feat(monitor): 抖音 Web 接口客户端 —— 绕开爬虫子进程，直接发 HTTP

移植自 mac-agent-os 的 mediacrawler_adapter：不起子进程、不开页面，用浏览器里那份登录态直接调抖音 Web 接口。产物键名照抄 store/douyin，所以 ingest 那条链路一个字不用改。 **目前能用的（真环境实测，非推断）**： profile/other : 200, 7075 字节 —— 博主主页指标（粉丝/获赞/作品数/昵称） aweme/detail : 200, 45425 字节 —— 单条作品详情（含点赞/评论/收藏/分享） **目前不能用的：作品列表 `aweme/post`。** 两个互相独立的原因： 1. 这个接口被抖音单独升级成了真校验：不带 x-tt-argus 回 403「Uifid Not Found」，带上 dummy 值回 200 + **空 body**。也就是说「头在不在」骗得过，「真校验」过不了。同一套头打 profile/other 和 aweme/detail 都是通的 —— 抖音是挑着接口加保护的，挑中的恰好是「批量拉作品列表」这个最敏感的动作。 2. 改走页面截获也不行：CDP 浏览器打开博主主页会落到「验证码中间页」（当天大量探测的代价，过几小时要重测）。所以现在的边界是：**已知作品的指标刷新能做，自动发现新作品做不了**。 **排查中控住变量后得到的两条事实**（都写进注释了）： · `Accept` / `Accept-Language` / `Referer` 才是主页接口能返回真数据的原因 —— 只有 UA+client hints+Cookie 时是 200 但仅 121 字节的空壳，补上这三个头变 7074 字节。（我先前猜的 sec-ch-ua 不是关键。） · 因此 UA 与 client hints 必须**成套地取自同一个浏览器**，所以 BrowserIdentity 一次从 CDP 取齐 cookie + UA + hints，而不是各自写死。「200 + 空 body 必须当场报错」也是刻意写死的：放过去它会在下游变成「这个博主没作品」，把一次失败伪装成一条正常结果 —— 爬虫那条路正是这么栽的，还被翻译成「账号被封」。测试 +11：cookie 解析、请求头成套性（含 uifid 缺失/回退）、产物键名与 store 对齐、以及 _get 的三条失败路径（空 body / 403 带网关原话 / 正常返回）。
2026-10-10 17:12:25 +08:00
parent 21ff01b894
commit 2112c1a870
1601 changed files with 367425 additions and 0 deletions
@@ -0,0 +1,64 @@
+"""
+comment_dom_scanner.py — 扫描评论区DOM结构
+"""
+import asyncio, json, os, sys
+sys.path.insert(0, os.path.dirname(__file__))
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'matrix_modules'))
+
+async def main():
+    from cdp_connector import CDPConnector
+
+    ID_DIR = os.path.expanduser('~/workbuddy-agent-os/agent-local/tools/matrix/identities/douyin_01_camo')
+    conn = CDPConnector(browser_type='camoufox', identity_dir=ID_DIR,
+                        headless=False, window=(702,783), window_position=(652,0))
+    print('🦊 启动...')
+    await conn.connect()
+    page = conn.page
+    await conn.init_anti_detection()
+    await page.goto('https://www.douyin.com/', timeout=15000)
+    await asyncio.sleep(3)
+
+    print('\n📌 手动进入播放页，然后回车继续...')
