added docker support

.dockerignore

@@ -0,0 +1,22 @@
+__pycache__
+*.pyc
+*.pyo
+.git
+.gitignore
+.env
+.env.local
+.env.*.local
+*.log
+nohup.out
+opencoder-server.pid
+rebuild_*.log
+rebuild_*.txt
+*.db
+archival_data/
+*.out
+.eggs/
+*.egg-info/
+dist/
+build/
+*.bak
+

.env.example

@@ -0,0 +1,13 @@
+# NewsArchiver Environment Variables
+# Copy this file to .env and edit with your values
+
+# Directory where archived files will be stored
+# This is perfect for NAS mounting
+ARCHIVE_DIR=/data/archives
+
+# Optional: Web server configuration
+# WEB_HOST=0.0.0.0
+# WEB_PORT=5000
+
+# Optional: Logging level (DEBUG, INFO, WARNING, ERROR)
+# LOG_LEVEL=INFO

Dockerfile

@@ -0,0 +1,56 @@
+FROM python:3.11-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies for Playwright
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements first for better caching
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Install Playwright browsers
+RUN playwright install chromium --with-deps || true
+
+# Create app directory structure
+RUN mkdir -p /app/archival_data
+
+# Set environment variable for archive directory (can be overridden)
+ENV ARCHIVE_DIR=/app/archival_data
+
+# Copy application code
+COPY run_archiver.py .
+COPY archive_engine.py .
+COPY rss_processor.py .
+COPY content_extractor.py .
+COPY storage_manager.py .
+COPY web_interface.py .
+COPY scheduler.py .
+COPY singlefile_archive.py .
+COPY ap_processor.py .
+COPY cleanup_old_files.py .
+COPY rebuild_database.py .
+COPY restore_database.py .
+COPY rss_feeds.json .
+
+# Copy templates and static directories if they exist
+COPY templates/ ./templates/ 2>/dev/null || true
+COPY static/ ./static/ 2>/dev/null || true
+
+# Copy entrypoint script
+COPY entrypoint.sh /entrypoint.sh
+RUN chmod +x /entrypoint.sh
+
+# Expose Flask port
+EXPOSE 5000
+
+# Use entrypoint script
+ENTRYPOINT ["/entrypoint.sh"]
+
+# Default command
+CMD ["python", "run_archiver.py", "--serve", "--host", "0.0.0.0", "--port", "5000"]

README.md

@@ -124,6 +124,52 @@ The SQLite database (`archival_data/cache.db`) stores:
 - Flask, Trafilatura, feedparser, APScheduler, requests, beautifulsoup4
 - SingleFile CLI (optional, for web page archiving)
 
+## Docker Deployment
+
+The NewsArchiver can be deployed using Docker for easier management and isolation.
+
+### Quick Start with Docker
+
+```bash
+# Build the Docker image
+docker build -t newsarchiver .
+
+# Run with default settings (archives stored in container)
+docker run -p 5000:5000 newsarchiver
+
+# Run with NAS storage mount
+docker run -p 5000:5000 \
+  -v /path/to/nas/backup:/data/archives \
+  -e ARCHIVE_DIR=/data/archives \
+  newsarchiver
+```
+
+### Using Docker Compose
+
+```bash
+# Edit docker-compose.yml to configure your NAS mount path
+vim docker-compose.yml
+
+# Start the service
+docker-compose up -d
+
+# View logs
+docker-compose logs -f
+
+# Stop the service
+docker-compose down
+```
+
+### Configuration
+
+The `ARCHIVE_DIR` environment variable controls where archived files are stored. To use NAS storage:
+
+1. Edit `docker-compose.yml` and update the volume mount path
+2. Set `ARCHIVE_DIR` to match the container path (e.g., `/data/archives`)
+3. Restart the container
+
+The archived data will persist even if the container is removed, as it's stored in a Docker volume or mounted NAS directory.
+
 ## Stopping Services
 
 To stop all NewsArchiver services:

archive_engine.py

@@ -43,8 +43,8 @@ except ImportError:
 
 
 
-SCRIPT_DIR = Path(__file__).parent
+SCRIPT_DIR = Path(__file__).parent.resolve()
-ARCHIVE_DIR = SCRIPT_DIR / 'archival_data'
+ARCHIVE_DIR = Path(os.environ.get("ARCHIVE_DIR", str(SCRIPT_DIR / "archival_data"))).resolve()
 ARCHIVE_DIR.mkdir(exist_ok=True)
 
 logging.basicConfig(

cleanup_old_files.py

@@ -19,6 +19,7 @@ Options:
 
 import argparse
 import logging
+import os
 import sys
 from datetime import datetime, timezone
 from pathlib import Path
@@ -38,7 +39,10 @@ logger = logging.getLogger(__name__)
 SCRIPT_DIR = Path(__file__).parent.resolve()
 
 # Path to archival_data directory
-ARCHIVAL_DATA_DIR = SCRIPT_DIR / "archival_data"
+ARCHIVE_DIR = Path(
+    os.environ.get("ARCHIVE_DIR", str(SCRIPT_DIR / "archival_data"))
+).resolve()
+ARCHIVAL_DATA_DIR = ARCHIVE_DIR
 
