tools: Machine audit - backend scripts to run on Nagios server

.gitignore

@@ -6,3 +6,5 @@ ansible/host_vars/*
 **/vendor_files
 .vscode/
 *.swp
+ansible/machine_audit/backend/collectedInfo
+ansible/machine_audit/backend/.env

ansible/machine_audit/backend/getNodeList.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python3
+
+# Some portions generated by IBM Bob
+
+import sys
+import jenkins
+from pathlib import Path
+
+def getIP(nodeConfig):
+    find1 = nodeConfig.find("<host>") + 6
+    find2 = nodeConfig.find("</host>")
+    if find1 > 5 and find2 > -1:
+        ip = nodeConfig[find1:find2]
+        return ip
+    else:
+        return None
+
+def getNodePort(nodeConfig):
+    find1 = nodeConfig.find("<port>") + 6
+    find2 = nodeConfig.find("</port>")
+    if find1 > 5 and find2 > -1:
+        port = nodeConfig[find1:find2]
+        return port
+    else:
+        return None
+
+def createServer(username, password, url):
+    try:
+        server = jenkins.Jenkins(url=url, username=username,
+                            password=password)
+        return server
+
+    except Exception as e:
+        print("Error: Could not connect to Jenkins server")
+        return sys.exit(1)
+
+def getNodeList(url, username, password):
+
+    try:
+        # Create collectedInfo directory if it doesn't exist
+        script_dir = Path(__file__).parent
+        collected_info_dir = script_dir / "collectedInfo"
+        collected_info_dir.mkdir(exist_ok=True)
+
+        # Define machine.list file path
+        machine_list_path = collected_info_dir / "machine.list"
+
+        # Remove existing file if it exists
+        if machine_list_path.exists():
+            machine_list_path.unlink()
+
+        # Connect to Jenkins
+        server = createServer(username, password, url)
+        nodes = server.get_nodes()
+
+        # Create new machine.list file and write node information
+        with open(machine_list_path, 'w') as f:
+            for node in nodes:
+                if "build" in node["name"] or "test" in node["name"] or "dockerhost" in node["name"]:
+                    config = server.get_node_config(node["name"])
+                    ip = getIP(config)
+                    port = getNodePort(config)
+                    f.write(f"{node['name']} {ip} {port}\n")
+
+        print(f"Machine list saved to: {machine_list_path}")
+
+    except jenkins.JenkinsException as e:
+        print(f"Jenkins error: {e}")
+        return None
+    except Exception as e:
+        print(f"Error: {e}")
+        return None
+
+if __name__ == "__main__":
+    url, username, password = sys.argv[1:4]
+    getNodeList(url, username, password)

ansible/machine_audit/backend/main.py

@@ -0,0 +1,121 @@
+#!/usr/bin/env python3
+
+# Some portions generated by IBM Bob
+
+import sys
+import subprocess
+from pathlib import Path
+from getNodeList import getNodeList
+
+# ANSI color codes
+GREEN = '\033[92m'
+RED = '\033[91m'
+CYAN = '\033[96m'
+RESET = '\033[0m'
+
+UNIX_LOG_PATH="/var/log/machine_info.json"
+WINDOWS_LOG_PATH="c:\\machine_info.json"
+
+def scp_machine_info(node_name, ip, port, collected_info_dir, log_path):
+
+    if ip is None or ip == "None" or port is None or port == "None":
+        print(f"  {CYAN}[SKIP]{RESET} {node_name}: IP or port is None")
+        return False
+
+    local_filename = f"{node_name}_machine_info.json"
+    local_filepath = collected_info_dir / local_filename
+
+    # Use nagios user to SCP the file
+    remote_location = f"nagios@{ip}:{log_path}"
+    scp_command = [
+        "scp",
+        "-P", port,
+        "-o", "StrictHostKeyChecking=no",
+        "-o", "ConnectTimeout=5",
+        "-o", "NumberOfPasswordPrompts=0",
+        remote_location,
+        str(local_filepath)
+    ]
+
+    print(f"  [INFO] Copying from {node_name} ({ip}:{port})...")
+
+    try:
+        result = subprocess.run(
+            scp_command,
+            capture_output=True,
+            text=True,
+            timeout=30
+        )
+
+        if result.returncode == 0:
+            print(f"  {GREEN}[SUCCESS]{RESET} File saved to {local_filename}")
+            return True
+        else:
+            print(f"  {RED}[ERROR]{RESET} SCP failed for {node_name}: {result.stderr.strip()}")
+            return False
+
+    except subprocess.TimeoutExpired:
+        print(f"  {RED}[ERROR]{RESET} SCP timeout for {node_name}")
+        return False
+    except Exception as e:
+        print(f"  {RED}[ERROR]{RESET} Exception for {node_name}: {e}")
+        return False
+
+
+def main():
+
+    # Jenkins credentials from command line
+    url, username, password = sys.argv[1:4]
+
+    # Generate machine list from Jenkins
+    print("\nFetching node list from Jenkins...")
+    getNodeList(url, username, password)
+
+    script_dir = Path(__file__).parent
+    collected_info_dir = script_dir / "collectedInfo"
+    machine_list_path = collected_info_dir / "machine.list"
+
+    if not machine_list_path.exists():
+        print(f"Error: machine.list not found at {machine_list_path}")
+        return 1
+
+    # Remove any existing *_machine_info.json files from collectedInfo directory
+    print("\nCleaning up old machine_info.json files...")
+    for old_file in collected_info_dir.glob("*_machine_info.json"):
+        old_file.unlink()
+        print(f"  Removed: {old_file.name}")
+
+    # Read machine list and collect files
+    print("\nCollecting machine_info.json from each machine:")
+    successful = 0
+    failed = 0
+
+    with open(machine_list_path, 'r') as f:
+        for line in f:
+            line = line.strip()
+            if not line:
+                continue
+
+            parts = line.split()
+            if len(parts) >= 3:
+                node_name = parts[0]
+                ip = parts[1]
+                port = parts[2]
+
+                # SCP only from non windows machines for now
+                if scp_machine_info(node_name, ip, port, collected_info_dir, UNIX_LOG_PATH):
+                    successful += 1
+                else:
+                    failed += 1
+
+    # Print summary
+    print(f"\n{'='*60}")
+    print(f"Collection Summary:")
+    print(f"  Successful: {successful}")
+    print(f"  Failed: {failed}")
+    print(f"{'='*60}")
+
+    return 0
+
+if __name__ == "__main__":
+    sys.exit(main())