Find PII (Personally Identifiable Information) using pdscan

pdscan_recursive.py

import glob
from selectors import EpollSelector
import subprocess

# Change these
ROOT_DIR = "/home/jimmy/desktop/spam"
PDSCAN_FILE = "/home/jimmy/desktop/pdscan" # Download from https://github.com/ankane/pdscan#installation

for filename in glob.iglob(ROOT_DIR + '**/**', recursive=True):
    result = subprocess.run([PDSCAN_FILE, "file://" + filename,"--show-data", "--show-all"], capture_output=True, text=True) # remove "--show-all" for high confidence results
    # print(result.stdout)

    if "Empty buffer" in result.stdout or  "No sensitive data found" in result.stdout:
        pass
    else:
        print(result.stdout)
        print("------------------------------------------------")