Python search all folders for aprx apart from those folders containing sub-string

Username1

Hi All,

I'm new to python and have created the code below after much googling. I'm trying to search through all subfolders within my directory and find all aprx's then list all of the features held within the aprx. My code achieves this but I'd like to make it more efficient by skipping over sub-folders that contain a certain sub-string.

For example I'd like to be able to remove all folders containing the string "myfolder" if the directory contained the following folders:

myfolder_1

myfolder2

testfolder

 

So my goal would be to only search for aprx's in the folder "testfolder".

 

My Code:

extensions = ('.aprx')#extention to search
exclude_directories = set(['Archived','#Archived','Archive','archived','archive','#archived','#archive','ss','SS']) #directory (only names) want to exclude
for dname, dirs, files in os.walk(r'C:\Users\MyDirectory'):
      dirs[:] = [d for d in dirs if d not in exclude_directories] # exclude directory if in exclude list
      for fname in files:
            if(fname.lower().endswith(extensions)): #check for extension
            fpath = os.path.join(dname, fname) #this generates full directory path for file
            aprx = arcpy.mp.ArcGISProject(fpath)
            for m in aprx.listMaps():
                  for lyr in m.listLayers():
                        if lyr.isBroken:
                            print("(BROKEN) " + lyr.name + " - " + m.name)
                        else:
                               if lyr.supports("DATASOURCE"):
                                    print ("Map Layer Name: " + lyr.name + "| SZ_gis_dataname: " + lyr.dataSource[211:])

 

 

Tonyalmeida

Here is a function I use once a year to help me clean up data, and it allows me to create a .xlsx and share it with my peers.

import arcpy
import pandas as pd

def export_sde_feature_datasets(sde_connection, output_excel):
    """ 
    Lists feature datasets and feature classes in an SDE database 
    and exports them to an Excel file. 
    """

    sde_connection = "" #Connection to SDE database
    # Set the workspace to the SDE connection
    arcpy.env.workspace = sde_connection

    # Empty list to store the results
    data = []

    # List of feature datasets in the SDE database
    feature_datasets = arcpy.ListDatasets(feature_type="feature") or []

    if not feature_datasets:
        print("No feature datasets found in the SDE database.")
    else:
        for dataset in feature_datasets:
            data.append([dataset, ""])  # Append dataset as a header

            # Get all feature classes within the dataset
            dataset_path = f"{sde_connection}\\{dataset}"
            arcpy.env.workspace = dataset_path
            feature_classes = arcpy.ListFeatureClasses() or []

            if not feature_classes:
                data.append(["", "No feature classes found"])
            else:
                for fc in feature_classes:
                    data.append(["", fc])

    # Process standalone feature classes (not inside a dataset)
    arcpy.env.workspace = sde_connection
    standalone_feature_classes = arcpy.ListFeatureClasses() or []

    data.append(["Standalone Feature Classes", ""])
    
    if not standalone_feature_classes:
        data.append(["", "No standalone feature classes found"])
    else:
        for fc in standalone_feature_classes:
            data.append(["", fc])

    # Convert list to DataFrame and export to Excel
    df = pd.DataFrame(data, columns=["Feature Dataset", "Feature Class"])
    df.to_excel(output_excel, index=False)

    print(f"Feature datasets and feature classes have been exported to {output_excel}.")

# Example usage
sde_connection = r"C:\Users\***\AppData\Roaming\Esri\ArcGISPro\Favorites\***.sde"
output_excel = r"C:\temp\SDEFeatureDatasetFeatureClassList.xlsx"

export_sde_feature_datasets(sde_connection, output_excel)