update

news_crawler/ollama_client.py

@@ -160,6 +160,147 @@ class OllamaClient:
                 'duration': time.time() - start_time
             }
     
+    def translate_title(self, title, target_language='English'):
+        """
+        Translate article title to target language
+        
+        Args:
+            title: Original title (typically German)
+            target_language: Target language (default: 'English')
+            
+        Returns:
+            {
+                'success': bool,             # Whether translation succeeded
+                'translated_title': str or None,  # Translated title
+                'error': str or None,        # Error message if failed
+                'duration': float            # Time taken in seconds
+            }
+        """
+        if not self.enabled:
+            return {
+                'success': False,
+                'translated_title': None,
+                'error': 'Ollama is not enabled',
+                'duration': 0
+            }
+        
+        if not title or len(title.strip()) == 0:
+            return {
+                'success': False,
+                'translated_title': None,
+                'error': 'Title is empty',
+                'duration': 0
+            }
+        
+        start_time = time.time()
+        
+        try:
+            # Construct prompt
+            prompt = self._build_translation_prompt(title, target_language)
+            
+            # Prepare request
+            url = f"{self.base_url}/api/generate"
+            headers = {'Content-Type': 'application/json'}
+            if self.api_key:
+                headers['Authorization'] = f'Bearer {self.api_key}'
+            
+            payload = {
+                'model': self.model,
+                'prompt': prompt,
+                'stream': False,
+                'options': {
+                    'temperature': 0.3,  # Lower temperature for consistent translations
+                    'num_predict': 100   # Limit response length for title-length outputs
+                }
+            }
+            
+            # Make request
+            response = requests.post(
+                url,
+                json=payload,
+                headers=headers,
+                timeout=self.timeout
+            )
+            response.raise_for_status()
+            
+            # Parse response
+            result = response.json()
+            translated_title = result.get('response', '').strip()
+            
+            if not translated_title:
+                return {
+                    'success': False,
+                    'translated_title': None,
+                    'error': 'Ollama returned empty translation',
+                    'duration': time.time() - start_time
+                }
+            
+            # Clean the translation output
+            translated_title = self._clean_translation(translated_title)
+            
+            return {
+                'success': True,
+                'translated_title': translated_title,
+                'error': None,
+                'duration': time.time() - start_time
+            }
+            
+        except requests.exceptions.Timeout:
+            return {
+                'success': False,
+                'translated_title': None,
+                'error': f'Request timed out after {self.timeout} seconds',
+                'duration': time.time() - start_time
+            }
+        except requests.exceptions.ConnectionError:
+            return {
+                'success': False,
+                'translated_title': None,
+                'error': f'Cannot connect to Ollama server at {self.base_url}',
+                'duration': time.time() - start_time
+            }
+        except requests.exceptions.HTTPError as e:
+            return {
+                'success': False,
+                'translated_title': None,
+                'error': f'HTTP error: {e.response.status_code} - {e.response.text[:100]}',
+                'duration': time.time() - start_time
+            }
+        except Exception as e:
+            return {
+                'success': False,
+                'translated_title': None,
+                'error': f'Unexpected error: {str(e)}',
+                'duration': time.time() - start_time
+            }
+    
+    def _build_translation_prompt(self, title, target_language):
+        """Build prompt for title translation"""
+        prompt = f"""Translate the following German news headline to {target_language}. Provide only the translation without any explanations, quotes, or additional text.
+
+German headline:
+{title}
+
+{target_language} translation:"""
+        
+        return prompt
+    
+    def _clean_translation(self, translation):
+        """Clean translation output by removing quotes and extra text"""
+        # Extract first line only
+        translation = translation.split('\n')[0]
+        
+        # Remove surrounding quotes (single and double)
+        translation = translation.strip()
+        if (translation.startswith('"') and translation.endswith('"')) or \
+           (translation.startswith("'") and translation.endswith("'")):
+            translation = translation[1:-1]
+        
+        # Trim whitespace again after quote removal
+        translation = translation.strip()
+        
+        return translation
+    
     def _build_summarization_prompt(self, content, max_words):
         """Build prompt for article summarization"""
         # Truncate content if too long (keep first 5000 words)