v1.0.11: 新增历史记录回填脚本 backfill.py(幂等, 支持指定任务), 补齐数据库功能上线前的爬取记录

README.md

@@ -23,6 +23,7 @@
 
 ### 1. 前端管理界面
 - **总体统计区**：任务总数 / 运行中 / 累计运行次数 / 成功失败页面 / 图片数 / 磁盘占用
+- **🔍 基本搜索**：顶部搜索框，按网址 / 标题 / 任务名即时查找已爬内容，可直接预览文件、查看元数据、跳转任务详情
 - **🗑️ 回收站**：删除的任务统一进回收站（可恢复）；只有手动在回收站中才能彻底删除或清空，防止误删
 - **日间/夜间双主题**：右上角按钮一键切换，自动记忆选择
 - 任务卡片总览：状态、进度、统计、下次调度时间一目了然
@@ -32,7 +33,10 @@
 - 运行中的任务参数支持**热更新**（修改后从下一页起生效）
 
 ### 2. 批量爬取模式
-一次粘贴多个网址（每行一个，`#` 注释），可配置：
+一次粘贴多个网址（每行一个，`#` 注释），或点击「📂 导入网址文件」上传 .txt 文件批量导入：
+- **处理方式可选**：追加（保留已有，默认）或覆盖（清空已有）
+- 自动识别 UTF-8/GBK 编码、自动去重、自动清理行内注释
+可配置：
 - 项目名称、输出目录（默认 `out/<任务ID>`，可填绝对路径）
 - 爬取间隔（随机秒数区间，防封 IP）、单页超时
 - 失败重试次数 / 重试间隔
@@ -59,6 +63,13 @@
 - **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
 
+### 6. 数据库记录（MySQL）
+任务、运行记录、爬取结果实时写入 MySQL（`121.40.164.32:16006`，账号 `uni_crawler`，库 `uni_crawler`），**网页完整内容不入库**（存磁盘文件），库中只存标题、网址、状态、文件路径等元数据：
+- `crawl_tasks` — 任务信息（含回收站标记 deleted_at）
+- `crawl_runs` — 每次运行记录（状态/进度/成功失败数/图片数/时间）
+- `crawl_results` — 每页一条（**status: OK/FAIL** 成功失败标记、标题、网址、来源链接、深度、错误信息、文件路径、图片数）
+- 数据库不可用时自动降级，不影响爬取主流程；删除任务进回收站同步标记，彻底删除同步清库
+
 ## 输出文件
 
 每个任务输出到独立目录（默认 `out/<任务ID>/`）：
@@ -78,6 +89,7 @@
 | POST | `/api/tasks/<id>/resume` | 恢复 |
 | POST | `/api/tasks/<id>/stop` | 终止 |
 | GET | `/api/trash` | 回收站列表 |
+| GET | `/api/search?q=` | 基本搜索（网址/标题/任务名子串匹配，轻量） |
 | POST | `/api/trash/<id>/restore` | 从回收站恢复任务 |
 | DELETE | `/api/trash/<id>` | 彻底删除单个（默认输出目录一并清理） |
 | DELETE | `/api/trash` | 清空回收站 |

app.py

@@ -10,6 +10,7 @@ from datetime import datetime
 from flask import Flask, jsonify, request, send_file, send_from_directory
 
 import store
+import db
 from engine import CrawlJob, probe_links
 from scheduler import Scheduler, cron_next, interval_delta
 
@@ -93,6 +94,10 @@ def persist_cb(task_id, run):
     done = run["progress"].get("done") or 0
     run["progress"]["percent"] = round(done * 100 / total) if total else 0
     store.save_run(task_id, run)
+    try:
+        db.sync_run(run, lambda tid, r: store.save_run(tid, r))
+    except Exception as e:
+        print(f"[db] 同步失败: {e}", flush=True)
 
 
 def start_run(task):
@@ -106,6 +111,7 @@ def start_run(task):
         job = CrawlJob(task, run, persist_cb)
         JOBS[task["id"]] = job
         job.start()
+        db.upsert_task(task)              # 确保任务在库中
         return run, None
 
 
@@ -154,6 +160,19 @@ def api_tasks():
     return jsonify(tasks)
 
 
+def _clean_urls(lines):
+    """清洗网址行: 去空白, 去行内 # 注释 (URL 本身不含空格, 安全), 自动补 https 前缀"""
+    out = []
+    for u in lines or []:
+        u = str(u).split(" #")[0].strip()
+        if not u:
+            continue
+        if not u.startswith("http"):
+            u = "https://" + u
+        out.append(u)
+    return out
+
+
 @app.route("/api/tasks", methods=["POST"])
 def api_create_task():
     body = request.get_json(force=True) or {}
@@ -171,7 +190,7 @@ def api_create_task():
         "created_at": now_str(),
         "updated_at": now_str(),
         "config": {**DEFAULT_CONFIG, **(body.get("config") or {})},
-        "urls": [u.strip() for u in (body.get("urls") or []) if u.strip()],
+        "urls": _clean_urls(body.get("urls") or []),
     }
 
