ts

xhs_crawler_core.py

@@ -570,35 +570,14 @@ def resolve_profile_by_search(
 
         for i in range(n):
             it = items.nth(i)
-            _log(log, f"[账号] 分析第 {i+1}/{n} 个结果...")
             if use_anchor_only:
                 href = (it.get_attribute("href") or "").strip()
                 nickname = ""
                 xhs_no = ""
                 try:
-                    full_text = (it.inner_text() or "").strip()
-                    # 解析昵称和账号：从完整文本中提取
-                    # 示例：青岛西门子家电规划师-海燕呀 1天前更新 小红书号：V13863940939 粉丝・52 笔记・217 关注
-                    # 提取昵称：从开头到 "小红书号" 之前，去除时间信息
-                    lines = full_text.split('\n')
-                    main_text = lines[0] if lines else full_text
-
-                    # 提取小红书号
-                    m = re.search(r'小红书号[：:]\s*([A-Za-z0-9]+)', main_text)
-                    if m:
-                        xhs_no = m.group(1).strip()
-
-                    # 提取昵称：去除时间信息和账号信息
-                    # 先移除小红书号部分
-                    nickname_part = re.sub(r'小红书号[：:]\s*[A-Za-z0-9]+.*', '', main_text)
-                    # 移除时间信息（如 "1天前更新"）
-                    nickname_part = re.sub(r'\d+[天小时分秒]*前更新', '', nickname_part)
-                    # 移除粉丝、笔记、关注信息
-                    nickname_part = re.sub(r'粉丝[・・]\d+\s*笔记[・・]\d+\s*关注.*', '', nickname_part)
-                    nickname = nickname_part.strip()
+                    nickname = (it.inner_text() or "").strip()
                 except Exception:
                     nickname = ""
-                    xhs_no = ""
             else:
                 href = (it.locator("a[href^='/user/profile/']").first.get_attribute("href") or "").strip()
                 nickname = ""
@@ -618,35 +597,17 @@ 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
-            if nickname and nickname.lower() == kw.lower():
-                score += 500
-                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
+                score += 100
+            # 昵称包含关键词
+            if nickname and kw in nickname:
+                score += 10
+            # 有有效的 profile ID
             if _extract_profile_id_from_href(href):
-                score += 5
-                score_reasons.append("有效Profile ID")
+                score += 1
 
-            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})")
+            _log(log, f"[账号]   - 昵称: {nickname[:30] if len(nickname) > 30 else nickname}, 账号: {xhs_no}, 得分: {score}")
 
             if score > best_score:
                 best_score = score