repo restructure

Dockerfile

@@ -13,19 +13,18 @@ COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
 # Copy application files
-COPY *.py ./
-COPY *config.json ./
+COPY src/ ./src/
+COPY config/ ./config/
 
 # Create output directories
-RUN mkdir -p /app/snapshots /app/logs
+RUN mkdir -p /app/data/snapshots /app/data/logs
 
 # Copy scripts
-COPY scheduler.sh ./
-COPY startup.sh ./
-RUN chmod +x scheduler.sh startup.sh
+COPY scripts/ ./scripts/
+RUN chmod +x scripts/*.sh
 
 # Copy cron configuration
-COPY crontab /etc/cron.d/parentzone-downloader
+COPY scripts/crontab /etc/cron.d/parentzone-downloader
 RUN chmod 0644 /etc/cron.d/parentzone-downloader
 RUN crontab /etc/cron.d/parentzone-downloader
 
@@ -40,7 +39,7 @@ ENV PYTHONPATH=/app
 EXPOSE 8080
 
 # Expose volume for persistent data
-VOLUME ["/app/snapshots", "/app/logs", "/app/parentzone_images"]
+VOLUME ["/app/data/snapshots", "/app/data/logs", "/app/data/parentzone_images"]
 
 # Start all services using startup script
-CMD ["./startup.sh"]
+CMD ["./scripts/startup.sh"]

config.json.example

@@ -1,12 +0,0 @@
-{
-  "api_url": "https://api.parentzone.me",
-  "output_dir": "snapshots",
-  "api_key": "YOUR_API_KEY_HERE",
-  "email": "your-email@example.com",
-  "password": "your-password",
-  "date_from": "2021-01-01",
-  "date_to": null,
-  "type_ids": [15],
-  "max_pages": null,
-  "debug_mode": false
-}

docker-compose.yml

@@ -13,17 +13,16 @@ services:
       # Timezone for cron scheduling
       - TZ=${TZ:-UTC}
     volumes:
-      # Persistent storage for snapshots and logs
-      - ./snapshots:/app/snapshots
-      - ./logs:/app/logs
-      # Mount your config file
-      - ./config.json:/app/config.json:ro
+      # Persistent storage for data
+      - ./data/snapshots:/app/data/snapshots
+      - ./data/logs:/app/data/logs
+      - ./data/parentzone_images:/app/data/parentzone_images
+      # Mount configuration directory
+      - ./config:/app/config:ro
     ports:
       - "8080:8080"
     restart: unless-stopped
 
 volumes:
-  snapshots:
-    driver: local
-  logs:
+  data:
     driver: local

docs/README.md

@@ -0,0 +1,242 @@
+# Image Downloader Script
+
+A Python script to download images from a REST API that provides endpoints for listing assets and downloading them in full resolution.
+
+## Features
+
+- **Concurrent Downloads**: Download multiple images simultaneously for better performance
+- **Error Handling**: Robust error handling with detailed logging
+- **Progress Tracking**: Real-time progress bar with download statistics
+- **Resume Support**: Skip already downloaded files
+- **Flexible API Integration**: Supports various API response formats
+- **Filename Sanitization**: Automatically handles invalid characters in filenames
+- **File Timestamps**: Preserves original file modification dates from API
+
+## Installation
+
+1. Clone or download this repository
+2. Install the required dependencies:
+
+```bash
+pip install -r requirements.txt
+```
+
+## Usage
+
+### Basic Usage
+
+```bash
+python image_downloader.py \
+  --api-url "https://api.example.com" \
+  --list-endpoint "/assets" \
+  --download-endpoint "/download" \
+  --output-dir "./images" \
+  --api-key "your_api_key_here"
+```
+
+### Advanced Usage
+
+```bash
+python image_downloader.py \
+  --api-url "https://api.example.com" \
+  --list-endpoint "/assets" \
+  --download-endpoint "/download" \
+  --output-dir "./images" \
+  --max-concurrent 10 \
+  --timeout 60 \
+  --api-key "your_api_key_here"
+```
+
+### Parameters
+
+- `--api-url`: Base URL of the API (required)
+- `--list-endpoint`: Endpoint to get the list of assets (required)
+- `--download-endpoint`: Endpoint to download individual assets (required)
+- `--output-dir`: Directory to save downloaded images (required)
+- `--max-concurrent`: Maximum number of concurrent downloads (default: 5)
+- `--timeout`: Request timeout in seconds (default: 30)
+- `--api-key`: API key for authentication (x-api-key header)
+- `--email`: Email for login authentication
+- `--password`: Password for login authentication
+
+## Authentication
+
+The script supports two authentication methods:
+
+### API Key Authentication
+- Uses `x-api-key` header for list endpoint
+- Uses `key` parameter for download endpoint
+- Configure with `--api-key` parameter or `api_key` in config file
+
+### Login Authentication
+- Performs login to `/v1/auth/login` endpoint
+- Uses session token for list endpoint
+- Uses `key` parameter for download endpoint
+- Configure with `--email` and `--password` parameters or in config file
+
+**Note**: Only one authentication method should be used at a time. API key takes precedence over login credentials.
+
+## API Integration
+
+The script is designed to work with REST APIs that follow these patterns:
+
+### List Endpoint
+The list endpoint should return a JSON response with asset information. The script supports these common formats:
+
+```json
+// Array of assets
+[
+  {"id": "1", "filename": "image1.jpg", "url": "..."},
+  {"id": "2", "filename": "image2.png", "url": "..."}
+]
+
+// Object with data array
+{
+  "data": [
+    {"id": "1", "filename": "image1.jpg"},
+    {"id": "2", "filename": "image2.png"}
+  ]
+}
+
+// Object with results array
+{
+  "results": [
+    {"id": "1", "filename": "image1.jpg"},
+    {"id": "2", "filename": "image2.png"}
+  ]
+}
+```
+
+### Download Endpoint
+The download endpoint should accept an asset ID and return the image file. Common patterns:
+
+- `GET /download/{asset_id}`
+- `GET /assets/{asset_id}/download`
+- `GET /images/{asset_id}`
+
+**ParentZone API Format:**
+- `GET /v1/media/{asset_id}/full?key={api_key}&u={updated_timestamp}`
+
+### Asset Object Fields
+
+The script looks for these fields in asset objects:
+
+**Required for identification:**
+- `id`, `asset_id`, `image_id`, `file_id`, `uuid`, or `key`
+
+**Optional for better filenames:**
+- `fileName`: Preferred filename (ParentZone API)
+- `filename`: Alternative filename field
+- `name`: Alternative name
+- `title`: Display title
+- `mimeType`: MIME type for proper file extension (ParentZone API)
+- `content_type`: Alternative MIME type field
+
+**Required for ParentZone API downloads:**
+- `updated`: Timestamp used in download URL parameter and file modification time
+
+## Examples
+
+### Example 1: ParentZone API with API Key
+```bash
+python image_downloader.py \
+  --api-url "https://api.parentzone.me" \
+  --list-endpoint "/v1/gallery" \
+  --download-endpoint "/v1/media" \
+  --output-dir "./parentzone_images" \
+  --api-key "your_api_key_here"
+```
+
+### Example 2: ParentZone API with Login
+```bash
+python image_downloader.py \
+  --api-url "https://api.parentzone.me" \
+  --list-endpoint "/v1/gallery" \
+  --download-endpoint "/v1/media" \
+  --output-dir "./parentzone_images" \
+  --email "your_email@example.com" \
+  --password "your_password_here"
+```
+
+### Example 2: API with Authentication
+The script now supports API key authentication via the `--api-key` parameter. For other authentication methods, you can modify the script to include custom headers:
+
+```python
+# In the get_asset_list method, add headers:
+headers = {
+    'Authorization': 'Bearer your_token_here',
+    'Content-Type': 'application/json'
+}
+async with session.get(url, headers=headers, timeout=self.timeout) as response:
+```
+
+### Example 3: Custom Response Format
+If your API returns a different format, you can modify the `get_asset_list` method:
+
+```python
+# For API that returns: {"images": [...]}
+if 'images' in data:
+    assets = data['images']
+```
+
+## Output
+
+The script creates:
+
+1. **Downloaded Images**: All images are saved to the specified output directory with original modification timestamps
+2. **Log File**: `download.log` in the output directory with detailed information
+3. **Progress Display**: Real-time progress bar showing:
+   - Total assets
+   - Successfully downloaded
+   - Failed downloads
+   - Skipped files (already exist)
+
+### File Timestamps
+
+The downloader automatically sets the file modification time to match the `updated` timestamp from the API response. This preserves the original file dates and helps with:
+
+- **File Organization**: Files are sorted by their original creation/update dates
+- **Backup Systems**: Backup tools can properly identify changed files
+- **Media Libraries**: Media management software can display correct dates
+- **Data Integrity**: Maintains the temporal relationship between files
+
+## Error Handling
+
+The script handles various error scenarios:
+
+- **Network Errors**: Retries and continues with other downloads
+- **Invalid Responses**: Logs errors and continues
+- **File System Errors**: Creates directories and handles permission issues
+- **API Errors**: Logs HTTP errors and continues
+
+## Performance
+
+- **Concurrent Downloads**: Configurable concurrency (default: 5)
+- **Connection Pooling**: Efficient HTTP connection reuse
+- **Chunked Downloads**: Memory-efficient large file handling
+- **Progress Tracking**: Real-time feedback on download progress
+
+## Troubleshooting
+
+### Common Issues
+
+1. **"No assets found"**: Check your list endpoint URL and response format
+2. **"Failed to fetch asset list"**: Verify API URL and network connectivity
+3. **"Content type is not an image"**: API might be returning JSON instead of image data
+4. **Permission errors**: Check write permissions for the output directory
+
+### Debug Mode
+
+For detailed debugging, you can modify the logging level:
+
+```python
+logging.basicConfig(level=logging.DEBUG)
+```
+
+## License
+
+This script is provided as-is for educational and personal use.
+
+## Contributing
+
+Feel free to submit issues and enhancement requests! 

examples/demo_asset_tracking.py

@@ -12,12 +12,12 @@ import sys
 import os
 from pathlib import Path
 
-# Add the current directory to the path so we can import modules
-sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+# Add the parent directory to the path so we can import modules
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from auth_manager import AuthManager
-from asset_tracker import AssetTracker
-from image_downloader import ImageDownloader
+from src.auth_manager import AuthManager
+from src.asset_tracker import AssetTracker
+from src.image_downloader import ImageDownloader
 
 
 async def demo_asset_tracking():
@@ -32,8 +32,7 @@ async def demo_asset_tracking():
 
     # Setup logging
     logging.basicConfig(
-        level=logging.INFO,
-        format='%(asctime)s - %(levelname)s - %(message)s'
+        level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
     )
 
     try:
@@ -78,7 +77,7 @@ async def demo_asset_tracking():
             email=email,
             password=password,
             track_assets=True,
-            max_concurrent=3
+            max_concurrent=3,
         )
 
         # First download run
@@ -104,12 +103,7 @@ async def demo_asset_tracking():
         print("Running again - should detect no new assets...")
 
