modifying photo upload code

etl/non_invasive_surveys/photos/app.py

@@ -1,4 +1,5 @@
 import boto3
+import os
 from PIL import Image
 from pathlib import Path
 from dotenv import load_dotenv
@@ -19,6 +20,10 @@ FOLDER_UPRN_LOOKUP = {
     "8 Corporation Rd DY2 7PX": 90070461
 }
 
+load_dotenv(ENV_FILEPATH)
+CLOUDFRONT_DISTRIBUTION_DOMAIN_NAME = os.getenv("CLOUDFRONT_DISTRIBUTION_DOMAIN_NAME", None)
+CDN_BUCKET_NAME = os.getenv("CDN_BUCKET_NAME", None)
+
 
 def list_subdirectories(directory_path):
     """
@@ -49,21 +54,33 @@ def list_files_in_directory(directory_path, file_extension=".jpg"):
     return file_list
 
 
-def create_images(input_path):
+def create_images(input_path, uprn):
+    # Need to create local directory if it doesn't exist
+    os.makedirs(f"non_invasive_photos/{uprn}", exist_ok=True)
+
     # Load the image
     with Image.open(input_path) as img:
+        # Define output paths
+        thumbnail_path = f"non_invasive_photos/{uprn}/thumbnail.jpg"
+        full_hd_path = f"non_invasive_photos/{uprn}/1080p.jpg"
+        webp_path = f"non_invasive_photos/{uprn}/webp.webp"  # Save as WebP format
+
         # Create a thumbnail
         thumbnail = img.copy()
-        thumbnail.thumbnail((128, 128), Image.ANTIALIAS)  # Resize to 128x128 (or any desired size)
-        thumbnail.save('thumbnail.jpg')
+        thumbnail.thumbnail((128, 128), Image.Resampling.LANCZOS)  # High-quality downsampling
+        thumbnail.save(thumbnail_path, 'JPEG', quality=85)  # Save as JPEG with quality setting
 
         # Create a 1080p version
         full_hd = img.copy()
-        full_hd.thumbnail((1920, 1080), Image.ANTIALIAS)  # Resize to 1080p
-        full_hd.save('1080p.jpg')
+        full_hd.thumbnail((1920, 1080), Image.Resampling.LANCZOS)
+        full_hd.save(full_hd_path, 'JPEG', quality=90)  # Slightly higher quality for larger image
+
+        # Convert to WebP for better compression
+        webp = img.copy()
+        webp.save(webp_path, 'WEBP', quality=90)
 
     # Return paths to the processed images
-    return 'thumbnail.jpg', '1080p.jpg', input_path
+    return thumbnail_path, full_hd_path, webp_path
 
 
 def upload_to_s3(bucket_name, file_path, object_name):
@@ -83,9 +100,9 @@ def generate_cdn_url(distribution_domain, object_name):
     return f"https://{distribution_domain}/{object_name}"
 
 
-def process_and_upload_images(input_image_path, bucket_name, distribution_domain):
+def process_and_upload_images(uprn, input_image_path, bucket_name, distribution_domain):
     # Create images
-    thumbnail, full_hd, original = create_images(input_image_path)
+    thumbnail, full_hd, original = create_images(str(uprn), input_image_path)
 
     # Upload images
     upload_photos_to_s3(bucket_name, [thumbnail, full_hd, original])
@@ -93,6 +110,10 @@ def process_and_upload_images(input_image_path, bucket_name, distribution_domain
     # Generate CDN links
     cdn_links = [generate_cdn_url(distribution_domain, path.split('/')[-1]) for path in [thumbnail, full_hd, original]]
 
+    # Delete local files
+    for path in [thumbnail, full_hd, original]:
+        os.remove(path)
+
     return cdn_links
 
 
@@ -112,9 +133,13 @@ def app():
     # For each property, we want to list all of the photos in the directory
     for property_dir in property_directories:
         photo_files = list_files_in_directory(property_dir)
+        uprn = FOLDER_UPRN_LOOKUP[property_dir.name]
 
         # We now want to convert each file, and upload it to s3
         for photo_filepath in photo_files:
             process_and_upload_images(
-                photo_filepath, "retrofit-datalake-dev", "cdn.retrofit.com"
+                uprn=uprn,
+                input_image_path=photo_filepath,
+                bucket_name=CDN_BUCKET_NAME,
+                distribution_domain=CLOUDFRONT_DISTRIBUTION_DOMAIN_NAME
             )