+    input()
+
+    # 按X打开评论区
+    await page.keyboard.press('KeyX')
+    print('\n⌨️ KeyX 打开了评论区')
+    await asyncio.sleep(2)
+
+    # 扫描所有元素的class，找包含comment的
+    classes = await page.evaluate("""() => {
+        const all = document.querySelectorAll('*');
+        const commentRelated = [...all].filter(el => {
+            const c = (el.className || '').toLowerCase();
+            const t = (el.tagName || '');
+            return c.includes('comment') || c.includes('chat') || c.includes('reply') || c.includes('input');
+        });
+        return commentRelated.map(el => ({
+            tag: el.tagName,
+            cls: (el.className || '').slice(0,80),
+            visible: el.offsetParent !== null,
+            rect: Object.values(el.getBoundingClientRect()).map(Math.round),
+            text: (el.textContent || '').slice(0,30)
+        }));
+    }""")
+    print(f'\n📊 找到 {len(classes)} 个评论相关元素:')
+    for c in classes:
+        print(f'  {c["tag"]:8s} cls={c["cls"][:40]:40s} vis={c["visible"]} rect={c["rect"]} \"{c["text"]}\"')
+
+    # 保存到文件
+    out = '/tmp/comment_dom_scan.json'
+    with open(out, 'w') as f:
+        json.dump(classes, f, ensure_ascii=False, indent=2)
+    print(f'\n💾 已保存到 {out}')
+
+    print('\n✅ 扫描完成，浏览器保持打开')
+    print('按 Ctrl+C 退出')
+
+    while True:
+        await asyncio.sleep(10)
+
+try:
+    asyncio.run(main())
+except KeyboardInterrupt:
+    print('\n👋 退出')
@@ -0,0 +1,253 @@
+#!/usr/bin/env python3
+"""
+comment_sender.py v2 — 状态感知的评论发送器
+
+流程（锚点驱动）:
+1. 检测评论区是否打开 → 否则 KeyX
+2. 检测输入框是否已激活 → 否则 JS focus
+3. 检测是否有内容 → 否则键盘输入
+4. Alt+Enter 发送
+5. 验证码检测 → 手动输入
+"""
+import asyncio, os, random, sys, json
+script_dir = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, os.path.dirname(script_dir))
+from cdp_connector import CDPConnector
+
+LOG_FILE = '/tmp/comment_sender.log'
+def log(m):
+    with open(LOG_FILE, 'a') as f: f.write(m + '\n')
+    print(m, flush=True)
+
+async def check_state(page) -> dict:
+    """检测评论区相关状态"""
+    return await page.evaluate("""() => {
+        const ae = document.activeElement;
+        // 评论区面板
+        const panel = document.querySelector('[class*="comment-header"]')
+                   || document.querySelector('[class*="comment"]')
+                   || document.querySelector('[class*="Comment"]');
+        // Draft.js 编辑器
+        const editor = document.querySelector('[contenteditable="true"][role="combobox"]')
+                    || document.querySelector('[class*="DraftEditor"] [contenteditable]');
+        // 输入框是否激活（activeElement 是编辑器或其子元素）
+        const editorActive = ae && (ae.isContentEditable
+            || ae.getAttribute('contenteditable') === 'true'
+            || ae.closest('[contenteditable]'));
+        return {
+            has_comment_area: !!panel,
+            has_editor: !!editor,
+            editor_active: editorActive,
+            active_tag: ae ? ae.tagName : 'none',
+            active_cls: ae ? (ae.className||'').slice(0,50) : '',
+            panel_rect: panel ? Object.values(panel.getBoundingClientRect()).map(Math.round) : null
+        };
+    }""")
+
+async def focus_editor(page) -> bool:
+    """尝试聚焦 Draft.js 编辑器，返回是否成功"""
+    ok = await page.evaluate("""() => {
+        // 直接找 contenteditable 且有 role 的
+        let ed = document.querySelector('[contenteditable="true"][role="combobox"]');
+        if (!ed) ed = document.querySelector('[class*="DraftEditor"] [contenteditable]');
+        if (!ed) ed = document.querySelector('[contenteditable="true"]');
+        if (ed) { ed.focus(); ed.click(); return true; }
+        return false;
+    }""")
+    await asyncio.sleep(0.5)
+    return ok
+
+async def send_comment(page, comment_text: str):