 # Path to websites folder (only this folder will be scanned in archival_data)
 WEBSITES_DIR = ARCHIVAL_DATA_DIR / "websites"

docker-compose.nas.example.yml

@@ -0,0 +1,37 @@
+# Example docker-compose configuration for NAS storage
+# Copy this file to docker-compose.yml and edit the volume path
+
+version: '3.8'
+
+services:
+  newsarchiver:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    container_name: newsarchiver
+    ports:
+      - "5000:5000"
+    environment:
+      - ARCHIVE_DIR=/data/archives
+    volumes:
+      # Example: Mount your NAS to /path/to/nas/archives
+      # Replace with your actual NAS path
+      - /path/to/nas/archives:/data/archives
+      # Or use Docker named volume for local storage:
+      # - newsarchiver_data:/data/archives
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:5000/"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+    # Optional: Run as specific UID/GID for NAS permissions
+    # user: "1000:1000"
+
+volumes:
+  newsarchiver_data:
+    driver: local
+    driver_opts:
+      type: none
+      o: bind
+      device: /path/to/nas/archives  # Replace with your NAS path

docker-compose.yml

@@ -0,0 +1,23 @@
+version: '3.8'
+
+services:
+  newsarchiver:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    container_name: newsarchiver
+    ports:
+      - "5000:5000"
+    environment:
+      - ARCHIVE_DIR=/data/archives
+    volumes:
+      - newsarchiver_data:/data/archives
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:5000/"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+
+volumes:
+  newsarchiver_data:

docker_backup.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+
+# Docker backup script for NewsArchiver
+# This script backs up archived data from the Docker volume to a local or NAS location
+
+set -e
+
+BACKUP_DIR="${BACKUP_DIR:-./backups}"
+TIMESTAMP=$(date +%Y%m%d_%H%M%S)
+BACKUP_NAME="newsarchiver_backup_${TIMESTAMP}.tar.gz"
+
+echo "Starting backup..."
+echo "Backup location: ${BACKUP_DIR}/${BACKUP_NAME}"
+
+# Create backup directory
+mkdir -p "$BACKUP_DIR"
+
+# Create backup from the Docker volume
+docker run --rm \
+  -v newsarchiver_data:/data:ro \
+  -v "${BACKUP_DIR}:/backup" \
+  alpine tar -czf "/backup/${BACKUP_NAME}" -C /data .
+
+echo "Backup complete: ${BACKUP_DIR}/${BACKUP_NAME}"
+echo ""
+echo "To restore from backup:"
+echo "  1. Stop the container: docker-compose down"
+echo "  2. Remove the volume: docker volume rm newsarchiver_data"
+echo "  3. Create a new volume: docker volume create newsarchiver_data"
+echo "  4. Restore: docker run --rm -v newsarchiver_data:/data -v \${BACKUP_DIR}:/backup alpine tar -xzf /backup/${BACKUP_NAME} -C /data"
+echo "  5. Start: docker-compose up -d"

docker_setup.sh

@@ -0,0 +1,47 @@
+#!/bin/bash
+
+# Docker setup script for NewsArchiver
+# This script helps configure the Docker environment
+
+set -e
+
+echo "NewsArchiver Docker Setup"
+echo "=========================="
+echo ""
+
+# Check if Docker is installed
+if ! command -v docker &> /dev/null; then
+    echo "ERROR: Docker is not installed. Please install Docker first."
+    exit 1
+fi
+
+# Check if docker-compose is available
+if ! command -v docker-compose &> /dev/null && ! docker compose version &> /dev/null; then
+    echo "ERROR: docker-compose is not installed. Please install docker-compose first."
+    exit 1
+fi
+
+echo "Docker is installed."
+echo ""
+
+# Check if the project has docker-compose.yml
+if [ ! -f docker-compose.yml ] && [ ! -f docker-compose.nas.example.yml ]; then
+    echo "WARNING: docker-compose.yml not found."
+    echo "Creating from example..."
+    cp docker-compose.nas.example.yml docker-compose.yml
+    echo ""
+    echo "Please edit docker-compose.yml to set your NAS path:"
+    echo "  1. Find the volume mount path (currently set to /path/to/nas/archives)"
+    echo "  2. Replace with your actual NAS path"
+    echo "  3. Save the file"
+    echo ""
+fi
+
+echo "Setup complete!"
+echo ""
+echo "Next steps:"
+echo "  1. Edit docker-compose.yml with your NAS path"
+echo "  2. Build and start: docker-compose up -d --build"
+echo "  3. Check logs: docker-compose logs -f"
+echo "  4. Access web interface at http://localhost:5000"
+echo ""

entrypoint.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+set -e
+
+# Use ARCHIVE_DIR from environment, default to /app/archival_data
+export ARCHIVE_DIR="${ARCHIVE_DIR:-/app/archival_data}"
+
+# Create archive directory if it does not exist
+mkdir -p "$ARCHIVE_DIR"
+
+# Run the command passed to docker
+exec "$@"