         # Reset stats for second run
-        downloader.stats = {
-            'total': 0,
-            'successful': 0,
-            'failed': 0,
-            'skipped': 0
-        }
+        downloader.stats = {"total": 0, "successful": 0, "failed": 0, "skipped": 0}
 
         # Second download run
         await downloader.download_all_assets()
@@ -118,7 +112,7 @@ async def demo_asset_tracking():
         print(f"   Assets to download: {downloader.stats['total']}")
         print(f"   New downloads: {downloader.stats['successful']}")
 
-        if downloader.stats['total'] == 0:
+        if downloader.stats["total"] == 0:
             print("   ✅ Perfect! No new assets found - all are up to date!")
         else:
             print(f"   Downloaded: {downloader.stats['successful']}")
@@ -149,6 +143,7 @@ async def demo_asset_tracking():
     except Exception as e:
         print(f"❌ Demo failed with error: {e}")
         import traceback
+
         traceback.print_exc()
         return False
 
@@ -177,7 +172,7 @@ def show_usage():
 
 async def main():
     """Main function."""
-    if len(sys.argv) > 1 and sys.argv[1] in ['--help', '-h']:
+    if len(sys.argv) > 1 and sys.argv[1] in ["--help", "-h"]:
         show_usage()
         return 0
 

scripts/crontab

@@ -1,9 +1,9 @@
 # ParentZone Downloaders Cron Schedule
 # Run both downloaders daily at 2:00 AM
-0 2 * * * /app/scheduler.sh >> /var/log/cron.log 2>&1
+0 2 * * * /app/scripts/scheduler.sh >> /var/log/cron.log 2>&1
 
 # Keep cron log file from growing too large (weekly cleanup)
 0 3 * * 0 find /var/log -name "cron.log" -size +100M -exec truncate -s 50M {} \; 2>/dev/null || true
 
 # Cleanup old snapshot files (keep last 90 days)
-30 3 * * 0 find /app/snapshots -name "*.html" -mtime +90 -delete 2>/dev/null || true
+30 3 * * 0 find /app/data/snapshots -name "*.html" -mtime +90 -delete 2>/dev/null || true

scripts/scheduler.sh

@@ -3,10 +3,10 @@
 # ParentZone Downloaders Daily Scheduler
 # This script runs both the config downloader and snapshot downloader
 
-LOG_DIR="/app/logs"
+LOG_DIR="/app/data/logs"
 LOG_FILE="$LOG_DIR/scheduler_$(date +%Y%m%d).log"
-SNAPSHOT_CONFIG_FILE="/app/snapshot_config.json"
-ASSET_CONFIG_FILE="/app/parentzone_config.json"
+SNAPSHOT_CONFIG_FILE="/app/config/snapshot_config.json"
+ASSET_CONFIG_FILE="/app/config/parentzone_config.json"
 
 # Create log directory if it doesn't exist
 mkdir -p "$LOG_DIR"
@@ -54,7 +54,7 @@ cd /app
 
 # Run config-based asset downloader
 if [ "$SKIP_ASSET_DOWNLOADER" = false ]; then
-    run_with_logging "python3 config_downloader.py --config $ASSET_CONFIG_FILE" "Config Asset Downloader"
+    run_with_logging "python3 src/config_downloader.py --config $ASSET_CONFIG_FILE" "Config Asset Downloader"
     asset_result=$?
 else
     log_message "SKIPPED: Config Asset Downloader (configuration file not found)"
@@ -62,15 +62,15 @@ else
 fi
 
 # Run config-based snapshot downloader
-run_with_logging "python3 config_snapshot_downloader.py --config $SNAPSHOT_CONFIG_FILE" "Config Snapshot Downloader"
+run_with_logging "python3 src/config_snapshot_downloader.py --config $SNAPSHOT_CONFIG_FILE" "Config Snapshot Downloader"
 config_result=$?
 
 # Run regular snapshot downloader with environment variables
 if [ -n "$API_KEY" ]; then
-    run_with_logging "python3 snapshot_downloader.py --api-key $API_KEY --output-dir snapshots" "Snapshot Downloader (API Key)"
+    run_with_logging "python3 src/snapshot_downloader.py --api-key $API_KEY --output-dir data/snapshots" "Snapshot Downloader (API Key)"
     snapshot_result=$?
 elif [ -n "$EMAIL" ] && [ -n "$PASSWORD" ]; then
-    run_with_logging "python3 snapshot_downloader.py --email $EMAIL --password $PASSWORD --output-dir snapshots" "Snapshot Downloader (Email/Password)"
+    run_with_logging "python3 src/snapshot_downloader.py --email $EMAIL --password $PASSWORD --output-dir data/snapshots" "Snapshot Downloader (Email/Password)"
     snapshot_result=$?
 else
     log_message "WARNING: No authentication method provided via environment variables, skipping direct snapshot downloader"

scripts/startup.sh

@@ -5,8 +5,8 @@
 
 set -e
 
-LOG_DIR="/app/logs"
-SNAPSHOTS_DIR="/app/snapshots"
+LOG_DIR="/app/data/logs"
+SNAPSHOTS_DIR="/app/data/snapshots"
 
 # Create directories if they don't exist
 mkdir -p "$LOG_DIR"
@@ -30,7 +30,7 @@ log_message "Cron daemon started"
 
 # Start web server in the background
 log_message "Starting web server on port 8080..."
-python3 webserver.py --host 0.0.0.0 --port 8080 --snapshots-dir "$SNAPSHOTS_DIR" &
+python3 src/webserver.py --host 0.0.0.0 --port 8080 --snapshots-dir "$SNAPSHOTS_DIR" &
 WEB_SERVER_PID=$!
 
 log_message "Web server started with PID: $WEB_SERVER_PID"

