refactored. untested.

backup-docker-to-local.py

@@ -1,6 +1,6 @@
 #!/bin/python
 # Backups volumes of running containers
-#
+
 import subprocess
 import os
 import re
@@ -8,114 +8,80 @@ import pathlib
 import pandas
 from datetime import datetime
 
-class RsyncCode24Exception(Exception):
+class BackupException(Exception):
-    """Exception for rsync error code 24."""
+    """Generic exception for backup errors."""
-    """rsync warning: some files vanished before they could be transferred"""
     pass
 
-def bash(command):
+def execute_shell_command(command):
+    """Execute a shell command and return its output."""
     print(command)
     process = subprocess.Popen([command], stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
     out, err = process.communicate()
-    stdout = out.splitlines()
+    if process.returncode != 0:
-    stderr = err.decode("utf-8")
+        raise BackupException(f"Error in command: {command}\nOutput: {out}\nError: {err}\nExit code: {process.returncode}")
-    output = [line.decode("utf-8") for line in stdout]
+    return [line.decode("utf-8") for line in out.splitlines()]
 
-    exitcode = process.wait()
+def get_machine_id():
-    if exitcode != 0:
+    """Get the machine identifier."""
-        print(f"Error in command: {command}\nOutput: {out}\nError: {err}\nExit code: {exitcode}")
+    return execute_shell_command("sha256sum /etc/machine-id")[0][0:64]
 
-        if "rsync" in command and exitcode == 24:
+def create_backup_directories(base_dir, machine_id, repository_name, backup_time):
-            raise RsyncCode24Exception(f"rsync error code 24 encountered: {stderr}")
+    """Create necessary directories for backup."""
+    version_dir = os.path.join(base_dir, machine_id, repository_name, backup_time)
+    pathlib.Path(version_dir).mkdir(parents=True, exist_ok=True)
+    return version_dir
 
-        raise Exception("Exit code is greater than 0")
+def get_database_name(container):
+    """Extract the database name from the container name."""
+    return re.split("(_|-)(database|db)", container)[0]
 