+    """发送一条评论（状态感知版）"""
+    # ── Step 1: 检测并确保评论区打开 ──
+    state = await check_state(page)
+    log(f'📊 初始状态: comment={state["has_comment_area"]} editor={state["has_editor"]} active={state["editor_active"]}')
+
+    if not state['has_comment_area']:
+        log('⌨️ KeyX 打开评论区')
+        await page.keyboard.press('KeyX')
+        await asyncio.sleep(2)
+    else:
+        log('✅ 评论区已打开，跳过KeyX')
+
+    # ── Step 2: 用真实鼠标点击激活输入框 ──
+    state = await check_state(page)
+    if state['editor_active']:
+        log('✅ 输入框已激活')
+    else:
+        # 找到编辑器位置 → 用 Playwright 真实鼠标点击
+        rect = await page.evaluate("""() => {
+            let el = document.querySelector('[contenteditable="true"][role="combobox"]');
+            if (!el) el = document.querySelector('[class*="DraftEditor"] [contenteditable]');
+            if (!el) el = document.querySelector('[contenteditable="true"]');
+            if (!el) return null;
+            const r = el.getBoundingClientRect();
+            return {x: r.x, y: r.y, w: r.width, h: r.height};
+        }""")
+        if rect and rect['w'] > 0 and rect['h'] > 0:
+            # 用 Playwright 生成真实鼠标事件链
+            x = rect['x'] + rect['w'] // 2
+            y = rect['y'] + rect['h'] // 2
+            log(f'🖱️ 真实鼠标点击编辑器: ({x:.0f}, {y:.0f})')
+            await page.mouse.click(x, y)
+            await asyncio.sleep(1)
+            # 再次确认
+            state = await check_state(page)
+            if state['editor_active']:
+                log('✅ 鼠标点击后输入框已激活')
+            else:
+                log('⚠️ 鼠标点击后仍未激活')
+        else:
+            log('⚠️ 找不到编辑器位置')
+            return 'failed'
+
+    await asyncio.sleep(0.5)
+
+    # ── Step 3: JS 设置内容（不用键盘，不依赖焦点）──
+    log(f'💬 JS设置内容: "{comment_text}"')
+    result = await page.evaluate(f'''() => {{
+        // 找 Draft.js 编辑器
+        let ed = document.querySelector('[contenteditable="true"][role="combobox"]');
+        if (!ed) ed = document.querySelector('[class*="DraftEditor"] [contenteditable]');
+        if (!ed) ed = document.querySelector('[contenteditable="true"]');
+
+        if (!ed) return {{ok: false, reason: 'no_editor'}};
+
+        // focus + 清空 + 设置内容
+        ed.focus();
+        ed.textContent = '';
+        ed.textContent = "{comment_text}";
+        ed.dispatchEvent(new Event('input', {{bubbles: true}}));
+        ed.dispatchEvent(new Event('change', {{bubbles: true}}));
+
+        const finalText = ed.textContent;
+        return {{ok: finalText.length > 0, text: finalText, tag: ed.tagName}};
+    }}''')
+    log(f'  结果: ok={result["ok"]} text="{result.get("text","")}" tag={result.get("tag","")}')
+
+    if not result.get('ok'):
+        log('⚠️ JS设置内容失败')
+        return 'failed'
+
+    await asyncio.sleep(0.5)
+
+    # ── Step 4: JS 触发发送（先找发送按钮，没有则 Alt+Enter）──
+    log('⌨️ JS触发发送...')
+    send_result = await page.evaluate('''() => {
+        // 找发送按钮
+        const btns = [...document.querySelectorAll('button')];
+        const sendBtn = btns.find(b =>
+            b.textContent.includes('发送') || b.textContent.includes('发布')
+        );
+        if (sendBtn) {
+            sendBtn.click();
+            return 'click_send_btn';
+        }
+        // 没按钮 → 触发 Alt+Enter
+        const ed = document.querySelector('[contenteditable="true"][role="combobox"]')
+                || document.querySelector('[contenteditable="true"]');
+        if (ed) {
+            ed.dispatchEvent(new KeyboardEvent('keydown', {
+                key: 'Enter', altKey: true, bubbles: true
+            }));
+            return 'alt_enter_event';
+        }
+        return 'failed';
+    }''')
+    log(f'  发送方式: {send_result}')
+    await asyncio.sleep(2)
+
+    # ── Step 5: 验证码 ──
