider.get_name()} failed for {domain}: {e}")
traceback.print_exc()
self.logger.logger.error(f"Provider {provider.get_name()} failed for {domain}: {e}")
print(f"Total unique domains discovered: {len(discovered_domains)}")
return discovered_domains
def get_graph_data(self) -> Dict[str, Any]:
"""
Get current graph data for visualization.
Returns:
Graph data formatted for frontend
"""
return self.graph.get_graph_data()
def export_results(self) -> Dict[str, Any]:
"""
Export complete scan results including graph and audit trail.
Returns:
Dictionary containing complete scan results
"""
# Get graph data
graph_data = self.graph.export_json()
# Get forensic audit trail
audit_trail = self.logger.export_audit_trail()
# Get provider statistics
provider_stats = {}
for provider in self.providers:
provider_stats[provider.get_name()] = provider.get_statistics()
# Combine all results
export_data = {
'scan_metadata': {
'target_domain': self.current_target,
'max_depth': self.max_depth,
'final_status': self.status,
'total_indicators_processed': self.indicators_processed,
'enabled_providers': list(provider_stats.keys())
},
'graph_data': graph_data,
'forensic_audit': audit_trail,
'provider_statistics': provider_stats,
'scan_summary': self.logger.get_forensic_summary()
}
return export_data
def remove_provider(self, provider_name: str) -> bool:
"""
Remove a provider from the scanner.
Args:
provider_name: Name of provider to remove
Returns:
bool: True if provider was removed
"""
for i, provider in enumerate(self.providers):
if provider.get_name() == provider_name:
self.providers.pop(i)
return True
return False
def get_provider_statistics(self) -> Dict[str, Dict[str, Any]]:
"""
Get statistics for all providers.
Returns:
Dictionary mapping provider names to their statistics
"""
stats = {}
for provider in self.providers:
stats[provider.get_name()] = provider.get_statistics()
return stats
class ScannerProxy:
def __init__(self):
self._scanner = None
print("ScannerProxy initialized")
def __getattr__(self, name):
if self._scanner is None:
print("Creating new Scanner instance...")
self._scanner = Scanner()
print("Scanner instance created")
return getattr(self._scanner, name)
# Global scanner instance
scanner = ScannerProxy()