bug fixes and performance improvements

docs/archived/SNAPSHOT_DOWNLOADER_SUMMARY.md

@@ -45,7 +45,7 @@ snapshots = await downloader.fetch_all_snapshots(
 downloader = SnapshotDownloader(
     # Option 1: Direct API key
     api_key="your-api-key-here",
-    
+
     # Option 2: Email/password (gets API key automatically)
     email="user@example.com",
     password="password"
@@ -75,7 +75,6 @@ curl 'https://api.parentzone.me/v1/posts?typeIDs[]=15&dateFrom=2021-10-18&dateTo
 - ✅ **Endpoint**: `/v1/posts`
 - ✅ **Type ID filtering**: `typeIDs[]=15` (configurable)
 - ✅ **Date range filtering**: `dateFrom` and `dateTo` parameters
-- ✅ **Pagination**: `page` and `per_page` parameters
 - ✅ **All required headers** from curl command
 - ✅ **Authentication**: `x-api-key` header support
 
@@ -271,7 +270,7 @@ parentzone_downloader/
         <div class="stats">Total: 150 snapshots</div>
         <input type="text" id="searchBox" placeholder="Search snapshots...">
     </header>
-    
+
     <main>
         <div class="snapshot">
             <h3>Snapshot Title</h3>
@@ -288,7 +287,7 @@ parentzone_downloader/
             </div>
         </div>
     </main>
-    
+
     <script>
         // Search, toggle, and interaction functions
     </script>
@@ -350,4 +349,4 @@ The system successfully addresses the original requirements:
 4. ✅ Includes interactive features for browsing and searching
 5. ✅ Supports flexible date ranges and filtering options
 
-**Ready to use immediately for downloading and viewing ParentZone snapshots!**
+**Ready to use immediately for downloading and viewing ParentZone snapshots!**

src/auth_manager.py

@@ -8,7 +8,6 @@ and manages session tokens for API requests.
 
 import asyncio
 import aiohttp
-import json
 import logging
 from typing import Optional, Dict, Any
 from urllib.parse import urljoin
@@ -22,7 +21,7 @@ class AuthManager:
         Args:
             api_url: Base URL of the API
         """
-        self.api_url = api_url.rstrip('/')
+        self.api_url = api_url.rstrip("/")
         self.login_url = urljoin(self.api_url, "/v1/auth/login")
         self.create_session_url = urljoin(self.api_url, "/v1/auth/create-session")
         self.session_token: Optional[str] = None
@@ -34,18 +33,18 @@ class AuthManager:
 
         # Standard headers for login requests
         self.headers = {
-            'accept': 'application/json, text/plain, */*',
-            'accept-language': 'en-GB,en-US;q=0.9,en;q=0.8,ro;q=0.7',
-            'content-type': 'application/json;charset=UTF-8',
-            'origin': 'https://www.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'
+            "accept": "application/json, text/plain, */*",
+            "accept-language": "en-GB,en-US;q=0.9,en;q=0.8,ro;q=0.7",
+            "content-type": "application/json;charset=UTF-8",
+            "origin": "https://www.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",
         }
 
     async def login(self, email: str, password: str) -> bool:
@@ -64,18 +63,13 @@ class AuthManager:
         self.logger.info(f"Attempting login for {email}")
 
         # Step 1: Login to get user accounts
-        login_data = {
-            "email": email,
-            "password": password
-        }
+        login_data = {"email": email, "password": password}
 
         timeout = aiohttp.ClientTimeout(total=30)
         async with aiohttp.ClientSession(timeout=timeout) as session:
             try:
                 async with session.post(
-                    self.login_url,
-                    headers=self.headers,
-                    json=login_data
+                    self.login_url, headers=self.headers, json=login_data
                 ) as response:
                     self.logger.info(f"Login response status: {response.status}")
 
@@ -89,20 +83,26 @@ class AuthManager:
                         if isinstance(data, list) and len(data) > 0:
                             # Use the first account
                             first_account = data[0]
-                            self.user_id = first_account.get('id')
-                            self.user_name = first_account.get('name')
-                            self.provider_name = first_account.get('providerName')
+                            self.user_id = first_account.get("id")
+                            self.user_name = first_account.get("name")
+                            self.provider_name = first_account.get("providerName")
 
-                            self.logger.info(f"Selected account: {self.user_name} at {self.provider_name} (ID: {self.user_id})")
+                            self.logger.info(
+                                f"Selected account: {self.user_name} at {self.provider_name} (ID: {self.user_id})"
+                            )
 
