How do I use Python 3.12 zipfile to extract all the data in a complex zip file

Question

I'm using this code:

with ZipFile(sourceZip, mode="r") as extraction:
    extraction.extractall(extractionPath)
    extraction.close()

What happens is it only extracts the first layer of Zip files in the sourceZip to extractionPath.

I have read "https://docs.python.org/3/library/zipfile.html#" and I need to get the code to extract all second layer of zip files.

Answer 1

Recursively extract the archive file contents until all nested levels have been extracted. Iterate through the contents of each zip file, detecting if a file is a zip archive, and then extracting the contents.

import os
import zipfile

def extract_zipfile_recursive(zip_file_path, extract_to):
    """
    Recursively extract the contents of a zip file and any nested zip files.
    zip_file_path: Path to the zip file.
    extract_to: Directory where extracted files should be saved.
    """
    with zipfile.ZipFile(zip_file_path, "r") as zip_ref:
        # Extract all contents of the zip file to the extract_to directory
        zip_ref.extractall(extract_to)

        # Iterate through each extracted item (files and directories)
        for item in zip_ref.infolist():
            # Check if the item is a directory or a file
            if item.is_dir():
                # Recursively extract contents of nested zip files in this directory
                dir_path = os.path.join(extract_to, item.filename)
                extract_zipfile_recursive(os.path.join(extract_to, item.filename), dir_path)
            elif item.filename.lower().endswith(".zip"):
                # The item is a zip file, recursively extract its contents
                nested_zip_path = os.path.join(extract_to, item.filename)
                nested_extract_to = os.path.join(extract_to, os.path.splitext(item.filename)[0])
                extract_zipfile_recursive(nested_zip_path, nested_extract_to)

# Example usage:
zip_file_path = "path/to/your/nested.zip"
extract_to_directory = "path/to/extracted/files"

# Create the directory if it doesn't exist
os.makedirs(extract_to_directory, exist_ok=True)

# Extract contents of the nested zip file recursively
extract_zipfile_recursive(zip_file_path, extract_to_directory)