+    has_code = await page.evaluate(
+        "() => !!document.querySelector('input[placeholder*=\"\\u9a8c\\u8bc1\\u7801\"]')"
+    )
+    if has_code:
+        log('⚠️ 验证码弹窗！')
+        return 'verify_code_required'
+
+    # ── Step 6: 验证发送结果 ──
+    found = await page.evaluate(
+        f'() => document.body.innerText.includes("{comment_text}")'
+    )
+    if found:
+        log('✅ 评论已发送')
+        return 'success'
+    else:
+        log('❌ 未在页面找到评论')
+        return 'failed'
+
+
+async def main():
+    import argparse
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--account', '-a', default='douyin_01')
+    parser.add_argument('--comment', '-c', default='好内容，已三连')
+    parser.add_argument('--count', '-n', type=int, default=2)
+    args = parser.parse_args()
+
+    ID_DIR = os.path.expanduser(
+        f'~/workbuddy-agent-os/agent-local/tools/matrix/identities/{args.account}_camo'
+    )
+    if not os.path.exists(ID_DIR):
+        print(f'❌ 账号目录不存在: {ID_DIR}')
+        return
+
+    print(f'🦊 启动: {args.account}')
+    conn = CDPConnector(browser_type='camoufox', identity_dir=ID_DIR,
+                        headless=False, window=(702,783), window_position=(652,0))
+    await conn.connect()
+    page = conn.page
+    await conn.init_anti_detection()
+    await page.goto('https://www.douyin.com/', timeout=30000)
+    await asyncio.sleep(3)
+
+    print('\n📌 请操作:')
+    print('   1. 进入视频播放页')
+    print('   2. 打开评论区（按 X）')
+    print('   3. 手动点击激活评论输入框')
+    print('   4. 回到终端按回车\n')
+    input()
+
+    # 检查是否在播放页
+    v = await page.evaluate('document.querySelectorAll("video").length')
+    if v < 2:
+        print('❌ 未检测到播放页')
+        return
+    print(f'✅ 播放页确认 (video={v})')
+
+    for i in range(args.count):
+        print(f'\n——— 第{i+1}/{args.count}次评论 ———')
+        result = await send_comment(page, args.comment)
+
+        if result == 'verify_code_required':
+            code = input('\n📱 验证码(6位): ').strip()
+            if code and len(code) == 6:
+                await page.evaluate(f'''() => {{
+                    const inp = document.querySelector('input[placeholder*="验证码"]');
+                    if (inp) {{
+                        inp.value = "{code}";
+                        inp.dispatchEvent(new Event('input', {{bubbles: true}}));
+                    }}
+                    const btn = [...document.querySelectorAll('button')]
+                        .find(b => b.textContent.includes('确认') || b.textContent.includes('提交'));
+                    if (btn) btn.click();
+                }}''')
+                print('✅ 验证码已提交')
+                await asyncio.sleep(2)
+
+        if i < args.count - 1:
+            print('⏳ 评论区保持打开，5秒后下一次...')
+            await asyncio.sleep(5)
+
+    print('\n✅ 完成，浏览器保持打开')
+    print('按 Ctrl+C 退出')
+    while True:
+        await asyncio.sleep(10)
+
+if __name__ == '__main__':
+    try:
+        asyncio.run(main())
+    except KeyboardInterrupt:
+        print('\n👋 退出')
+    except Exception as e:
+        import traceback; traceback.print_exc()
@@ -0,0 +1,370 @@
+#!/usr/bin/env python3
+"""
+小红书登录后 DOM 重分析工具
+============================
+
+用途：登录小红书后重新分析 DOM 结构，验证当前选择器是否仍然有效，
+     输出结构化报告指导选择器更新。
+
+用法:
+  python tools/reanalyze_xhs_dom.py <identity_name>
+  python tools/reanalyze_xhs_dom.py xhs_01 --full-dump   # 输出完整 DOM 快照
+  python tools/reanalyze_xhs_dom.py xhs_01 --explore-url https://www.xiaohongshu.com/explore  # 自定义 URL
+
+流程:
+  1. 通过 Camoufox 连接身份目录（复用登录态）
+  2. 导航到小红书 explore 首页
+  3. 等待渲染稳定
+  4. Dump 关键区域的 DOM 结构（保留选择器相关特征）
+  5. 验证当前 selectors.py 中的每个选择器是否仍能匹配
+  6. 输出结构化的重分析报告
+"""
+
+import argparse
+import asyncio
+import json
+import os
+import sys
+import time