                             # Step 2: Create session with the account ID
                             return await self._create_session(password)
                         else:
-                            self.logger.error(f"Unexpected login response format: {data}")
+                            self.logger.error(
+                                f"Unexpected login response format: {data}"
+                            )
                             return False
                     else:
                         error_text = await response.text()
-                        self.logger.error(f"Login failed with status {response.status}: {error_text}")
+                        self.logger.error(
+                            f"Login failed with status {response.status}: {error_text}"
+                        )
                         return False
 
             except Exception as e:
@@ -125,24 +125,21 @@ class AuthManager:
 
         self.logger.info(f"Creating session for user ID: {self.user_id}")
 
-        session_data = {
-            "id": self.user_id,
-            "password": password
-        }
+        session_data = {"id": self.user_id, "password": password}
 
         # Add x-api-product header for session creation
         session_headers = self.headers.copy()
-        session_headers['x-api-product'] = 'iConnect'
+        session_headers["x-api-product"] = "iConnect"
 
         timeout = aiohttp.ClientTimeout(total=30)
         async with aiohttp.ClientSession(timeout=timeout) as session:
             try:
                 async with session.post(
-                    self.create_session_url,
-                    headers=session_headers,
-                    json=session_data
+                    self.create_session_url, headers=session_headers, json=session_data
                 ) as response:
-                    self.logger.info(f"Create session response status: {response.status}")
+                    self.logger.info(
+                        f"Create session response status: {response.status}"
+                    )
 
                     if response.status == 200:
                         data = await response.json()
@@ -150,16 +147,20 @@ class AuthManager:
                         self.logger.debug(f"Session response data: {data}")
 
                         # Extract API key from response
-                        if isinstance(data, dict) and 'key' in data:
-                            self.api_key = data['key']
+                        if isinstance(data, dict) and "key" in data:
+                            self.api_key = data["key"]
                             self.logger.info("API key obtained successfully")
                             return True
                         else:
-                            self.logger.error(f"No 'key' field in session response: {data}")
+                            self.logger.error(
+                                f"No 'key' field in session response: {data}"
+                            )
                             return False
                     else:
                         error_text = await response.text()
-                        self.logger.error(f"Session creation failed with status {response.status}: {error_text}")
+                        self.logger.error(
+                            f"Session creation failed with status {response.status}: {error_text}"
+                        )
                         return False
 
             except Exception as e:
@@ -177,8 +178,8 @@ class AuthManager:
 
         if self.api_key:
             # Use x-api-key header for authenticated requests
-            headers['x-api-key'] = self.api_key
-            headers['x-api-product'] = 'iConnect'
+            headers["x-api-key"] = self.api_key
+            headers["x-api-product"] = "iConnect"
 
         return headers
 
@@ -216,7 +217,11 @@ async def test_login():
         print("✅ Login successful!")
         print(f"User: {auth_manager.user_name} at {auth_manager.provider_name}")
         print(f"User ID: {auth_manager.user_id}")
-        print(f"API Key: {auth_manager.api_key[:20]}..." if auth_manager.api_key else "No API key found")
+        print(
+            f"API Key: {auth_manager.api_key[:20]}..."
+            if auth_manager.api_key
+            else "No API key found"
+        )
 
         # Test getting auth headers
         headers = auth_manager.get_auth_headers()

src/image_downloader.py

@@ -12,17 +12,16 @@ Usage:
 
 import argparse
 import asyncio
-import aiohttp
-import aiofiles
-import os
-import json
 import logging
-from pathlib import Path
-from urllib.parse import urljoin, urlparse
-from typing import List, Dict, Any, Optional
+import os
 import time
+from pathlib import Path
+from typing import Any, Dict, List
+from urllib.parse import urljoin, urlparse
+
+import aiofiles
+import aiohttp
 from tqdm import tqdm
-import hashlib
 
 # Import the auth manager and asset tracker
 try:
@@ -341,8 +340,8 @@ class ImageDownloader:
                     # Set file modification time to match the updated timestamp
                     if "updated" in asset:
                         try:
-                            from datetime import datetime
                             import os
+                            from datetime import datetime
 
                             # Parse the ISO timestamp
                             updated_time = datetime.fromisoformat(

src/snapshot_downloader.py

@@ -8,16 +8,16 @@ and generates a comprehensive markup file containing all the snapshot informatio
 
 import argparse
 import asyncio
-import aiohttp
+import html
 import json
 import logging
-import os
 from datetime import datetime, timedelta
 from pathlib import Path
-from typing import List, Dict, Any, Optional
-from urllib.parse import urlencode, urljoin
-import html
+from typing import Any, Dict, List, Optional
+from urllib.parse import urlencode
+
 import aiofiles
+import aiohttp
 
 # Import the auth manager
 try:
@@ -132,12 +132,11 @@ class SnapshotDownloader:
     async def fetch_snapshots_page(
         self,
         session: aiohttp.ClientSession,
-        type_ids: List[int] = [15],
+        type_ids: list[int] = [15],
         date_from: str = "2021-10-18",
-        date_to: str = None,
+        date_to: str = "",
         cursor: str = None,
-        per_page: int = 100,
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         """
         Fetch a single page of snapshots from the API using cursor-based pagination.
 
