v1.0.2: 自动爬取试爬取功能 + 每个页面/图片生成操作信息元数据(模式/时间/网址/来源链接/深度等)

README.md

@@ -45,12 +45,19 @@
 
 ### 4. 自动爬取模式
 给定一个起始网址，系统自动从页面里发现链接、按规则筛选后 BFS 爬取：
+- **🧪 试爬取**：先用起始网址试跑一次，展示规则筛选后的链接清单（将爬取哪些、排除哪些及原因），确认规则符合预期后再正式开爬
 - **包含规则**：只爬包含指定子串（或正则）的链接
 - **排除规则**：跳过匹配的链接（如 login、/tag/）
 - **仅同域名**：限制在起始网站内
 - **最大页数 / 最大深度**：控制爬取规模
 - 其余参数（间隔、重试、图片、通知）同批量模式
 
+### 5. 资源操作信息（元数据）
+每个爬取的网页和图片都自动生成 `.meta.json` 操作信息文件：
+- **网页**（`<文件名>.meta.json`）：爬取模式（批量/定时/自动）、爬取时间、爬取网址、**来源链接**（自动模式下从哪个页面发现）、爬取深度、任务/运行 ID、页面标题、状态、尝试次数、文件列表、图片明细
+- **图片集**（`<文件名>_img/meta.json`）：所属页面、来源链接、每张图片的原始 URL / 大小 / 下载时间
+- 详情页结果表中点「📋 元数据」即可在线查看
+
 ## 输出文件
 
 每个任务输出到独立目录（默认 `out/<任务ID>/`）：
@@ -69,6 +76,8 @@
 | POST | `/api/tasks/<id>/pause` | 暂停 |
 | POST | `/api/tasks/<id>/resume` | 恢复 |
 | POST | `/api/tasks/<id>/stop` | 终止 |
+| POST | `/api/probe` | 试爬取（表单规则预览链接清单） |
+| POST | `/api/tasks/<id>/probe` | 对已保存的自动任务试爬取 |
 | GET | `/api/runs/<rid>` | 运行详情（结果+日志） |
 | GET | `/api/runs/<rid>/logs?offset=N` | 增量日志 |
 | GET | `/api/file?task_id=&path=` | 读取输出文件（HTML/TXT/图片） |

app.py

@@ -10,7 +10,7 @@ from datetime import datetime
 from flask import Flask, jsonify, request, send_file, send_from_directory
 
 import store
-from engine import CrawlJob
+from engine import CrawlJob, probe_links
 from scheduler import Scheduler, cron_next, interval_delta
 
 HERE = os.path.dirname(os.path.abspath(__file__))
@@ -337,6 +337,48 @@ def api_stats():
     })
 
 
+# ---------------- API: 试爬取 ----------------
+
+@app.route("/api/probe", methods=["POST"])
+def api_probe():
+    """试爬取: 按表单给出的规则探测起始页, 返回将爬取的链接清单"""
+    body = request.get_json(force=True) or {}
+    seed = (body.get("seed_url") or "").strip()
+    if not seed:
+        return jsonify({"error": "请填写起始网址"}), 400
+    if not seed.startswith("http"):
+        seed = "https://" + seed
+    result = probe_links(
+        seed,
+        include=[x.strip() for x in (body.get("include") or []) if x.strip()],
+        exclude=[x.strip() for x in (body.get("exclude") or []) if x.strip()],
+        same_domain=body.get("same_domain", True),
+        use_regex=bool(body.get("use_regex", False)),
+        timeout=int(body.get("timeout") or 45),
+    )
+    return jsonify(result)
+
+
+@app.route("/api/tasks/<tid>/probe", methods=["POST"])
+def api_task_probe(tid):
+    """对已保存的自动任务执行试爬取 (使用保存的规则)"""
+    task = store.get_task(tid)
+    if not task:
+        return jsonify({"error": "任务不存在"}), 404
+    if task.get("mode") != "auto":
+        return jsonify({"error": "仅自动爬取任务支持试爬取"}), 400
+    auto = task.get("auto", {})
+    result = probe_links(
+        auto.get("seed_url", ""),
+        include=auto.get("include", []),
+        exclude=auto.get("exclude", []),
+        same_domain=auto.get("same_domain", True),
+        use_regex=bool(auto.get("use_regex", False)),
+        timeout=int((task.get("config") or {}).get("timeout", 60)),
+    )
+    return jsonify(result)
+
+
 # ---------------- API: 运行记录与文件 ----------------
 
