Add comprehensive RSS scraper implementation with security and testing

- Modular architecture with separate modules for scraping, parsing, security, validation, and caching
- Comprehensive security measures including HTML sanitization, rate limiting, and input validation
- Robust error handling with custom exceptions and retry logic
- HTTP caching with ETags and Last-Modified headers for efficiency
- Pre-compiled regex patterns for improved performance
- Comprehensive test suite with 66 tests covering all major functionality
- Docker support for containerized deployment
- Configuration management with environment variable support
- Working parser that successfully extracts 32 articles from Warhammer Community

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

tests/test_rss_generator.py

@@ -0,0 +1,162 @@
+"""Tests for RSS generator module."""
+
+import pytest
+import os
+import tempfile
+from datetime import datetime
+import pytz
+from unittest.mock import patch, mock_open
+
+from src.rss_scraper.rss_generator import generate_rss_feed, save_rss_feed, save_debug_html
+from src.rss_scraper.exceptions import FileOperationError
+
+
+class TestGenerateRssFeed:
+    """Test RSS feed generation functionality."""
+    
+    def test_generate_rss_feed_with_articles(self):
+        """Test RSS generation with valid articles."""
+        timezone = pytz.UTC
+        articles = [
+            {
+                'title': 'Test Article 1',
+                'link': 'https://example.com/article1',
+                'date': datetime(2024, 1, 1, tzinfo=timezone)
+            },
+            {
+                'title': 'Test Article 2',
+                'link': 'https://example.com/article2',
+                'date': datetime(2024, 1, 2, tzinfo=timezone)
+            }
+        ]
+        
+        feed_url = "https://example.com"
+        rss_content = generate_rss_feed(articles, feed_url)
+        
+        assert isinstance(rss_content, bytes)
+        rss_str = rss_content.decode('utf-8')
+        assert 'Test Article 1' in rss_str
+        assert 'Test Article 2' in rss_str
+        assert 'https://example.com/article1' in rss_str
+        assert 'https://example.com/article2' in rss_str
+        assert '<?xml version=' in rss_str
+        assert '<rss version=' in rss_str
+    
+    def test_generate_rss_feed_empty_articles(self):
+        """Test RSS generation with empty articles list."""
+        articles = []
+        feed_url = "https://example.com"
+        
+        rss_content = generate_rss_feed(articles, feed_url)
+        
+        assert isinstance(rss_content, bytes)
+        rss_str = rss_content.decode('utf-8')
+        assert '<?xml version=' in rss_str
+        assert '<rss version=' in rss_str
+        # Should still contain feed metadata
+        assert 'Warhammer Community RSS Feed' in rss_str
+    
+    def test_generate_rss_feed_unicode_content(self):
+        """Test RSS generation with unicode content."""
+        timezone = pytz.UTC
+        articles = [
+            {
+                'title': 'Tëst Artìclé with Ūnïcödë',
+                'link': 'https://example.com/unicode',
+                'date': datetime(2024, 1, 1, tzinfo=timezone)
+            }
+        ]
+        
+        feed_url = "https://example.com"
+        rss_content = generate_rss_feed(articles, feed_url)
+        
+        assert isinstance(rss_content, bytes)
+        rss_str = rss_content.decode('utf-8')
+        assert 'Tëst Artìclé with Ūnïcödë' in rss_str
+
+
+class TestSaveRssFeed:
+    """Test RSS feed saving functionality."""
+    
+    def test_save_rss_feed_success(self):
+        """Test successful RSS feed saving."""
+        rss_content = b'<?xml version="1.0"?><rss>test</rss>'
+        
+        with tempfile.TemporaryDirectory() as temp_dir:
+            result_path = save_rss_feed(rss_content, temp_dir)
+            
+            assert os.path.exists(result_path)
+            assert result_path.endswith('warhammer_rss_feed.xml')
+            
+            with open(result_path, 'rb') as f:
+                saved_content = f.read()
+            assert saved_content == rss_content
+    
+    def test_save_rss_feed_permission_error(self):
+        """Test RSS feed saving with permission error."""
+        rss_content = b'<?xml version="1.0"?><rss>test</rss>'
+        
+        with patch('builtins.open', side_effect=PermissionError("Permission denied")):
+            with pytest.raises(FileOperationError):
+                save_rss_feed(rss_content, "/some/path")
+    
+    def test_save_rss_feed_creates_directory(self):
+        """Test that RSS feed saving creates directory if needed."""
+        rss_content = b'<?xml version="1.0"?><rss>test</rss>'
+        
+        with tempfile.TemporaryDirectory() as temp_dir:
+            new_subdir = os.path.join(temp_dir, "new_subdir")
+            result_path = save_rss_feed(rss_content, new_subdir)
+            
+            assert os.path.exists(new_subdir)
+            assert os.path.exists(result_path)
+
+
+class TestSaveDebugHtml:
+    """Test debug HTML saving functionality."""
+    
+    def test_save_debug_html_success(self):
+        """Test successful debug HTML saving."""
+        html_content = "<html><body>Test content</body></html>"
+        
+        with tempfile.TemporaryDirectory() as temp_dir:
+            save_debug_html(html_content, temp_dir)
+            
+            html_path = os.path.join(temp_dir, "page.html")
+            assert os.path.exists(html_path)
+            
+            with open(html_path, 'r', encoding='utf-8') as f:
+                saved_content = f.read()
+            # BeautifulSoup prettifies the content
+            assert "Test content" in saved_content
+    
+    def test_save_debug_html_permission_error(self):
+        """Test debug HTML saving with permission error (should not raise)."""
+        html_content = "<html><body>Test content</body></html>"
+        
+        with patch('builtins.open', side_effect=PermissionError("Permission denied")):
+            # Should not raise exception, just log warning
+            save_debug_html(html_content, "/some/path")
+    
+    def test_save_debug_html_malformed_content(self):
+        """Test debug HTML saving with malformed HTML content."""
+        malformed_html = "<html><body>Unclosed tags"
+        
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Should handle malformed HTML gracefully
+            save_debug_html(malformed_html, temp_dir)
+            
+            html_path = os.path.join(temp_dir, "page.html")
+            assert os.path.exists(html_path)
+    
+    def test_save_debug_html_creates_directory(self):
+        """Test that debug HTML saving creates directory if needed."""
+        html_content = "<html><body>Test content</body></html>"
+        
+        with tempfile.TemporaryDirectory() as temp_dir:
+            new_subdir = os.path.join(temp_dir, "new_subdir")
+            save_debug_html(html_content, new_subdir)
+            
+            assert os.path.exists(new_subdir)
+            html_path = os.path.join(new_subdir, "page.html")
+            assert os.path.exists(html_path)