@@ -147,12 +146,11 @@ class SnapshotDownloader:
             date_from: Start date in YYYY-MM-DD format
             date_to: End date in YYYY-MM-DD format
             cursor: Cursor for pagination (None for first page)
-            per_page: Number of items per page
 
         Returns:
             Dictionary containing the API response
         """
-        if date_to is None:
+        if date_to == "":
             date_to = datetime.now().strftime("%Y-%m-%d")
 
         # Build query parameters
@@ -167,7 +165,7 @@ class SnapshotDownloader:
 
         # Add type IDs - API expects typeIDs[]=15 format
         for type_id in type_ids:
-            params[f"typeIDs[]"] = type_id
+            params["typeIDs[]"] = type_id
 
         # Build URL with parameters
         query_string = urlencode(params, doseq=True)
@@ -198,13 +196,12 @@ class SnapshotDownloader:
                     if (
                         len(data.get("posts", [])) <= 3
                     ):  # Only print full data if few posts
-                        print(f"Full Response Data:")
+                        print("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")
 
                 page_info = f"cursor: {cursor[:20]}..." if cursor else "first page"
                 self.logger.info(f"Retrieved {len(snapshots)} snapshots ({page_info})")
@@ -394,11 +391,11 @@ class SnapshotDownloader:
                 image_name = html.escape(image.get("fileName", "Image"))
 
                 if local_path:
-                    media_html += f'<div class="image-item">\n'
+                    media_html += '<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 += "</div>\n"
                 else:
                     # Fallback to API URL if download failed
                     image_url = (
@@ -407,13 +404,13 @@ class SnapshotDownloader:
                         else ""
                     )
                     if image_url:
-                        media_html += f'<div class="image-item">\n'
+                        media_html += '<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-meta">Updated: {self.format_date(image.get("updated", ""))}</p>\n'
-                        media_html += f"</div>\n"
+                        media_html += "</div>\n"
 
             media_html += "</div>\n</div>\n"
 
@@ -469,11 +466,11 @@ class SnapshotDownloader:
             if value:
                 if isinstance(value, list):
                     value = ", ".join(str(v) for v in value)
-                metadata_html += f'<div class="metadata-item">\n'
+                metadata_html += '<div class="metadata-item">\n'
                 metadata_html += (
                     f"  <strong>{label}:</strong> {html.escape(str(value))}\n"
                 )
-                metadata_html += f"</div>\n"
+                metadata_html += "</div>\n"
 
         # Raw JSON data (collapsed by default)
         metadata_html += '<details class="raw-data">\n'
@@ -1230,7 +1227,7 @@ Examples:
 
         if html_file:
             print(f"\n✅ Success! Snapshots downloaded and saved to: {html_file}")
-            print(f"📁 Open the file in your browser to view the snapshots")
+            print("📁 Open the file in your browser to view the snapshots")
         else:
             print("⚠️ No snapshots were found for the specified period")
 

tests/test_snapshot_downloader.py

@@ -222,7 +222,6 @@ class SnapshotDownloaderTester:
                     date_from="2024-01-01",
                     date_to="2024-01-31",
                     page=1,
-                    per_page=100,
                 )
             except Exception as e:
                 # Expected - we just want to capture the URL
@@ -339,7 +338,7 @@ class SnapshotDownloaderTester:
                 print("   ✅ HTML file created")
 
                 # Check file content
-                with open(html_file, 'r', encoding='utf-8') as f:
+                with open(html_file, "r", encoding="utf-8") as f:
                     content = f.read()
 
                 if "<!DOCTYPE html>" in content:
@@ -514,9 +513,7 @@ class SnapshotDownloaderTester:
             # Override the fetch_snapshots_page method to use our mock
             original_method = downloader.fetch_snapshots_page
 
-            async def mock_fetch_page(
-                session, type_ids, date_from, date_to, page, per_page
-            ):
+            async def mock_fetch_page(session, type_ids, date_from, date_to, page):
                 response_data = mock_session.pages[page - 1]
                 mock_session.call_count += 1
                 downloader.stats["pages_fetched"] += 1
@@ -601,6 +598,7 @@ class SnapshotDownloaderTester:
         except Exception as e:
             print(f"\n❌ TEST SUITE FAILED: {e}")
             import traceback
+
             traceback.print_exc()
             return False
 
@@ -660,7 +658,7 @@ def main():
     # Setup logging
     logging.basicConfig(
         level=logging.INFO,
-        format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+        format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
     )
 
     tester = SnapshotDownloaderTester()