 @app.route("/api/runs/<rid>")

engine.py

@@ -3,6 +3,8 @@
 通用爬虫引擎 (Playwright + stealth + 系统 Chrome)
 - 批量模式: 逐条爬取网址列表
 - 自动模式: 从起始网址按匹配规则自动发现链接并 BFS 爬取
+- 试爬取: 仅抓取起始页, 列出按规则将爬取的链接(不保存文件)
+- 每个页面/图片生成 .meta.json 操作信息(模式/时间/网址/来源链接/深度等)
 - 支持: 随机延迟 / 重试 / 图片下载 / 暂停恢复 / 终止 / 配置热更新 / cookie 复用
 """
 import json
@@ -40,7 +42,6 @@ def is_challenge_page(title, html):
     for mark in _CHALLENGE_MARKS:
         if mark in t or mark in low:
             return True
-    # 极小页面 + 无正文结构 -> 疑似验证壳
     if len(html) < 5000 and ("<article" not in low and "<main" not in low):
         return True
     return False
@@ -52,6 +53,122 @@ def safe_name(url, idx):
     return f"{idx:04d}_{host}_{ts}"
 
 
+def _settle_wait(page, timeout_s):
+    """等待页面稳定(无 stop/pause 检查, 供试爬取等独立流程使用)"""
+    last_title, stable = "", 0
+    start = time.time()
+    while time.time() - start < timeout_s:
+        time.sleep(1)
+        try:
+            title = page.title()
+            html = page.content()
+        except Exception:
+            continue
+        if is_challenge_page(title, html):
+            stable = 0
+            continue
+        if title == last_title:
+            stable += 1
+            if stable >= 2 and len(html) > 1000:
+                return True, title, html
+        else:
+            stable = 0
+        last_title = title
+    return True, page.title(), page.content()
+
+
+def filter_links(hrefs, seed_url, include=None, exclude=None,
+                 same_domain=True, use_regex=False):
+    """按规则过滤链接, 返回 (included, excluded); excluded 含排除原因"""
+    include = include or []
+    exclude = exclude or []
+    included, excluded = [], []
+    seed_host = urllib.parse.urlparse(seed_url).hostname or ""
+    for h in hrefs:
+        if not str(h).startswith("http"):
+            continue
+        if same_domain and seed_host:
+            host = urllib.parse.urlparse(h).hostname or ""
+            if host != seed_host and not host.endswith("." + seed_host):
+                excluded.append({"url": h, "reason": "不在同域名内"})
+                continue
+        if use_regex:
+            if include and not any(re.search(p, h) for p in include):
+                excluded.append({"url": h, "reason": "未匹配包含规则"})
+                continue
+            hit = next((p for p in exclude if re.search(p, h)), None)
+            if hit:
+                excluded.append({"url": h, "reason": f"命中排除规则: {hit}"})
+                continue
+        else:
+            if include and not any(p.lower() in h.lower() for p in include):
+                excluded.append({"url": h, "reason": "未匹配包含规则"})
+                continue
+            hit = next((p for p in exclude if p.lower() in h.lower()), None)
+            if hit:
+                excluded.append({"url": h, "reason": f"命中排除规则: {hit}"})
+                continue
+        included.append(h)
+    return included, excluded
+
+
+def probe_links(seed_url, include=None, exclude=None,
+                same_domain=True, use_regex=False, timeout=45):
+    """试爬取: 抓取起始页并列出按规则将爬取的链接 (不保存任何文件)"""
+    result = {"ok": False, "error": "", "seed_url": seed_url, "title": "",
+              "crawled_at": "", "total_links": 0,
+              "total_included": 0, "total_excluded": 0,
+              "included": [], "excluded": []}
+    try:
+        p = sync_playwright().start()
+        browser = p.chromium.launch(
+            headless=True, executable_path=CHROME,
+            args=["--disable-blink-features=AutomationControlled",
+                  "--no-sandbox", "--disable-gpu", "--disable-dev-shm-usage"],
+        )
+        ctx = browser.new_context(
+            user_agent=DEFAULT_UA,
+            viewport={"width": 1920, "height": 1080},
+            locale="en-US",
+        )
+        Stealth().apply_stealth_sync(ctx)
+        page = ctx.new_page()
+        try:
+            page.goto(seed_url, wait_until="domcontentloaded", timeout=timeout * 1000)
+            _ok, title, html = _settle_wait(page, timeout)
+            if is_challenge_page(title, html):
+                result["error"] = f"起始页被反爬拦截: title={title!r}"
+            else:
+                try:
+                    hrefs = page.evaluate(
+                        "() => Array.from(document.querySelectorAll('a[href]')).map(a => a.href)"
+                    )
+                except Exception:
+                    hrefs = []
+                included, excluded = filter_links(
+                    hrefs, seed_url, include, exclude, same_domain, use_regex)
+                result.update(
+                    ok=True, title=title, crawled_at=store.now_str(),
+                    total_links=len(hrefs),
+                    total_included=len(included), total_excluded=len(excluded),
+                    included=included[:200], excluded=excluded[:200],
+                )
+        except Exception as e:
+            result["error"] = f"试爬取失败: {e}"
+        finally:
+            try:
+                browser.close()
+            except Exception:
+                pass
+            try:
+                p.stop()
+            except Exception:
+                pass
+    except Exception as e:
+        result["error"] = f"浏览器启动失败: {e}"
+    return result
+
+
 class CrawlJob:
     """一次爬取执行 (独立线程运行)"""
 
