v1.4.0: 通知日志分页+筛选 / 仪表盘TOP10+更多链接 / 数据源走web-capture-api抓取(获取方式与参数可编辑) / 系统错误邮件通知(频率+静默时段)

templates/500.html

@@ -0,0 +1,10 @@
+{% extends "base.html" %}
+{% block title %}系统异常 - 新闻智能跟踪{% endblock %}
+{% block content %}
+<div style="text-align:center;padding:80px 20px;">
+  <div style="font-size:64px;">⚠️</div>
+  <h1 style="margin:12px 0;">系统处理出错</h1>
+  <p class="muted">请求处理时发生异常，已自动记录并邮件通知管理员。</p>
+  <a class="btn" href="/dashboard" style="margin-top:16px;">← 返回仪表盘</a>
+</div>
+{% endblock %}

templates/dashboard.html

@@ -21,7 +21,7 @@
 
 <div class="two-col">
   <section class="card">
-    <h3>🔥 重要资讯 TOP</h3>
+    <h3>🔥 重要资讯 TOP <a class="more" href="/news?important=1">更多 ›</a></h3>
     {% for a in important %}
     <div class="item">
       <a class="item-title" href="/news/{{ a.id }}">{{ a.title }}</a>
@@ -50,7 +50,7 @@
 </div>
 
 <section class="card">
-  <h3>🕒 最新收录</h3>
+  <h3>🕒 最新收录 <a class="more" href="/news">更多 ›</a></h3>
   {% for a in latest %}
   <div class="item">
     <a class="item-title" href="/news/{{ a.id }}">{{ a.title }}</a>

templates/logs.html

@@ -3,9 +3,31 @@
 {% block title %}通知日志 - 新闻智能跟踪{% endblock %}
 {% block content %}
 <div class="page-head">
-  <h1>✉️ 通知日志</h1>
-  <button class="btn" onclick="testMail()">📮 发送测试邮件</button>
+  <h1>✉️ 通知日志 <span class="muted">共 {{ total }} 条</span></h1>
+  <div class="actions">
+    <button class="btn" onclick="testMail()">📮 发送测试邮件</button>
+    <button class="btn" onclick="testErrorMail()">⚠️ 测试错误通知</button>
+  </div>
 </div>
+
+<form class="filters" method="get" action="/logs">
+  <select name="type">
+    <option value="">全部类型</option>
+    <option value="realtime" {{ 'selected' if f_type=='realtime' }}>🔥 实时重要资讯</option>
+    <option value="summary" {{ 'selected' if f_type=='summary' }}>📰 新闻汇总</option>
+    <option value="custom_summary" {{ 'selected' if f_type=='custom_summary' }}>🎯 定制监控汇总</option>
+    <option value="error" {{ 'selected' if f_type=='error' }}>⚠️ 系统错误</option>
+  </select>
+  <select name="status">
+    <option value="">全部状态</option>
+    <option value="ok" {{ 'selected' if f_status=='ok' }}>✅ 成功</option>
+    <option value="error" {{ 'selected' if f_status=='error' }}>❌ 失败</option>
+  </select>
+  <input type="text" name="q" value="{{ q }}" placeholder="搜索主题 / 详情...">
+  <button class="btn" type="submit">筛选</button>
+  <a class="btn" href="/logs">重置</a>
+</form>
+
 <div class="card">
   <table>
     <thead><tr><th>ID</th><th>类型</th><th>主题</th><th>条数</th><th>状态</th><th>发送时间</th></tr></thead>
@@ -13,18 +35,32 @@
     {% for l in logs %}
       <tr>
         <td>{{ l.id }}</td>
-        <td>{% if l.type=='realtime' %}<span class="tag hot">实时</span>{% else %}<span class="tag ok">汇总</span>{% endif %}</td>
-        <td>{{ l.subject }}</td>
+        <td>
+          {% if l.type=='realtime' %}<span class="tag hot">🔥 实时</span>
+          {% elif l.type=='summary' %}<span class="tag ok">📰 新闻汇总</span>
+          {% elif l.type=='custom_summary' %}<span class="tag">🎯 定制汇总</span>
+          {% elif l.type=='error' %}<span class="tag err">⚠️ 系统错误</span>
+          {% else %}<span class="tag">{{ l.type }}</span>{% endif %}
+        </td>
+        <td>{{ l.subject }}
+          {% if l.detail %}<div class="muted small">{{ l.detail }}</div>{% endif %}
+        </td>
         <td>{{ l.count }}</td>
         <td>{% if l.status=='ok' %}<span class="tag ok">成功</span>{% else %}<span class="tag err">失败</span>{% endif %}</td>
-        <td>{{ l.sent_at }}</td>
+        <td class="small">{{ l.sent_at }}</td>
       </tr>
     {% else %}
-      <tr><td colspan="6" class="empty">暂无通知记录</td></tr>
+      <tr><td colspan="6" class="empty">暂无匹配的通知记录</td></tr>
     {% endfor %}
     </tbody>
   </table>
 </div>
+
+<div class="pager">
+  {% if page > 1 %}<a class="btn" href="/logs?page={{ page-1 }}&type={{ f_type }}&status={{ f_status }}&q={{ q }}">上一页</a>{% endif %}
+  <span class="muted">第 {{ page }} / {{ pages }} 页</span>
+  {% if page < pages %}<a class="btn" href="/logs?page={{ page+1 }}&type={{ f_type }}&status={{ f_status }}&q={{ q }}">下一页</a>{% endif %}
+</div>
 {% endblock %}
 {% block script %}
 <script>
@@ -32,5 +68,9 @@ async function testMail(){
   const r = await API.json('/api/actions', {action:'test_mail'});
   toast(r.ok ? '✅ 测试邮件已发送' : ('❌ ' + r.error), r.ok);
 }
+async function testErrorMail(){
+  const r = await API.json('/api/actions', {action:'test_error_mail'});
+  toast(r.ok ? '✅ 测试错误通知邮件已发送' : ('❌ ' + r.error), r.ok);
+}
 </script>
 {% endblock %}