nohup.out

@@ -216,3 +216,19 @@ opencode server listening on http://0.0.0.0:4096
 2026-03-31 12:16:03,370 - INFO - 192.168.8.226 - - [31/Mar/2026 12:16:03] "GET / HTTP/1.1" 200 -
 2026-03-31 12:16:03,475 - INFO - 192.168.8.226 - - [31/Mar/2026 12:16:03] "GET /static/style.css HTTP/1.1" 304 -
 2026-03-31 13:05:25,475 - INFO - 192.168.8.226 - - [31/Mar/2026 13:05:25] "GET /rss HTTP/1.1" 200 -
+2026-03-31 14:38:42,845 - INFO - 192.168.8.110 - - [31/Mar/2026 14:38:42] "GET /source/404%20Media HTTP/1.1" 200 -
+2026-03-31 14:38:42,872 - INFO - 192.168.8.110 - - [31/Mar/2026 14:38:42] "GET /static/style.css HTTP/1.1" 200 -
+2026-03-31 14:38:42,883 - INFO - 192.168.8.110 - - [31/Mar/2026 14:38:42] "GET /favicon.ico HTTP/1.1" 404 -
+2026-03-31 14:38:44,029 - INFO - 192.168.8.110 - - [31/Mar/2026 14:38:44] "GET /source/404%20media/article/76744 HTTP/1.1" 200 -
+2026-03-31 14:38:44,043 - INFO - 192.168.8.110 - - [31/Mar/2026 14:38:44] "GET /static/style.css HTTP/1.1" 304 -
+2026-03-31 14:40:43,351 - INFO - 192.168.8.110 - - [31/Mar/2026 14:40:43] "GET /archive-file//home/user/playground/NewsArchiver/archival_data/websites/404%20Media/html/2026-03-31/article_17749630811.html HTTP/1.1" 308 -
+2026-03-31 14:40:43,358 - INFO - Archive file path: /home/user/playground/NewsArchiver/archival_data/home/user/playground/NewsArchiver/archival_data/websites/404 Media/html/2026-03-31/article_17749630811.html, exists: False
+2026-03-31 14:40:43,358 - INFO - 192.168.8.110 - - [31/Mar/2026 14:40:43] "GET /archive-file/home/user/playground/NewsArchiver/archival_data/websites/404%20Media/html/2026-03-31/article_17749630811.html HTTP/1.1" 404 -
+2026-03-31 14:40:43,374 - INFO - 192.168.8.110 - - [31/Mar/2026 14:40:43] "GET /favicon.ico HTTP/1.1" 404 -
+2026-03-31 14:51:00,206 - INFO - 192.168.8.110 - - [31/Mar/2026 14:51:00] "GET /source/404%20media/article/76744 HTTP/1.1" 200 -
+2026-03-31 14:51:00,220 - INFO - 192.168.8.110 - - [31/Mar/2026 14:51:00] "GET /static/style.css HTTP/1.1" 200 -
+2026-03-31 14:51:00,225 - INFO - 192.168.8.110 - - [31/Mar/2026 14:51:00] "GET /favicon.ico HTTP/1.1" 404 -
+2026-03-31 14:51:02,123 - INFO - 192.168.8.110 - - [31/Mar/2026 14:51:02] "GET /archive-file//home/user/playground/NewsArchiver/archival_data/websites/404%20Media/html/2026-03-31/article_17749630811.html HTTP/1.1" 308 -
+2026-03-31 14:51:02,127 - INFO - Archive file path: /home/user/playground/NewsArchiver/archival_data/home/user/playground/NewsArchiver/archival_data/websites/404 Media/html/2026-03-31/article_17749630811.html, exists: False
+2026-03-31 14:51:02,127 - INFO - 192.168.8.110 - - [31/Mar/2026 14:51:02] "GET /archive-file/home/user/playground/NewsArchiver/archival_data/websites/404%20Media/html/2026-03-31/article_17749630811.html HTTP/1.1" 404 -
+2026-03-31 14:51:02,142 - INFO - 192.168.8.110 - - [31/Mar/2026 14:51:02] "GET /favicon.ico HTTP/1.1" 404 -

requirements.txt

@@ -0,0 +1,7 @@
+flask
+requests
+trafilatura
+feedparser
+apscheduler
+beautifulsoup4
+playwright

run_archiver.py

@@ -62,8 +62,8 @@ except ImportError:
     print("WARNING: singlefile_archive module not found")
     print("SingleFile integration will not be available")
 
-SCRIPT_DIR = Path(__file__).parent
+SCRIPT_DIR = Path(__file__).parent.resolve()
-ARCHIVE_DIR = SCRIPT_DIR / 'archival_data'
+ARCHIVE_DIR = Path(os.environ.get("ARCHIVE_DIR", str(SCRIPT_DIR / "archival_data"))).resolve()
 ARCHIVE_DIR.mkdir(exist_ok=True)
 