snapshots_test/snapshots.log

@@ -1,162 +0,0 @@
-2025-09-05 22:23:50,764 - INFO - Starting snapshot download with configuration
-2025-09-05 22:23:50,764 - INFO - Date range: 2021-10-18 to 2025-09-05
-2025-09-05 22:23:50,764 - INFO - Type IDs: [15]
-2025-09-05 22:23:50,764 - INFO - Output directory: ./snapshots_test
-2025-09-05 22:23:50,764 - INFO - Max pages limit: 2
-2025-09-05 22:23:50,764 - INFO - Starting snapshot download for period 2021-10-18 to 2025-09-05
-2025-09-05 22:23:50,764 - INFO - Attempting login authentication...
-2025-09-05 22:23:50,765 - INFO - Attempting login for tudor.sitaru@gmail.com
-2025-09-05 22:23:51,594 - INFO - Login response status: 200
-2025-09-05 22:23:51,594 - INFO - Login successful
-2025-09-05 22:23:51,594 - INFO - Selected account: Tudor Sitaru at Noddy's Nursery School (ID: e518bd01-e516-4b3c-aefa-bcb369823a2e)
-2025-09-05 22:23:51,594 - INFO - Creating session for user ID: e518bd01-e516-4b3c-aefa-bcb369823a2e
-2025-09-05 22:23:51,994 - INFO - Create session response status: 200
-2025-09-05 22:23:51,995 - INFO - Session creation successful
-2025-09-05 22:23:51,995 - INFO - API key obtained successfully
-2025-09-05 22:23:51,996 - INFO - Login authentication successful
-2025-09-05 22:23:51,996 - INFO - Starting snapshot fetch from 2021-10-18 to 2025-09-05
-2025-09-05 22:23:51,996 - INFO - Fetching snapshots (first page): https://api.parentzone.me/v1/posts?dateFrom=2021-10-18&dateTo=2025-09-05&typeIDs%5B%5D=15
-2025-09-05 22:23:52,398 - INFO - Retrieved 25 snapshots (first page)
-2025-09-05 22:23:52,398 - INFO - Page 1: 25 snapshots (total: 25)
-2025-09-05 22:23:52,399 - INFO - Fetching snapshots (cursor: eyJsYXN0SUQiOjIzODE4...): https://api.parentzone.me/v1/posts?dateFrom=2021-10-18&dateTo=2025-09-05&cursor=eyJsYXN0SUQiOjIzODE4NTcsImxhc3RTdGFydFRpbWUiOiIyMDI0LTEwLTIzVDE0OjEyOjAwIn0%3D&typeIDs%5B%5D=15
-2025-09-05 22:23:52,708 - INFO - Retrieved 25 snapshots (cursor: eyJsYXN0SUQiOjIzODE4...)
-2025-09-05 22:23:52,708 - INFO - Page 2: 25 snapshots (total: 50)
-2025-09-05 22:23:52,708 - INFO - Reached maximum pages limit: 2
-2025-09-05 22:23:52,708 - INFO - Total snapshots fetched: 50
-2025-09-05 22:23:52,715 - INFO - Generated HTML file: snapshots_test/snapshots_2021-10-18_to_2025-09-05.html
-2025-09-05 22:42:28,035 - INFO - Starting snapshot download with configuration
-2025-09-05 22:42:28,035 - INFO - Date range: 2021-10-18 to 2025-09-05
-2025-09-05 22:42:28,036 - INFO - Type IDs: [15]
-2025-09-05 22:42:28,036 - INFO - Output directory: ./snapshots_test
-2025-09-05 22:42:28,036 - INFO - Max pages limit: 2
-2025-09-05 22:42:28,036 - INFO - Starting snapshot download for period 2021-10-18 to 2025-09-05
-2025-09-05 22:42:28,036 - INFO - Attempting login authentication...
-2025-09-05 22:42:28,036 - INFO - Attempting login for tudor.sitaru@gmail.com
-2025-09-05 22:42:28,783 - INFO - Login response status: 200
-2025-09-05 22:42:28,783 - INFO - Login successful
-2025-09-05 22:42:28,783 - INFO - Selected account: Tudor Sitaru at Noddy's Nursery School (ID: e518bd01-e516-4b3c-aefa-bcb369823a2e)
-2025-09-05 22:42:28,783 - INFO - Creating session for user ID: e518bd01-e516-4b3c-aefa-bcb369823a2e
-2025-09-05 22:42:29,171 - INFO - Create session response status: 200
-2025-09-05 22:42:29,172 - INFO - Session creation successful
-2025-09-05 22:42:29,172 - INFO - API key obtained successfully
-2025-09-05 22:42:29,173 - INFO - Login authentication successful
-2025-09-05 22:42:29,173 - INFO - Starting snapshot fetch from 2021-10-18 to 2025-09-05
-2025-09-05 22:42:29,173 - INFO - Fetching snapshots (first page): https://api.parentzone.me/v1/posts?dateFrom=2021-10-18&dateTo=2025-09-05&typeIDs%5B%5D=15
-2025-09-05 22:42:29,705 - INFO - Retrieved 25 snapshots (first page)
-2025-09-05 22:42:29,706 - INFO - Page 1: 25 snapshots (total: 25)
-2025-09-05 22:42:29,706 - INFO - Fetching snapshots (cursor: eyJsYXN0SUQiOjIzODE4...): https://api.parentzone.me/v1/posts?dateFrom=2021-10-18&dateTo=2025-09-05&cursor=eyJsYXN0SUQiOjIzODE4NTcsImxhc3RTdGFydFRpbWUiOiIyMDI0LTEwLTIzVDE0OjEyOjAwIn0%3D&typeIDs%5B%5D=15
-2025-09-05 22:42:30,033 - INFO - Retrieved 25 snapshots (cursor: eyJsYXN0SUQiOjIzODE4...)
-2025-09-05 22:42:30,034 - INFO - Page 2: 25 snapshots (total: 50)
-2025-09-05 22:42:30,034 - INFO - Reached maximum pages limit: 2
-2025-09-05 22:42:30,034 - INFO - Total snapshots fetched: 50
-2025-09-05 22:42:30,039 - INFO - Generated HTML file: snapshots_test/snapshots_2021-10-18_to_2025-09-05.html
-2025-09-05 22:49:12,928 - INFO - Starting snapshot download with configuration
-2025-09-05 22:49:12,928 - INFO - Date range: 2021-10-18 to 2025-09-05
-2025-09-05 22:49:12,928 - INFO - Type IDs: [15]
-2025-09-05 22:49:12,928 - INFO - Output directory: ./snapshots_test
-2025-09-05 22:49:12,928 - INFO - Max pages limit: 2
-2025-09-05 22:49:12,928 - INFO - Starting snapshot download for period 2021-10-18 to 2025-09-05
-2025-09-05 22:49:12,929 - INFO - Attempting login authentication...
-2025-09-05 22:49:12,929 - INFO - Attempting login for tudor.sitaru@gmail.com
-2025-09-05 22:49:13,677 - INFO - Login response status: 200
-2025-09-05 22:49:13,678 - INFO - Login successful
-2025-09-05 22:49:13,678 - INFO - Selected account: Tudor Sitaru at Noddy's Nursery School (ID: e518bd01-e516-4b3c-aefa-bcb369823a2e)
-2025-09-05 22:49:13,678 - INFO - Creating session for user ID: e518bd01-e516-4b3c-aefa-bcb369823a2e
-2025-09-05 22:49:14,082 - INFO - Create session response status: 200
-2025-09-05 22:49:14,083 - INFO - Session creation successful
-2025-09-05 22:49:14,083 - INFO - API key obtained successfully
-2025-09-05 22:49:14,084 - INFO - Login authentication successful
-2025-09-05 22:49:14,085 - INFO - Starting snapshot fetch from 2021-10-18 to 2025-09-05
-2025-09-05 22:49:14,085 - INFO - Fetching snapshots (first page): https://api.parentzone.me/v1/posts?dateFrom=2021-10-18&dateTo=2025-09-05&typeIDs%5B%5D=15
-2025-09-05 22:49:14,512 - INFO - Retrieved 25 snapshots (first page)
-2025-09-05 22:49:14,512 - INFO - Page 1: 25 snapshots (total: 25)
-2025-09-05 22:49:14,512 - INFO - Fetching snapshots (cursor: eyJsYXN0SUQiOjIzODE4...): https://api.parentzone.me/v1/posts?dateFrom=2021-10-18&dateTo=2025-09-05&cursor=eyJsYXN0SUQiOjIzODE4NTcsImxhc3RTdGFydFRpbWUiOiIyMDI0LTEwLTIzVDE0OjEyOjAwIn0%3D&typeIDs%5B%5D=15
-2025-09-05 22:49:14,754 - INFO - Retrieved 25 snapshots (cursor: eyJsYXN0SUQiOjIzODE4...)
-2025-09-05 22:49:14,754 - INFO - Page 2: 25 snapshots (total: 50)
-2025-09-05 22:49:14,754 - INFO - Reached maximum pages limit: 2
-2025-09-05 22:49:14,754 - INFO - Total snapshots fetched: 50
-2025-09-05 22:49:14,758 - INFO - Generated HTML file: snapshots_test/snapshots_2021-10-18_to_2025-09-05.html
-2025-09-05 23:02:05,096 - INFO - Starting snapshot download with configuration
-2025-09-05 23:02:05,097 - INFO - Date range: 2021-10-18 to 2025-09-05
-2025-09-05 23:02:05,097 - INFO - Type IDs: [15]
-2025-09-05 23:02:05,097 - INFO - Output directory: ./snapshots_test
-2025-09-05 23:02:05,097 - INFO - Max pages limit: 2
-2025-09-05 23:02:05,097 - INFO - Starting snapshot download for period 2021-10-18 to 2025-09-05
-2025-09-05 23:02:05,097 - INFO - Attempting login authentication...
-2025-09-05 23:02:05,097 - INFO - Attempting login for tudor.sitaru@gmail.com
-2025-09-05 23:02:05,767 - INFO - Login response status: 200
-2025-09-05 23:02:05,767 - INFO - Login successful
-2025-09-05 23:02:05,767 - INFO - Selected account: Tudor Sitaru at Noddy's Nursery School (ID: e518bd01-e516-4b3c-aefa-bcb369823a2e)
-2025-09-05 23:02:05,767 - INFO - Creating session for user ID: e518bd01-e516-4b3c-aefa-bcb369823a2e
-2025-09-05 23:02:06,174 - INFO - Create session response status: 200
-2025-09-05 23:02:06,175 - INFO - Session creation successful
-2025-09-05 23:02:06,175 - INFO - API key obtained successfully
-2025-09-05 23:02:06,176 - INFO - Login authentication successful
-2025-09-05 23:02:06,176 - INFO - Starting snapshot fetch from 2021-10-18 to 2025-09-05
-2025-09-05 23:02:06,176 - INFO - Fetching snapshots (first page): https://api.parentzone.me/v1/posts?dateFrom=2021-10-18&dateTo=2025-09-05&typeIDs%5B%5D=15
-2025-09-05 23:02:06,600 - INFO - Retrieved 25 snapshots (first page)
-2025-09-05 23:02:06,600 - INFO - Page 1: 25 snapshots (total: 25)
-2025-09-05 23:02:06,600 - INFO - Fetching snapshots (cursor: eyJsYXN0SUQiOjIzODE4...): https://api.parentzone.me/v1/posts?dateFrom=2021-10-18&dateTo=2025-09-05&cursor=eyJsYXN0SUQiOjIzODE4NTcsImxhc3RTdGFydFRpbWUiOiIyMDI0LTEwLTIzVDE0OjEyOjAwIn0%3D&typeIDs%5B%5D=15
-2025-09-05 23:02:06,997 - INFO - Retrieved 25 snapshots (cursor: eyJsYXN0SUQiOjIzODE4...)
-2025-09-05 23:02:06,997 - INFO - Page 2: 25 snapshots (total: 50)
-2025-09-05 23:02:06,998 - INFO - Reached maximum pages limit: 2
-2025-09-05 23:02:06,998 - INFO - Total snapshots fetched: 50
-2025-09-05 23:02:06,998 - INFO - Attempting login authentication...
-2025-09-05 23:02:06,998 - INFO - Attempting login for tudor.sitaru@gmail.com
-2025-09-05 23:02:07,608 - INFO - Login response status: 200
-2025-09-05 23:02:07,608 - INFO - Login successful
-2025-09-05 23:02:07,608 - INFO - Selected account: Tudor Sitaru at Noddy's Nursery School (ID: e518bd01-e516-4b3c-aefa-bcb369823a2e)
-2025-09-05 23:02:07,608 - INFO - Creating session for user ID: e518bd01-e516-4b3c-aefa-bcb369823a2e
-2025-09-05 23:02:07,895 - INFO - Create session response status: 200
-2025-09-05 23:02:07,896 - INFO - Session creation successful
-2025-09-05 23:02:07,896 - INFO - API key obtained successfully
-2025-09-05 23:02:07,897 - INFO - Login authentication successful
-2025-09-05 23:02:07,897 - INFO - Downloading media file: DCC724DD-0E3C-445D-BB6A-628C355533F2.jpeg
-2025-09-05 23:02:08,250 - INFO - Successfully downloaded media: DCC724DD-0E3C-445D-BB6A-628C355533F2.jpeg
-2025-09-05 23:02:08,251 - INFO - Downloading media file: e4e51387-1fee-4129-bd47-e49523b26697.jpeg
-2025-09-05 23:02:08,445 - INFO - Successfully downloaded media: e4e51387-1fee-4129-bd47-e49523b26697.jpeg
-2025-09-05 23:02:08,447 - INFO - Downloading media file: 7ED768A6-16A7-480A-B238-34B1DB87BDE6.jpeg
-2025-09-05 23:02:08,700 - INFO - Successfully downloaded media: 7ED768A6-16A7-480A-B238-34B1DB87BDE6.jpeg
-2025-09-05 23:02:08,700 - INFO - Downloading media file: 6CE82D8D-FAE8-4CD3-987F-A9F0BDD57919.jpeg
-2025-09-05 23:02:09,026 - INFO - Successfully downloaded media: 6CE82D8D-FAE8-4CD3-987F-A9F0BDD57919.jpeg
-2025-09-05 23:02:09,026 - INFO - Downloading media file: 04F440B5-549B-48E5-A480-4CEB0B649834.jpeg
-2025-09-05 23:02:09,402 - INFO - Successfully downloaded media: 04F440B5-549B-48E5-A480-4CEB0B649834.jpeg
-2025-09-05 23:02:09,403 - INFO - Downloading media file: AB2FE0B6-0932-4179-A3AE-933E05FA8519.jpeg
-2025-09-05 23:02:09,861 - INFO - Successfully downloaded media: AB2FE0B6-0932-4179-A3AE-933E05FA8519.jpeg
-2025-09-05 23:02:09,861 - INFO - Downloading media file: 466557B6-6ED0-4750-BA37-EC6DF92CB18B.jpeg
-2025-09-05 23:02:10,242 - INFO - Successfully downloaded media: 466557B6-6ED0-4750-BA37-EC6DF92CB18B.jpeg
-2025-09-05 23:02:10,243 - INFO - Downloading media file: 7268DAC2-8275-47DA-8A0D-FA659F850C31.jpeg
-2025-09-05 23:02:10,510 - INFO - Successfully downloaded media: 7268DAC2-8275-47DA-8A0D-FA659F850C31.jpeg
-2025-09-05 23:02:10,511 - INFO - Downloading media file: 692E5DAF-0D7B-433F-AA94-75CC265F1A59.jpeg
-2025-09-05 23:02:10,815 - INFO - Successfully downloaded media: 692E5DAF-0D7B-433F-AA94-75CC265F1A59.jpeg
-2025-09-05 23:02:10,815 - INFO - Downloading media file: CCE3933F-84FD-4A6D-987A-77993183A054.jpeg
-2025-09-05 23:02:11,036 - INFO - Successfully downloaded media: CCE3933F-84FD-4A6D-987A-77993183A054.jpeg
-2025-09-05 23:02:11,036 - INFO - Downloading media file: 2A5EE1D8-A113-43F8-9416-316287DE3E8F.jpeg
-2025-09-05 23:02:11,243 - INFO - Successfully downloaded media: 2A5EE1D8-A113-43F8-9416-316287DE3E8F.jpeg
-2025-09-05 23:02:11,243 - INFO - Downloading media file: 80702FD5-DF2C-4EC3-948C-70EBAE7C4BFF.jpeg
-2025-09-05 23:02:11,460 - INFO - Successfully downloaded media: 80702FD5-DF2C-4EC3-948C-70EBAE7C4BFF.jpeg
-2025-09-05 23:02:11,460 - INFO - Downloading media file: 1BC2789D-99B7-4CC5-84F3-AEA1F0CB39B2.jpeg
-2025-09-05 23:02:11,727 - INFO - Successfully downloaded media: 1BC2789D-99B7-4CC5-84F3-AEA1F0CB39B2.jpeg
-2025-09-05 23:02:11,728 - INFO - Downloading media file: BA2B3A67-356C-4D22-9FA2-2CF2040EC080.jpeg
-2025-09-05 23:02:11,969 - INFO - Successfully downloaded media: BA2B3A67-356C-4D22-9FA2-2CF2040EC080.jpeg
-2025-09-05 23:02:11,969 - INFO - Downloading media file: F3411311-E3CE-4A74-84CB-372DA00F80B7.jpeg
-2025-09-05 23:02:12,233 - INFO - Successfully downloaded media: F3411311-E3CE-4A74-84CB-372DA00F80B7.jpeg
-2025-09-05 23:02:12,233 - INFO - Downloading media file: 1715613184982FE8C3F62-2F0C-4A43-8F57-864F5BA9E112.jpeg.jpg
-2025-09-05 23:02:12,448 - INFO - Successfully downloaded media: 1715613184982FE8C3F62-2F0C-4A43-8F57-864F5BA9E112.jpeg.jpg
-2025-09-05 23:02:12,448 - INFO - Downloading media file: 171561318498211415BA1-6E38-4D1C-8962-8ED04199856D.jpeg.jpg
-2025-09-05 23:02:12,675 - INFO - Successfully downloaded media: 171561318498211415BA1-6E38-4D1C-8962-8ED04199856D.jpeg.jpg
-2025-09-05 23:02:12,676 - INFO - Downloading media file: 07B7B911-58C7-4998-BBDE-A773351854D5.jpeg
-2025-09-05 23:02:13,209 - INFO - Successfully downloaded media: 07B7B911-58C7-4998-BBDE-A773351854D5.jpeg
-2025-09-05 23:02:13,209 - INFO - Downloading media file: 1073B5D1-D162-4D78-8135-45447BA04CAB.jpeg
-2025-09-05 23:02:14,432 - INFO - Successfully downloaded media: 1073B5D1-D162-4D78-8135-45447BA04CAB.jpeg
-2025-09-05 23:02:14,433 - INFO - Downloading media file: 25E15BAA-58B3-47C8-BEC9-D777ED71A0AB.jpeg
-2025-09-05 23:02:14,707 - INFO - Successfully downloaded media: 25E15BAA-58B3-47C8-BEC9-D777ED71A0AB.jpeg
-2025-09-05 23:02:14,707 - INFO - Downloading media file: C959CBD6-A829-43AB-87CF-732269921ADB.jpeg
-2025-09-05 23:02:15,058 - INFO - Successfully downloaded media: C959CBD6-A829-43AB-87CF-732269921ADB.jpeg
-2025-09-05 23:02:15,058 - INFO - Downloading media file: 045D878D-47E3-4EB5-B9DB-36B9B63299E9.jpeg
-2025-09-05 23:02:15,349 - INFO - Successfully downloaded media: 045D878D-47E3-4EB5-B9DB-36B9B63299E9.jpeg
-2025-09-05 23:02:15,350 - INFO - Downloading media file: 6BC18F39-5C1A-43FB-AD64-0D5AB616A292.jpeg
-2025-09-05 23:02:15,634 - INFO - Successfully downloaded media: 6BC18F39-5C1A-43FB-AD64-0D5AB616A292.jpeg
-2025-09-05 23:02:15,635 - INFO - Downloading media file: D827391F-6BB7-4F61-B315-FB791E5ADC2F.jpeg
-2025-09-05 23:02:15,918 - INFO - Successfully downloaded media: D827391F-6BB7-4F61-B315-FB791E5ADC2F.jpeg
-2025-09-05 23:02:15,920 - INFO - Generated HTML file: snapshots_test/snapshots_2021-10-18_to_2025-09-05.html