+from pathlib import Path
+
+SCRIPTS_DIR = Path(__file__).parent.parent
+sys.path.insert(0, str(SCRIPTS_DIR))
+
+LOCAL_ROOT = Path.home() / "workbuddy-agent-os" / "agent-local" / "tools" / "matrix"
+IDENTITIES_ROOT = LOCAL_ROOT / "identities"
+
+
+async def analyze(identity_name: str, full_dump: bool = False, explore_url: str = None):
+    """主分析流程"""
+    print(f"\n{'='*60}")
+    print(f" 🔍 小红书 DOM 重分析工具")
+    print(f" {'='*60}")
+    print(f"    身份: {identity_name}")
+    print(f"    模式: {'完整快照' if full_dump else '选择器验证'}")
+    print()
+
+    # ── 1. 确定身份目录 ──
+    # 优先从 accounts.yaml 读取
+    import yaml
+    config_path = LOCAL_ROOT / "config" / "accounts.yaml"
+    try:
+        with open(config_path) as f:
+            data = yaml.safe_load(f)
+        acct = None
+        for a in data.get("accounts", []):
+            if a["id"] == identity_name:
+                acct = a
+                break
+    except:
+        acct = None
+
+    if acct:
+        identity_dir_str = acct.get("identity_dir", identity_name)
+        if not identity_dir_str.startswith("/"):
+            identity_dir_str = str(LOCAL_ROOT / identity_dir_str)
+    else:
+        identity_dir_str = str(IDENTITIES_ROOT / identity_name)
+
+    # 清理锁文件
+    import glob
+    for lock_file in glob.glob(f"{identity_dir_str}/user_data/**/.parentlock", recursive=True):
+        try:
+            os.remove(lock_file)
+        except:
+            pass
+    for lock_file in glob.glob(f"{identity_dir_str}/user_data/**/lock", recursive=True):
+        try:
+            os.remove(lock_file)
+        except:
+            pass
+
+    # ── 2. 连接浏览器 ──
+    from cdp_connector import CDPConnector
+    conn = CDPConnector(
+        identity_dir=identity_dir_str,
+        headless=False,
+        window=(702, 783),
+    )
+    print(f"   🚀 连接浏览器: {identity_dir_str}")
+    try:
+        await conn.connect()
+    except Exception as e:
+        print(f"   ❌ 连接失败: {e}")
+        sys.exit(1)
+    print(f"      ✅ 浏览器已连接")
+    print(f"      📐 视口: 702×783")
+
+    # 反检测
+    try:
+        await conn.init_anti_detection()
+    except Exception:
+        pass
+
+    # ── 3. 导航到小红书 ──
+    target_url = explore_url or "https://www.xiaohongshu.com/explore"
+    print(f"\n   🌐 导航到: {target_url}")
+    for attempt in range(1, 4):
+        try:
+            await conn.page.goto(target_url, timeout=20000, wait_until="domcontentloaded")
+            print(f"      ✅ 导航成功 (第{attempt}次)")
+            break
+        except Exception as e:
+            print(f"      ⚠️ 导航失败 (第{attempt}次): {e}")
+            if attempt < 3:
+                await asyncio.sleep(3)
+            else:
+                print(f"      ❌ 导航最终失败")
+                await conn.close()
+                return
+
+    # ── 等待渲染 ──
+    print(f"\n   ⏳ 等待页面渲染...")
+    await asyncio.sleep(5)
+
+    # 关闭登录弹窗
+    try:
+        await conn.page.evaluate("""
+        () => {
+            document.querySelectorAll('[class*=modal], [class*=dialog], [class*=mask], [role=dialog]').forEach(m => {
+                m.style.display = 'none';
+            });
+        }
+        """)
+    except:
+        pass
+    await asyncio.sleep(1)
+
+    # ── 4. 检测登录状态 ──
+    print(f"\n   🔐 登录状态检测")
+    try:
+        from auth_manager import check_login_by_cookie_sync, count_platform_cookies
+        cookies = await conn.context.cookies()
+        logged_in = check_login_by_cookie_sync(cookies, "xiaohongshu")
+        cookie_cnt = count_platform_cookies(cookies, "xiaohongshu")
+        print(f"      Cookie 检测: {'✅ 已登录' if logged_in else '❌ 未登录'}")
+        print(f"      平台 Cookie 数: {cookie_cnt}")
+    except Exception as e:
+        print(f"      ⚠️ 登录检测异常: {e}")
+
