Model/etl/non_intrusive_surveys/photos/app.py
2024-04-15 16:33:15 +01:00

149 lines
5.2 KiB
Python

import boto3
import os
from PIL import Image
from pathlib import Path
from dotenv import load_dotenv
# Inputs
ENV_FILEPATH = "etl/non_intrusive_surveys/photos/.env"
PHOTO_DIRECTORY = "/Users/khalimconn-kowlessar/Downloads/IMMO - Dudley Pilot - non-invasive raw data"
FOLDER_UPRN_LOOKUP = {
"91 Osprey Drive DY1 2JS": 90048026,
"195 Ashenhurst Rd DY1 2JB": 90051858,
"6 Beech Rd DY1 4BP": 90055152,
"53 Bromley DY5 4PJ": 90060989,
"5 Oaklands B62 0JA": 90028499,
"47 Fairfield Rd DY8 5UJ": 90077535,
"150 Huntingtree Rd B63 4HP": 90093693,
"27 Milton Rd DY1 2JB": 90106884,
"21 Wells Rd DY5 3TB": 90022227,
"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):
"""
List all subdirectories within a given directory.
:param directory_path: Path to the directory.
:return: A list of paths to the subdirectories.
"""
directory = Path(directory_path)
subdirectories = [subdir for subdir in directory.iterdir() if subdir.is_dir()]
return subdirectories
def list_files_in_directory(directory_path, file_extension=".jpg"):
"""
List all files with a specific extension within a given directory and its subdirectories.
:param directory_path: Path to the directory to scan.
:param file_extension: File extension to filter by.
:return: A list of paths to the files.
"""
# Convert the directory path to a Path object if it's not already one
directory = Path(directory_path) if not isinstance(directory_path, Path) else directory_path
# List all files of the specified type in the directory and subdirectories
file_list = [file for file in directory.rglob(f'*{file_extension}')]
return file_list
def create_images(input_path, uprn):
# Define the base directory path
base_directory = f"non_intrusive_photos/{uprn}"
print(f"Creating directory: {base_directory}") # Debug: print the directory to be created
# Need to create local directory if it doesn't exist
os.makedirs(base_directory, exist_ok=True)
# Define output paths
thumbnail_path = os.path.join(base_directory, "thumbnail.jpg")
full_hd_path = os.path.join(base_directory, "1080p.jpg")
webp_path = os.path.join(base_directory, "webp.webp") # Save as WebP format
# Load the image
with Image.open(input_path) as img:
# Create a thumbnail
thumbnail = img.copy()
thumbnail.thumbnail((128, 128), Image.Resampling.LANCZOS)
thumbnail.save(thumbnail_path, 'JPEG', quality=85)
# Create a 1080p version
full_hd = img.copy()
full_hd.thumbnail((1920, 1080), Image.Resampling.LANCZOS)
full_hd.save(full_hd_path, 'JPEG', quality=90)
# Convert to WebP for better compression
webp = img.copy()
webp.save(webp_path, 'WEBP', quality=90)
# Return paths to the processed images
return thumbnail_path, full_hd_path, webp_path
def upload_to_s3(bucket_name, file_path, object_name):
s3_client = boto3.client('s3')
s3_client.upload_file(file_path, bucket_name, object_name)
print(f"Uploaded {object_name} to S3 bucket {bucket_name}")
def upload_photos_to_s3(bucket_name, photo_paths):
# Upload each photo
for path in photo_paths:
object_name = path.split('/')[-1] # Assuming the path format is folder/filename
upload_to_s3(bucket_name, path, object_name)
def generate_cdn_url(distribution_domain, object_name):
return f"https://{distribution_domain}/{object_name}"
def process_and_upload_images(uprn, input_image_path, bucket_name, distribution_domain):
# Create images
thumbnail, full_hd, original = create_images(input_image_path, uprn=str(uprn))
# Upload images
upload_photos_to_s3(bucket_name, photo_paths=[thumbnail, full_hd, original])
# 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
def app():
"""
This application is tasked with uploading the photos, recorded during the non-invasive surveys, to s3 and the
database.
To begin with, this app will simply read the files from the local machine, however we will come up with a more
efficient way to do this in the future.
:return:
"""
# List all files in the directory using pathlib
property_directories = list_subdirectories(PHOTO_DIRECTORY)
# 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(
uprn=uprn,
input_image_path=photo_filepath,
bucket_name=CDN_BUCKET_NAME,
distribution_domain=CLOUDFRONT_DISTRIBUTION_DOMAIN_NAME
)