src/__init__.py

@@ -0,0 +1,44 @@
+"""
+ParentZone Downloader - Source Package
+
+This package contains the core application modules for the ParentZone Downloader.
+
+Modules:
+    - asset_tracker: Track downloaded assets to avoid re-downloads
+    - auth_manager: Handle authentication with ParentZone API
+    - config_downloader: Configuration-based image downloader
+    - config_snapshot_downloader: Configuration-based snapshot downloader
+    - image_downloader: Download images from ParentZone API
+    - snapshot_downloader: Download snapshots from ParentZone API
+    - webserver: Web server to serve downloaded snapshots
+"""
+
+__version__ = "1.0.0"
+__author__ = "ParentZone Downloader Team"
+
+# Import main classes for easier access
+try:
+    from .asset_tracker import AssetTracker
+    from .auth_manager import AuthManager
+    from .config_downloader import ConfigImageDownloader
+    from .config_snapshot_downloader import ConfigSnapshotDownloader
+    from .image_downloader import ImageDownloader
+    from .snapshot_downloader import SnapshotDownloader
+    from .webserver import SnapshotsWebServer
+
+    __all__ = [
+        "AssetTracker",
+        "AuthManager",
+        "ConfigImageDownloader",
+        "ConfigSnapshotDownloader",
+        "ImageDownloader",
+        "SnapshotDownloader",
+        "SnapshotsWebServer",
+    ]
+
+except ImportError as e:
+    # Handle case where dependencies might not be available
+    __all__ = []
+    import warnings
+
+    warnings.warn(f"Some modules could not be imported: {e}")

src/config_downloader.py

@@ -24,12 +24,12 @@ from tqdm import tqdm
 
 # Import the auth manager and asset tracker
 try:
-    from auth_manager import AuthManager
+    from src.auth_manager import AuthManager
 except ImportError:
     AuthManager = None
 
 try:
-    from asset_tracker import AssetTracker
+    from src.asset_tracker import AssetTracker
 except ImportError:
     AssetTracker = None
 
@@ -453,8 +453,8 @@ Examples:
   python config_downloader.py --config config.json
 
   # Create a config file first:
-  cp config_example.json my_config.json
-  # Edit my_config.json with your API details
+  cp config/config_example.json config/my_config.json
+  # Edit config/my_config.json with your API details
   python config_downloader.py --config my_config.json
         """,
     )

src/config_snapshot_downloader.py

@@ -16,9 +16,11 @@ from pathlib import Path
 
 # Import the snapshot downloader
 try:
-    from snapshot_downloader import SnapshotDownloader
+    from src.snapshot_downloader import SnapshotDownloader
 except ImportError:
-    print("Error: snapshot_downloader.py not found. Please ensure it's in the same directory.")
+    print(
+        "Error: snapshot_downloader.py not found. Please ensure it's in the same directory."
+    )
     exit(1)
 
 
@@ -35,38 +37,47 @@ class ConfigSnapshotDownloader:
 
         # Create the underlying snapshot downloader
         self.downloader = SnapshotDownloader(
-            api_url=self.config.get('api_url', 'https://api.parentzone.me'),
-            output_dir=self.config.get('output_dir', 'snapshots'),
-            api_key=self.config.get('api_key'),
-            email=self.config.get('email'),
-            password=self.config.get('password')
+            api_url=self.config.get("api_url", "https://api.parentzone.me"),
+            output_dir=self.config.get("output_dir", "snapshots"),
+            api_key=self.config.get("api_key"),
+            email=self.config.get("email"),
+            password=self.config.get("password"),
         )
 
     def load_config(self, config_file: str) -> dict:
         """Load configuration from JSON file."""
         try:
-            with open(config_file, 'r') as f:
+            with open(config_file, "r") as f:
                 config = json.load(f)
 
             # Validate required authentication
-            has_api_key = 'api_key' in config and config['api_key']
-            has_credentials = 'email' in config and 'password' in config and config['email'] and config['password']
+            has_api_key = "api_key" in config and config["api_key"]
+            has_credentials = (
+                "email" in config
+                and "password" in config
+                and config["email"]
+                and config["password"]
+            )
 
             if not has_api_key and not has_credentials:
-                raise ValueError("Either 'api_key' or both 'email' and 'password' must be provided in config")
+                raise ValueError(
+                    "Either 'api_key' or both 'email' and 'password' must be provided in config"
+                )
 
             # Set defaults for optional fields
-            config.setdefault('api_url', 'https://api.parentzone.me')
-            config.setdefault('output_dir', 'snapshots')
-            config.setdefault('type_ids', [15])
-            config.setdefault('max_pages', None)
+            config.setdefault("api_url", "https://api.parentzone.me")
+            config.setdefault("output_dir", "snapshots")
+            config.setdefault("type_ids", [15])
+            config.setdefault("max_pages", None)
 
             # Set default date range (last year) if not specified
-            if 'date_from' not in config or not config['date_from']:
-                config['date_from'] = (datetime.now() - timedelta(days=365)).strftime("%Y-%m-%d")
+            if "date_from" not in config or not config["date_from"]:
+                config["date_from"] = (datetime.now() - timedelta(days=365)).strftime(
+                    "%Y-%m-%d"
+                )
 
-            if 'date_to' not in config or not config['date_to']:
-                config['date_to'] = datetime.now().strftime("%Y-%m-%d")
+            if "date_to" not in config or not config["date_to"]:
+                config["date_to"] = datetime.now().strftime("%Y-%m-%d")
 
             return config
 
@@ -77,17 +88,14 @@ class ConfigSnapshotDownloader:
 
     def setup_logging(self):
         """Setup logging configuration."""
-        output_dir = Path(self.config['output_dir'])
+        output_dir = Path(self.config["output_dir"])
         output_dir.mkdir(exist_ok=True)
-        log_file = output_dir / 'snapshots.log'
+        log_file = output_dir / "snapshots.log"
 
         logging.basicConfig(
             level=logging.INFO,
-            format='%(asctime)s - %(levelname)s - %(message)s',
-            handlers=[
-                logging.FileHandler(log_file),
-                logging.StreamHandler()
-            ]
+            format="%(asctime)s - %(levelname)s - %(message)s",
+            handlers=[logging.FileHandler(log_file), logging.StreamHandler()],
         )
         self.logger = logging.getLogger(__name__)
 
@@ -99,19 +107,21 @@ class ConfigSnapshotDownloader:
             Path to the generated HTML file
         """
         self.logger.info("Starting snapshot download with configuration")
-        self.logger.info(f"Date range: {self.config['date_from']} to {self.config['date_to']}")
+        self.logger.info(
+            f"Date range: {self.config['date_from']} to {self.config['date_to']}"
+        )
         self.logger.info(f"Type IDs: {self.config['type_ids']}")
         self.logger.info(f"Output directory: {self.config['output_dir']}")
 
-        if self.config.get('max_pages'):
+        if self.config.get("max_pages"):
             self.logger.info(f"Max pages limit: {self.config['max_pages']}")
 
         try:
             html_file = await self.downloader.download_snapshots(
-                type_ids=self.config['type_ids'],
-                date_from=self.config['date_from'],
-                date_to=self.config['date_to'],
-                max_pages=self.config.get('max_pages')
+                type_ids=self.config["type_ids"],
+                date_from=self.config["date_from"],
+                date_to=self.config["date_to"],
+                max_pages=self.config.get("max_pages"),
             )
 
             return html_file
@@ -131,10 +141,10 @@ class ConfigSnapshotDownloader:
         print(f"Date To: {self.config['date_to']}")
         print(f"Type IDs: {self.config['type_ids']}")
 
-        auth_method = "API Key" if self.config.get('api_key') else "Email/Password"
+        auth_method = "API Key" if self.config.get("api_key") else "Email/Password"
         print(f"Authentication: {auth_method}")
 
-        if self.config.get('max_pages'):
+        if self.config.get("max_pages"):
             print(f"Max Pages: {self.config['max_pages']}")
 
         print("=" * 60)
@@ -151,11 +161,11 @@ def create_example_config():
         "max_pages": null,
         "api_key": "your-api-key-here",
         "email": "your-email@example.com",
-        "password": "your-password-here"
+        "password": "your-password-here",
     }
 
     config_file = Path("snapshot_config_example.json")
-    with open(config_file, 'w') as f:
+    with open(config_file, "w") as f:
         json.dump(example_config, f, indent=2)
 
     print(f"✅ Example configuration created: {config_file}")
@@ -196,30 +206,27 @@ Notes:
 - 'date_from' and 'date_to' default to last year if not specified
 - 'type_ids' defaults to [15] (snapshot type)
 - 'max_pages' limits pages fetched (useful for testing)
-        """
+        """,
+    )
+
+    parser.add_argument("--config", help="Path to the JSON configuration file")
+
+    parser.add_argument(
+        "--create-example",
+        action="store_true",
+        help="Create an example configuration file and exit",
     )
 
     parser.add_argument(
-        '--config',
-        help='Path to the JSON configuration file'
+        "--show-config",
+        action="store_true",
+        help="Show configuration summary before downloading",
     )
 
     parser.add_argument(
-        '--create-example',
-        action='store_true',
-        help='Create an example configuration file and exit'
-    )
-
-    parser.add_argument(
-        '--show-config',
-        action='store_true',
-        help='Show configuration summary before downloading'
-    )
-
-    parser.add_argument(
-        '--debug',
-        action='store_true',
-        help='Enable debug mode with detailed server response logging'
+        "--debug",
+        action="store_true",
+        help="Enable debug mode with detailed server response logging",
     )
 
     args = parser.parse_args()

src/image_downloader.py

@@ -26,20 +26,30 @@ import hashlib
 
 # Import the auth manager and asset tracker
 try:
-    from auth_manager import AuthManager
+    from src.auth_manager import AuthManager
 except ImportError:
     AuthManager = None
 
 try:
-    from asset_tracker import AssetTracker
+    from src.asset_tracker import AssetTracker
 except ImportError:
     AssetTracker = None
 
 
 class ImageDownloader:
-    def __init__(self, api_url: str, list_endpoint: str, download_endpoint: str,
-                 output_dir: str, max_concurrent: int = 5, timeout: int = 30, api_key: str = None,
-                 email: str = None, password: str = None, track_assets: bool = True):
+    def __init__(
+        self,
+        api_url: str,
+        list_endpoint: str,
+        download_endpoint: str,
+        output_dir: str,
+        max_concurrent: int = 5,
+        timeout: int = 30,
+        api_key: str = None,
+        email: str = None,
+        password: str = None,
+        track_assets: bool = True,
+    ):
         """
         Initialize the image downloader.
 
