clean-text-to-keywords/keyword_extractor.py

@@ -2,8 +2,11 @@
 
 from __future__ import annotations
 
+import logging
 import math
 import re
+logger = logging.getLogger(__name__)
+
 from dataclasses import dataclass, field
 from typing import Any, Dict, Iterable, List, Mapping, Optional, Sequence, Set, Tuple
 
@@ -199,7 +202,8 @@ class KeywordExtractor:
     def _extract_yake_scores(self, text: str) -> Dict[str, float]:
         try:
             import yake
-        except Exception:
+        except ImportError:
+            logger.warning("yake not installed, skipping relevance scoring")
             return {}
 
         text_token_count = len(text.split())
@@ -208,7 +212,8 @@ class KeywordExtractor:
         try:
             extractor = yake.KeywordExtractor(lan="en", n=2, dedupLim=0.9, top=top_n)
             phrase_scores = extractor.extract_keywords(text)
-        except Exception:
+        except (ValueError, TypeError) as e:
+            logger.warning("YAKE extraction failed: %s", e)
             return {}
 
         token_scores: Dict[str, float] = {}