HDFS cron to delete old files in directory

hdfs_file_cleanup_cron.sh

#!/bin/bash
now=$(date +%s);
days_to_keep=5

# Loop through files
hdfs dfs -ls /some_hdfs_directory | while read f; do

  # Get File Date and File Name
  file_date=`echo $f | awk '{print $6}'`;
  file_name=`echo $f | awk '{print $8}'`;

  echo $file_date
  echo $file_name

  # Calculate Days Difference
  difference=$(( ($now - $(date -d "$file_date" +%s)) / (24 * 60 * 60) ));
  if [ $difference -gt $days_to_keep ]; then
    echo "Deleting $file_name it is older than $days_to_keep and is dated $file_date.";
    hdfs dfs -rm $file_name
  fi
done

Thank you, this is very helpful 🙏