     if mode == "auto":
@@ -201,6 +220,7 @@ def api_create_task():
             return jsonify({"error": "请至少填写一个网址"}), 400
 
     store.upsert_task(task)
+    db.upsert_task(task)
     return jsonify(task), 201
 
 
@@ -230,7 +250,7 @@ def api_update_task(tid):
         if "name" in body and str(body["name"]).strip():
             task["name"] = str(body["name"]).strip()
         if "urls" in body:
-            task["urls"] = [u.strip() for u in body["urls"] if u.strip()]
+            task["urls"] = _clean_urls(body["urls"])
         if "config" in body:
             merged = {**task.get("config", {}), **body["config"]}
             task["config"] = merged
@@ -247,6 +267,7 @@ def api_update_task(tid):
             task["schedule"] = sch
         task["updated_at"] = now_str()
         store.upsert_task(task)
+        db.upsert_task(task)
     return jsonify(task)
 
 
@@ -262,6 +283,7 @@ def api_delete_task(tid):
     with JOBS_LOCK:
         JOBS.pop(tid, None)
     store.soft_delete_task(tid, now_str())
+    db.upsert_task(store.get_task(tid))
     return jsonify({"ok": True, "msg": "已移入回收站"})
 
 
@@ -296,6 +318,7 @@ def api_trash_restore(tid):
     if not task or not task.get("deleted_at"):
         return jsonify({"error": "任务不在回收站中"}), 404
     store.restore_task(tid)
+    db.upsert_task(store.get_task(tid))
     return jsonify({"ok": True, "msg": "已恢复"})
 
 
@@ -307,6 +330,7 @@ def api_trash_purge(tid):
     out_dir = resolve_out_dir(task)
     removed = _purge_out_dir(out_dir)
     store.purge_task(tid)
+    db.purge_task_db(tid)
     return jsonify({"ok": True, "purged": True, "files_removed": removed, "out_dir": out_dir})
 
 
@@ -315,6 +339,7 @@ def api_trash_clear():
     items = store.list_trash()
     dirs = [resolve_out_dir(t) for t in items]
     store.purge_trash()
+    db.purge_trash_db()
     removed = sum(1 for d in dirs if _purge_out_dir(d))
     return jsonify({"ok": True, "purged": len(items), "dirs_removed": removed})
 
@@ -443,6 +468,69 @@ def api_task_probe(tid):
     return jsonify(result)
 
 
+# ---------------- API: 搜索 ----------------
+
+@app.route("/api/search")
+def api_search():
+    """基本搜索: 对任务名/网址/标题做子串匹配 (仅遍历本地内存数据, 轻量)"""
+    q = (request.args.get("q") or "").strip()
+    if not q:
+        return jsonify({"q": q, "count": 0, "results": []})
+    ql = q.lower()
+    results = []
+    seen = set()
+    for task in store.load_tasks():
+        if task.get("deleted_at"):
+            continue                       # 回收站任务不参与搜索
+        auto = task.get("auto") or {}
+        task_hit = (
+            ql in (task.get("name") or "").lower()
+            or any(ql in u.lower() for u in task.get("urls", []))
+            or ql in ((auto.get("seed_url") or "").lower())
+        )
+        for run in store.get_runs(task["id"]):
+            for r in run.get("results", []):
+                url = r.get("url") or ""
+                title = r.get("title") or ""
+                if ql not in url.lower() and ql not in title.lower():
+                    continue
+                key = (task["id"], run.get("id"), url)
+                if key in seen:
+                    continue
+                seen.add(key)
+                results.append({
+                    "type": "page",
+                    "task_id": task["id"],
+                    "task_name": task.get("name", ""),
+                    "mode": task.get("mode", ""),
+                    "run_id": run.get("id", ""),
+                    "run_status": run.get("status", ""),
+                    "url": url,
+                    "title": title,
+                    "status": r.get("status", ""),
+                    "crawl_time": r.get("crawl_time", ""),
+                    "html_file": r.get("html_file", ""),
+                    "txt_file": r.get("txt_file", ""),
+                    "meta_file": r.get("meta_file", ""),
+                    "images": len(r.get("images", []) or []),
+                })
+                if len(results) >= 100:
+                    break
+            if len(results) >= 100:
+                break
+        if task_hit and len(results) < 100:
+            results.append({
+                "type": "task",
+                "task_id": task["id"],
+                "task_name": task.get("name", ""),
+                "mode": task.get("mode", ""),
+                "urls_count": len(task.get("urls", [])),
+                "created_at": task.get("created_at", ""),
+                "seed_url": auto.get("seed_url", ""),
+            })
+    return jsonify({"q": q, "count": len(results), "results": results})
+
+
 # ---------------- API: 运行记录与文件 ----------------
 
