feat: 爬虫页取代抓取任务/入库任务两页,抓取改全量+覆盖率跳过
一、后台只留一个「爬虫」页(/admin/spider) 抓取与入库本就是同一条流水线的上下游,分两页看谁都看不全。 新页三块:状态条(在线/卡住 + 队列数 + 待入库数)、正在抓(含进度与心跳)、 最近入库结果(品牌/场次/结果/说明)。只读,取消与重试一并下线。 二、抓取一律全量 删除品牌页的场次上限下拉与 hidden maxShows=3,入队固定 0(全量)。 crawl_tasks.max_shows 列保留,历史任务照常显示。 三、跳过判定改覆盖率 - brand_runways 增加 expected_images(spider 上报的应有张数) - /shows/covered 返回 images + expected - 实际张数 >= 应有 - 5 才跳过;expected=0 时回落 10 张阈值 - 实体已存在时不再直接跳过:按 key 比对把缺的图补进库(repaired) 否则「判定不完整→重爬→后端跳过」会形成死循环,带宽白花、缺图永远补不上 四、租约 900→300 秒,且心跳算存活 只看 locked_at 会把跑了几小时的全量抓取误判成卡死; 加上 progress_at 后,真卡住 5 分钟才回收。
This commit is contained in:
134
internal/handler/templates/pages/spider.html
Normal file
134
internal/handler/templates/pages/spider.html
Normal file
@ -0,0 +1,134 @@
|
||||
{{define "title"}}爬虫 · 管理后台{{end}}
|
||||
{{define "barLabel"}}管理后台 · 爬虫{{end}}
|
||||
{{define "barRight"}}<a href="/admin/brands">去品牌管理加任务</a> · <a href="/admin/logout">退出</a>{{end}}
|
||||
{{define "content"}}
|
||||
{{template "bar" .}}
|
||||
<div class="main">
|
||||
<h1>爬虫</h1>
|
||||
<p class="muted">
|
||||
这里看「爬虫现在在干什么」:<strong>正在抓</strong>是当下,
|
||||
<strong>待抓队列</strong>是排队等着的品牌,
|
||||
<strong>最近入库结果</strong>是后端已经处理完的场次。
|
||||
</p>
|
||||
<p class="muted">
|
||||
入队请去<a href="/admin/brands">品牌管理</a>勾选品牌。抓取一律全量,
|
||||
已经抓全的场次会被自动跳过,不会重复下载。
|
||||
</p>
|
||||
|
||||
<p class="muted" id="spider-status">
|
||||
爬虫 <span class="badge {{.StateClass}}" id="st-state">{{.State}}</span>
|
||||
· 正在抓 <strong id="st-running">{{.RunningCount}}</strong> 个
|
||||
· 队列 <strong id="st-queued">{{.QueuedCount}}</strong> 个
|
||||
· 待入库 <strong id="st-pending">{{.PendingIngest}}</strong> 条
|
||||
</p>
|
||||
|
||||
<h2>正在抓</h2>
|
||||
<table>
|
||||
<thead><tr><th>品牌</th><th>进度</th><th>心跳</th><th>Worker</th></tr></thead>
|
||||
<tbody id="running-body">
|
||||
{{range .Running}}<tr>
|
||||
<td><strong>{{.BrandName}}</strong></td>
|
||||
<td class="progress{{if .Stale}} stale{{end}}">{{if .Progress}}{{.Progress}}{{else}}刚领取,正在拉取秀列表…{{end}}</td>
|
||||
<td class="muted{{if .Stale}} stale{{end}}">{{.Beat}}前</td>
|
||||
<td class="muted">{{.Worker}}</td>
|
||||
</tr>{{end}}
|
||||
{{if not .Running}}<tr id="running-empty"><td colspan="4" class="muted">当前没有正在抓取的任务。</td></tr>{{end}}
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
<h2>待抓队列({{.QueuedCount}})</h2>
|
||||
<table>
|
||||
<thead><tr><th>品牌</th><th>入队时间</th><th>已等待</th></tr></thead>
|
||||
<tbody>
|
||||
{{range .Queued}}<tr>
|
||||
<td>{{.BrandName}}</td>
|
||||
<td class="muted">{{.Since}}</td>
|
||||
<td class="muted">{{.Waiting}}</td>
|
||||
</tr>{{end}}
|
||||
{{if not .Queued}}<tr><td colspan="3" class="muted">队列为空。</td></tr>{{end}}
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
<h2>最近入库结果</h2>
|
||||
<p class="muted">最近 50 条。「已存在跳过」是正常状态——说明这场秀之前抓过,没有重复写库。</p>
|
||||
<table>
|
||||