templates/settings.html

@@ -98,7 +98,72 @@
 </section>
 
 <section class="card">
-  <h3>🤖 大模型接口
+  <h3>🌐 网页提取服务（web-capture-api）
+    <span class="muted small">（数据源真实网页默认通过该服务抓取，每源可单独选获取方式与参数）</span>
+  </h3>
+  <div class="setting-row">
+    <label>启用 web-capture-api 抓取</label>
+    <input type="checkbox" id="w_enabled" {{ 'checked' if auto.webcapture.enabled }}>
+  </div>
+  <div class="setting-row">
+    <label>API 地址</label>
+    <input id="w_api_url" value="{{ auto.webcapture.api_url }}" placeholder="http://121.40.164.32:16025">
+  </div>
+  <div class="setting-row">
+    <label>抓取超时（秒）</label>
+    <input type="number" id="w_timeout" value="{{ auto.webcapture.timeout }}">
+  </div>
+  <div class="setting-row">
+    <label>连通性测试</label>
+    <span style="display:flex;gap:8px;align-items:center;">
+      <button class="btn mini" type="button" onclick="testWebcapture()">🧪 测试接口</button>
+      <span id="wc_test_result" class="muted small"></span>
+    </span>
+  </div>
+</section>
+
+<section class="card">
+  <h3>⚠️ 系统错误邮件通知
+    <span class="muted small">（采集/分析/通知/汇总/系统异常自动邮件通知，可设通知频率与静默时段）</span>
+  </h3>
+  <div class="setting-row">
+    <label>启用错误邮件通知</label>
+    <input type="checkbox" id="e_enabled" {{ 'checked' if auto.errnotify.enabled }}>
+  </div>
+  <div class="setting-row">
+    <label>通知方式</label>
+    <select id="e_mode">
+      <option value="immediate" {{ 'selected' if auto.errnotify.mode=='immediate' }}>⚡ 立即（出现即尝试发，仍受冷却限制）</option>
+      <option value="cooldown" {{ 'selected' if auto.errnotify.mode=='cooldown' }}>⏱ 按冷却聚合（到冷却时间集中发一封）</option>
+      <option value="off" {{ 'selected' if auto.errnotify.mode=='off' }}>🚫 关闭（仅记录不发送）</option>
+    </select>
+  </div>
+  <div class="setting-row">
+    <label>通知频率（冷却分钟）<span class="muted small">— 两次错误邮件最小间隔</span></label>
+    <input type="number" id="e_cooldown_min" value="{{ auto.errnotify.cooldown_min }}">
+  </div>
+  <div class="setting-row">
+    <label>单封最多错误条数</label>
+    <input type="number" id="e_max_items" value="{{ auto.errnotify.max_items }}">
+  </div>
+  <div class="setting-row">
+    <label>启用静默时段</label>
+    <input type="checkbox" id="e_quiet_enabled" {{ 'checked' if auto.errnotify.quiet_enabled }}>
+  </div>
+  <div style="margin-top:10px;">
+    <label style="font-size:12px;color:#6b7280;">静默时段（每行一段 <b>HH:MM-HH:MM</b>，支持跨午夜、多段；静默期不发送，结束后自动补发）</label>