 @app.route("/api/runs/<rid>")
@@ -487,6 +575,10 @@ scheduler = Scheduler(start_run)
 def main():
     os.makedirs(os.path.join(HERE, "data"), exist_ok=True)
     os.makedirs(os.path.join(HERE, "out"), exist_ok=True)
+    db.init_db()
+    # 全量同步存量任务到数据库
+    for t in store.load_tasks():
+        db.upsert_task(t)
     scheduler.start()
     print(f"[universal-crawler] 启动完成, 管理界面: http://0.0.0.0:{PORT}/")
     app.run(host="0.0.0.0", port=PORT, threaded=True, debug=False)

backfill.py

@@ -0,0 +1,26 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+历史爬取记录回填数据库 (幂等, 可重复执行)
+
+用法:
+    python backfill.py                  # 回填所有任务的历史记录
+    python backfill.py <task_id> ...    # 只回填指定任务
+
+说明:
+    - 将本地 data/ 中的任务/运行/爬取结果(含成功与失败)全量写入 MySQL
+    - 网页内容不入库, 只写元数据; 重复执行不会产生重复记录
+"""
+import sys
+
+import db
+import store
+
+if __name__ == "__main__":
+    ids = [a for a in sys.argv[1:] if a.strip()] or None
+    db.init_db()
+    stats = db.sync_all_history(ids)
+    if ids:
+        print(f"[backfill] 已回填 {len(ids)} 个任务: {stats}")
+    else:
+        print(f"[backfill] 已回填全部任务: {stats}")