 

scheduler.py

@@ -26,8 +26,8 @@ except ImportError:
     print("ERROR: archive_engine is required")
     sys.exit(1)
 
-SCRIPT_DIR = Path(__file__).parent
+SCRIPT_DIR = Path(__file__).parent.resolve()
-ARCHIVE_DIR = SCRIPT_DIR / 'archival_data'
+ARCHIVE_DIR = Path(os.environ.get("ARCHIVE_DIR", str(SCRIPT_DIR / "archival_data"))).resolve()
 ARCHIVE_DIR.mkdir(exist_ok=True)
 
 logging.basicConfig(

storage_manager.py

@@ -23,8 +23,8 @@ try:
 except ImportError:
     FEEDGENERATOR_AVAILABLE = False
 
-SCRIPT_DIR = Path(__file__).parent
+SCRIPT_DIR = Path(__file__).parent.resolve()
-ARCHIVE_DIR = SCRIPT_DIR / "archival_data"
+ARCHIVE_DIR = Path(os.environ.get("ARCHIVE_DIR", str(SCRIPT_DIR / "archival_data"))).resolve()
 ARCHIVE_DIR.mkdir(exist_ok=True)
 
 logging.basicConfig(

web_interface.py

@@ -6,28 +6,30 @@ Flask web server for browsing archived news articles.
 
 import json
 import logging
+import os
 import sys
-from datetime import datetime
+import xml.etree.ElementTree as ET
+from datetime import datetime, timezone
 from pathlib import Path
 from typing import Optional
 from urllib.parse import quote
 
-from flask import Flask, jsonify, request, render_template, make_response
+from flask import Flask, jsonify, make_response, render_template, request
-import xml.etree.ElementTree as ET
-from datetime import datetime, timezone
 
 from storage_manager import (
+    DB_PATH,
     get_all_sources,
-    get_source_stats,
-    get_articles_by_source,
     get_article,
+    get_articles_by_source,
     get_latest_articles,
-    DB_PATH
+    get_source_stats,
 )
 
-SCRIPT_DIR = Path(__file__).parent
+SCRIPT_DIR = Path(__file__).parent.resolve()
-ARCHIVE_DIR = SCRIPT_DIR / 'archival_data'
+ARCHIVE_DIR = Path(
-RSS_FEEDS_PATH = SCRIPT_DIR / 'rss_feeds.json'
+    os.environ.get("ARCHIVE_DIR", str(SCRIPT_DIR / "archival_data"))
+).resolve()
+RSS_FEEDS_PATH = SCRIPT_DIR / "rss_feeds.json"
 
 RSS_FEEDS = {}
 
@@ -35,163 +37,173 @@ RSS_FEEDS = {}
 def load_rss_feeds() -> dict:
     """Load RSS feeds configuration."""
     global RSS_FEEDS
-    
+
     if RSS_FEEDS:
         return RSS_FEEDS
-    
+
     if not RSS_FEEDS_PATH.exists():
         logger.warning("RSS feeds file not found: %s", RSS_FEEDS_PATH)
         return {}
-    
+
     try:
-        with open(RSS_FEEDS_PATH, 'r', encoding='utf-8') as f:
+        with open(RSS_FEEDS_PATH, "r", encoding="utf-8") as f:
             RSS_FEEDS = json.load(f)
             return RSS_FEEDS
     except Exception as e:
         logger.error("Failed to load RSS feeds: %s", str(e))
         return {}
 
+
 app = Flask(
     __name__,
-    static_folder=str(SCRIPT_DIR / 'static'),
+    static_folder=str(SCRIPT_DIR / "static"),
-    template_folder=str(SCRIPT_DIR / 'templates')
+    template_folder=str(SCRIPT_DIR / "templates"),
 )
 
 logging.basicConfig(
     level=logging.INFO,
-    format='%(asctime)s - %(levelname)s - %(message)s',
+    format="%(asctime)s - %(levelname)s - %(message)s",
     handlers=[
         logging.StreamHandler(sys.stdout),
-        logging.FileHandler(ARCHIVE_DIR / 'processing.log', encoding='utf-8')
+        logging.FileHandler(ARCHIVE_DIR / "processing.log", encoding="utf-8"),
-    ]
+    ],
 )
 logger = logging.getLogger(__name__)
 
 
 def get_pagination_info(total: int, page: int, per_page: int) -> dict:
     """Calculate pagination information.
-    
+
     Args:
         total: Total number of items
         page: Current page number
         per_page: Items per page
-        
+
     Returns:
         Dictionary with pagination details
     """
     total_pages = (total + per_page - 1) // per_page if total > 0 else 1
-    
+
     return {
-        'total': total,
+        "total": total,
-        'page': page,
+        "page": page,
-        'per_page': per_page,
+        "per_page": per_page,
-        'has_next': page < total_pages,
+        "has_next": page < total_pages,
-        'has_prev': page > 1,
+        "has_prev": page > 1,
-        'next_num': page + 1 if page < total_pages else None,
+        "next_num": page + 1 if page < total_pages else None,
-        'prev_num': page - 1 if page > 1 else None,
+        "prev_num": page - 1 if page > 1 else None,
-        'pages': total_pages
+        "pages": total_pages,
     }
 