@@ -195,8 +312,8 @@ class CrawlJob:
             text = ""
         return title, html, text
 
-    def _crawl_images(self, ctx, page, out_dir, base):
+    def _crawl_images(self, ctx, page, out_dir, base, page_url, source_url):
-        """下载页面图片, 返回 [{file, url, size}]"""
+        """下载页面图片并生成图片集 meta.json, 返回 [{file,url,size,download_time}]"""
         try:
             urls = page.evaluate(
                 "() => Array.from(document.querySelectorAll('img'))"
@@ -222,26 +339,78 @@ class CrawlJob:
                     os.makedirs(img_dir, exist_ok=True)
                     with open(os.path.join(img_dir, fname), "wb") as f:
                         f.write(resp.body())
-                    saved.append({"file": f"{base}_img/{fname}", "url": u, "size": len(resp.body())})
+                    saved.append({
+                        "file": f"{base}_img/{fname}", "url": u,
+                        "size": len(resp.body()), "download_time": store.now_str(),
+                    })
             except Exception:
                 continue
+        if saved:
+            try:
+                meta = {
+                    "type": "images",
+                    "mode": self.run.get("mode"),
+                    "task_id": self.task["id"],
+                    "task_name": self.task.get("name", ""),
+                    "run_id": self.run.get("id"),
+                    "crawl_time": store.now_str(),
+                    "page_url": page_url,
+                    "source_url": source_url,
+                    "images": saved,
+                }
+                with open(os.path.join(img_dir, "meta.json"), "w", encoding="utf-8") as f:
+                    json.dump(meta, f, ensure_ascii=False, indent=2)
+            except Exception:
+                pass
         return saved
 
