Excel 文件移除 href 和 detail_content 字段

修复账号解析逻辑，正确提取昵称和账号
优化 Web 性能

app/static/index.html

@@ -881,12 +881,17 @@
     }
   }
   let _lastProg = '';
+  let _lastUpdateTime = 0;
   function updateProgressLine(s){
     if(!s || !s.progress) return;
     const p = s.progress;
     const key = `${p.status}-${p.done}-${p.total}-${p.current}`;
     if(key === _lastProg) return;
+    // 限制更新频率：最多每 2 秒更新一次进度
+    const now = Date.now();
+    if(now - _lastUpdateTime < 2000 && key === _lastProg) return;
     _lastProg = key;
+    _lastUpdateTime = now;
     if(p.status === 'running'){
       log(`进度：${p.done}/${p.total} 当前：${p.current || '-'}`);
     }else if(p.status && p.status !== 'idle'){
@@ -1367,13 +1372,18 @@
   });
 
   // ========= 文件输出 =========
+  let _refreshFilesPending = false;
   async function refreshOutFiles(){
     if(!authed) return;
+    if(_refreshFilesPending) return;  // 防止重复请求
+    _refreshFilesPending = true;
     try{
       const files = await apiGet('/api/files');
       renderFiles(files || []);
     }catch(e){
       // ignore
+    }finally{
+      _refreshFilesPending = false;
     }
   }
 
@@ -1477,10 +1487,10 @@
     log('页面加载完成。');
     connectLogs();
     await pollStatus();
-    // 每2秒无感检测一次（不刷新页面）
-    setInterval(pollStatus, 5000);
-    // 输出文件偶尔刷新一下
-    setInterval(refreshOutFiles, 15000);
+    // 状态轮询：降低频率到 10 秒（原 5 秒）
+    setInterval(pollStatus, 10000);
+    // 输出文件偶尔刷新一下：降低频率到 30 秒（原 15 秒）
+    setInterval(refreshOutFiles, 30000);
   })();
 </script>
 

xhs_crawler_core.py

@@ -558,11 +558,31 @@ def resolve_profile_by_search(
             if use_anchor_only:
                 href = (it.get_attribute("href") or "").strip()
                 nickname = ""
+                xhs_no = ""
                 try:
-                    nickname = (it.inner_text() or "").strip()
+                    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()
                 except Exception:
                     nickname = ""
-                xhs_no = ""
+                    xhs_no = ""
             else:
                 href = (it.locator("a[href^='/user/profile/']").first.get_attribute("href") or "").strip()
                 nickname = ""
@@ -947,8 +967,8 @@ def crawl_detail(
                 wb = Workbook()
                 ws = wb.active
                 ws.title = "data"
-                # 按需求文档的字段顺序
-                headers = ["href", "detail_title", "detail_content", "like", "collect", "comment", "detail_date_loc", "crawled_at"]
+                # Excel 导出字段（不包含 href 和 detail_content）
+                headers = ["detail_title", "like", "collect", "comment", "detail_date_loc", "crawled_at"]
                 ws.append(headers)
                 for r in results:
                     ws.append([r.get(h, "") for h in headers])