bug: Fixes parallelization and improves output logic

README.md

@@ -65,20 +65,20 @@ There is a docker build file if you want to run the scanner from a container:
 ### Command-line options
 
 ```
-usage: gcp-scanner -o /folder_to_save_results/ -g -
+usage: python3 scanner.py -o folder_to_save_results -g -
 
 GCP Scanner
 
 options:
   -h, --help            show this help message and exit
+  -ls, --light-scan     Return only the most important GCP resource fields in the output.
   -k KEY_PATH, --sa-key-path KEY_PATH
                         Path to directory with SA keys in json format
   -g GCLOUD_PROFILE_PATH, --gcloud-profile-path GCLOUD_PROFILE_PATH
                         Path to directory with gcloud profile. Specify - to search for credentials in default gcloud config path
   -m, --use-metadata    Extract credentials from GCE instance metadata
   -at ACCESS_TOKEN_FILES, --access-token-files ACCESS_TOKEN_FILES
-                        A list of comma separated files with access token and OAuth scopes.TTL limited. A token and scopes should be stored in JSON
-                        format.
+                        A list of comma separated files with access token and OAuth scopes.TTL limited. A token and scopes should be stored in JSON format.
   -rt REFRESH_TOKEN_FILES, --refresh-token-files REFRESH_TOKEN_FILES
                         A list of comma separated files with refresh_token, client_id,token_uri and client_secret stored in JSON format.
   -s KEY_NAME, --service-account KEY_NAME
@@ -89,10 +89,14 @@ options:
                         Comma separated list of project names to include in the scan
   -c CONFIG_PATH, --config CONFIG_PATH
                         A path to config file with a set of specific resources to scan.
-  -l {INFO,WARNING,ERROR}, --logging {INFO,WARNING,ERROR}
+  -l {DEBUG,INFO,WARNING,ERROR,CRITICAL}, --logging {DEBUG,INFO,WARNING,ERROR,CRITICAL}
                         Set logging level (INFO, WARNING, ERROR)
-  -lf LOG_DIRECTORY, --log-file LOG_DIRECTORY
+  -lf LOG_FILE, --log-file LOG_FILE
                         Save logs to the path specified rather than displaying in console
+  -pwc PROJECT_WORKER_COUNT, --project-worker-count PROJECT_WORKER_COUNT
+                        Set limit for project crawlers run in parallel.
+  -rwc RESOURCE_WORKER_COUNT, --resource-worker-count RESOURCE_WORKER_COUNT
+                        Set limit for resource crawlers run in parallel.
 
 Required parameters:
   -o OUTPUT, --output-dir OUTPUT

src/gcp_scanner/arguments.py

@@ -129,11 +129,17 @@ def arg_parser():
       help='Save logs to the path specified rather than displaying in\
  console')
   parser.add_argument(
-      '-wc',
-      '--worker-count',
+      '-pwc',
+      '--project-worker-count',
       default=1,
-      dest='worker_count',
-      help='Set limit for workers run in parallel.')
+      dest='project_worker_count',
+      help='Set limit for project crawlers run in parallel.')
+  parser.add_argument(
+      '-rwc',
+      '--resource-worker-count',
+      default=1,
+      dest='resource_worker_count',
+      help='Set limit for resource crawlers run in parallel.')
 
   args: argparse.Namespace = parser.parse_args()
 

src/gcp_scanner/models.py

@@ -58,7 +58,7 @@ def __init__(
     sa_name,
     credentials,
     chain_so_far,
-    worker_count
+    resource_worker_count
   ):
     self.project = project
     self.sa_results = sa_results
@@ -70,4 +70,4 @@ def __init__(
     self.sa_name = sa_name
     self.credentials = credentials
     self.chain_so_far = chain_so_far
-    self.worker_count = worker_count
+    self.resource_worker_count = resource_worker_count