db.py

@@ -0,0 +1,291 @@
+# -*- coding: utf-8 -*-
+"""
+MySQL 记录层: 任务 / 运行 / 爬取结果 写入数据库
+- 网页完整内容不入库 (只存磁盘文件), 库中只存标题、网址、状态、文件路径等元数据
+- 爬取成功/失败均有 status 标记 (OK / FAIL), 运行记录有 run 状态标记
+- 所有操作容错: 数据库不可用时不影响爬取主流程 (仅打印日志)
+"""
+import json
+import os
+import time
+
+import pymysql
+
+DB_CONFIG = dict(
+    host="121.40.164.32",
+    port=16006,
+    user="uni_crawler",
+    password="wleD6x2T",
+    charset="utf8mb4",
+)
+
+DB_NAME = "uni_crawler"
+
+DDL = [
+    """
+    CREATE TABLE IF NOT EXISTS crawl_tasks (
+      id VARCHAR(32) PRIMARY KEY,
+      name VARCHAR(200) NOT NULL,
+      mode VARCHAR(20) NOT NULL,
+      config TEXT,
+      urls TEXT,
+      auto_config TEXT,
+      schedule_config TEXT,
+      created_at DATETIME,
+      updated_at DATETIME,
+      deleted_at DATETIME NULL
+    ) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4
+    """,
+    """
+    CREATE TABLE IF NOT EXISTS crawl_runs (
+      id VARCHAR(32) PRIMARY KEY,
+      task_id VARCHAR(32) NOT NULL,
+      mode VARCHAR(20) NOT NULL,
+      status VARCHAR(20) NOT NULL DEFAULT 'running',
+      total INT DEFAULT 0,
+      done INT DEFAULT 0,
+      ok_count INT DEFAULT 0,
+      fail_count INT DEFAULT 0,
+      image_count INT DEFAULT 0,
+      started_at DATETIME NULL,
+      finished_at DATETIME NULL,
+      out_dir VARCHAR(500),
+      KEY idx_task (task_id)
+    ) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4
+    """,
+    """
+    CREATE TABLE IF NOT EXISTS crawl_results (
+      id BIGINT AUTO_INCREMENT PRIMARY KEY,
+      run_id VARCHAR(32) NOT NULL,
+      task_id VARCHAR(32) NOT NULL,
+      mode VARCHAR(20),
+      url VARCHAR(2000) NOT NULL,
+      title VARCHAR(500),
+      status VARCHAR(10) NOT NULL,
+      error TEXT,
+      crawl_time DATETIME,
+      source_url VARCHAR(2000),
+      depth INT,
+      attempts INT DEFAULT 1,
+      html_file VARCHAR(500),
+      txt_file VARCHAR(500),
+      meta_file VARCHAR(500),
+      image_count INT DEFAULT 0,
+      image_files TEXT,
+      UNIQUE KEY uk_run_url (run_id, url(500))
+    ) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4
+    """,
+]
+
+
+def _conn():
+    cfg = dict(DB_CONFIG)
+    cfg["database"] = DB_NAME
+    return pymysql.connect(**cfg, autocommit=True, connect_timeout=5)
+
+
+def _safe(fn, *args, **kwargs):
+    """执行数据库操作, 失败仅打印日志不抛出"""
+    try:
+        fn(*args, **kwargs)
+    except Exception as e:
+        print(f"[db] 操作失败: {e}", flush=True)
+
+
+def init_db():
+    """建库建表 (幂等)"""
+    try:
+        conn = pymysql.connect(**DB_CONFIG, autocommit=True, connect_timeout=5)
+        with conn.cursor() as cur:
+            cur.execute(f"CREATE DATABASE IF NOT EXISTS `{DB_NAME}` DEFAULT CHARACTER SET utf8mb4")
+        conn.close()
+        conn = _conn()
+        with conn.cursor() as cur:
+            for ddl in DDL:
+                cur.execute(ddl)
+        conn.close()
+        print("[db] 数据库初始化完成 (crawler: crawl_tasks / crawl_runs / crawl_results)")
+    except Exception as e:
+        print(f"[db] 数据库初始化失败: {e}", flush=True)
+
+
+# ---------------- 序列化工具 ----------------
+
+def _dt(v):
+    """datetime 字符串 -> MySQL DATETIME (无效返回 None)"""
+    if not v:
+        return None
+    s = str(v).replace("T", " ")
+    if len(s) >= 19:
+        return s[:19]
+    return None
+
+
+def _j(v):
+    return json.dumps(v, ensure_ascii=False) if v else None
+
+
+# ---------------- 任务 ----------------
+
+def upsert_task(task):
+    """任务写入/更新 (含回收站状态 deleted_at)"""
+    def _do():
+        conn = _conn()
+        with conn.cursor() as cur:
+            cur.execute(
+                """INSERT INTO crawl_tasks
+                   (id, name, mode, config, urls, auto_config, schedule_config,
+                    created_at, updated_at, deleted_at)
+                   VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)
+                   ON DUPLICATE KEY UPDATE
+                   name=%s, mode=%s, config=%s, urls=%s, auto_config=%s,
+                   schedule_config=%s, updated_at=%s, deleted_at=%s""",
+                (
+                    task["id"], task.get("name", ""), task.get("mode", ""),
+                    _j(task.get("config")), _j(task.get("urls")),
+                    _j(task.get("auto")), _j(task.get("schedule")),
+                    _dt(task.get("created_at")), _dt(task.get("updated_at")),
+                    _dt(task.get("deleted_at")),
+                    task.get("name", ""), task.get("mode", ""),
+                    _j(task.get("config")), _j(task.get("urls")),
+                    _j(task.get("auto")), _j(task.get("schedule")),
+                    _dt(task.get("updated_at")), _dt(task.get("deleted_at")),
+                ),
+            )
+        conn.close()
+    _safe(_do)
+
+
+def purge_task_db(task_id):
+    """彻底删除任务记录"""
+    def _do():
+        conn = _conn()
+        with conn.cursor() as cur:
+            cur.execute("DELETE FROM crawl_results WHERE task_id=%s", (task_id,))
+            cur.execute("DELETE FROM crawl_runs WHERE task_id=%s", (task_id,))
+            cur.execute("DELETE FROM crawl_tasks WHERE id=%s", (task_id,))
+        conn.close()
+    _safe(_do)
+
+
+def purge_trash_db():
+    """清空回收站 (删除所有已标记删除的任务记录)"""
+    def _do():
+        conn = _conn()
+        with conn.cursor() as cur:
+            cur.execute("SELECT id FROM crawl_tasks WHERE deleted_at IS NOT NULL")
+            ids = [r[0] for r in cur.fetchall()]
+            for tid in ids:
+                cur.execute("DELETE FROM crawl_results WHERE task_id=%s", (tid,))
+                cur.execute("DELETE FROM crawl_runs WHERE task_id=%s", (tid,))
+                cur.execute("DELETE FROM crawl_tasks WHERE id=%s", (tid,))
+        conn.close()
+    _safe(_do)
+
+
+# ---------------- 运行记录 ----------------
+
+def upsert_run(run):
+    """运行记录写入/更新"""
+    def _do():
+        conn = _conn()
+        st = run.get("stats") or {}
+        with conn.cursor() as cur:
+            cur.execute(
+                """INSERT INTO crawl_runs
+                   (id, task_id, mode, status, total, done,
+                    ok_count, fail_count, image_count,
+                    started_at, finished_at, out_dir)
+                   VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)
+                   ON DUPLICATE KEY UPDATE
+                   status=%s, total=%s, done=%s, ok_count=%s, fail_count=%s,
+                   image_count=%s, finished_at=%s, out_dir=%s""",
+                (
+                    run["id"], run.get("task_id", ""), run.get("mode", ""),
+                    run.get("status", ""), run.get("progress", {}).get("total", 0),
+                    run.get("progress", {}).get("done", 0),
+                    st.get("ok", 0), st.get("fail", 0), st.get("images", 0),
+                    _dt(run.get("started_at")), _dt(run.get("finished_at")),
+                    run.get("out_dir", ""),
+                    run.get("status", ""), run.get("progress", {}).get("total", 0),
+                    run.get("progress", {}).get("done", 0),
+                    st.get("ok", 0), st.get("fail", 0), st.get("images", 0),
+                    _dt(run.get("finished_at")), run.get("out_dir", ""),
+                ),
+            )
+        conn.close()
+    _safe(_do)
+
+
+# ---------------- 爬取结果 (每页一条, 成功失败均记录) ----------------
+
+def insert_results(run, results):
+    """批量插入爬取结果 (增量)"""
+    if not results:
+        return
+
+    def _do():
+        conn = _conn()
+        rows = []
+        for r in results:
+            rows.append((
+                run["id"], run.get("task_id", ""), run.get("mode", ""),
+                (r.get("url") or "")[:2000], (r.get("title") or "")[:500],
+                r.get("status", "FAIL"), r.get("error"),
+                _dt(r.get("crawl_time")), (r.get("source_url") or "")[:2000],
+                r.get("depth"), r.get("attempts", 1),
+                r.get("html_file", ""), r.get("txt_file", ""), r.get("meta_file", ""),
+                len(r.get("images", []) or []),
+                _j([im.get("file") for im in (r.get("images") or [])]),
+            ))
+        with conn.cursor() as cur:
+            cur.executemany(
+                """INSERT IGNORE INTO crawl_results
+                   (run_id, task_id, mode, url, title, status, error,
+                    crawl_time, source_url, depth, attempts,
+                    html_file, txt_file, meta_file, image_count, image_files)
+                   VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)""",
+                rows,
+            )
+        conn.close()
+    _safe(_do)
+
+
+def sync_run(run, persist):
+    """持久化回调: 同步运行记录 + 增量同步爬取结果
+    persist: callable(task_id, run) 用于回写已同步进度标记
+    """
+    upsert_run(run)
+    results = run.get("results", [])
+    synced = run.get("_db_count", 0)
+    if len(results) > synced:
+        insert_results(run, results[synced:])
+        run["_db_count"] = len(results)
+        persist(run.get("task_id"), run)
+
+
+# ---------------- 历史数据回填 (幂等) ----------------
+
+def sync_all_history(task_ids=None):
+    """把本地 JSON 中的历史任务/运行/结果全量回填数据库
+    可重复执行 (INSERT IGNORE + 唯一键去重)
+    task_ids: 指定只回填的任务ID列表, 默认全部
+    返回统计 dict
+    """
+    import store as _store
+    stats = {"tasks": 0, "runs": 0, "results": 0}
+    for task in _store.load_tasks():
+        if task_ids and task["id"] not in task_ids:
+            continue
+        upsert_task(task)
+        stats["tasks"] += 1
+        for run in _store.get_runs(task["id"]):
+            upsert_run(run)
+            stats["runs"] += 1
+            results = run.get("results", [])
+            if results:
+                insert_results(run, results)
+                stats["results"] += len(results)
+                run["_db_count"] = len(results)
+                _store.save_run(task["id"], run)   # 记录已同步标记, 避免运行中重复插入
+    return stats