-    def _retry_crawl(self, page, ctx, url, idx, out_dir):
+    def _write_page_meta(self, out_dir, base, entry):
-        """带重试的单页爬取, 返回结果 entry"""
+        """为每个爬取页面生成操作信息 meta.json"""
+        meta = {
+            "type": "page",
+            "mode": self.run.get("mode"),
+            "task_id": self.task["id"],
+            "task_name": self.task.get("name", ""),
+            "run_id": self.run.get("id"),
+            "crawl_time": entry.get("crawl_time", ""),
+            "url": entry.get("url", ""),
+            "source_url": entry.get("source_url", ""),
+            "depth": entry.get("depth"),
+            "title": entry.get("title", ""),
+            "status": entry.get("status", ""),
+            "error": entry.get("error", ""),
+            "attempts": entry.get("attempts", 1),
+            "html_file": entry.get("html_file", ""),
+            "txt_file": entry.get("txt_file", ""),
+            "images": entry.get("images", []),
+        }
+        try:
+            with open(os.path.join(out_dir, base + ".meta.json"), "w", encoding="utf-8") as f:
+                json.dump(meta, f, ensure_ascii=False, indent=2)
+        except Exception:
+            pass
+
+    def _retry_crawl(self, page, ctx, url, idx, out_dir, source_url="", depth=None):
+        """带重试的单页爬取, 返回结果 entry (含 meta 信息)"""
         timeout = int(self._cfg("timeout", 60))
         retries = int(self._cfg("retry_count", 2))
         retry_wait = float(self._cfg("retry_interval", 3))
         crawl_images = bool(self._cfg("crawl_images", False))
 
-        entry = {"url": url, "title": "", "status": "FAIL", "error": "",
-                 "html_file": "", "txt_file": "", "images": []}
         base = safe_name(url, idx)
+        entry = {
+            "url": url, "title": "", "status": "FAIL", "error": "",
+            "html_file": "", "txt_file": "", "meta_file": base + ".meta.json",
+            "crawl_time": store.now_str(),
+            "source_url": source_url, "depth": depth,
+            "images": [], "attempts": 0,
+        }
         for attempt in range(retries + 1):
             if self._stop.is_set():
                 entry["error"] = "任务已终止"
                 break
             self._wait_if_paused()
+            entry["attempts"] += 1
             try:
                 title, html, text = self._crawl_one(page, url, timeout)
                 html_path = os.path.join(out_dir, base + ".html")
@@ -251,13 +420,15 @@ class CrawlJob:
                 with open(txt_path, "w", encoding="utf-8") as f:
                     f.write(text)
                 entry.update(title=title, status="OK",
-                             html_file=base + ".html", txt_file=base + ".txt")
+                             html_file=base + ".html", txt_file=base + ".txt",
+                             error="", crawl_time=store.now_str())
                 if crawl_images:
-                    entry["images"] = self._crawl_images(ctx, page, out_dir, base)
+                    entry["images"] = self._crawl_images(ctx, page, out_dir, base, url, source_url)
                 self._log("info", f"OK {title[:50]!r} html={len(html)//1024}KB 图片={len(entry['images'])}")
                 break
             except Exception as e:
                 entry["error"] = str(e)
+                entry["crawl_time"] = store.now_str()
                 self._log("warn", f"第{attempt + 1}次失败 {url}: {e}")
                 if attempt < retries:
                     self._wait_if_paused()
@@ -267,6 +438,7 @@ class CrawlJob:
                             break
                         self._wait_if_paused()
                         time.sleep(0.3)
+        self._write_page_meta(out_dir, base, entry)
         return entry
 
     def _delay(self):
@@ -317,7 +489,6 @@ class CrawlJob:
                     self._log("error", f"邮件通知失败: {msg}")
             except Exception as e:
                 self._log("error", f"邮件通知异常: {e}")
-                self._persist()
         self._log("info", f"任务结束: {run['status']} 成功{run['stats'].get('ok', 0)} 失败{run['stats'].get('fail', 0)}")
         self._persist()
 