+    <textarea id="e_quiet_periods" rows="3" style="margin-top:4px;">{{ '\n'.join(auto.errnotify.quiet_periods) }}</textarea>
+  </div>
+  <div class="setting-row">
+    <label>测试</label>
+    <span style="display:flex;gap:8px;align-items:center;">
+      <button class="btn mini" type="button" onclick="testErrorMail()">📨 发一封测试错误通知</button>
+      <span id="e_test_result" class="muted small"></span>
+    </span>
+  </div>
+</section>
+
+<section class="card">
     <span class="muted small">（切换后即时生效，智能分析将使用当前接口；失败自动切换下一个可用接口）</span>
   </h3>
   <div class="form-row" style="margin-bottom:12px;">
@@ -170,10 +235,39 @@ async function saveAll(){
     custom_summary_window_hours: parseInt(G('c_custom_summary_window_hours'))||24,
     custom_max_summary_items: parseInt(G('c_custom_max_summary_items'))||20,
   };
-  const r = await API.json('/api/settings', { ...auto, mail, custom });
+  const webcapture = {
+    enabled: document.getElementById('w_enabled').checked ? 1 : 0,
+    api_url: G('w_api_url').trim() || 'http://121.40.164.32:16025',
+    timeout: parseInt(G('w_timeout')) || 60,
+  };
+  const errnotify = {
+    enabled: document.getElementById('e_enabled').checked ? 1 : 0,
+    mode: G('e_mode'),
+    cooldown_min: parseInt(G('e_cooldown_min')) || 60,
+    max_items: parseInt(G('e_max_items')) || 10,
+    quiet_enabled: document.getElementById('e_quiet_enabled').checked ? 1 : 0,
+    quiet_periods: G('e_quiet_periods').split(/[\n,;，；]/).map(s=>s.trim()).filter(Boolean),
+  };
+  const r = await API.json('/api/settings', { ...auto, mail, custom, webcapture, errnotify });
   toast(r.ok ? '✅ 设置已保存' : '❌ 保存失败', r.ok);
 }
 
+async function testWebcapture(){
+  const el = document.getElementById('wc_test_result');
+  el.textContent = '⏳ 测试中...';
+  const r = await API.json('/api/actions', {action:'test_webcapture'});
+  if (r.ok) el.textContent = `✅ ${r.api_url} 正常，抓取到：${r.title}（${(r.text||'').trim()}）`;
+  else el.textContent = '❌ ' + (r.error || '测试失败');
+}
+
+async function testErrorMail(){
+  const el = document.getElementById('e_test_result');
+  el.textContent = '⏳ 发送中...';
+  const r = await API.json('/api/actions', {action:'test_error_mail'});
+  if (r.ok) el.textContent = '✅ 测试错误通知邮件已发送';
+  else el.textContent = '❌ ' + (r.error || '发送失败');
+}
+
 async function addProvider(){
   const r = await API.json('/api/llm', {
     action:'add',

