v1.0.14: 自动爬取支持深度/页数无限制(默认0/1000), 待爬链接持久化缓存队列(停止后续爬), 起始网址不去重, 清空缓存API

static/app.js

@@ -434,7 +434,8 @@ async function openEdit(tid) {
     f.elements["exclude"].value = (t.auto.exclude || []).join("\n");
     f.elements["same_domain"].checked = t.auto.same_domain !== false;
     f.elements["use_regex"].checked = !!t.auto.use_regex;
-    f.elements["max_pages"].value = t.auto.max_pages ?? 200;
+    f.elements["max_pages"].value = t.auto.max_pages ?? 1000;
+    f.elements["max_depth"].value = t.auto.max_depth ?? 0;
   }
   syncScheduleUI();
   $("formHint").textContent = t.running
@@ -480,7 +481,8 @@ async function submitForm(e) {
       exclude: splitLines(f.elements["exclude"].value),
       same_domain: f.elements["same_domain"].checked,
       use_regex: f.elements["use_regex"].checked,
-      max_pages: parseInt(f.elements["max_pages"].value) || 200,
+      max_pages: parseInt(f.elements["max_pages"].value) || 0,
+      max_depth: parseInt(f.elements["max_depth"].value) || 0,
     };
   }
   if (mode === "scheduled") {
@@ -542,7 +544,10 @@ function renderDetail() {
       <span>任务ID: <b>${t.id}</b></span>
       <span>创建: <b>${fmtTime(t.created_at)}</b></span>
       <span>输出: <b>${esc(cfg.out_dir || "out/" + t.id)}</b></span>
-      ${t.mode === "auto" ? `<span>起始: <b>${esc((t.auto && t.auto.seed_url) || "")}</b></span>` : ""}
+      ${t.mode === "auto" ? `
+        <span>起始: <b>${esc((t.auto && t.auto.seed_url) || "")}</b></span>
+        <span>待爬缓存: <b>${(t.auto && (t.auto.pending || []).length) || 0}</b> 条（停止后可继续爬取）</span>
+        <span>已爬: <b>${(t.auto && (t.auto.visited || []).length) || 0}</b> 页</span>` : ""}
     </div>`;
 
   let sched = "";
@@ -563,7 +568,8 @@ function renderDetail() {
         <button class="btn" onclick="actTask('${t.id}','pause')">⏸ 暂停</button>
         <button class="btn danger" onclick="actTask('${t.id}','stop')">⏹ 终止</button>`
       : `<button class="btn primary" onclick="actTask('${t.id}','start')">▶ 立即执行</button>`}
-      ${t.mode === "auto" ? `<button class="btn" onclick="probeTask('${t.id}')">🧪 试爬取</button>` : ""}
+      ${t.mode === "auto" ? `<button class="btn" onclick="probeTask('${t.id}')">🧪 试爬取</button>
+        <button class="btn" ${t.running ? "disabled" : ""} onclick="clearCache('${t.id}')">🧹 清空缓存</button>` : ""}
       <button class="btn" onclick="openEdit('${t.id}')">✏️ 编辑配置</button>
     </div>`;
 
@@ -719,6 +725,15 @@ async function probeTask(tid) {
   } catch (e) { toast(e.message, true); }
 }
 
+async function clearCache(tid) {
+  if (!confirm("清空待爬缓存与已爬记录？\n下次运行将从起始网址重新开始爬取。")) return;
+  try {
+    const r = await api(`/api/tasks/${tid}/clear_cache`, { method: "POST" });
+    toast(r.msg || "已清空");
+    openDetail(tid);
+  } catch (e) { toast(e.message, true); }
+}
+
 function renderProbe(r) {
   const body = $("probeBody");
   if (!r.ok) {

static/index.html

@@ -132,8 +132,12 @@
             <div class="field check"><label><input name="same_domain" type="checkbox" checked> 仅爬同域名</label></div>
             <div class="field check"><label><input name="use_regex" type="checkbox"> 规则按正则匹配</label></div>
           </div>
-          <div class="field"><label>最大页数（安全上限，达到后自动停止；不设深度限制，会一直递归爬取到无新链接可爬为止）</label>
-            <input name="max_pages" type="number" value="200"></div>
+          <div class="row2">
+            <div class="field"><label>最大爬取深度（0=无限制，N=只爬 N 层）</label>
+              <input name="max_depth" type="number" min="0" value="0"></div>
+            <div class="field"><label>最大页数（0=无限制，默认 1000 作安全上限）</label>
+              <input name="max_pages" type="number" min="0" value="1000"></div>
+          </div>
         </div>
       </div>
       <div class="modal-foot">