 
-@app.route('/')
+@app.route("/")
 def index():
     """Newspaper listing page."""
     sources = get_all_sources()
     rss_feeds = load_rss_feeds()
-    
+
     source_list = []
     disabled_sources = []
-    
+
     for source_name in sources:
         stats = get_source_stats(source_name)
-        
+
         source_info = {
-            'name': source_name.title(),
+            "name": source_name.title(),
-            'slug': source_name,
+            "slug": source_name,
-            'article_count': stats['total_articles'],
+            "article_count": stats["total_articles"],
-            'last_archived': stats.get('last_archived'),
+            "last_archived": stats.get("last_archived"),
-            'status': 'success' if stats['total_articles'] > 0 else 'pending'
+            "status": "success" if stats["total_articles"] > 0 else "pending",
         }
-        
+
         if source_name in rss_feeds:
             feed_info = rss_feeds[source_name]
-            if feed_info.get('disabled', False):
+            if feed_info.get("disabled", False):
-                source_info['disabled'] = True
+                source_info["disabled"] = True
-                source_info['disable_reason'] = feed_info.get('disable_reason', 'No reason provided')
+                source_info["disable_reason"] = feed_info.get(
+                    "disable_reason", "No reason provided"
+                )
                 disabled_sources.append(source_info)
                 continue
-        
+
         source_list.append(source_info)
-    
+
     source_list.extend(disabled_sources)
-    
+
-    return render_template('index.html', sources=source_list)
+    return render_template("index.html", sources=source_list)
 
 
-@app.route('/source/<slug>')
+@app.route("/source/<slug>")
 def articles(slug: str):
     """Article listing page for a specific source."""
-    page = request.args.get('page', 1, type=int)
+    page = request.args.get("page", 1, type=int)
     per_page = 50
-    
+
     sources = get_all_sources()
     source_name = None
     for s in sources:
         if s.lower() == slug.lower():
             source_name = s
             break
-    
+
     if not source_name:
-        return render_template('article_not_found.html', slug=slug, article_id=0), 404
+        return render_template("article_not_found.html", slug=slug, article_id=0), 404
-    
+
-    articles_list = get_articles_by_source(source_name, limit=per_page, offset=(page - 1) * per_page)
+    articles_list = get_articles_by_source(
+        source_name, limit=per_page, offset=(page - 1) * per_page
+    )
     stats = get_source_stats(source_name)
-    total = stats['total_articles']
+    total = stats["total_articles"]
-    
+
     pagination = get_pagination_info(total, page, per_page)
-    
+
     articles_data = []
     for article in articles_list:
-        articles_data.append({
+        articles_data.append(
-            'id': getattr(article, 'id', 0),
+            {
-            'title': article.title or 'Untitled',
+                "id": getattr(article, "id", 0),
-            'date': article.publish_date or '',
+                "title": article.title or "Untitled",
-            'summary': article.content_text[:200] if article.content_text else '',
+                "date": article.publish_date or "",
-            'url': f'/source/{source_name.lower()}/article/{getattr(article, "id", 0)}'
+                "summary": article.content_text[:200] if article.content_text else "",
-        })
+                "url": f"/source/{source_name.lower()}/article/{getattr(article, 'id', 0)}",
-    
+            }
+        )
+
     return render_template(
-        'articles.html',
+        "articles.html",
         source_name=source_name.title(),
         source_slug=source_name.lower(),
         articles=articles_data,
-        pagination=pagination
+        pagination=pagination,
     )
 
 
-@app.route('/archive/<path:archive_path>')
+@app.route("/archive/<path:archive_path>")
 def serve_archive(archive_path):
     """Serve archived HTML file."""
     archive_file = ARCHIVE_DIR / archive_path
     if archive_file.exists():
-        return archive_file.read_text(encoding='utf-8')
+        return archive_file.read_text(encoding="utf-8")
-    return 'Archive not found', 404
+    return "Archive not found", 404
 
 
-@app.route('/archive-file/<path:encoded_path>')
+@app.route("/archive-file/<path:encoded_path>")
 def serve_archive_file(encoded_path):
     """Serve archived HTML file from encoded path."""
     import urllib.parse
     from pathlib import Path
+
     archive_path = urllib.parse.unquote(encoded_path)
     archive_file = ARCHIVE_DIR / archive_path
-    logger.info("Archive file path: %s, exists: %s", str(archive_file), archive_file.exists())
+    logger.info(
+        "Archive file path: %s, exists: %s", str(archive_file), archive_file.exists()
+    )
     if archive_file.exists():
-        return archive_file.read_text(encoding='utf-8')
+        return archive_file.read_text(encoding="utf-8")
-    return 'Archive not found', 404
+    return "Archive not found", 404
 