-    return output
+def backup_database(container, databases, version_dir):
-
+    """Backup database if applicable."""
-def print_bash(command):
+    database_name = get_database_name(container)
-    output = bash(command)
+    database_entry = databases.loc[databases['database'] == database_name].iloc[0]
-    print(list_to_string(output))
+    mysqldump_destination_dir = os.path.join(version_dir, "sql")
-    return output
-
-
-def list_to_string(list):
-    return str(' '.join(list))
-
-
-print('start backup routine...')
-
-dirname = os.path.dirname(__file__)
-repository_name = os.path.basename(dirname)
-# identifier of this backups
-machine_id = bash("sha256sum /etc/machine-id")[0][0:64]
-# Folder in which all Backups are stored
-backups_dir = '/Backups/'
-# Folder in which the versions off docker volume backups are stored
-versions_dir = backups_dir + machine_id + "/" + repository_name + "/"
-# Time when the backup started
-backup_time = datetime.now().strftime("%Y%m%d%H%M%S")
-# Folder containing the current version
-version_dir = versions_dir + backup_time + "/"
-
-# Create folder to store version in
-pathlib.Path(version_dir).mkdir(parents=True, exist_ok=True)
-
-print('start volume backups...')
-print('load connection data...')
-databases = pandas.read_csv(dirname + "/databases.csv", sep=";")
-volume_names = bash("docker volume ls --format '{{.Name}}'")
-for volume_name in volume_names:
-    print('start backup routine for volume: ' + volume_name)
-    containers = bash("docker ps --filter volume=\"" + volume_name + "\" --format '{{.Names}}'")
-    if len(containers) == 0:
-        print('skipped due to no running containers using this volume.')
-    else:
-        container = containers[0]
-        # Folder to which the volumes are copied
-        volume_destination_dir = version_dir + volume_name
-        # Database name
-        database_name = re.split("(_|-)(database|db)", container)[0]
-        # Entries with database login data concerning this container
-        databases_entries = databases.loc[databases['database'] == database_name]
-        # Exception for akaunting due to fast implementation
-        if len(databases_entries) == 1 and container != 'akaunting':
-            print("Backup database...")
-            mysqldump_destination_dir = volume_destination_dir + "/sql"
-            mysqldump_destination_file = mysqldump_destination_dir + "/backup.sql"
     pathlib.Path(mysqldump_destination_dir).mkdir(parents=True, exist_ok=True)
-            database_entry = databases_entries.iloc[0]
+    mysqldump_destination_file = os.path.join(mysqldump_destination_dir, "backup.sql")
-            database_backup_command = "docker exec " + container + " /usr/bin/mariadb-dump -u " + database_entry["username"] + " -p" + database_entry["password"] + " " + database_entry["database"] + " > " + mysqldump_destination_file
+    database_backup_command = f"docker exec {container} /usr/bin/mariadb-dump -u {database_entry['username']} -p{database_entry['password']} {database_entry['database']} > {mysqldump_destination_file}"
-            print_bash(database_backup_command)
+    execute_shell_command(database_backup_command)
-        print("Backup files...")
+
-        files_rsync_destination_path = volume_destination_dir + "/files"
+def backup_volume(volume_name, version_dir):
+    """Backup files of a volume."""
+    files_rsync_destination_path = os.path.join(version_dir, volume_name, "files")
     pathlib.Path(files_rsync_destination_path).mkdir(parents=True, exist_ok=True)
-        versions = os.listdir(versions_dir)
+    source_dir = f"/var/lib/docker/volumes/{volume_name}/_data/"
-        versions.sort(reverse=True)
+    rsync_command = f"rsync -abP --delete --delete-excluded {source_dir} {files_rsync_destination_path}"
-        if len(versions) > 1:
+    execute_shell_command(rsync_command)
-            last_version = versions[1]
+
-            last_version_files_dir = versions_dir + last_version + "/" + volume_name + "/files"
+def main():
-            if os.path.isdir(last_version_files_dir):
+    print('Start backup routine...')
-                link_dest_parameter="--link-dest='" + last_version_files_dir + "' "
+    dirname = os.path.dirname(__file__)
-            else:
+    repository_name = os.path.basename(dirname)
-                print("No previous version exists in path "+ last_version_files_dir + ".")
+    machine_id = get_machine_id()
-                link_dest_parameter=""
+    backups_dir = '/Backups/'
-        else:
+    backup_time = datetime.now().strftime("%Y%m%d%H%M%S")
-            print("No previous version exists in path "+ last_version_files_dir + ".")
+    version_dir = create_backup_directories(backups_dir, machine_id, repository_name, backup_time)
-            link_dest_parameter=""
+
-        source_dir = "/var/lib/docker/volumes/" + volume_name + "/_data/"
+    print('Start volume backups...')
-        rsync_command = "rsync -abP --delete --delete-excluded " + link_dest_parameter + source_dir + " " + files_rsync_destination_path
+    databases = pandas.read_csv(os.path.join(dirname, "databases.csv"), sep=";")
-        try:
+    volume_names = execute_shell_command("docker volume ls --format '{{.Name}}'")
-            print_bash(rsync_command)
+    
-        except RsyncCode24Exception:
+    for volume_name in volume_names:
-             print("Ignoring rsync error code 24, proceeding with the next command.")
+        print(f'Start backup routine for volume: {volume_name}')
-        print("stop containers...")
+        containers = execute_shell_command(f"docker ps --filter volume=\"{volume_name}\" --format '{{.Names}}'")
-        print("Backup data after container is stopped...")
+        if not containers:
-        print_bash("docker stop " + list_to_string(containers))
+            print('Skipped due to no running containers using this volume.')
-        print_bash(rsync_command)
+            continue
-        print("start containers...")
+
-        print_bash("docker start " + list_to_string(containers))
+        for container in containers:
-    print("end backup routine for volume:" + volume_name)
+            if container != 'akaunting':
-print('finished volume backups.')
+                backup_database(container, databases, version_dir)
-print('restart docker service...')
+            backup_volume(volume_name, version_dir)
-print_bash("systemctl restart docker")
+
-print('finished backup routine.')
+    print('Finished volume backups.')
+    print('Restart docker service...')
+    execute_shell_command("systemctl restart docker")
+    print('Finished backup routine.')
+
+if __name__ == "__main__":
+    main()