@@ -55,9 +65,9 @@ class ImageDownloader:
             password: Password for login authentication
             track_assets: Whether to enable asset tracking to avoid re-downloads
         """
-        self.api_url = api_url.rstrip('/')
-        self.list_endpoint = list_endpoint.lstrip('/')
-        self.download_endpoint = download_endpoint.lstrip('/')
+        self.api_url = api_url.rstrip("/")
+        self.list_endpoint = list_endpoint.lstrip("/")
+        self.download_endpoint = download_endpoint.lstrip("/")
         self.output_dir = Path(output_dir)
         self.max_concurrent = max_concurrent
         self.timeout = timeout
@@ -72,11 +82,11 @@ class ImageDownloader:
         # Setup logging
         logging.basicConfig(
             level=logging.INFO,
-            format='%(asctime)s - %(levelname)s - %(message)s',
+            format="%(asctime)s - %(levelname)s - %(message)s",
             handlers=[
-                logging.FileHandler(self.output_dir / 'download.log'),
-                logging.StreamHandler()
-            ]
+                logging.FileHandler(self.output_dir / "download.log"),
+                logging.StreamHandler(),
+            ],
         )
         self.logger = logging.getLogger(__name__)
 
@@ -86,17 +96,14 @@ class ImageDownloader:
             self.asset_tracker = AssetTracker(storage_dir=str(self.output_dir))
             self.logger.info("Asset tracking enabled")
         elif track_assets:
-            self.logger.warning("Asset tracking requested but AssetTracker not available")
+            self.logger.warning(
+                "Asset tracking requested but AssetTracker not available"
+            )
         else:
             self.logger.info("Asset tracking disabled")
 
         # Track download statistics
-        self.stats = {
-            'total': 0,
-            'successful': 0,
-            'failed': 0,
-            'skipped': 0
-        }
+        self.stats = {"total": 0, "successful": 0, "failed": 0, "skipped": 0}
 
     async def authenticate(self):
         """Perform login authentication if credentials are provided."""
@@ -111,10 +118,16 @@ class ImageDownloader:
                 self.logger.error("Login authentication failed")
                 raise Exception("Login authentication failed")
         elif self.email or self.password:
-            self.logger.warning("Both email and password must be provided for login authentication")
-            raise Exception("Both email and password must be provided for login authentication")
+            self.logger.warning(
+                "Both email and password must be provided for login authentication"
+            )
+            raise Exception(
+                "Both email and password must be provided for login authentication"
+            )
 
-    async def get_asset_list(self, session: aiohttp.ClientSession) -> List[Dict[str, Any]]:
+    async def get_asset_list(
+        self, session: aiohttp.ClientSession
+    ) -> List[Dict[str, Any]]:
         """
         Fetch the list of assets from the API.
 
@@ -132,13 +145,15 @@ class ImageDownloader:
 
             # Use API key if provided
             if self.api_key:
-                headers['x-api-key'] = self.api_key
+                headers["x-api-key"] = self.api_key
 
             # Use login authentication if provided
             elif self.auth_manager and self.auth_manager.is_authenticated():
                 headers.update(self.auth_manager.get_auth_headers())
 
-            async with session.get(url, headers=headers, timeout=self.timeout) as response:
+            async with session.get(
+                url, headers=headers, timeout=self.timeout
+            ) as response:
                 response.raise_for_status()
                 data = await response.json()
 
@@ -147,12 +162,12 @@ class ImageDownloader:
                     assets = data
                 elif isinstance(data, dict):
                     # Common patterns for API responses
-                    if 'data' in data:
-                        assets = data['data']
-                    elif 'results' in data:
-                        assets = data['results']
-                    elif 'items' in data:
-                        assets = data['items']
+                    if "data" in data:
+                        assets = data["data"]
+                    elif "results" in data:
+                        assets = data["results"]
+                    elif "items" in data:
+                        assets = data["items"]
                     else:
                         assets = [data]  # Single asset
                 else:
@@ -179,7 +194,7 @@ class ImageDownloader:
         asset_id = None
 
         # Common field names for asset identifiers
-        id_fields = ['id', 'asset_id', 'image_id', 'file_id', 'uuid', 'key']
+        id_fields = ["id", "asset_id", "image_id", "file_id", "uuid", "key"]
         for field in id_fields:
             if field in asset:
                 asset_id = asset[field]
@@ -192,12 +207,11 @@ class ImageDownloader:
         # Build download URL with required parameters
         from urllib.parse import urlencode
 
-        params = {
-            'key': self.api_key,
-            'u': asset.get('updated', '')
-        }
+        params = {"key": self.api_key, "u": asset.get("updated", "")}
 
-        download_url = urljoin(self.api_url, f"/v1/media/{asset_id}/full?{urlencode(params)}")
+        download_url = urljoin(
+            self.api_url, f"/v1/media/{asset_id}/full?{urlencode(params)}"
+        )
         return download_url
 
     def get_filename(self, asset: Dict[str, Any], url: str) -> str:
@@ -212,27 +226,27 @@ class ImageDownloader:
             Filename for the asset
         """
         # Try to get filename from asset metadata
-        if 'fileName' in asset:
-            filename = asset['fileName']
-        elif 'filename' in asset:
-            filename = asset['filename']
-        elif 'name' in asset:
-            filename = asset['name']
-        elif 'title' in asset:
-            filename = asset['title']
+        if "fileName" in asset:
+            filename = asset["fileName"]
+        elif "filename" in asset:
+            filename = asset["filename"]
+        elif "name" in asset:
+            filename = asset["name"]
+        elif "title" in asset:
+            filename = asset["title"]
         else:
             # Extract filename from URL
             parsed_url = urlparse(url)
             filename = os.path.basename(parsed_url.path)
 
             # If no extension, try to get it from content-type or add default
-            if '.' not in filename:
-                if 'mimeType' in asset:
-                    ext = self._get_extension_from_mime(asset['mimeType'])
-                elif 'content_type' in asset:
-                    ext = self._get_extension_from_mime(asset['content_type'])
+            if "." not in filename:
+                if "mimeType" in asset:
+                    ext = self._get_extension_from_mime(asset["mimeType"])
+                elif "content_type" in asset:
+                    ext = self._get_extension_from_mime(asset["content_type"])
                 else:
-                    ext = '.jpg'  # Default extension
+                    ext = ".jpg"  # Default extension
                 filename += ext
 
         # Sanitize filename
@@ -251,35 +265,39 @@ class ImageDownloader:
     def _get_extension_from_mime(self, mime_type: str) -> str:
         """Get file extension from MIME type."""
         mime_to_ext = {
-            'image/jpeg': '.jpg',
-            'image/jpg': '.jpg',
-            'image/png': '.png',
-            'image/gif': '.gif',
-            'image/webp': '.webp',
-            'image/bmp': '.bmp',
-            'image/tiff': '.tiff',
-            'image/svg+xml': '.svg'
+            "image/jpeg": ".jpg",
+            "image/jpg": ".jpg",
+            "image/png": ".png",
+            "image/gif": ".gif",
+            "image/webp": ".webp",
+            "image/bmp": ".bmp",
+            "image/tiff": ".tiff",
+            "image/svg+xml": ".svg",
         }
-        return mime_to_ext.get(mime_type.lower(), '.jpg')
+        return mime_to_ext.get(mime_type.lower(), ".jpg")
 
     def _sanitize_filename(self, filename: str) -> str:
         """Sanitize filename by removing invalid characters."""
         # Remove or replace invalid characters
         invalid_chars = '<>:"/\\|?*'
         for char in invalid_chars:
-            filename = filename.replace(char, '_')
+            filename = filename.replace(char, "_")
 
         # Remove leading/trailing spaces and dots
-        filename = filename.strip('. ')
+        filename = filename.strip(". ")
 
         # Ensure filename is not empty
         if not filename:
-            filename = 'image'
+            filename = "image"
 
         return filename
 
-    async def download_asset(self, session: aiohttp.ClientSession, asset: Dict[str, Any],
-                           semaphore: asyncio.Semaphore) -> bool:
+    async def download_asset(
+        self,
+        session: aiohttp.ClientSession,
+        asset: Dict[str, Any],
+        semaphore: asyncio.Semaphore,
+    ) -> bool:
         """
         Download a single asset.
 
@@ -300,7 +318,7 @@ class ImageDownloader:
                 # Check if file already exists and we're not tracking assets
                 if filepath.exists() and not self.asset_tracker:
                     self.logger.info(f"Skipping {filename} (already exists)")
-                    self.stats['skipped'] += 1
+                    self.stats["skipped"] += 1
                     return True
 
                 self.logger.info(f"Downloading {filename} from {download_url}")
@@ -309,34 +327,46 @@ class ImageDownloader:
                     response.raise_for_status()
 
                     # Get content type to verify it's an image
-                    content_type = response.headers.get('content-type', '')
-                    if not content_type.startswith('image/'):
-                        self.logger.warning(f"Content type is not an image: {content_type}")
+                    content_type = response.headers.get("content-type", "")
+                    if not content_type.startswith("image/"):
+                        self.logger.warning(
+                            f"Content type is not an image: {content_type}"
+                        )
 
                     # Download the file
-                    async with aiofiles.open(filepath, 'wb') as f:
+                    async with aiofiles.open(filepath, "wb") as f:
                         async for chunk in response.content.iter_chunked(8192):
                             await f.write(chunk)
 
                     # Set file modification time to match the updated timestamp
-                    if 'updated' in asset:
+                    if "updated" in asset:
                         try:
                             from datetime import datetime
                             import os
+
                             # Parse the ISO timestamp
-                            updated_time = datetime.fromisoformat(asset['updated'].replace('Z', '+00:00'))
+                            updated_time = datetime.fromisoformat(
+                                asset["updated"].replace("Z", "+00:00")
+                            )
                             # Set file modification time
-                            os.utime(filepath, (updated_time.timestamp(), updated_time.timestamp()))
-                            self.logger.info(f"Set file modification time to {asset['updated']}")
+                            os.utime(
+                                filepath,
+                                (updated_time.timestamp(), updated_time.timestamp()),
+                            )
+                            self.logger.info(
+                                f"Set file modification time to {asset['updated']}"
+                            )
                         except Exception as e:
-                            self.logger.warning(f"Failed to set file modification time: {e}")
+                            self.logger.warning(
+                                f"Failed to set file modification time: {e}"
+                            )
 
                 # Mark asset as downloaded in tracker
                 if self.asset_tracker:
                     self.asset_tracker.mark_asset_downloaded(asset, filepath, True)
 
                 self.logger.info(f"Successfully downloaded {filename}")
-                self.stats['successful'] += 1
+                self.stats["successful"] += 1
                 return True
 
             except Exception as e:
@@ -347,8 +377,10 @@ class ImageDownloader:
                     filepath = self.output_dir / filename
                     self.asset_tracker.mark_asset_downloaded(asset, filepath, False)
 