 
-@app.route('/source/<slug>/article/<int:article_id>')
+@app.route("/source/<slug>/article/<int:article_id>")
 def article(slug: str, article_id: int):
     """Individual article page."""
     sources = get_all_sources()
@@ -200,289 +212,324 @@ def article(slug: str, article_id: int):
         if s.lower() == slug.lower():
             source_name = s
             break
-    
+
     if not source_name:
-        return render_template('article_not_found.html', slug=slug, article_id=article_id), 404
+        return render_template(
-    
+            "article_not_found.html", slug=slug, article_id=article_id
+        ), 404
+
     article = get_article(source_name, article_id)
     if not article:
-        return render_template('article_not_found.html', slug=slug, article_id=article_id), 404
+        return render_template(
-    
+            "article_not_found.html", slug=slug, article_id=article_id
+        ), 404
+
     article_data = {
-        'id': article_id,
+        "id": article_id,
-        'title': article.title or 'Untitled',
+        "title": article.title or "Untitled",
-        'publish_date': article.publish_date or '',
+        "publish_date": article.publish_date or "",
-        'author': article.author or '',
+        "author": article.author or "",
-        'url': article.url or '',
+        "url": article.url or "",
-        'content_text': article.content_text or '',
+        "content_text": article.content_text or "",
-        'archive_file_path': article.archive_file_path or ''
+        "archive_file_path": article.archive_file_path or "",
     }
-    
+
     return render_template(
-        'article.html',
+        "article.html",
         source_name=source_name.title(),
         source_slug=source_name.lower(),
-        article=article_data
+        article=article_data,
     )
 
 
-@app.route('/status')
+@app.route("/status")
 def status():
     """System status page."""
     sources = get_all_sources()
     rss_feeds = load_rss_feeds()
-    
+
     sources_info = []
     disabled_sources = []
     total_articles = 0
     failed_jobs = 0
     disabled_count = 0
-    
+
     for source_name in sources:
         stats = get_source_stats(source_name)
-        
+
         source_info = {
-            'name': source_name.title(),
+            "name": source_name.title(),
-            'slug': source_name,
+            "slug": source_name,
-            'article_count': stats['total_articles'],
+            "article_count": stats["total_articles"],
-            'last_archived': stats.get('last_archived'),
+            "last_archived": stats.get("last_archived"),
-            'status': 'success' if stats['total_articles'] > 0 else 'pending'
+            "status": "success" if stats["total_articles"] > 0 else "pending",
         }
-        
+
         if source_name in rss_feeds:
             feed_info = rss_feeds[source_name]
-            if feed_info.get('disabled', False):
+            if feed_info.get("disabled", False):
-                source_info['disabled'] = True
+                source_info["disabled"] = True
                 disabled_count += 1
                 disabled_sources.append(source_info)
                 continue
-        
+
         sources_info.append(source_info)
-        total_articles += stats['total_articles']
+        total_articles += stats["total_articles"]
-        failed_jobs += stats['failed']
+        failed_jobs += stats["failed"]
-    
+
     sources_info.extend(disabled_sources)
-    
+
     return render_template(
-        'status.html',
+        "status.html",
         sources=sources_info,
         total_articles=total_articles,
         failed_jobs=failed_jobs,
         sources_monitored=len(sources) - disabled_count,
-        disabled_sources=disabled_count
+        disabled_sources=disabled_count,
     )
 
 
-@app.route('/api/sources')
+@app.route("/api/sources")
 def api_sources():
     """API endpoint for listing all sources."""
     sources = get_all_sources()
     rss_feeds = load_rss_feeds()
-    
+
     source_list = []
     disabled_sources = []
-    
+
     for source_name in sources:
         stats = get_source_stats(source_name)
-        
+
         source_info = {
-            'name': source_name.title(),
+            "name": source_name.title(),
-            'slug': source_name,
+            "slug": source_name,
-            'article_count': stats['total_articles'],
+            "article_count": stats["total_articles"],
-            'last_archived': stats.get('last_archived'),
+            "last_archived": stats.get("last_archived"),
-            'status': 'success' if stats['total_articles'] > 0 else 'pending'
+            "status": "success" if stats["total_articles"] > 0 else "pending",
         }
-        
+
         if source_name in rss_feeds:
             feed_info = rss_feeds[source_name]
-            if feed_info.get('disabled', False):
+            if feed_info.get("disabled", False):
-                source_info['disabled'] = True
+                source_info["disabled"] = True
-                source_info['disable_reason'] = feed_info.get('disable_reason', 'No reason provided')
+                source_info["disable_reason"] = feed_info.get(
+                    "disable_reason", "No reason provided"
+                )
                 disabled_sources.append(source_info)
                 continue
-        
+
         source_list.append(source_info)
-    
+
     source_list.extend(disabled_sources)
-    
+
-    return jsonify({'sources': source_list})
+    return jsonify({"sources": source_list})
 