@@ -353,37 +524,18 @@ class CrawlJob:
     def _discover_links(self, page):
         """从当前页面提取符合规则的链接"""
         auto = self.task.get("auto", {})
-        include = [x.strip() for x in (auto.get("include") or []) if x.strip()]
-        exclude = [x.strip() for x in (auto.get("exclude") or []) if x.strip()]
-        use_regex = bool(auto.get("use_regex", False))
-        same_domain = auto.get("same_domain", True)
-        seed_host = urllib.parse.urlparse(auto.get("seed_url", "")).hostname or ""
         try:
             hrefs = page.evaluate(
                 "() => Array.from(document.querySelectorAll('a[href]')).map(a => a.href)"
             )
         except Exception:
             return []
-        out = []
+        included, _excluded = filter_links(
-        for h in hrefs:
+            hrefs, auto.get("seed_url", ""),
-            if not str(h).startswith("http"):
+            auto.get("include", []), auto.get("exclude", []),
-                continue
+            auto.get("same_domain", True), bool(auto.get("use_regex", False)),
-            if same_domain and seed_host:
+        )
-                host = urllib.parse.urlparse(h).hostname or ""
+        return included
-                if host != seed_host and not host.endswith("." + seed_host):
-                    continue
-            if use_regex:
-                if include and not any(re.search(p, h) for p in include):
-                    continue
-                if any(re.search(p, h) for p in exclude):
-                    continue
-            else:
-                if include and not any(p.lower() in h.lower() for p in include):
-                    continue
-                if any(p.lower() in h.lower() for p in exclude):
-                    continue
-            out.append(h)
-        return out
 
     def _crawl_auto(self):
         run = self.run
@@ -398,14 +550,14 @@ class CrawlJob:
         self._persist()
 
         p, browser, ctx, page, cookie_file = self._open_browser()
-        queue = [(seed, 0)]
+        queue = [(seed, 0, "")]               # (url, depth, 来源链接)
         visited = set()
         queued = set([seed])
         idx = 0
         try:
             while queue and not self._stop.is_set():
                 self._wait_if_paused()
-                url, depth = queue.pop(0)
+                url, depth, src = queue.pop(0)
                 if url in visited:
                     continue
                 if len(visited) >= max_pages:
@@ -415,7 +567,8 @@ class CrawlJob:
                 run["progress"]["current_url"] = url
                 run["progress"]["done"] = len(visited)
                 self._persist()
-                entry = self._retry_crawl(page, ctx, url, idx, out_dir)
+                entry = self._retry_crawl(page, ctx, url, idx, out_dir,
+                                          source_url=src, depth=depth)
                 run["results"].append(entry)
                 self._bump_stats(entry)
                 self._persist()
@@ -423,7 +576,7 @@ class CrawlJob:
                     for link in self._discover_links(page):
                         if link not in visited and link not in queued:
                             queued.add(link)
-                            queue.append((link, depth + 1))
+                            queue.append((link, depth + 1, url))
                 if entry["status"] == "OK":
                     self._delay()
         finally:

static/app.js

@@ -359,6 +359,7 @@ 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>` : ""}
       <button class="btn" onclick="openEdit('${t.id}')">✏️ 编辑配置</button>
     </div>`;
 
@@ -389,13 +390,18 @@ function renderRunPanel(t, run) {
     const txt = r.txt_file ? `<span class="file-link" onclick="previewFile('${t.id}','${esc(r.txt_file)}','文本: ${esc(r.url)}')">TXT</span>` : "—";
     const imgs = (r.images || []).length
       ? `<span class="file-link" onclick="scrollThumbs()">🖼️ ${(r.images || []).length}</span>` : "—";
+    const ctime = r.crawl_time ? `<span title="${esc(r.crawl_time)}">${esc(r.crawl_time.slice(5, 19))}</span>` : "—";
+    const meta = r.meta_file
+      ? `<span class="file-link" onclick="showMeta('${t.id}','${esc(r.meta_file)}')">📋 元数据</span>` : "—";
     return `<tr>
       <td>${i + 1}</td>
       <td class="${statusCls}">${r.status}</td>
       <td class="title-cell" title="${esc(r.title)}">${esc(r.title)}</td>
       <td class="url-cell" title="${esc(r.url)}">${esc(r.url)}</td>
+      <td>${ctime}</td>
       <td>${html}</td><td>${txt}</td><td>${imgs}</td>
-      <td title="${esc(r.error || "")}">${esc((r.error || "").slice(0, 60))}</td>
+      <td>${meta}</td>
+      <td title="${esc(r.error || "")}">${esc((r.error || "").slice(0, 50))}</td>
     </tr>`;
   }).join("");
   const thumbs = results.flatMap((r) => r.images || []).slice(0, 60);
@@ -421,7 +427,7 @@ function renderRunPanel(t, run) {
     ${results.length ? `
       <div class="table-wrap">
         <table>
-          <thead><tr><th>#</th><th>状态</th><th>标题</th><th>网址</th><th>HTML</th><th>TXT</th><th>图片</th><th>错误</th></tr></thead>
+          <thead><tr><th>#</th><th>状态</th><th>标题</th><th>网址</th><th>爬取时间</th><th>HTML</th><th>TXT</th><th>图片</th><th>元数据</th><th>错误</th></tr></thead>
           <tbody>${rows}</tbody>
         </table>
       </div>` : '<div class="card-line">暂无结果</div>'}
@@ -475,6 +481,120 @@ function stopLogPoll() {
   if (state.logTimer) { clearInterval(state.logTimer); state.logTimer = null; }
 }
 