-                self.logger.error(f"Failed to download asset {asset.get('id', 'unknown')}: {e}")
-                self.stats['failed'] += 1
+                self.logger.error(
+                    f"Failed to download asset {asset.get('id', 'unknown')}: {e}"
+                )
+                self.stats["failed"] += 1
                 return False
 
     async def download_all_assets(self, force_redownload: bool = False):
@@ -364,7 +396,9 @@ class ImageDownloader:
         connector = aiohttp.TCPConnector(limit=100, limit_per_host=30)
         timeout = aiohttp.ClientTimeout(total=self.timeout)
 
-        async with aiohttp.ClientSession(connector=connector, timeout=timeout) as session:
+        async with aiohttp.ClientSession(
+            connector=connector, timeout=timeout
+        ) as session:
             try:
                 # Perform authentication if needed
                 await self.authenticate()
@@ -380,24 +414,27 @@ class ImageDownloader:
                 # Filter for new/modified assets if tracking is enabled
                 if self.asset_tracker and not force_redownload:
                     assets = self.asset_tracker.get_new_assets(all_assets)
-                    self.logger.info(f"Found {len(assets)} new/modified assets to download")
+                    self.logger.info(
+                        f"Found {len(assets)} new/modified assets to download"
+                    )
                     if len(assets) == 0:
                         self.logger.info("All assets are up to date!")
                         return
                 else:
                     assets = all_assets
                     if force_redownload:
-                        self.logger.info("Force redownload enabled - downloading all assets")
+                        self.logger.info(
+                            "Force redownload enabled - downloading all assets"
+                        )
 
-                self.stats['total'] = len(assets)
+                self.stats["total"] = len(assets)
 
                 # Create semaphore to limit concurrent downloads
                 semaphore = asyncio.Semaphore(self.max_concurrent)
 
                 # Create tasks for all downloads
                 tasks = [
-                    self.download_asset(session, asset, semaphore)
-                    for asset in assets
+                    self.download_asset(session, asset, semaphore) for asset in assets
                 ]
 
                 # Download all assets with progress bar
@@ -405,11 +442,13 @@ class ImageDownloader:
                     for coro in asyncio.as_completed(tasks):
                         result = await coro
                         pbar.update(1)
-                        pbar.set_postfix({
-                            'Success': self.stats['successful'],
-                            'Failed': self.stats['failed'],
-                            'Skipped': self.stats['skipped']
-                        })
+                        pbar.set_postfix(
+                            {
+                                "Success": self.stats["successful"],
+                                "Failed": self.stats["failed"],
+                                "Skipped": self.stats["skipped"],
+                            }
+                        )
 
             except Exception as e:
                 self.logger.error(f"Error during download process: {e}")
@@ -441,84 +480,75 @@ Examples:
                             --output-dir "./images" \\
                             --max-concurrent 10 \\
                             --timeout 60
-        """
+        """,
     )
 
     parser.add_argument(
-        '--api-url',
+        "--api-url",
         required=True,
-        help='Base URL of the API (e.g., https://api.example.com)'
+        help="Base URL of the API (e.g., https://api.example.com)",
     )
 
     parser.add_argument(
-        '--list-endpoint',
+        "--list-endpoint",
         required=True,
-        help='Endpoint to get the list of assets (e.g., /assets or /images)'
+        help="Endpoint to get the list of assets (e.g., /assets or /images)",
     )
 
     parser.add_argument(
-        '--download-endpoint',
+        "--download-endpoint",
         required=True,
-        help='Endpoint to download individual assets (e.g., /download or /assets)'
+        help="Endpoint to download individual assets (e.g., /download or /assets)",
     )
 
     parser.add_argument(
-        '--output-dir',
-        required=True,
-        help='Directory to save downloaded images'
+        "--output-dir", required=True, help="Directory to save downloaded images"
     )
 
     parser.add_argument(
-        '--max-concurrent',
+        "--max-concurrent",
         type=int,
         default=5,
-        help='Maximum number of concurrent downloads (default: 5)'
+        help="Maximum number of concurrent downloads (default: 5)",
     )
 
     parser.add_argument(
-        '--timeout',
+        "--timeout",
         type=int,
         default=30,
-        help='Request timeout in seconds (default: 30)'
+        help="Request timeout in seconds (default: 30)",
     )
 
     parser.add_argument(
-        '--api-key',
-        help='API key for authentication (x-api-key header)'
+        "--api-key", help="API key for authentication (x-api-key header)"
+    )
+
+    parser.add_argument("--email", help="Email for login authentication")
+
+    parser.add_argument("--password", help="Password for login authentication")
+
+    parser.add_argument(
+        "--no-tracking",
+        action="store_true",
+        help="Disable asset tracking (will re-download all assets)",
     )
 
     parser.add_argument(
-        '--email',
-        help='Email for login authentication'
+        "--force-redownload",
+        action="store_true",
+        help="Force re-download of all assets, even if already tracked",
     )
 
     parser.add_argument(
-        '--password',
-        help='Password for login authentication'
+        "--show-stats",
+        action="store_true",
+        help="Show asset tracking statistics and exit",
     )
 
     parser.add_argument(
-        '--no-tracking',
-        action='store_true',
-        help='Disable asset tracking (will re-download all assets)'
-    )
-
-    parser.add_argument(
-        '--force-redownload',
-        action='store_true',
-        help='Force re-download of all assets, even if already tracked'
-    )
-
-    parser.add_argument(
-        '--show-stats',
-        action='store_true',
-        help='Show asset tracking statistics and exit'
-    )
-
-    parser.add_argument(
-        '--cleanup',
-        action='store_true',
-        help='Clean up metadata for missing files and exit'
+        "--cleanup",
+        action="store_true",
+        help="Clean up metadata for missing files and exit",
     )
 
     args = parser.parse_args()
@@ -546,11 +576,13 @@ Examples:
         api_key=args.api_key,
         email=args.email,
         password=args.password,
-        track_assets=not args.no_tracking
+        track_assets=not args.no_tracking,
     )
 
     try:
-        asyncio.run(downloader.download_all_assets(force_redownload=args.force_redownload))
+        asyncio.run(
+            downloader.download_all_assets(force_redownload=args.force_redownload)
+        )
     except KeyboardInterrupt:
         print("\nDownload interrupted by user")
     except Exception as e:

src/snapshot_downloader.py

@@ -21,15 +21,21 @@ import aiofiles
 
 # Import the auth manager
 try:
-    from auth_manager import AuthManager
+    from src.auth_manager import AuthManager
 except ImportError:
     AuthManager = None
 
 
 class SnapshotDownloader:
-    def __init__(self, api_url: str = "https://api.parentzone.me",
-                 output_dir: str = "snapshots", api_key: str = None,
-                 email: str = None, password: str = None, debug_mode: bool = False):
+    def __init__(
+        self,
+        api_url: str = "https://api.parentzone.me",
+        output_dir: str = "snapshots",
+        api_key: str = None,
+        email: str = None,
+        password: str = None,
+        debug_mode: bool = False,
+    ):
         """
         Initialize the snapshot downloader.
 
@@ -41,7 +47,7 @@ class SnapshotDownloader:
             password: Password for login authentication
             debug_mode: Enable detailed server response logging
         """
-        self.api_url = api_url.rstrip('/')
+        self.api_url = api_url.rstrip("/")
         self.snapshots_endpoint = "/v1/posts"
         self.output_dir = Path(output_dir)
         self.output_dir.mkdir(parents=True, exist_ok=True)
@@ -62,39 +68,36 @@ class SnapshotDownloader:
 
         # Standard headers based on the curl command
         self.headers = {
-            'accept': 'application/json, text/plain, */*',
-            'accept-language': 'en-GB,en-US;q=0.9,en;q=0.8,ro;q=0.7',
-            'origin': 'https://parentzone.me',
-            'priority': 'u=1, i',
-            'sec-ch-ua': '"Not;A=Brand";v="99", "Google Chrome";v="139", "Chromium";v="139"',
-            'sec-ch-ua-mobile': '?0',
-            'sec-ch-ua-platform': '"macOS"',
-            'sec-fetch-dest': 'empty',
-            'sec-fetch-mode': 'cors',
-            'sec-fetch-site': 'same-site',
-            'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36',
-            'x-client-version': '3.54.0'
+            "accept": "application/json, text/plain, */*",
+            "accept-language": "en-GB,en-US;q=0.9,en;q=0.8,ro;q=0.7",
+            "origin": "https://parentzone.me",
+            "priority": "u=1, i",
+            "sec-ch-ua": '"Not;A=Brand";v="99", "Google Chrome";v="139", "Chromium";v="139"',
+            "sec-ch-ua-mobile": "?0",
+            "sec-ch-ua-platform": '"macOS"',
+            "sec-fetch-dest": "empty",
+            "sec-fetch-mode": "cors",
+            "sec-fetch-site": "same-site",
+            "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36",
+            "x-client-version": "3.54.0",
         }
 
         # Statistics
         self.stats = {
-            'total_snapshots': 0,
-            'pages_fetched': 0,
-            'failed_requests': 0,
-            'generated_files': 0
+            "total_snapshots": 0,
+            "pages_fetched": 0,
+            "failed_requests": 0,
+            "generated_files": 0,
         }
 
     def setup_logging(self):
         """Setup logging configuration."""
-        log_file = self.output_dir / 'snapshots.log'
+        log_file = self.output_dir / "snapshots.log"
 
         logging.basicConfig(
             level=logging.INFO,
-            format='%(asctime)s - %(levelname)s - %(message)s',
-            handlers=[
-                logging.FileHandler(log_file),
-                logging.StreamHandler()
-            ]
+            format="%(asctime)s - %(levelname)s - %(message)s",
+            handlers=[logging.FileHandler(log_file), logging.StreamHandler()],
         )
         self.logger = logging.getLogger(__name__)
 
@@ -109,8 +112,8 @@ class SnapshotDownloader:
                 self.logger.info("Login authentication successful")
                 # Use the API key from auth manager
                 auth_headers = self.auth_manager.get_auth_headers()
-                if 'x-api-key' in auth_headers:
-                    self.api_key = auth_headers['x-api-key']
+                if "x-api-key" in auth_headers:
+                    self.api_key = auth_headers["x-api-key"]
             else:
                 self.logger.error("Login authentication failed")
                 raise Exception("Login authentication failed")
@@ -120,18 +123,21 @@ class SnapshotDownloader:
         headers = self.headers.copy()
 
         if self.api_key:
-            headers['x-api-key'] = self.api_key
+            headers["x-api-key"] = self.api_key
         elif self.auth_manager and self.auth_manager.is_authenticated():
             headers.update(self.auth_manager.get_auth_headers())
 
         return headers
 
-    async def fetch_snapshots_page(self, session: aiohttp.ClientSession,
+    async def fetch_snapshots_page(
+        self,
+        session: aiohttp.ClientSession,
         type_ids: List[int] = [15],
         date_from: str = "2021-10-18",
         date_to: str = None,
         cursor: str = None,
-                                 per_page: int = 100) -> Dict[str, Any]:
+        per_page: int = 100,
+    ) -> Dict[str, Any]:
         """
         Fetch a single page of snapshots from the API using cursor-based pagination.
 
