souleyez 2.43.29__py3-none-any.whl → 3.0.0__py3-none-any.whl

souleyez/parsers/smbmap_parser.py

@@ -56,168 +56,189 @@ def parse_smbmap_output(output: str, target: str = "") -> Dict[str, Any]:
         }
     """
     result = {
-        'target': target,
-        'status': None,
-        'shares': [],
-        'files': [],
-        'smb_detected': False,
-        'hosts_count': 0,
-        'error': None
+        "target": target,
+        "status": None,
+        "shares": [],
+        "files": [],
+        "smb_detected": False,
+        "hosts_count": 0,
+        "error": None,
     }
 
     # Check for SMB detection (even if tool crashes later)
     # [*] Detected 1 hosts serving SMB
-    smb_detected_match = re.search(r'\[\*\]\s*Detected\s+(\d+)\s+hosts?\s+serving\s+SMB', output)
+    smb_detected_match = re.search(
+        r"\[\*\]\s*Detected\s+(\d+)\s+hosts?\s+serving\s+SMB", output
+    )
     if smb_detected_match:
-        result['smb_detected'] = True
-        result['hosts_count'] = int(smb_detected_match.group(1))
+        result["smb_detected"] = True
+        result["hosts_count"] = int(smb_detected_match.group(1))
 
     # Check for Python traceback (tool crash)
-    if 'Traceback (most recent call last):' in output:
+    if "Traceback (most recent call last):" in output:
         # Extract error message from traceback
-        error_match = re.search(r'(?:Error|Exception).*?[\'"]([^\'"]+)[\'"]', output, re.DOTALL)
+        error_match = re.search(
+            r'(?:Error|Exception).*?[\'"]([^\'"]+)[\'"]', output, re.DOTALL
+        )
         if error_match:
-            result['error'] = error_match.group(1)
+            result["error"] = error_match.group(1)
         else:
             # Try to get the last line of the traceback
-            traceback_lines = output.split('Traceback (most recent call last):')[-1].strip().split('\n')
+            traceback_lines = (
+                output.split("Traceback (most recent call last):")[-1]
+                .strip()
+                .split("\n")
+            )
             for line in reversed(traceback_lines):
                 line = line.strip()
-                if line and not line.startswith('File') and not line.startswith('raise'):
-                    result['error'] = line[:200]  # Limit length
+                if (
+                    line
+                    and not line.startswith("File")
+                    and not line.startswith("raise")
+                ):
+                    result["error"] = line[:200]  # Limit length
                     break
 
-    lines = output.split('\n')
+    lines = output.split("\n")
     in_share_table = False
     current_share = None
 
     for i, line in enumerate(lines):
         # Remove ANSI color codes and control characters more thoroughly
-        line = re.sub(r'\x1b\[[0-9;]*[a-zA-Z]', '', line)  # All ANSI escape sequences
-        line = re.sub(r'\x1b\].*?\x07', '', line)  # OSC sequences
+        line = re.sub(r"\x1b\[[0-9;]*[a-zA-Z]", "", line)  # All ANSI escape sequences
+        line = re.sub(r"\x1b\].*?\x07", "", line)  # OSC sequences
         # Only remove leading progress indicators, not all brackets
-        line = re.sub(r'^[\[\]\|/\\-]+\s*', '', line)
+        line = re.sub(r"^[\[\]\|/\\-]+\s*", "", line)
         line = line.strip()
 
         # Extract target and status
         # [+] IP: 10.0.0.82:445	Name: 10.0.0.82           	Status: Authenticated
-        if line.startswith('+') and 'IP:' in line and 'Status:' in line:
-            status_match = re.search(r'Status:\s+(\w+)', line)
+        if line.startswith("+") and "IP:" in line and "Status:" in line:
+            status_match = re.search(r"Status:\s+(\w+)", line)
             if status_match:
-                result['status'] = status_match.group(1)
+                result["status"] = status_match.group(1)
 
             # Extract target IP if not provided
-            if not result['target']:
-                ip_match = re.search(r'IP:\s+([\d\.]+)', line)
+            if not result["target"]:
+                ip_match = re.search(r"IP:\s+([\d\.]+)", line)
                 if ip_match:
-                    result['target'] = ip_match.group(1)
+                    result["target"] = ip_match.group(1)
 
         # Detect share table header
         # Disk                                                  	Permissions	Comment
-        elif 'Disk' in line and 'Permissions' in line and 'Comment' in line:
+        elif "Disk" in line and "Permissions" in line and "Comment" in line:
             in_share_table = True
             continue
 
         # Skip separator line
-        elif line.startswith('----') or line.startswith('==='):
+        elif line.startswith("----") or line.startswith("==="):
             continue
 