+/* ---------------- 试爬取 ---------------- */
+function collectProbeFromForm() {
+  const f = $("taskForm");
+  return {
+    seed_url: f.elements["seed_url"].value.trim(),
+    include: splitLines(f.elements["include"].value),
+    exclude: splitLines(f.elements["exclude"].value),
+    same_domain: f.elements["same_domain"].checked,
+    use_regex: f.elements["use_regex"].checked,
+    timeout: parseInt(f.elements["timeout"].value) || 60,
+  };
+}
+
+async function runProbe(params, btn) {
+  if (btn) { btn.disabled = true; btn.textContent = "⏳ 探测中..."; }
+  try {
+    const r = await api("/api/probe", {
+      method: "POST", headers: { "Content-Type": "application/json" },
+      body: JSON.stringify(params),
+    });
+    renderProbe(r);
+  } catch (e) { toast(e.message, true); }
+  finally {
+    if (btn) { btn.disabled = false; btn.textContent = "🧪 试爬取"; }
+  }
+}
+
+async function probeTask(tid) {
+  try {
+    const r = await api(`/api/tasks/${tid}/probe`, { method: "POST" });
+    renderProbe(r);
+  } catch (e) { toast(e.message, true); }
+}
+
+function renderProbe(r) {
+  const body = $("probeBody");
+  if (!r.ok) {
+    body.innerHTML = `<div class="card-line">❌ ${esc(r.error || "试爬取失败")}</div>`;
+    showModal("probeModal");
+    return;
+  }
+  const included = r.included || [];
+  const excluded = r.excluded || [];
+  const incHtml = included.length
+    ? included.map((u) => `<div class="probe-item included"><span class="u">${esc(u)}</span></div>`).join("")
+    : '<div class="card-line">没有符合条件的链接，请调整规则</div>';
+  const excHtml = excluded.length
+    ? excluded.map((x) => `<div class="probe-item excluded"><span class="u">${esc(x.url)}</span><span class="reason">${esc(x.reason)}</span></div>`).join("")
+    : '<div class="card-line">无</div>';
+  const moreInc = r.total_included > included.length
+    ? `<div class="card-line">... 还有 ${r.total_included - included.length} 条未显示</div>` : "";
+  const moreExc = r.total_excluded > excluded.length
+    ? `<div class="card-line">... 还有 ${r.total_excluded - excluded.length} 条未显示</div>` : "";
+  body.innerHTML = `
+    <div class="probe-summary">
+      <span>页面标题: <b>${esc(r.title)}</b></span>
+      <span>抓取时间: <b>${esc(r.crawled_at)}</b></span>
+    </div>
+    <div class="probe-summary">
+      <span>发现链接: <b>${r.total_links}</b> 条</span>
+      <span class="t-ok">✅ 将爬取: <b>${r.total_included}</b> 条</span>
+      <span class="t-fail">🚫 被排除: <b>${r.total_excluded}</b> 条</span>
+    </div>
+    <div class="card-line" style="font-weight:600">✅ 符合规则、将爬取的链接（显示前 ${included.length} 条）:</div>
+    <div class="probe-list">${incHtml}${moreInc}</div>
+    <div class="card-line" style="font-weight:600;margin-top:8px">🚫 被排除的链接及原因（显示前 ${excluded.length} 条）:</div>