@@ -151,17 +157,17 @@ class SnapshotDownloader:
 
         # Build query parameters
         params = {
-            'dateFrom': date_from,
-            'dateTo': date_to,
+            "dateFrom": date_from,
+            "dateTo": date_to,
         }
 
         # Add cursor for pagination (skip for first request)
         if cursor:
-            params['cursor'] = cursor
+            params["cursor"] = cursor
 
         # Add type IDs - API expects typeIDs[]=15 format
         for type_id in type_ids:
-            params[f'typeIDs[]'] = type_id
+            params[f"typeIDs[]"] = type_id
 
         # Build URL with parameters
         query_string = urlencode(params, doseq=True)
@@ -184,21 +190,25 @@ class SnapshotDownloader:
                     print(f"Status Code: {response.status}")
                     print(f"Headers: {dict(response.headers)}")
                     print(f"Response Type: {type(data)}")
-                    print(f"Response Keys: {list(data.keys()) if isinstance(data, dict) else 'Not a dict'}")
+                    print(
+                        f"Response Keys: {list(data.keys()) if isinstance(data, dict) else 'Not a dict'}"
+                    )
                     print(f"Posts count: {len(data.get('posts', []))}")
                     print(f"Cursor: {data.get('cursor', 'None')}")
-                    if len(data.get('posts', [])) <= 3:  # Only print full data if few posts
+                    if (
+                        len(data.get("posts", [])) <= 3
+                    ):  # Only print full data if few posts
                         print(f"Full Response Data:")
                         print(json.dumps(data, indent=2, default=str))
                     print("=" * 50)
 
                 # The API returns snapshots in 'posts' field
-                snapshots = data.get('posts', [])
-                cursor_value = data.get('cursor')
+                snapshots = data.get("posts", [])
+                cursor_value = data.get("cursor")
 
                 page_info = f"cursor: {cursor[:20]}..." if cursor else "first page"
                 self.logger.info(f"Retrieved {len(snapshots)} snapshots ({page_info})")
-                self.stats['pages_fetched'] += 1
+                self.stats["pages_fetched"] += 1
 
                 # Return the actual API response format
                 return data
@@ -206,14 +216,17 @@ class SnapshotDownloader:
         except Exception as e:
             page_info = f"cursor: {cursor[:20]}..." if cursor else "first page"
             self.logger.error(f"Failed to fetch snapshots ({page_info}): {e}")
-            self.stats['failed_requests'] += 1
+            self.stats["failed_requests"] += 1
             raise
 
-    async def fetch_all_snapshots(self, session: aiohttp.ClientSession,
+    async def fetch_all_snapshots(
+        self,
+        session: aiohttp.ClientSession,
         type_ids: List[int] = [15],
         date_from: str = "2021-10-18",
         date_to: str = None,
-                                max_pages: int = None) -> List[Dict[str, Any]]:
+        max_pages: int = None,
+    ) -> List[Dict[str, Any]]:
         """
         Fetch all snapshots across all pages using cursor-based pagination.
 
@@ -231,7 +244,9 @@ class SnapshotDownloader:
         cursor = None
         page_count = 0
 
-        self.logger.info(f"Starting snapshot fetch from {date_from} to {date_to or 'now'}")
+        self.logger.info(
+            f"Starting snapshot fetch from {date_from} to {date_to or 'now'}"
+        )
 
         while True:
             page_count += 1
@@ -246,17 +261,19 @@ class SnapshotDownloader:
                 )
 
                 # Extract snapshots from response
-                snapshots = response.get('posts', [])
-                new_cursor = response.get('cursor')
+                snapshots = response.get("posts", [])
+                new_cursor = response.get("cursor")
 
                 if not snapshots:
                     self.logger.info("No more snapshots found (empty posts array)")
                     break
 
                 all_snapshots.extend(snapshots)
-                self.stats['total_snapshots'] += len(snapshots)
+                self.stats["total_snapshots"] += len(snapshots)
 
-                self.logger.info(f"Page {page_count}: {len(snapshots)} snapshots (total: {len(all_snapshots)})")
+                self.logger.info(
+                    f"Page {page_count}: {len(snapshots)} snapshots (total: {len(all_snapshots)})"
+                )
 
                 # If no cursor returned, we've reached the end
                 if not new_cursor:
@@ -273,7 +290,9 @@ class SnapshotDownloader:
         self.logger.info(f"Total snapshots fetched: {len(all_snapshots)}")
         return all_snapshots
 
-    async def format_snapshot_html(self, snapshot: Dict[str, Any], session: aiohttp.ClientSession) -> str:
+    async def format_snapshot_html(
+        self, snapshot: Dict[str, Any], session: aiohttp.ClientSession
+    ) -> str:
         """
         Format a single snapshot as HTML.
 
@@ -284,34 +303,46 @@ class SnapshotDownloader:
             HTML string for the snapshot
         """
         # Extract key information from ParentZone snapshot format
-        snapshot_id = snapshot.get('id', 'unknown')
-        content = snapshot.get('notes', '')  # Don't escape HTML in notes field
-        start_time = snapshot.get('startTime', '')
-        snapshot_type = snapshot.get('type', 'Snapshot')
+        snapshot_id = snapshot.get("id", "unknown")
+        content = snapshot.get("notes", "")  # Don't escape HTML in notes field
+        start_time = snapshot.get("startTime", "")
+        snapshot_type = snapshot.get("type", "Snapshot")
 
         # Format dates
-        start_date = self.format_date(start_time) if start_time else 'Unknown'
+        start_date = self.format_date(start_time) if start_time else "Unknown"
 
         # Extract additional information
-        author = snapshot.get('author', {})
-        author_forename = author.get('forename', '') if author else ''
-        author_surname = author.get('surname', '') if author else ''
-        author_name = html.escape(f"{author_forename} {author_surname}".strip()) if author else 'Unknown'
+        author = snapshot.get("author", {})
+        author_forename = author.get("forename", "") if author else ""
+        author_surname = author.get("surname", "") if author else ""
+        author_name = (
+            html.escape(f"{author_forename} {author_surname}".strip())
+            if author
+            else "Unknown"
+        )
 
         # Extract child information (if any)
-        child = snapshot.get('child', {})
-        child_forename = child.get('forename', '') if child else ''
-        child_name = html.escape(f"{child.get('forename', '')} {child.get('surname', '')}".strip()) if child else ''
+        child = snapshot.get("child", {})
+        child_forename = child.get("forename", "") if child else ""
+        child_name = (
+            html.escape(
+                f"{child.get('forename', '')} {child.get('surname', '')}".strip()
+            )
+            if child
+            else ""
+        )
 
         # Create title in format: "Child Forename by Author Forename Surname"
         if child_forename and author_forename:
-            title = html.escape(f"{child_forename} by {author_forename} {author_surname}".strip())
+            title = html.escape(
+                f"{child_forename} by {author_forename} {author_surname}".strip()
+            )
         else:
             title = html.escape(f"Snapshot {snapshot_id}")
 
         # Extract location/activity information
-        activity = snapshot.get('activity', {})
-        activity_name = html.escape(activity.get('name', '')) if activity else ''
+        activity = snapshot.get("activity", {})
+        activity_name = html.escape(activity.get("name", "")) if activity else ""
 
         # Build HTML
         html_content = f"""
@@ -327,12 +358,12 @@ class SnapshotDownloader:
         </div>
 
         <div class="snapshot-content">
-            {f'<div class="snapshot-author">👤 Author: {author_name}</div>' if author_name != 'Unknown' else ''}
-            {f'<div class="snapshot-child">👶 Child: {child_name}</div>' if child_name else ''}
-            {f'<div class="snapshot-activity">🎯 Activity: {activity_name}</div>' if activity_name else ''}
+            {f'<div class="snapshot-author">👤 Author: {author_name}</div>' if author_name != "Unknown" else ""}
+            {f'<div class="snapshot-child">👶 Child: {child_name}</div>' if child_name else ""}
+            {f'<div class="snapshot-activity">🎯 Activity: {activity_name}</div>' if activity_name else ""}
 
             <div class="snapshot-description">
-                <div class="notes-content">{content if content else '<em>No description provided</em>'}</div>
+                <div class="notes-content">{content if content else "<em>No description provided</em>"}</div>
             </div>
 
             {await self.format_snapshot_media(snapshot, session)}
@@ -343,112 +374,130 @@ class SnapshotDownloader:
 
         return html_content.strip()
 
-    async def format_snapshot_media(self, snapshot: Dict[str, Any], session: aiohttp.ClientSession) -> str:
+    async def format_snapshot_media(
+        self, snapshot: Dict[str, Any], session: aiohttp.ClientSession
+    ) -> str:
         """Format media attachments for a snapshot."""
         media_html = ""
 
         # Check for media (images and other files)
-        media = snapshot.get('media', [])
-        images = [m for m in media if m.get('type') == 'image']
+        media = snapshot.get("media", [])
+        images = [m for m in media if m.get("type") == "image"]
         if images:
             media_html += '<div class="snapshot-images">\n'
-            media_html += '<h4>📸 Images:</h4>\n'
+            media_html += "<h4>📸 Images:</h4>\n"
             media_html += '<div class="image-grid">\n'
 
             for image in images:
                 # Download the image file
                 local_path = await self.download_media_file(session, image)
-                image_name = html.escape(image.get('fileName', 'Image'))
+                image_name = html.escape(image.get("fileName", "Image"))
 
                 if local_path:
                     media_html += f'<div class="image-item">\n'
                     media_html += f'  <img src="{local_path}" alt="{image_name}" loading="lazy">\n'
                     media_html += f'  <p class="image-caption">{image_name}</p>\n'
                     media_html += f'  <p class="image-meta">Updated: {self.format_date(image.get("updated", ""))}</p>\n'
-                    media_html += f'</div>\n'
+                    media_html += f"</div>\n"
                 else:
                     # Fallback to API URL if download failed
-                    image_url = f"{self.api_url}/v1/media/{image.get('id')}/full" if image.get('id') else ''
+                    image_url = (
+                        f"{self.api_url}/v1/media/{image.get('id')}/full"
+                        if image.get("id")
+                        else ""
+                    )
                     if image_url:
                         media_html += f'<div class="image-item">\n'
                         media_html += f'  <img src="{image_url}" alt="{image_name}" loading="lazy">\n'
-                        media_html += f'  <p class="image-caption">{image_name} (online)</p>\n'
+                        media_html += (
+                            f'  <p class="image-caption">{image_name} (online)</p>\n'
+                        )
                         media_html += f'  <p class="image-meta">Updated: {self.format_date(image.get("updated", ""))}</p>\n'
-                        media_html += f'</div>\n'
+                        media_html += f"</div>\n"
 
-            media_html += '</div>\n</div>\n'
+            media_html += "</div>\n</div>\n"
 
         # Check for non-image media as attachments
-        attachments = [m for m in media if m.get('type') != 'image']
+        attachments = [m for m in media if m.get("type") != "image"]
         if attachments:
             media_html += '<div class="snapshot-attachments">\n'
-            media_html += '<h4>📎 Attachments:</h4>\n'
+            media_html += "<h4>📎 Attachments:</h4>\n"
             media_html += '<ul class="attachment-list">\n'
 
             for attachment in attachments:
                 # Download the attachment file
                 local_path = await self.download_media_file(session, attachment)
-                attachment_name = html.escape(attachment.get('fileName', 'Attachment'))
-                attachment_type = attachment.get('mimeType', 'unknown')
+                attachment_name = html.escape(attachment.get("fileName", "Attachment"))
+                attachment_type = attachment.get("mimeType", "unknown")
 
                 if local_path:
                     media_html += f'  <li><a href="{local_path}" target="_blank">{attachment_name} ({attachment_type})</a></li>\n'
                 else:
                     # Fallback to API URL if download failed
-                    attachment_url = f"{self.api_url}/v1/media/{attachment.get('id')}/full" if attachment.get('id') else ''
+                    attachment_url = (
+                        f"{self.api_url}/v1/media/{attachment.get('id')}/full"
+                        if attachment.get("id")
+                        else ""
+                    )
                     if attachment_url:
                         media_html += f'  <li><a href="{attachment_url}" target="_blank">{attachment_name} ({attachment_type}) - online</a></li>\n'
                     else:
-                        media_html += f'  <li>{attachment_name} ({attachment_type})</li>\n'
+                        media_html += (
+                            f"  <li>{attachment_name} ({attachment_type})</li>\n"
+                        )
 