templates/sources.html

@@ -9,13 +9,14 @@
 
 <div class="card">
   <table>
-    <thead><tr><th>ID</th><th>名称</th><th>监控方式</th><th>类型</th><th>权重</th><th>采集周期</th><th>状态</th><th>最近采样</th><th>条数</th><th>操作</th></tr></thead>
+    <thead><tr><th>ID</th><th>名称</th><th>监控方式</th><th>获取方式</th><th>类型</th><th>权重</th><th>采集周期</th><th>状态</th><th>最近采样</th><th>条数</th><th>操作</th></tr></thead>
     <tbody>
     {% for s in sources %}
-      <tr data-sid="{{ s.id }}" data-name="{{ s.name }}" data-type="{{ s.type }}" data-url="{{ s.url }}" data-desc="{{ s.description }}" data-weight="{{ s.weight }}" data-kind="{{ s.kind }}" data-standard="{{ s.monitor_standard or '' }}" data-interval="{{ s.scan_interval_min or 0 }}">
+      <tr data-sid="{{ s.id }}" data-name="{{ s.name }}" data-type="{{ s.type }}" data-url="{{ s.url }}" data-desc="{{ s.description }}" data-weight="{{ s.weight }}" data-kind="{{ s.kind }}" data-standard="{{ s.monitor_standard or '' }}" data-interval="{{ s.scan_interval_min or 0 }}" data-fetch="{{ s.fetch_method or 'auto' }}" data-capture="{{ s.capture_params or '{}' }}">
         <td>{{ s.id }}</td>
         <td><b>{{ s.name }}</b><br><span class="muted small">{{ s.description }}</span><br><span class="muted small" style="word-break:break-all;">{{ s.url }}</span></td>
         <td>{% if s.kind == 'custom' %}<span class="tag hot">🎯 定制监控</span>{% else %}<span class="tag ok">普通</span>{% endif %}</td>
+        <td>{% if s.fetch_method == 'direct' %}<span class="tag">⚡ 直接抓取</span>{% elif s.fetch_method == 'webcapture' %}<span class="tag">🌐 web-capture</span>{% else %}<span class="tag ok">🌐 自动</span>{% endif %}</td>
         <td>{{ s.type }}</td>
         <td>{% if s.kind == 'custom' %}<span class="muted small">—</span>{% else %}{{ s.weight }}{% endif %}</td>
         <td>{% if s.scan_interval_min %}{{ s.scan_interval_min }}分{% else %}<span class="muted small">默认</span>{% endif %}</td>
@@ -33,8 +34,9 @@
     </tbody>
   </table>
   <div class="muted small" style="margin-top:8px;">
-    💡 真实 URL 源自动抓取页面并清洗可读正文入库；example.com 等占位地址走模拟数据。<br>
+    💡 真实 URL 源默认通过 web-capture-api 网页提取服务抓取（可每源改获取方式与参数）；example.com 等占位地址走模拟数据。<br>
     ⏱ 采集周期：0=跟随所属机制全局值（普通源=设置页采集间隔，定制源=定制监控间隔），填分钟数则本源自定义。<br>
+    🌐 获取方式：<b>自动</b>=优先 web-capture-api、失败回退直接抓取；<b>web-capture</b>=仅走网页提取服务；<b>直接抓取</b>=requests+正文清洗。设置页可改 web-capture-api 地址。<br>
     🎯 <b>定制监控</b>：与新闻监控独立，无权重，按「推送标准」由大模型判断是否推送，命中实时推送 + 单独汇总。
   </div>
 </div>
@@ -59,6 +61,35 @@
       <label>采集周期（分钟）<span class="muted small">— 0 表示跟随所属机制的全局间隔</span></label>
       <input id="m_interval" type="number" min="0" step="1" value="0" placeholder="0=跟随全局（普通源30 / 定制源15）">
 