+    <div class="probe-list">${excHtml}${moreExc}</div>`;
+  showModal("probeModal");
+}
+
+/* ---------------- 元数据查看 ---------------- */
+const META_FIELDS = [
+  ["type", "资源类型"], ["mode", "爬取模式"], ["task_name", "任务名称"],
+  ["task_id", "任务ID"], ["run_id", "运行ID"], ["crawl_time", "爬取时间"],
+  ["url", "爬取网址"], ["source_url", "来源链接"], ["depth", "爬取深度"],
+  ["title", "页面标题"], ["status", "状态"], ["attempts", "尝试次数"],
+  ["error", "错误信息"], ["html_file", "HTML文件"], ["txt_file", "文本文件"],
+  ["page_url", "所属页面"],
+];
+
+async function showMeta(taskId, metaFile) {
+  try {
+    const data = await api(`/api/file?task_id=${taskId}&path=${encodeURIComponent(metaFile)}`);
+    const rows = META_FIELDS.filter(([k]) => data[k] !== undefined && data[k] !== "" && data[k] !== null)
+      .map(([k, label]) => {
+        let v = data[k];
+        if (k === "status") v = `<span class="${v === "OK" ? "t-ok" : "t-fail"}">${esc(v)}</span>`;
+        if (k === "mode") v = `<span class="badge ${esc(v)}">${MODE_LABEL[v] || esc(v)}</span>`;
+        if (k === "type") v = v === "images" ? "🖼️ 图片集" : "📄 网页";
+        if (k === "depth") v = v === 0 ? "0（起始页）" : esc(v);
+        return `<tr><td>${label}</td><td>${v}</td></tr>`;
+      }).join("");
+    // 来源链接空值也显示(起始页无来源)
+    const srcRow = `<tr><td>来源链接</td><td>${data.source_url ? esc(data.source_url) : "—（起始页，无来源）"}</td></tr>`;
+    const finalRows = rows.includes(srcRow) ? rows : rows + srcRow;
+    let imgs = "";
+    if (data.images && data.images.length) {
+      imgs = `
+        <div class="card-line" style="font-weight:600;margin-top:8px">🖼️ 图片明细（${data.images.length} 张）:</div>
+        <div class="table-wrap" style="max-height:200px">
+          <table><thead><tr><th>文件</th><th>原始URL</th><th>大小</th><th>下载时间</th></tr></thead><tbody>
+          ${data.images.map((im) => `<tr>
+            <td>${esc(im.file)}</td>
+            <td class="url-cell" title="${esc(im.url)}">${esc(im.url)}</td>
+            <td>${im.size ? Math.round(im.size / 1024) + " KB" : "—"}</td>
+            <td>${esc(im.download_time || "")}</td></tr>`).join("")}
+          </tbody></table>
+        </div>`;
+    }
+    $("metaBody").innerHTML = `<table class="meta-table"><tbody>${finalRows}</tbody></table>${imgs}`;
+    showModal("metaModal");
+  } catch (e) { toast(e.message, true); }
+}
+
 /* ---------------- 文件预览 ---------------- */
 function previewFile(tid, path, title) {
   $("previewTitle").textContent = title || "预览";
@@ -513,6 +633,11 @@ try {
 $("btnNew").onclick = openCreate;
 $("btnNew2").onclick = openCreate;
 $("btnRefresh").onclick = loadTasks;
+$("btnProbe").onclick = () => {
+  const p = collectProbeFromForm();
+  if (!p.seed_url) { toast("请先填写起始网址", true); return; }
+  runProbe(p, $("btnProbe"));
+};
 