-            media_html += '</ul>\n</div>\n'
+            media_html += "</ul>\n</div>\n"
 
         return media_html
 
     def format_snapshot_metadata(self, snapshot: Dict[str, Any]) -> str:
         """Format additional metadata for a snapshot."""
         metadata_html = '<div class="snapshot-metadata">\n'
-        metadata_html += '<h4>ℹ️ Additional Information:</h4>\n'
+        metadata_html += "<h4>ℹ️ Additional Information:</h4>\n"
         metadata_html += '<div class="metadata-grid">\n'
 
         # Add any additional fields that might be interesting
         metadata_fields = [
-            ('code', 'Code'),
-            ('frameworkIndicatorCount', 'Framework Indicators'),
-            ('signed', 'Signed Status'),
-            ('type', 'Type')
+            ("code", "Code"),
+            ("frameworkIndicatorCount", "Framework Indicators"),
+            ("signed", "Signed Status"),
+            ("type", "Type"),
         ]
 
         for field, label in metadata_fields:
             value = snapshot.get(field)
             if value:
                 if isinstance(value, list):
-                    value = ', '.join(str(v) for v in value)
+                    value = ", ".join(str(v) for v in value)
                 metadata_html += f'<div class="metadata-item">\n'
-                metadata_html += f'  <strong>{label}:</strong> {html.escape(str(value))}\n'
-                metadata_html += f'</div>\n'
+                metadata_html += (
+                    f"  <strong>{label}:</strong> {html.escape(str(value))}\n"
+                )
+                metadata_html += f"</div>\n"
 
         # Raw JSON data (collapsed by default)
         metadata_html += '<details class="raw-data">\n'
-        metadata_html += '<summary>🔍 Raw JSON Data</summary>\n'
+        metadata_html += "<summary>🔍 Raw JSON Data</summary>\n"
         metadata_html += '<pre class="json-data">\n'
         metadata_html += html.escape(json.dumps(snapshot, indent=2, default=str))
-        metadata_html += '\n</pre>\n'
-        metadata_html += '</details>\n'
+        metadata_html += "\n</pre>\n"
+        metadata_html += "</details>\n"
 
-        metadata_html += '</div>\n</div>\n'
+        metadata_html += "</div>\n</div>\n"
         return metadata_html
 
     def format_date(self, date_string: str) -> str:
         """Format a date string for display."""
         try:
             # Try to parse ISO format date
-            dt = datetime.fromisoformat(date_string.replace('Z', '+00:00'))
+            dt = datetime.fromisoformat(date_string.replace("Z", "+00:00"))
             return dt.strftime("%Y-%m-%d %H:%M:%S")
         except:
             return date_string
 
-    async def download_media_file(self, session: aiohttp.ClientSession, media: Dict[str, Any]) -> Optional[str]:
+    async def download_media_file(
+        self, session: aiohttp.ClientSession, media: Dict[str, Any]
+    ) -> Optional[str]:
         """
         Download a media file to the assets folder.
 
@@ -459,11 +508,11 @@ class SnapshotDownloader:
         Returns:
             Relative path to downloaded file, or None if download failed
         """
-        media_id = media.get('id')
+        media_id = media.get("id")
         if not media_id:
             return None
 
-        filename = media.get('fileName', f'media_{media_id}')
+        filename = media.get("fileName", f"media_{media_id}")
         # Sanitize filename
         filename = self._sanitize_filename(filename)
 
@@ -480,11 +529,13 @@ class SnapshotDownloader:
             self.logger.info(f"Downloading media file: {filename}")
 
             headers = self.get_auth_headers()
-            async with session.get(download_url, headers=headers, timeout=30) as response:
+            async with session.get(
+                download_url, headers=headers, timeout=30
+            ) as response:
                 response.raise_for_status()
 
                 # Download the file
-                async with aiofiles.open(filepath, 'wb') as f:
+                async with aiofiles.open(filepath, "wb") as f:
                     async for chunk in response.content.iter_chunked(8192):
                         await f.write(chunk)
 
@@ -502,19 +553,20 @@ class SnapshotDownloader:
         # Remove or replace invalid characters
         invalid_chars = '<>:"/\\|?*'
         for char in invalid_chars:
-            filename = filename.replace(char, '_')
+            filename = filename.replace(char, "_")
 
         # Remove leading/trailing spaces and dots
-        filename = filename.strip('. ')
+        filename = filename.strip(". ")
 
         # Ensure filename is not empty
         if not filename:
-            filename = 'media_file'
+            filename = "media_file"
 
         return filename
 
-    async def generate_html_file(self, snapshots: List[Dict[str, Any]],
-                          date_from: str, date_to: str) -> Path:
+    async def generate_html_file(
+        self, snapshots: List[Dict[str, Any]], date_from: str, date_to: str
+    ) -> Path:
         """
         Generate an HTML file containing all snapshots.
 
@@ -528,9 +580,7 @@ class SnapshotDownloader:
         """
         # Sort snapshots by start time (newest first)
         sorted_snapshots = sorted(
-            snapshots,
-            key=lambda x: x.get('startTime', ''),
-            reverse=True
+            snapshots, key=lambda x: x.get("startTime", ""), reverse=True
         )
 
         # Generate filename
@@ -538,19 +588,22 @@ class SnapshotDownloader:
         filepath = self.output_dir / filename
 
         # Generate HTML content
-        html_content = await self.generate_html_template(sorted_snapshots, date_from, date_to)
+        html_content = await self.generate_html_template(
+            sorted_snapshots, date_from, date_to
+        )
 
         # Write to file
-        with open(filepath, 'w', encoding='utf-8') as f:
+        with open(filepath, "w", encoding="utf-8") as f:
             f.write(html_content)
 
         self.logger.info(f"Generated HTML file: {filepath}")
-        self.stats['generated_files'] += 1
+        self.stats["generated_files"] += 1
 
         return filepath
 
-    async def generate_html_template(self, snapshots: List[Dict[str, Any]],
-                             date_from: str, date_to: str) -> str:
+    async def generate_html_template(
+        self, snapshots: List[Dict[str, Any]], date_from: str, date_to: str
+    ) -> str:
         """Generate the complete HTML template."""
 
         # Generate individual snapshot HTML
@@ -560,7 +613,9 @@ class SnapshotDownloader:
         connector = aiohttp.TCPConnector(limit=100, limit_per_host=30)
         timeout = aiohttp.ClientTimeout(total=30)
 
-        async with aiohttp.ClientSession(connector=connector, timeout=timeout) as session:
+        async with aiohttp.ClientSession(
+            connector=connector, timeout=timeout
+        ) as session:
             # Authenticate session for media downloads
             await self.authenticate()
 
@@ -604,7 +659,7 @@ class SnapshotDownloader:
 
         <footer class="page-footer">
             <p>Generated by ParentZone Snapshot Downloader</p>
-            <p>Total snapshots: {len(snapshots)} | Pages fetched: {self.stats['pages_fetched']}</p>
+            <p>Total snapshots: {len(snapshots)} | Pages fetched: {self.stats["pages_fetched"]}</p>
         </footer>
     </div>
 
@@ -991,9 +1046,13 @@ class SnapshotDownloader:
         });
         """
 
-    async def download_snapshots(self, type_ids: List[int] = [15],
-                               date_from: str = None, date_to: str = None,
-                               max_pages: int = None) -> Path:
+    async def download_snapshots(
+        self,
+        type_ids: List[int] = [15],
+        date_from: str = None,
+        date_to: str = None,
+        max_pages: int = None,
+    ) -> Path:
         """
         Download all snapshots and generate HTML file.
 
@@ -1013,13 +1072,17 @@ class SnapshotDownloader:
         if date_to is None:
             date_to = datetime.now().strftime("%Y-%m-%d")
 
-        self.logger.info(f"Starting snapshot download for period {date_from} to {date_to}")
+        self.logger.info(
+            f"Starting snapshot download for period {date_from} to {date_to}"
+        )
 
         # Create aiohttp session
         connector = aiohttp.TCPConnector(limit=100, limit_per_host=30)
         timeout = aiohttp.ClientTimeout(total=30)
 
-        async with aiohttp.ClientSession(connector=connector, timeout=timeout) as session:
+        async with aiohttp.ClientSession(
+            connector=connector, timeout=timeout
+        ) as session:
             try:
                 # Authenticate if needed
                 await self.authenticate()
@@ -1077,64 +1140,53 @@ Examples:
 
   # Specify output directory
   python3 snapshot_downloader.py --api-key KEY --output-dir ./my_snapshots
-        """
+        """,
+    )
+
+    parser.add_argument("--api-key", help="API key for authentication")
+
+    parser.add_argument("--email", help="Email for login authentication")
+
+    parser.add_argument("--password", help="Password for login authentication")
+
+    parser.add_argument(
+        "--date-from", help="Start date in YYYY-MM-DD format (default: 1 year ago)"
     )
 
     parser.add_argument(
-        '--api-key',
-        help='API key for authentication'
+        "--date-to", help="End date in YYYY-MM-DD format (default: today)"
     )
 
     parser.add_argument(
-        '--email',
-        help='Email for login authentication'
-    )
-
-    parser.add_argument(
-        '--password',
-        help='Password for login authentication'
-    )
-
-    parser.add_argument(
-        '--date-from',
-        help='Start date in YYYY-MM-DD format (default: 1 year ago)'
-    )
-
-    parser.add_argument(
-        '--date-to',
-        help='End date in YYYY-MM-DD format (default: today)'
-    )
-
-    parser.add_argument(
-        '--type-ids',
-        nargs='+',
+        "--type-ids",
+        nargs="+",
         type=int,
         default=[15],
-        help='Type IDs to filter by (default: [15])'
+        help="Type IDs to filter by (default: [15])",
     )
 
     parser.add_argument(
-        '--output-dir',
-        default='snapshots',
-        help='Directory to save snapshot files (default: snapshots)'
+        "--output-dir",
+        default="snapshots",
+        help="Directory to save snapshot files (default: snapshots)",
     )
 
     parser.add_argument(
-        '--max-pages',
+        "--max-pages",
         type=int,
-        help='Maximum number of cursor pages to fetch (for testing)'
+        help="Maximum number of cursor pages to fetch (for testing)",
     )
 
     parser.add_argument(
-        '--api-url',
-        default='https://api.parentzone.me',
-        help='ParentZone API URL (default: https://api.parentzone.me)'
+        "--api-url",
+        default="https://api.parentzone.me",
+        help="ParentZone API URL (default: https://api.parentzone.me)",
     )
 
     parser.add_argument(
-        '--debug',
-        action='store_true',
-        help='Enable debug mode with detailed server response logging'
+        "--debug",
+        action="store_true",
+        help="Enable debug mode with detailed server response logging",
     )
 
     args = parser.parse_args()
@@ -1160,19 +1212,21 @@ Examples:
             api_key=args.api_key,
             email=args.email,
             password=args.password,
-            debug_mode=args.debug
+            debug_mode=args.debug,
         )
 
         if args.debug:
             print("🔍 DEBUG MODE ENABLED - Detailed server responses will be printed")
 
         # Download snapshots
-        html_file = asyncio.run(downloader.download_snapshots(
+        html_file = asyncio.run(
+            downloader.download_snapshots(
                 type_ids=args.type_ids,
                 date_from=args.date_from,
                 date_to=args.date_to,
-            max_pages=args.max_pages
-        ))
+                max_pages=args.max_pages,
+            )
+        )
 
         if html_file:
             print(f"\n✅ Success! Snapshots downloaded and saved to: {html_file}")