ts

xhs_crawler_core.py

@@ -560,6 +560,9 @@ def resolve_profile_by_search(
                     m = re.search(r'小红书号[：:]\s*([A-Za-z0-9]+)', full_text)
                     if m:
                         xhs_no = m.group(1).strip()
+                        _log(log, f"[调试{i+1}] 提取到小红书号: {xhs_no}")
+                    else:
+                        _log(log, f"[调试{i+1}] 未匹配到小红书号，文本前100字符: {full_text[:100]}")
 
                     # 提取昵称：从开头去除干扰信息
                     lines = full_text.split('\n')
@@ -578,7 +581,8 @@ def resolve_profile_by_search(
                         nickname = re.sub(r'\s+', ' ', main_text).strip()
                     else:
                         nickname = full_text
-                except Exception:
+                except Exception as e:
+                    _log(log, f"[调试{i+1}] 解析异常: {e}")
                     nickname = ""
                     xhs_no = ""
             else:
@@ -603,9 +607,11 @@ def resolve_profile_by_search(
             # 精确匹配小红书号：最高优先级
             if xhs_no and xhs_no.lower() == kw.lower():
                 score += 100
+                _log(log, f"[调试{i+1}] 小红书号精确匹配！+100分")
             # 昵称包含关键词
             if nickname and kw in nickname:
                 score += 10
+                _log(log, f"[调试{i+1}] 昵称包含关键词！+10分")
             # 有有效的 profile ID
             if _extract_profile_id_from_href(href):
                 score += 1