refector: optimized concurrent.futures

aws-emr.py

@@ -16,13 +16,12 @@ def getRegions(all_regions=False):
     response = ec2.describe_regions(AllRegions=all_regions)
     return [region['RegionName'] for region in response['Regions']]
 
-def printResources(region_name: str) -> list[list[str | int]]:
+def getResources(region_name: str) -> list[list[str | int]]:
     return_data = []
     client = boto3.client('emr', region_name=region_name)
     response = client.list_clusters()
     for i in response['Clusters']:
-        if i:
-            return_data.append([i['Name'], i['Status'], i['NormalizedInstanceHours'], region_name])
+        return_data.append([i['Name'], i['Status'], i['NormalizedInstanceHours'], region_name])
     return return_data
 
 # Main function
@@ -31,16 +30,14 @@ def main() -> None:
     wb = load_workbook('aws-inventory.xlsx')
     ws = wb.create_sheet("EMR")
 
-    final_data = []
     ws.append(["Name", "Status", "NormalizedInstanceHours", "Region"])
-    with concurrent.futures.ProcessPoolExecutor(max_workers=6) as executor:
-        futures = [executor.submit(printResources, region_name=r) for r in getRegions()]
-        for future in concurrent.futures.as_completed(futures):
-            region_data = future.result()
-            final_data.extend(region_data)
-
-    for row in final_data:
-        ws.append(row)
+    with concurrent.futures.ThreadPoolExecutor(max_workers=8) as executor:
+        results = executor.map(getResources, getRegions())
+        for region_rows in results:
+            # append to worksheet only if resoruces are found in the region
+            if region_rows:
+                for row in region_rows:
+                    ws.append(row)
 
     wb.save('aws-inventory.xlsx')