From 420c9b872ae30ce77a6303fe896ce126acbceb46 Mon Sep 17 00:00:00 2001
From: mzl <mzl@hnxinyouhe.com>
Date: Sat, 10 Jan 2026 22:09:31 +0800
Subject: [PATCH] =?UTF-8?q?=E8=A7=A3=E6=9E=90=E8=B4=A6=E5=8F=B7?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 app/server.py       | 33 +++++++++------------------------
 xhs_crawler_core.py | 20 ++++++++++++++++----
 2 files changed, 25 insertions(+), 28 deletions(-)

diff --git a/app/server.py b/app/server.py
index e98cbae..fba40ab 100644
--- a/app/server.py
+++ b/app/server.py
@@ -544,30 +544,15 @@ def resolve_profile(payload: Dict[str, Any], token: Optional[str] = None):
     slow_mo = int(payload.get("slow_mo", 0))
 
     try:
-        # 判断是否为小红书号（纯字母数字，不含空格和特殊字符）
-        import re
-        is_xhs_id = bool(re.match(r'^[A-Za-z0-9]+$', keyword))
-
-        if is_xhs_id:
-            # 对于小红书号，使用直接访问方式避免搜索跳转问题
-            loghub.emit(f"[解析] 检测到小红书号格式，使用直接访问方式：{keyword}")
-            profile = resolve_profile_by_direct_url(
-                xhs_id=keyword,
-                storage_state_path=storage_path,
-                headless=headless,
-                slow_mo=slow_mo,
-                log=loghub.emit,
-            )
-        else:
-            # 对于昵称或其他关键词，使用搜索方式
-            loghub.emit(f"[解析] 使用搜索方式解析：{keyword}")
-            profile = resolve_profile_by_search(
-                keyword=keyword,
-                storage_state_path=storage_path,
-                headless=headless,
-                slow_mo=slow_mo,
-                log=loghub.emit,
-            )
+        # 统一使用搜索方式解析（按您的需求：搜索框输入 → 用户标签 → 获取URL）
+        loghub.emit(f"[解析] 开始搜索解析：{keyword}")
+        profile = resolve_profile_by_search(
+            keyword=keyword,
+            storage_state_path=storage_path,
+            headless=headless,
+            slow_mo=slow_mo,
+            log=loghub.emit,
+        )
     except Exception as e:
         loghub.emit(f"[解析][错误] {e}")
         raise HTTPException(status_code=400, detail=str(e))
diff --git a/xhs_crawler_core.py b/xhs_crawler_core.py
index b676680..cf714cc 100644
--- a/xhs_crawler_core.py
+++ b/xhs_crawler_core.py
@@ -618,23 +618,35 @@ def resolve_profile_by_search(
                 continue
 
             score = 0
+            score_reasons = []
+
             # 精确匹配小红书号：最高优先级
             if xhs_no and xhs_no.lower() == kw.lower():
                 score += 1000
+                score_reasons.append("小红书号精确匹配")
+
             # 精确匹配昵称：高优先级
-            elif nickname and nickname.lower() == kw.lower():
+            if nickname and nickname.lower() == kw.lower():
                 score += 500
-            # 昵称包含关键词：中优先级
-            elif nickname and kw.lower() in nickname.lower():
+                score_reasons.append("昵称精确匹配")
+
+            # 昵称包含关键词：中优先级（不使用 elif，允许累加）
+            if nickname and kw.lower() in nickname.lower() and nickname.lower() != kw.lower():
                 score += 50
+                score_reasons.append("昵称包含关键词")
+
             # URL 中包含关键词：低优先级
             if kw.lower() in href.lower():
                 score += 20
+                score_reasons.append("URL包含关键词")
+
             # 有有效的 profile ID：基础分
             if _extract_profile_id_from_href(href):
                 score += 5
+                score_reasons.append("有效Profile ID")
 
-            _log(log, f"[账号]   - 昵称: {nickname[:30] if len(nickname) > 30 else nickname}, 账号: {xhs_no}, 得分: {score}")
+            reasons_str = ", ".join(score_reasons) if score_reasons else "无匹配"
+            _log(log, f"[账号]   - 昵称: {nickname[:30] if len(nickname) > 30 else nickname}, 账号: {xhs_no}, 得分: {score} ({reasons_str})")
 
             if score > best_score:
                 best_score = score