engine.py

@@ -37,13 +37,12 @@ _CHALLENGE_MARKS = [
 
 
 def is_challenge_page(title, html):
+    """判断是否仍在反爬验证页 (仅关键词启发, 避免误伤正常小页面)"""
     low = html.lower()
     t = (title or "").lower()
     for mark in _CHALLENGE_MARKS:
         if mark in t or mark in low:
             return True
-    if len(html) < 5000 and ("<article" not in low and "<main" not in low):
-        return True
     return False
 
 
@@ -77,6 +76,36 @@ def _settle_wait(page, timeout_s):
     return True, page.title(), page.content()
 
 
+_TRACKING_PARAMS = {
+    "utm_source", "utm_medium", "utm_campaign", "utm_term", "utm_content",
+    "fbclid", "gclid", "yclid", "mc_cid", "mc_eid", "ref", "ref_src",
+}
+
+
+def normalize_url(url):
+    """URL 规范化 (用于去重): 去锚点/跟踪参数/尾部斜杠/默认端口, host 小写"""
+    try:
+        p = urllib.parse.urlparse(str(url))
+        host = (p.hostname or "").lower()
+        if not host:
+            return str(url)
+        port = ""
+        if p.port and p.port not in (80, 443):
+            port = f":{p.port}"
+        path = p.path or "/"
+        if len(path) > 1 and path.endswith("/"):
+            path = path.rstrip("/")
+        query = ""
+        if p.query:
+            kept = [kv for kv in p.query.split("&")
+                    if kv.split("=", 1)[0].lower() not in _TRACKING_PARAMS]
+            if kept:
+                query = "?" + "&".join(kept)
+        return f"{p.scheme.lower()}://{host}{port}{path}{query}"
+    except Exception:
+        return str(url)
+
+
 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"""
@@ -551,18 +580,19 @@ class CrawlJob:
 
