initial commit

split_zip_into_under_5GB_chunks.py

@@ -0,0 +1,77 @@
+import os
+import zipfile
+from shutil import copy2
+
+def split_zip_into_groups(zip_path, max_group_size_gb):
+    # Open the existing zip file in read mode
+    with zipfile.ZipFile(zip_path, 'r') as zip_ref:
+        # Extract all the contents into a temporary directory
+        temp_dir = os.path.splitext(zip_path)[0] + '_extracted'
+        if not os.path.exists(temp_dir):
+            os.makedirs(temp_dir)
+        
+        zip_ref.extractall(temp_dir)
+    
+    # Get a list of all files in the temporary directory
+    file_list = [os.path.join(root, f) for root, dirs, files in os.walk(temp_dir) for f in files]
+    
+    # Calculate the maximum size in bytes for each group
+    max_group_size_bytes = max_group_size_gb * 1024**3
+    
+    # Create a new directory to hold the split zip files
+    output_dir = os.path.splitext(zip_path)[0] + '_split'
+    if not os.path.exists(output_dir):
+        os.makedirs(output_dir)
+    
+    group_count = 1
+    current_group_size = 0
+    current_group_files = []
+    
+    for file in file_list:
+        # Get the size of the current file in bytes
+        file_size = os.path.getsize(file)
+        
+        if current_group_size + file_size > max_group_size_bytes:
+            # If adding the current file exceeds the group size, save the current group and create a new one
+            output_zip_path = os.path.join(output_dir, f'group_{group_count}.zip')
+            
+            with zipfile.ZipFile(output_zip_path, 'w', zipfile.ZIP_DEFLATED) as zip_ref:
+                for file in current_group_files:
+                    # Copy each file to the temporary directory and add it to the new zip
+                    temp_file = os.path.join(temp_dir, os.path.relpath(file, start=temp_dir))
+                    copy2(file, temp_file)
+                    zip_ref.write(temp_file, os.path.relpath(file, start=temp_dir))
+                    os.remove(temp_file)  # Clean up the temporary file
+        
+            group_count += 1
+            current_group_size = 0
+            current_group_files = []
+        
+        current_group_size += file_size
+        current_group_files.append(file)
+    
+    # If there are any remaining files in the last group, save them too
+    if current_group_files:
+        output_zip_path = os.path.join(output_dir, f'group_{group_count}.zip')
+        with zipfile.ZipFile(output_zip_path, 'w', zipfile.ZIP_DEFLATED) as zip_ref:
+            for file in current_group_files:
+                temp_file = os.path.join(temp_dir, os.path.relpath(file, start=temp_dir))
+                copy2(file, temp_file)
+                zip_ref.write(temp_file, os.path.relpath(file, start=temp_dir))
+                os.remove(temp_file)  # Clean up the temporary file
+    
+    # Clean up the temporary directory
+    shutil.rmtree(temp_dir)
+
+def get_zip_path():
+    while True:
+        zip_path = input("Enter the path to the zipped file: ")
+        if os.path.isfile(zip_path):
+            return zip_path
+        else:
+            print(f"The file at {zip_path} does not exist. Please try again.")
+
+# Example usage
+zip_path = get_zip_path()
+max_group_size_gb = 5
+split_zip_into_groups(zip_path, max_group_size_gb)