         # Parse share entries
-        elif in_share_table and line and not line.startswith('*') and not line.startswith('Closed'):
+        elif (
+            in_share_table
+            and line
+            and not line.startswith("*")
+            and not line.startswith("Closed")
+        ):
             # Try to parse share line
             # Format: sharename <tabs/spaces> permissions <tabs/spaces> comment
             # tmp                                               	READ, WRITE	oh noes!
 
             share_name = None
             permissions = None
-            comment = ''
+            comment = ""
 
             # Try tab split first
-            parts = re.split(r'\t+', line)
+            parts = re.split(r"\t+", line)
             if len(parts) >= 2:
                 share_name = parts[0].strip()
                 # Find permissions in remaining parts
                 for p in parts[1:]:
                     p = p.strip().upper()
-                    if any(x in p for x in ['READ', 'WRITE', 'NO ACCESS', 'NOACCESS']):
+                    if any(x in p for x in ["READ", "WRITE", "NO ACCESS", "NOACCESS"]):
                         permissions = p
                         break
                 # Comment is everything after permissions
                 if permissions and len(parts) > 2:
-                    perm_idx = next((i for i, p in enumerate(parts) if permissions in p.upper()), -1)
+                    perm_idx = next(
+                        (i for i, p in enumerate(parts) if permissions in p.upper()), -1
+                    )
                     if perm_idx >= 0 and perm_idx + 1 < len(parts):
-                        comment = ' '.join(parts[perm_idx + 1:]).strip()
+                        comment = " ".join(parts[perm_idx + 1 :]).strip()
 
             # No tabs or tab parse failed - try space-based parsing
             if not permissions:
                 # Match patterns with flexible spacing and permission variations
                 permission_patterns = [
-                    r'^\s*(\S+)\s{2,}(READ,?\s*WRITE|READ\s*ONLY|WRITE\s*ONLY|NO\s*ACCESS|READ|WRITE)(?:\s{2,}(.*))?$',
-                    r'^\s*(\S+)\s+(READ,?\s*WRITE|READ\s*ONLY|WRITE\s*ONLY|NO\s*ACCESS|READ|WRITE)\s*(.*)$',
+                    r"^\s*(\S+)\s{2,}(READ,?\s*WRITE|READ\s*ONLY|WRITE\s*ONLY|NO\s*ACCESS|READ|WRITE)(?:\s{2,}(.*))?$",
+                    r"^\s*(\S+)\s+(READ,?\s*WRITE|READ\s*ONLY|WRITE\s*ONLY|NO\s*ACCESS|READ|WRITE)\s*(.*)$",
                 ]
                 for pattern in permission_patterns:
                     match = re.match(pattern, line, re.IGNORECASE)
                     if match:
                         share_name = match.group(1).strip()
                         permissions = match.group(2).strip().upper()
-                        comment = match.group(3).strip() if match.group(3) else ''
+                        comment = match.group(3).strip() if match.group(3) else ""
                         break
 
             if not share_name or not permissions:
                 continue
 
             # Skip empty lines or non-share lines
-            if not share_name or share_name in ['Disk', 'IPC', '', '*']:
+            if not share_name or share_name in ["Disk", "IPC", "", "*"]:
                 continue
 
             # Skip separator lines (----, ===, etc.)
-            if re.match(r'^[\-=]+$', share_name):
+            if re.match(r"^[\-=]+$", share_name):
                 continue
 
             # Determine share type (Disk vs IPC)
-            share_type = 'IPC' if share_name.endswith('$') and 'IPC' in comment else 'Disk'
+            share_type = (
+                "IPC" if share_name.endswith("$") and "IPC" in comment else "Disk"
+            )
 
             # Parse permissions
-            readable = 'READ' in permissions.upper()
-            writable = 'WRITE' in permissions.upper()
+            readable = "READ" in permissions.upper()
+            writable = "WRITE" in permissions.upper()
 
             share_info = {
-                'name': share_name,
-                'type': share_type,
-                'permissions': permissions,
-                'comment': comment,
-                'readable': readable,
-                'writable': writable
+                "name": share_name,
+                "type": share_type,
+                "permissions": permissions,
+                "comment": comment,
+                "readable": readable,
+                "writable": writable,
             }
 
-            result['shares'].append(share_info)
+            result["shares"].append(share_info)
             current_share = share_name
 