         p, browser, ctx, page, cookie_file = self._open_browser()
         queue = [(seed, 0, "")]               # (url, depth, 来源链接)
-        visited = set()
-        queued = set([seed])
+        visited = set()                        # 规范化 URL 去重
+        queued = set([normalize_url(seed)])
         idx = 0
         try:
             while queue and not self._stop.is_set():
                 self._wait_if_paused()
                 url, depth, src = queue.pop(0)
-                if url in visited:
+                key = normalize_url(url)
+                if key in visited:
                     continue
                 if len(visited) >= max_pages:
                     break
-                visited.add(url)
+                visited.add(key)
                 idx += 1
                 run["progress"]["current_url"] = url
                 run["progress"]["done"] = len(visited)
@@ -574,8 +604,9 @@ class CrawlJob:
                 self._persist()
                 if entry["status"] == "OK" and depth < max_depth:
                     for link in self._discover_links(page):
-                        if link not in visited and link not in queued:
-                            queued.add(link)
+                        lk = normalize_url(link)
+                        if lk not in visited and lk not in queued:
+                            queued.add(lk)
                             queue.append((link, depth + 1, url))
                 if entry["status"] == "OK":
                     self._delay()

requirements.txt

@@ -1,3 +1,4 @@
 flask>=3.0
 playwright>=1.40
 playwright-stealth>=1.0
+pymysql>=1.1

scheduler.py

@@ -116,5 +116,10 @@ class Scheduler(threading.Thread):
                 sch["last_run"] = now.strftime("%Y-%m-%d %H:%M:%S")
                 sch["runs_count"] = sch.get("runs_count", 0) + 1
                 store.upsert_task(task)
+                try:
+                    import db
+                    db.upsert_task(task)
+                except Exception:
+                    pass
             except Exception:
                 pass

static/app.js

@@ -79,10 +79,28 @@ function taskStatusBadge(t) {
   return '<span class="badge">未运行</span>';
 }
 
+const GROUPS = [
+  { key: "batch", label: "📄 批量爬取", desc: "一次性爬取指定网址列表" },
+  { key: "scheduled", label: "⏰ 定时爬取", desc: "按间隔或 cron 表达式定时执行" },
+  { key: "auto", label: "🤖 自动爬取", desc: "从起始网址自动发现链接并爬取" },
+];
+
 function renderTasks() {
   const box = $("taskList");
   $("emptyState").classList.toggle("hidden", state.tasks.length > 0);
-  box.innerHTML = state.tasks.map(taskCard).join("");
+  box.innerHTML = GROUPS.map((g) => {
+    const items = state.tasks.filter((t) => t.mode === g.key);
+    if (!items.length) return "";
+    return `
+      <div class="group">
+        <div class="group-head">
+          <span class="group-title">${g.label}</span>
+          <span class="group-desc">${g.desc}</span>
+          <span class="group-count">${items.length} 个任务</span>
+        </div>
+        <div class="task-grid">${items.map(taskCard).join("")}</div>
+      </div>`;
+  }).join("");
 }
 
 function taskCard(t) {
@@ -161,6 +179,128 @@ async function delTask(tid) {
   } catch (e) { toast(e.message, true); }
 }
 