 
-@app.route('/api/source/<slug>/articles')
+@app.route("/api/source/<slug>/articles")
 def api_articles(slug: str):
     """API endpoint for listing articles for a source."""
-    page = request.args.get('page', 1, type=int)
+    page = request.args.get("page", 1, type=int)
     per_page = 50
-    
+
     sources = get_all_sources()
     source_name = None
     for s in sources:
         if s.lower() == slug.lower():
             source_name = s
             break
-    
+
     if not source_name:
-        return jsonify({'error': 'Source not found'}), 404
+        return jsonify({"error": "Source not found"}), 404
-    
+
-    articles_list = get_articles_by_source(source_name, limit=per_page, offset=(page - 1) * per_page)
+    articles_list = get_articles_by_source(
+        source_name, limit=per_page, offset=(page - 1) * per_page
+    )
     stats = get_source_stats(source_name)
-    total = stats['total_articles']
+    total = stats["total_articles"]
-    
+
     pagination = get_pagination_info(total, page, per_page)
-    
+
     articles_data = []
     for article in articles_list:
-        articles_data.append({
+        articles_data.append(
-            'id': getattr(article, 'id', 0),
+            {
-            'title': article.title or 'Untitled',
+                "id": getattr(article, "id", 0),
-            'date': article.publish_date or '',
+                "title": article.title or "Untitled",
-            'summary': article.content_text[:200] if article.content_text else '',
+                "date": article.publish_date or "",
-            'url': f'/source/{source_name.lower()}/article/{getattr(article, "id", 0)}'
+                "summary": article.content_text[:200] if article.content_text else "",
-        })
+                "url": f"/source/{source_name.lower()}/article/{getattr(article, 'id', 0)}",
-    
+            }
-    return jsonify({
+        )
-        'source_name': source_name.title(),
+
-        'articles': articles_data,
+    return jsonify(
-        'total': total,
+        {
-        'page': page,
+            "source_name": source_name.title(),
-        'per_page': per_page,
+            "articles": articles_data,
-        'has_next': pagination['has_next'],
+            "total": total,
-        'has_prev': pagination['has_prev']
+            "page": page,
-    })
+            "per_page": per_page,
+            "has_next": pagination["has_next"],
+            "has_prev": pagination["has_prev"],
+        }
+    )
 
 
-@app.route('/api/status')
+@app.route("/api/status")
 def api_status():
     """API endpoint for system status."""
     sources = get_all_sources()
-    
+
     sources_monitored = len(sources)
     total_articles = 0
     failed_jobs = 0
     last_archive_run = None
-    
+
     for source_name in sources:
         stats = get_source_stats(source_name)
-        total_articles += stats['total_articles']
+        total_articles += stats["total_articles"]
-        failed_jobs += stats['failed']
+        failed_jobs += stats["failed"]
-        
+
-        if stats.get('last_archive_run'):
+        if stats.get("last_archive_run"):
-            if last_archive_run is None or stats['last_archive_run'] > last_archive_run:
+            if last_archive_run is None or stats["last_archive_run"] > last_archive_run:
-                last_archive_run = stats['last_archive_run']
+                last_archive_run = stats["last_archive_run"]
-    
+
-    return jsonify({
+    return jsonify(
-        'status': 'online',
+        {
-        'last_archive_run': last_archive_run,
+            "status": "online",
-        'pending_jobs': 0,
+            "last_archive_run": last_archive_run,
-        'failed_jobs': failed_jobs,
+            "pending_jobs": 0,
-        'sources_monitored': sources_monitored,
+            "failed_jobs": failed_jobs,
-        'total_articles': total_articles
+            "sources_monitored": sources_monitored,
-    })
+            "total_articles": total_articles,
+        }
+    )
 