         # Parse file listings (if -R was used)
         # dr--r--r--                0 Sat May 16 14:06:55 2009	.
         # dr--r--r--                0 Sat May 16 14:06:55 2009	..
         # fr--r--r--              512 Sat May 16 14:06:55 2009	script.sh
-        elif current_share and re.match(r'^[df]r', line):
+        elif current_share and re.match(r"^[df]r", line):
             # File listing format: permissions size timestamp filename
-            file_match = re.match(r'^([df]r[\-rwx]+)\s+(\d+)\s+(.+?)\s{2,}(.+)$', line)
+            file_match = re.match(r"^([df]r[\-rwx]+)\s+(\d+)\s+(.+?)\s{2,}(.+)$", line)
             if file_match:
                 perms, size, timestamp, filename = file_match.groups()
 
                 # Skip . and .. entries
-                if filename in ['.', '..']:
+                if filename in [".", ".."]:
                     continue
 
                 file_info = {
-                    'share': current_share,
-                    'path': filename,
-                    'size': int(size),
-                    'timestamp': timestamp.strip(),
-                    'is_directory': perms.startswith('d')
+                    "share": current_share,
+                    "path": filename,
+                    "size": int(size),
+                    "timestamp": timestamp.strip(),
+                    "is_directory": perms.startswith("d"),
                 }
-                result['files'].append(file_info)
+                result["files"].append(file_info)
 
         # Detect end of output
-        elif 'Closed' in line and 'connections' in line:
+        elif "Closed" in line and "connections" in line:
             in_share_table = False
             current_share = None
 
@@ -240,86 +261,121 @@ def extract_findings(parsed_data: Dict[str, Any]) -> List[Dict[str, Any]]:
     findings = []
 
     # Finding 1: Writable shares (HIGH severity)
-    writable_shares = [s for s in parsed_data['shares'] if s['writable']]
+    writable_shares = [s for s in parsed_data["shares"] if s["writable"]]
     if writable_shares:
-        share_names = ', '.join([s['name'] for s in writable_shares])
-        findings.append({
-            'title': 'Writable SMB Shares Detected',
-            'severity': 'high',
-            'description': f"Found {len(writable_shares)} SMB share(s) with WRITE permissions: {share_names}. "
-            "Writable shares can be exploited to upload malicious files, plant ransomware, "
-            "or exfiltrate sensitive data.",
-            'evidence': '\n'.join([
-                f"- {s['name']}: {s['permissions']} ({s['comment']})"
-                for s in writable_shares
-            ])
-        })
+        share_names = ", ".join([s["name"] for s in writable_shares])
+        findings.append(
+            {
+                "title": "Writable SMB Shares Detected",
+                "severity": "high",
+                "description": f"Found {len(writable_shares)} SMB share(s) with WRITE permissions: {share_names}. "
+                "Writable shares can be exploited to upload malicious files, plant ransomware, "
+                "or exfiltrate sensitive data.",
+                "evidence": "\n".join(
+                    [
+                        f"- {s['name']}: {s['permissions']} ({s['comment']})"
+                        for s in writable_shares
+                    ]
+                ),
+            }
+        )
 
     # Finding 2: Readable shares (MEDIUM severity)
-    readable_shares = [s for s in parsed_data['shares']
-                       if s['readable'] and not s['writable'] and s['type'] == 'Disk']
+    readable_shares = [
+        s
+        for s in parsed_data["shares"]
+        if s["readable"] and not s["writable"] and s["type"] == "Disk"
+    ]
     if readable_shares:
-        share_names = ', '.join([s['name'] for s in readable_shares])
-        findings.append({
-            'title': 'Readable SMB Shares Detected',
-            'severity': 'medium',
-            'description': f"Found {len(readable_shares)} SMB share(s) with READ permissions: {share_names}. "
-            "These shares may contain sensitive information accessible without proper authentication.",
-            'evidence': '\n'.join([
-                f"- {s['name']}: {s['permissions']} ({s['comment']})"
-                for s in readable_shares
-            ])
-        })
+        share_names = ", ".join([s["name"] for s in readable_shares])
+        findings.append(
+            {
+                "title": "Readable SMB Shares Detected",
+                "severity": "medium",
+                "description": f"Found {len(readable_shares)} SMB share(s) with READ permissions: {share_names}. "
+                "These shares may contain sensitive information accessible without proper authentication.",
+                "evidence": "\n".join(
+                    [
+                        f"- {s['name']}: {s['permissions']} ({s['comment']})"
+                        for s in readable_shares
+                    ]
+                ),
+            }
+        )
 