+/* ---------------- 网址文件导入 ---------------- */
+const MAX_IMPORT_SIZE = 2 * 1024 * 1024;   // 2MB 上限
+
+async function readFileSmart(file) {
+  /* 自动识别 UTF-8 / GBK 编码 */
+  const buf = await file.arrayBuffer();
+  let text = new TextDecoder("utf-8").decode(buf);
+  if (text.includes("\uFFFD")) {
+    try { text = new TextDecoder("gbk").decode(buf); } catch (e) { /* 保留 utf-8 结果 */ }
+  }
+  return text;
+}
+
+function importUrlsText(text, mode) {
+  const ta = $("taskForm").elements["urls"];
+  const clean = (s) => s.split(" #")[0].trim();     // 去掉行内注释 (URL 不含空格, 安全)
+  const existing = new Set(
+    mode === "overwrite" ? [] : ta.value.split(/\r?\n/).map(clean).filter(Boolean)
+  );
+  const fresh = text.split(/\r?\n/).map(clean).filter(Boolean);
+  let added = 0;
+  for (const line of fresh) {
+    if (!existing.has(line)) { existing.add(line); added++; }
+  }
+  ta.value = Array.from(existing).join("\n");
+  return { total: fresh.length, added };
+}
+
+$("btnImportUrls").onclick = () => $("urlFileInput").click();
+$("urlFileInput").onchange = async (e) => {
+  const file = e.target.files && e.target.files[0];
+  e.target.value = "";                    // 允许重复选择同一文件
+  if (!file) return;
+  if (file.size > MAX_IMPORT_SIZE) {
+    toast("文件过大（上限 2MB），请拆分后导入", true);
+    return;
+  }
+  try {
+    const text = await readFileSmart(file);
+    const mode = $("importMode").value;
+    const r = importUrlsText(text, mode);
+    formDirty = true;
+    if (mode === "overwrite") {
+      toast(`已导入 ${file.name}：共 ${r.total} 行（覆盖原列表，新增 ${r.added} 条）`);
+    } else {
+      toast(`已导入 ${file.name}：共 ${r.total} 行，新增 ${r.added} 条网址（追加）`);
+    }
+  } catch (err) {
+    toast("文件读取失败: " + err.message, true);
+  }
+};
+
+/* ---------------- 搜索 ---------------- */
+async function doSearch() {
+  const q = $("searchInput").value.trim();
+  if (!q) { toast("请输入搜索关键词", true); return; }
+  try {
+    const d = await api(`/api/search?q=${encodeURIComponent(q)}`);
+    renderSearch(d);
+    showModal("searchModal");
+  } catch (e) { toast(e.message, true); }
+}
+
+function renderSearch(d) {
+  const body = $("searchBody");
+  if (!d.results.length) {
+    body.innerHTML = `<div class="empty" style="padding:40px 0"><div class="empty-icon">🔍</div><p>没有找到与「${esc(d.q)}」相关的内容</p></div>`;
+    return;
+  }
+  const items = d.results.map((r) => {
+    const badge = `<span class="badge ${esc(r.mode)}">${MODE_LABEL[r.mode] || esc(r.mode)}</span>`;
+    if (r.type === "task") {
+      return `
+      <div class="search-item">
+        <div class="row">
+          ${badge}
+          <span class="title">📋 ${esc(r.task_name)}</span>
+          <span class="badge">任务</span>
+        </div>
+        <div class="url">${r.seed_url ? "起始: " + esc(r.seed_url) : "网址 " + (r.urls_count || 0) + " 个"} · 创建于 ${esc(r.created_at || "")}</div>
+        <div class="row">
+          <button class="btn sm" onclick="searchOpenDetail('${r.task_id}')">📋 查看任务</button>
+        </div>
+      </div>`;
+    }
+    const stCls = r.status === "OK" ? "t-ok" : "t-fail";
+    const html = r.html_file ? `<span class="file-link" onclick="searchPreview('${r.task_id}','${esc(r.html_file)}','HTML: ${esc(r.url)}')">HTML</span>` : "";
+    const txt = r.txt_file ? `<span class="file-link" onclick="searchPreview('${r.task_id}','${esc(r.txt_file)}','文本: ${esc(r.url)}')">TXT</span>` : "";
+    const meta = r.meta_file ? `<span class="file-link" onclick="searchMeta('${r.task_id}','${esc(r.meta_file)}')">📋 元数据</span>` : "";
+    return `
+    <div class="search-item">
+      <div class="row">
+        ${badge}
+        <span class="title" title="${esc(r.title)}">${esc(r.title) || "（无标题）"}</span>
+        <span class="badge ${stCls}">${r.status}</span>
+        <span class="badge">${esc(r.run_status)}</span>
+        <span class="card-line">${esc(r.crawl_time || "")}</span>
+      </div>
+      <div class="url">🌐 ${esc(r.url)}${r.images ? ` · 🖼️ ${r.images}` : ""}</div>
+      <div class="row">
+        ${html}${txt}${meta}
+        <button class="btn sm" onclick="searchOpenDetail('${r.task_id}')">📋 任务详情</button>
+      </div>
+    </div>`;
+  }).join("");
+  body.innerHTML = `<div class="probe-summary"><span>关键词: <b>${esc(d.q)}</b></span><span>共 <b>${d.count}</b> 条结果</span></div>${items}`;
+}
+
+/* 搜索结果的跳转动作: 先关搜索弹窗再打开目标 */
+function searchOpenDetail(tid) {
+  hideModal("searchModal");
+  openDetail(tid);
+}
+function searchPreview(tid, path, title) {
+  hideModal("searchModal");
+  previewFile(tid, path, title);
+}
+function searchMeta(tid, metaFile) {
+  hideModal("searchModal");
+  showMeta(tid, metaFile);
+}
+
 /* ---------------- 回收站 ---------------- */
 async function openTrash() {
   try {
@@ -700,6 +840,8 @@ $("btnNew").onclick = openCreate;
 $("btnNew2").onclick = openCreate;
 $("btnRefresh").onclick = loadTasks;
 $("btnTrash").onclick = openTrash;
+$("btnSearch").onclick = doSearch;
+$("searchInput").addEventListener("keydown", (e) => { if (e.key === "Enter") doSearch(); });
 $("btnProbe").onclick = () => {
   const p = collectProbeFromForm();
   if (!p.seed_url) { toast("请先填写起始网址", true); return; }
@@ -718,6 +860,7 @@ document.querySelectorAll("[data-close-preview]").forEach((b) => b.onclick = ()
 document.querySelectorAll("[data-close-probe]").forEach((b) => b.onclick = () => hideModal("probeModal"));
 document.querySelectorAll("[data-close-meta]").forEach((b) => b.onclick = () => hideModal("metaModal"));
 document.querySelectorAll("[data-close-trash]").forEach((b) => b.onclick = () => hideModal("trashModal"));
+document.querySelectorAll("[data-close-search]").forEach((b) => b.onclick = () => hideModal("searchModal"));
 