 
-@app.route('/rss')
+@app.route("/rss")
 def rss_feed():
     """RSS 2.0 endpoint for latest archived articles."""
-    limit = request.args.get('limit', 50, type=int)
+    limit = request.args.get("limit", 50, type=int)
-    
+
     articles = get_latest_articles(limit=limit)
-    
+
-    server_url = f'http://192.168.8.150:5000'
+    server_url = f"http://192.168.8.150:5000"
-    
+
     rss_items = []
     for article in articles:
-        if article.title and article.content_text and 'Performing security verification' not in article.content_text:
+        if (
+            article.title
+            and article.content_text
+            and "Performing security verification" not in article.content_text
+        ):
             pub_date = None
             if article.publish_date:
                 try:
-                    dt = datetime.fromisoformat(article.publish_date.replace('Z', '+00:00'))
+                    dt = datetime.fromisoformat(
-                    pub_date = dt.strftime('%a, %d %b %Y %H:%M:%S %z').strip()
+                        article.publish_date.replace("Z", "+00:00")
+                    )
+                    pub_date = dt.strftime("%a, %d %b %Y %H:%M:%S %z").strip()
                 except (ValueError, AttributeError):
                     try:
                         dt = datetime.fromisoformat(article.publish_date)
-                        pub_date = dt.strftime('%a, %d %b %Y %H:%M:%S +0000')
+                        pub_date = dt.strftime("%a, %d %b %Y %H:%M:%S +0000")
                     except (ValueError, AttributeError):
-                        pub_date = datetime.now(timezone.utc).strftime('%a, %d %b %Y %H:%M:%S +0000')
+                        pub_date = datetime.now(timezone.utc).strftime(
-            
+                            "%a, %d %b %Y %H:%M:%S +0000"
-            source_name = article.source_name or 'unknown'
+                        )
+
+            source_name = article.source_name or "unknown"
             encoded_source = quote(source_name.lower())
             item = {
-                'title': article.title,
+                "title": article.title,
-                'link': f'{server_url}/source/{encoded_source}/article/{article.id}',
+                "link": f"{server_url}/source/{encoded_source}/article/{article.id}",
-                'pubDate': pub_date,
+                "pubDate": pub_date,
-                'description': article.content_text[:500] if article.content_text else '',
+                "description": article.content_text[:500]
-                'guid': article.url or f'article-{article.id}'
+                if article.content_text
+                else "",
+                "guid": article.url or f"article-{article.id}",
             }
             if article.author:
-                item['author'] = article.author
+                item["author"] = article.author
             rss_items.append(item)
-    
+
     rss_template = render_template(
-        'rss.xml',
+        "rss.xml",
-        title='NewsArchiver - Latest Articles',
+        title="NewsArchiver - Latest Articles",
         link=server_url,
-        description='Latest archived news articles',
+        description="Latest archived news articles",
-        last_build_date=datetime.now(timezone.utc).strftime('%a, %d %b %Y %H:%M:%S +0000'),
+        last_build_date=datetime.now(timezone.utc).strftime(
-        items=rss_items
+            "%a, %d %b %Y %H:%M:%S +0000"
+        ),
+        items=rss_items,
     )
-    
+
     response = make_response(rss_template)
-    response.headers['Content-Type'] = 'application/rss+xml; charset=utf-8'
+    response.headers["Content-Type"] = "application/rss+xml; charset=utf-8"
     return response
 
 
-@app.route('/atom')
+@app.route("/atom")
 def atom_feed():
     """Atom 1.0 endpoint for latest archived articles."""
-    limit = request.args.get('limit', 50, type=int)
+    limit = request.args.get("limit", 50, type=int)
-    
+
     articles = get_latest_articles(limit=limit)
-    
+
-    server_url = f'http://192.168.8.150:5000'
+    server_url = f"http://192.168.8.150:5000"
-    
+
     atom_entries = []
     for article in articles:
-        if article.title and article.content_text and 'Performing security verification' not in article.content_text:
+        if (
+            article.title
+            and article.content_text
+            and "Performing security verification" not in article.content_text
+        ):
             pub_date = None
             if article.publish_date:
                 try:
-                    dt = datetime.fromisoformat(article.publish_date.replace('Z', '+00:00'))
+                    dt = datetime.fromisoformat(
-                    pub_date = dt.strftime('%Y-%m-%dT%H:%M:%S+00:00')
+                        article.publish_date.replace("Z", "+00:00")
+                    )
+                    pub_date = dt.strftime("%Y-%m-%dT%H:%M:%S+00:00")
                 except (ValueError, AttributeError):
-                    pub_date = datetime.now(timezone.utc).strftime('%Y-%m-%dT%H:%M:%S+00:00')
+                    pub_date = datetime.now(timezone.utc).strftime(
-            
+                        "%Y-%m-%dT%H:%M:%S+00:00"
-            source_name = article.source_name or 'unknown'
+                    )
+
+            source_name = article.source_name or "unknown"
             encoded_source = quote(source_name.lower())
             entry = {
-                'title': article.title,
+                "title": article.title,
-                'link': f'{server_url}/source/{encoded_source}/article/{article.id}',
+                "link": f"{server_url}/source/{encoded_source}/article/{article.id}",
-                'published': pub_date,
+                "published": pub_date,
-                'summary': article.content_text[:500] if article.content_text else '',
+                "summary": article.content_text[:500] if article.content_text else "",
-                'id': article.url or f'article-{article.id}'
+                "id": article.url or f"article-{article.id}",
             }
             if article.author:
-                entry['author'] = {'name': article.author}
+                entry["author"] = {"name": article.author}
             atom_entries.append(entry)
-    
+
     atom_template = render_template(
-        'atom.xml',
+        "atom.xml",
-        title='NewsArchiver - Latest Articles',
+        title="NewsArchiver - Latest Articles",
         link=server_url,
-        updated=datetime.now(timezone.utc).strftime('%Y-%m-%dT%H:%M:%S+00:00'),
+        updated=datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%S+00:00"),
-        entries=atom_entries
+        entries=atom_entries,
     )
-    
+
     response = make_response(atom_template)
-    response.headers['Content-Type'] = 'application/atom+xml; charset=utf-8'
+    response.headers["Content-Type"] = "application/atom+xml; charset=utf-8"
     return response
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     logger.info("Starting web interface...")
-    
+
     if not DB_PATH.exists():
         logger.info("Database not found, initializing...")
         from storage_manager import initialize_storage
+
         initialize_storage()
-    
+
-    app.run(host='0.0.0.0', port=5000, debug=True)
+    app.run(host="0.0.0.0", port=5000, debug=True)