dwonload image for card printing

scripts/storage_image.py

@@ -0,0 +1,53 @@
+import subprocess
+import os
+import pandas as pd
+import concurrent.futures
+
+def download_image(bucket_url, directory_path, destination_folder, destination_filename):
+    """Download images from a specific directory in Google Cloud Storage if they don't exist locally."""
+    os.makedirs(destination_folder, exist_ok=True)
+    
+    # List images in the GCS directory
+    gsutil_ls_command = f"gsutil ls '{bucket_url}/{directory_path}/*.jpg'"
+    result = subprocess.run(gsutil_ls_command, shell=True, capture_output=True, text=True)
+
+    # Extract image filenames from the gsutil ls command output
+    image_filenames = result.stdout.strip().split('\n')
+
+    for image_filename in image_filenames:
+        image_filename = os.path.basename(image_filename)
+        # local_path = os.path.join(destination_folder, image_filename)
+        local_path = os.path.join(destination_folder, destination_filename)
+
+        # Check if the image already exists locally
+        if not os.path.exists(local_path):
+            # Download the image only if it doesn't exist locally
+            gsutil_cp_command = f"gsutil cp '{bucket_url}/{directory_path}/{image_filename}' '{local_path}'"
+            subprocess.run(gsutil_cp_command, shell=True, check=True)
+            # print(f"Downloaded: {local_path}")
+        # else:
+        #     print(f"Skipped (Already Exists): {local_path}")
+
+    # print(f"All images downloaded to: {destination_folder}")
+
+def user_image(sample_id):
+    bucket_url = "gs://hpos-prod.appspot.com"
+    directory_path = f"{sample_id}"
+    destination_folder = "data/images"
+    destination_filename = f"{sample_id}.jpg"
+
+    local_path = os.path.join(destination_folder, destination_filename)
+
+    if not os.path.exists(local_path):
+        download_image(bucket_url, directory_path, destination_folder, destination_filename)
+
+
+if __name__ == "__main__":
+    curdir = os.getcwd()
+    path_delim = '/'
+    df = pd.read_excel(curdir + path_delim + "data/CardPrint.xlsx", sheet_name="op")
+    
+     # Using ThreadPoolExecutor for parallel processing
+    with concurrent.futures.ThreadPoolExecutor() as executor:
+        # Map the user_image function to the list of sample IDs, allowing parallel execution
+        executor.map(user_image, df['Sample ID'])