 /* 表单改动监听 -> 脏标记 */
 $("taskForm").addEventListener("input", () => { formDirty = true; });
@@ -744,7 +887,7 @@ document.addEventListener("keydown", (e) => {
     }
     stopLogPoll();
     $("previewFrame").src = "about:blank";
-    ["detailModal", "probeModal", "metaModal", "trashModal", "previewModal"].forEach((id) => $(id).classList.add("hidden"));
+    ["detailModal", "probeModal", "metaModal", "trashModal", "searchModal", "previewModal"].forEach((id) => $(id).classList.add("hidden"));
   }
 });
 

static/index.html

@@ -10,6 +10,10 @@
 <header>
   <div class="logo">🕷️ 通用爬虫系统 <span id="version" class="version"></span></div>
   <div class="header-right">
+    <div class="search-box">
+      <input id="searchInput" placeholder="搜索网址 / 标题 / 任务名..." maxlength="100">
+      <button id="btnSearch" class="btn sm primary" title="搜索">🔍</button>
+    </div>
     <span class="status-pill" id="statusPill">运行中任务: 0</span>
     <button id="btnTheme" class="btn ghost" title="切换日间/夜间主题">☀️</button>
     <button id="btnTrash" class="btn ghost" title="回收站">🗑️ 回收站 <span id="trashCount" class="trash-count">0</span></button>
@@ -69,7 +73,17 @@
           <div class="field"><label>通知邮箱</label><input name="notify_email" value="wlq@tphai.com"></div>
         </div>
 
-        <div class="field" id="urlsField"><label>网址列表（每行一个，# 开头为注释）</label>
+        <div class="field" id="urlsField">
+          <label>网址列表（每行一个，# 开头为注释）</label>
+          <div class="row2" style="align-items:center">
+            <button type="button" class="btn sm" id="btnImportUrls">📂 导入网址文件(.txt)</button>
+            <select id="importMode" title="对已有网址的处理方式">
+              <option value="append" selected>追加（保留已有）</option>
+              <option value="overwrite">覆盖（清空已有）</option>
+            </select>
+            <span class="card-line">支持 UTF-8 / GBK，自动去重</span>
+            <input type="file" id="urlFileInput" accept=".txt,.csv,.urls,text/plain" hidden>
+          </div>
           <textarea name="urls" rows="5" placeholder="https://www.example.com/&#10;https://www.example.com/page2"></textarea>
         </div>
 
@@ -144,6 +158,17 @@
   </div>
 </div>
 
+<!-- 搜索结果弹窗 -->
+<div id="searchModal" class="modal-overlay hidden">
+  <div class="modal wide">
+    <div class="modal-head">
+      <span>🔍 搜索结果</span>
+      <button class="btn ghost sm" data-close-search>✕</button>
+    </div>
+    <div id="searchBody" class="detail-wrap"></div>
+  </div>
+</div>
+
 <!-- 回收站弹窗 -->
 <div id="trashModal" class="modal-overlay hidden">
   <div class="modal wide">

static/style.css

@@ -85,6 +85,16 @@ main { padding: 20px 24px; max-width: 1500px; margin: 0 auto; }
 .stat-num.num-run { color: var(--accent); }
 .stat-label { font-size: 12px; color: var(--muted); margin-top: 3px; }
 
+/* ---------- 分组展示 ---------- */
+.group { display: flex; flex-direction: column; gap: 12px; margin-bottom: 24px; }
+.group-head { display: flex; align-items: baseline; gap: 10px; flex-wrap: wrap; }
+.group-title { font-size: 16px; font-weight: 700; }
+.group-desc { font-size: 12px; color: var(--muted); }
+.group-count {
+  font-size: 11px; padding: 2px 10px; border-radius: 10px;
+  background: var(--panel2); border: 1px solid var(--border); color: var(--muted);
+}
+
 /* ---------- task grid ---------- */
 .task-grid { display: grid; grid-template-columns: repeat(auto-fill, minmax(380px, 1fr)); gap: 16px; }
 .card {
@@ -215,7 +225,16 @@ 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; }
 
-/* ---------- 回收站 ---------- */
+/* ---------------- 回收站 ---------------- */
+.search-box { display: flex; gap: 6px; align-items: center; }
+.search-box input { width: 250px; }
+.search-item {
+  border: 1px solid var(--border); border-radius: 10px; padding: 10px 12px;
+  display: flex; flex-direction: column; gap: 5px; background: var(--panel2);
+}
+.search-item .row { display: flex; align-items: center; gap: 8px; flex-wrap: wrap; }
+.search-item .title { font-weight: 600; max-width: 420px; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }
+.search-item .url { color: var(--muted); word-break: break-all; font-size: 12px; }
 .trash-count {
   display: inline-block; min-width: 18px; padding: 0 5px; border-radius: 9px;
   background: var(--red); color: #fff; font-size: 11px; line-height: 18px;