 document.querySelectorAll("#modeTabs .tab").forEach((b) => {
   b.onclick = () => { switchMode(b.dataset.mode, false); };
@@ -523,6 +648,8 @@ $("taskForm").elements["schedule_type"].onchange = syncScheduleUI;
 document.querySelectorAll("[data-close]").forEach((b) => b.onclick = safeCloseTaskModal);
 document.querySelectorAll("[data-close-detail]").forEach((b) => b.onclick = () => { stopLogPoll(); hideModal("detailModal"); });
 document.querySelectorAll("[data-close-preview]").forEach((b) => b.onclick = () => { $("previewFrame").src = "about:blank"; hideModal("previewModal"); });
+document.querySelectorAll("[data-close-probe]").forEach((b) => b.onclick = () => hideModal("probeModal"));
+document.querySelectorAll("[data-close-meta]").forEach((b) => b.onclick = () => hideModal("metaModal"));
 
 /* 表单改动监听 -> 脏标记 */
 $("taskForm").addEventListener("input", () => { formDirty = true; });
@@ -549,7 +676,7 @@ document.addEventListener("keydown", (e) => {
     }
     stopLogPoll();
     $("previewFrame").src = "about:blank";
-    ["detailModal", "previewModal"].forEach((id) => $(id).classList.add("hidden"));
+    ["detailModal", "probeModal", "metaModal", "previewModal"].forEach((id) => $(id).classList.add("hidden"));
   }
 });
 

static/index.html

@@ -102,7 +102,11 @@
 
         <div id="autoBox" class="hidden box">
           <div class="field"><label>起始网址 *（系统将自动发现符合规则的链接并爬取）</label>
-            <input name="seed_url" placeholder="https://example.com/news"></div>
+            <div class="row2">
+              <input name="seed_url" placeholder="https://example.com/news" style="flex:1">
+              <button type="button" class="btn sm" id="btnProbe">🧪 试爬取</button>
+            </div>
+          </div>
           <div class="row2">
             <div class="field"><label>包含规则（每行一个，子串或正则）</label>
               <textarea name="include" rows="3" placeholder="techpowerup.com/review&#10;/news/"></textarea></div>
@@ -139,6 +143,28 @@
   </div>
 </div>
 
+<!-- 试爬取结果弹窗 -->
+<div id="probeModal" class="modal-overlay hidden">
+  <div class="modal wide">
+    <div class="modal-head">
+      <span>🧪 试爬取结果（规则筛选预览）</span>
+      <button class="btn ghost sm" data-close-probe>✕</button>
+    </div>
+    <div id="probeBody" class="detail-wrap"></div>
+  </div>
+</div>
+
+<!-- 元数据弹窗 -->
+<div id="metaModal" class="modal-overlay hidden">
+  <div class="modal">
+    <div class="modal-head">
+      <span>📋 资源操作信息（元数据）</span>
+      <button class="btn ghost sm" data-close-meta>✕</button>
+    </div>
+    <div id="metaBody" class="detail-wrap"></div>
+  </div>
+</div>
+
 <!-- 文件预览弹窗 -->
 <div id="previewModal" class="modal-overlay hidden">
   <div class="modal wide tall">

static/style.css

@@ -215,6 +215,21 @@ td.title-cell { max-width: 220px; overflow: hidden; text-overflow: ellipsis; }
 /* ---------- preview ---------- */
 #previewFrame { flex: 1; border: none; background: var(--preview-bg); border-radius: 0 0 14px 14px; }
 
+/* ---------- 试爬取结果 / 元数据 ---------- */
+.probe-summary { display: flex; flex-wrap: wrap; gap: 16px; font-size: 13px; }
+.probe-list {
+  border: 1px solid var(--border); border-radius: 8px; max-height: 260px;
+  overflow: auto; padding: 8px 12px; display: flex; flex-direction: column;
+  gap: 5px; font-size: 12px; background: var(--log-bg);
+}
+.probe-item { display: flex; gap: 10px; align-items: baseline; }
+.probe-item .u { color: var(--text); word-break: break-all; }
+.probe-item.included .u { color: var(--green); }
+.probe-item.excluded .u { color: var(--muted); text-decoration: line-through; }
+.probe-item .reason { color: var(--yellow); font-size: 11px; flex-shrink: 0; }
+.meta-table td { white-space: normal; word-break: break-all; }
+.meta-table td:first-child { width: 110px; color: var(--muted); }
+
 /* ---------- misc ---------- */
 .toast {
   position: fixed; top: 70px; left: 50%; transform: translateX(-50%);