     # Finding 3: Anonymous access (MEDIUM severity)
-    if parsed_data.get('status') in ['Guest', 'Anonymous']:
-        accessible_shares = [s for s in parsed_data['shares']
-                             if s['readable'] or s['writable']]
+    if parsed_data.get("status") in ["Guest", "Anonymous"]:
+        accessible_shares = [
+            s for s in parsed_data["shares"] if s["readable"] or s["writable"]
+        ]
         if accessible_shares:
-            findings.append({
-                'title': 'Anonymous SMB Access Allowed',
-                'severity': 'medium',
-                'description': f"Anonymous/guest access is permitted, allowing access to {len(accessible_shares)} share(s) "
-                "without authentication. This violates the principle of least privilege.",
-                'evidence': f"Authentication Status: {parsed_data.get('status')}\n"
-                + '\n'.join([f"- {s['name']}: {s['permissions']}" for s in accessible_shares])
-            })
+            findings.append(
+                {
+                    "title": "Anonymous SMB Access Allowed",
+                    "severity": "medium",
+                    "description": f"Anonymous/guest access is permitted, allowing access to {len(accessible_shares)} share(s) "
+                    "without authentication. This violates the principle of least privilege.",
+                    "evidence": f"Authentication Status: {parsed_data.get('status')}\n"
+                    + "\n".join(
+                        [
+                            f"- {s['name']}: {s['permissions']}"
+                            for s in accessible_shares
+                        ]
+                    ),
+                }
+            )
 
     # Finding 4: Sensitive files exposed (if files were enumerated)
     sensitive_patterns = [
-        (r'\.config$', 'Configuration files'),
-        (r'password|passwd|pwd', 'Password files'),
-        (r'\.key|\.pem|\.crt', 'Cryptographic keys/certificates'),
-        (r'backup|\.bak|\.old', 'Backup files'),
-        (r'\.sql|\.db|\.sqlite', 'Database files'),
-        (r'id_rsa|id_dsa|\.ssh', 'SSH private keys')
+        (r"\.config$", "Configuration files"),
+        (r"password|passwd|pwd", "Password files"),
+        (r"\.key|\.pem|\.crt", "Cryptographic keys/certificates"),
+        (r"backup|\.bak|\.old", "Backup files"),
+        (r"\.sql|\.db|\.sqlite", "Database files"),
+        (r"id_rsa|id_dsa|\.ssh", "SSH private keys"),
     ]
 
     for pattern, desc in sensitive_patterns:
-        matching_files = [f for f in parsed_data['files']
-                          if re.search(pattern, f['path'], re.IGNORECASE)]
+        matching_files = [
+            f
+            for f in parsed_data["files"]
+            if re.search(pattern, f["path"], re.IGNORECASE)
+        ]
         if matching_files:
-            findings.append({
-                'title': f'Sensitive Files Exposed: {desc}',
-                'severity': 'high',
-                'description': f"Found {len(matching_files)} potentially sensitive file(s) ({desc}) "
-                "accessible via SMB shares.",
-                'evidence': '\n'.join([
-                    f"- {f['share']}/{f['path']} ({f['size']} bytes)"
-                    for f in matching_files[:10]  # Limit to first 10
-                ]) + (f"\n... and {len(matching_files) - 10} more" if len(matching_files) > 10 else "")
-            })
+            findings.append(
+                {
+                    "title": f"Sensitive Files Exposed: {desc}",
+                    "severity": "high",
+                    "description": f"Found {len(matching_files)} potentially sensitive file(s) ({desc}) "
+                    "accessible via SMB shares.",
+                    "evidence": "\n".join(
+                        [
+                            f"- {f['share']}/{f['path']} ({f['size']} bytes)"
+                            for f in matching_files[:10]  # Limit to first 10
+                        ]
+                    )
+                    + (
+                        f"\n... and {len(matching_files) - 10} more"
+                        if len(matching_files) > 10
+                        else ""
+                    ),
+                }
+            )
 
     # Finding 5: Info - All shares enumerated
-    if parsed_data['shares']:
-        findings.append({
-            'title': 'SMB Share Enumeration Successful',
-            'severity': 'info',
-            'description': f"Successfully enumerated {len(parsed_data['shares'])} SMB share(s) on target.",
-            'evidence': '\n'.join([
-                f"- {s['name']} ({s['type']}): {s['permissions']}"
-                for s in parsed_data['shares']
-            ])
-        })
+    if parsed_data["shares"]:
+        findings.append(
+            {
+                "title": "SMB Share Enumeration Successful",
+                "severity": "info",
+                "description": f"Successfully enumerated {len(parsed_data['shares'])} SMB share(s) on target.",
+                "evidence": "\n".join(
+                    [
+                        f"- {s['name']} ({s['type']}): {s['permissions']}"
+                        for s in parsed_data["shares"]
+                    ]
+                ),
+            }
+        )
 
     return findings