+      <label>获取网页方式<span class="muted small">— 真实 URL 网页通过 web-capture-api 抓取（设置页可改接口地址）</span></label>
+      <select id="m_fetch" onchange="onFetchChange()">
+        <option value="auto">🌐 自动（优先 web-capture-api，失败回退直接抓取）</option>
+        <option value="webcapture">🌐 web-capture-api（网页提取服务，反爬强）</option>
+        <option value="direct">⚡ 直接抓取（requests + 正文清洗）</option>
+      </select>
+
+      <div id="m_capture_row">
+        <label>抓取动作<span class="muted small">— html 提取资讯链接；text 整页作为一条资讯</span></label>
+        <select id="m_c_action">
+          <option value="html">html（提取链接）</option>
+          <option value="text">text（直接取正文）</option>
+        </select>
+        <div class="form-row" style="justify-content:flex-start;margin-top:6px;">
+          <label style="display:flex;align-items:center;gap:5px;font-size:12px;color:#6b7280;white-space:nowrap;">等待加载(ms)
+            <input id="m_c_wait" type="number" value="2000" style="width:90px;"></label>
+          <label style="display:flex;align-items:center;gap:5px;font-size:12px;color:#6b7280;white-space:nowrap;">滚动次数
+            <input id="m_c_scroll" type="number" value="0" style="width:70px;"></label>
+          <label style="display:flex;align-items:center;gap:5px;font-size:12px;color:#6b7280;white-space:nowrap;">后端
+            <select id="m_c_backend" style="width:130px;">
+              <option value="auto">auto</option>
+              <option value="agent-browser">agent-browser</option>
+              <option value="playwright">playwright</option>
+            </select></label>
+        </div>
+        <label>高级参数(JSON，可留空)</label>
+        <textarea id="m_c_extra" rows="2" placeholder='{"scroll_delay":1000,"full_page":false,"viewport":{"width":1280,"height":800}}'></textarea>
+      </div>
+
       <div id="m_weight_row">
         <label>权重（综合评分中该源占比，0.1~2.0）</label>
         <input id="m_weight" type="number" step="0.1" min="0.1" max="2" value="0.8">
@@ -130,13 +161,28 @@ function openModal(id){
     setV('m_kind', row.dataset.kind || 'normal');
     setV('m_standard', row.dataset.standard || '');
     setV('m_interval', row.dataset.interval || '0');
+    const cap = parseCapture(row.dataset.capture);
+    setV('m_fetch', row.dataset.fetch || 'auto');
+    setV('m_c_action', cap.action || 'html');
+    setV('m_c_wait', cap.wait_time != null ? cap.wait_time : '2000');
+    setV('m_c_scroll', cap.scroll_times != null ? cap.scroll_times : '0');
+    setV('m_c_backend', cap.backend || 'auto');
+    const extra = {...cap};
+    ['action','wait_time','scroll_times','backend'].forEach(k => delete extra[k]);
+    setV('m_c_extra', Object.keys(extra).length ? JSON.stringify(extra) : '');
   } else {
-    ['m_name','m_type','m_url','m_desc','m_standard'].forEach(k=>setV(k,''));
+    ['m_name','m_type','m_url','m_desc','m_standard','m_c_extra'].forEach(k=>setV(k,''));
     setV('m_weight', '0.8');
     setV('m_kind', 'normal');
     setV('m_interval', '0');
+    setV('m_fetch', 'auto');
+    setV('m_c_action', 'html');
+    setV('m_c_wait', '2000');
+    setV('m_c_scroll', '0');
+    setV('m_c_backend', 'auto');
   }
   onKindChange();
+  onFetchChange();
   document.getElementById('sourceModal').style.display = 'flex';
 }
 function closeModal(){ document.getElementById('sourceModal').style.display = 'none'; editId = null; }
@@ -147,14 +193,41 @@ function onKindChange(){
   document.getElementById('m_standard_row').style.display = custom ? 'block' : 'none';
 }
 
+function onFetchChange(){
+  document.getElementById('m_capture_row').style.display =
+    getV('m_fetch') === 'direct' ? 'none' : 'block';
+}
+
+function parseCapture(s){
+  try { const o = JSON.parse(s || '{}'); return o && typeof o === 'object' ? o : {}; } catch(e){ return {}; }
+}
+
 async function saveSource(){
   const kind = getV('m_kind');
+  let captureParams = '{}';
+  if (getV('m_fetch') !== 'direct'){
+    const base = {
+      action: getV('m_c_action') || 'html',
+      wait_time: parseInt(getV('m_c_wait')) || 2000,
+      scroll_times: parseInt(getV('m_c_scroll')) || 0,
+      backend: getV('m_c_backend') || 'auto'
+    };
+    let adv = {};
+    const extraTxt = getV('m_c_extra').trim();
+    if (extraTxt){
+      try { adv = JSON.parse(extraTxt); }
+      catch(e){ toast('高级参数 JSON 格式错误', false); return; }
+    }
+    captureParams = JSON.stringify({ ...base, ...adv });
+  }
   const body = {
     name: getV('m_name').trim(), type: getV('m_type').trim(), url: getV('m_url').trim(),
     description: getV('m_desc').trim(), kind,
     monitor_standard: kind === 'custom' ? getV('m_standard').trim() : '',
     weight: parseFloat(getV('m_weight') || '1') || 1,
-    scan_interval_min: parseInt(getV('m_interval')) || 0
+    scan_interval_min: parseInt(getV('m_interval')) || 0,
+    fetch_method: getV('m_fetch'),
+    capture_params: captureParams
   };
   if (!body.name){ toast('请填写名称', false); return; }
   if (kind === 'custom' && !body.monitor_standard){ toast('请填写推送标准', false); return; }