<thead><tr><th>时间</th><th>品牌</th><th>场次</th><th>结果</th><th>说明</th></tr></thead>
|
||||
<tbody>
|
||||
{{range .Results}}<tr>
|
||||
<td class="muted">{{.At}}</td>
|
||||
<td>{{.BrandName}}</td>
|
||||
<td>{{.Title}}</td>
|
||||
<td>{{if .Bad}}<span class="badge failed">{{.Result}}</span>{{else}}<span class="badge done">{{.Result}}</span>{{end}}</td>
|
||||
<td class="err break">{{.Note}}</td>
|
||||
</tr>{{end}}
|
||||
{{if not .Results}}<tr><td colspan="5" class="muted">还没有入库记录。</td></tr>{{end}}
|
||||
</tbody>
|
||||
</table>
|
||||
</div>
|
||||
<script>
|
||||
// 抓取进度轮询:只刷新状态条与「正在抓」表格。
|
||||
//
|
||||
// 用 DOM API 建行而不是拼 innerHTML:品牌名来自数据库,直接拼字符串会把
|
||||
// 特殊字符当成标签解析(既会破版,也是一条注入面)。
|
||||
(function () {
|
||||
var body = document.getElementById('running-body');
|
||||
if (!body) return;
|
||||
|
||||
function cell(text, cls) {
|
||||
var td = document.createElement('td');
|
||||
td.textContent = text;
|
||||
if (cls) td.className = cls;
|
||||
return td;
|
||||
}
|
||||
|
||||
function paint(list) {
|
||||
while (body.firstChild) body.removeChild(body.firstChild);
|
||||
if (!list.length) {
|
||||
var tr0 = document.createElement('tr');
|
||||
var td0 = document.createElement('td');
|
||||
td0.colSpan = 4;
|
||||
td0.className = 'muted';
|
||||
td0.textContent = '当前没有正在抓取的任务。';
|
||||
tr0.appendChild(td0);
|
||||
body.appendChild(tr0);
|
||||
return;
|
||||
}
|
||||
list.forEach(function (it) {
|
||||
var tr = document.createElement('tr');
|
||||
|
||||
var tdBrand = document.createElement('td');
|
||||
var b = document.createElement('strong');
|
||||
b.textContent = it.brand || '—';
|
||||
tdBrand.appendChild(b);
|
||||
tr.appendChild(tdBrand);
|
||||
|
||||
tr.appendChild(cell(it.progress || '刚领取,正在拉取秀列表…', it.stale ? 'progress stale' : 'progress'));
|
||||
tr.appendChild(cell((it.beat || '0 秒') + '前', it.stale ? 'muted stale' : 'muted'));
|
||||
tr.appendChild(cell(it.worker || '—', 'muted'));
|
||||
body.appendChild(tr);
|
||||
});
|
||||
}
|
||||
|
||||
function tick() {
|
||||
fetch('/admin/spider/live', { credentials: 'same-origin' })
|
||||
.then(function (r) { return r.ok ? r.json() : null; })
|
||||
.then(function (d) {
|
||||
if (!d) return;
|
||||
var st = document.getElementById('st-state');
|
||||
if (st) { st.textContent = d.state; st.className = 'badge ' + d.state_class; }
|
||||
var rn = document.getElementById('st-running');
|
||||
if (rn) rn.textContent = (d.running || []).length;
|
||||
var qn = document.getElementById('st-queued');
|
||||
if (qn) qn.textContent = d.queued;
|
||||
var pn = document.getElementById('st-pending');
|
||||
if (pn) pn.textContent = d.pending_ingest;
|
||||
paint(d.running || []);
|
||||
})
|
||||
.catch(function () { /* 网络抖动忽略,下一轮再拉 */ });
|
||||
}
|
||||
|
||||
setInterval(tick, 4000);
|
||||
tick();
|
||||
})();
|
||||
</script>
|
||||
{{end}}
|
||||
Reference in New Issue
Block a user