+    # ── 5. 检查页面基本结构 ──
+    print(f"\n   📄 页面基本结构")
+    page_info = await conn.page.evaluate("""
+    () => {
+        return {
+            url: location.href,
+            title: document.title,
+            app_present: !!document.querySelector('#app'),
+            body_children: document.body ? document.body.children.length : 0,
+            viewport: {w: window.innerWidth, h: window.innerHeight},
+            scroll: {x: window.scrollX, y: window.scrollY},
+        };
+    }
+    """)
+    print(f"      URL: {page_info.get('url', '?')}")
+    print(f"      Title: {page_info.get('title', '?')}")
+    print(f"      #app: {'✅' if page_info.get('app_present') else '❌'}")
+    print(f"      body children: {page_info.get('body_children', '?')}")
+
+    # ── 6. 验证 selectors.py 中的选择器 ──
+    print(f"\n{'='*60}")
+    print(f"   📋 选择器验证")
+    print(f"   {'='*60}")
+
+    # 导入当前选择器
+    sys.path.insert(0, str(SCRIPTS_DIR / "matrix_modules" / "ops" / "xhs"))
+    from selectors import (
+        NOTE_CARD, NOTE_CARD_COVER, NOTE_CARD_IMG,
+        SEARCH_INPUT, SEARCH_BUTTON,
+        FEED_CONTAINER, LOGIN_MODAL, LOGIN_MODAL_CLOSE,
+        LIKE_BUTTON, COLLECT_BUTTON, FOLLOW_BUTTON,
+        COMMENT_ENTRY, COMMENT_INPUT, COMMENT_SEND,
+        ANCHORS,
+    )
+
+    selector_tests = {
+        "首页/瀑布流": [
+            ("瀑布流容器", FEED_CONTAINER),
+            ("笔记卡片", NOTE_CARD),
+            ("卡片封面链接", NOTE_CARD_COVER),
+            ("卡片图片", NOTE_CARD_IMG),
+        ],
+        "搜索": [
+            ("搜索框", SEARCH_INPUT),
+            ("搜索按钮", SEARCH_BUTTON),
+        ],
+        "弹窗": [
+            ("登录弹窗", LOGIN_MODAL),
+            ("关闭按钮", LOGIN_MODAL_CLOSE),
+        ],
+        "互动(详情页)": [
+            ("点赞按钮", LIKE_BUTTON),
+            ("收藏按钮", COLLECT_BUTTON),
+            ("关注按钮", FOLLOW_BUTTON),
+            ("评论入口", COMMENT_ENTRY),
+            ("评论输入框", COMMENT_INPUT),
+            ("发送按钮", COMMENT_SEND),
+        ],
+    }
+
+    all_ok = True
+    for category, selectors in selector_tests.items():
+        print(f"\n   【{category}】")
+        js_code = "var sel = arguments[0]; return document.querySelector(sel) ? document.querySelector(sel).outerHTML.substring(0, 200) : null;"
+        for name, sel in selectors:
+            try:
+                count = await conn.page.evaluate(f"document.querySelectorAll('{sel.replace(chr(39), chr(92) + chr(39))}').length")
+                first_match = None
+                if count > 0:
+                    first_match = await conn.page.evaluate(f"try {{ let el = document.querySelector('{sel.replace(chr(39), chr(92) + chr(39))}'); return el ? el.tagName + (el.className ? '.' + el.className.split(' ')[0] : '') : 'N/A'; }} catch(e) {{ return 'JS_ERR'; }}")
+                status = "✅" if count > 0 else "⚠️"
+                if count == 0:
+                    all_ok = False
+                print(f"      {status} {name}: \"{sel}\"")
+                if count > 0:
+                    print(f"         匹配 {count} 个元素, 首元素: {first_match}")
+            except Exception as e:
+                print(f"      ❌ {name}: JS 异常 - {e}")
+                all_ok = False
+
+    # ── 7. 锚点验证 ──
+    print(f"\n   【锚点验证】")
+    for anchor_name, anchor_sel in ANCHORS.items():
+        try:
+            count = await conn.page.evaluate(f"document.querySelectorAll('{anchor_sel.replace(chr(39), chr(92) + chr(39))}').length")
+            status = "✅" if count > 0 else "⚠️"
+            if count == 0:
+                all_ok = False
+            print(f"      {status} {anchor_name}: \"{anchor_sel}\" → {count} 个")
+        except Exception as e:
+            print(f"      ❌ {anchor_name}: {e}")
+
+    # ── 8. 完整 DOM 快照（可选）──
+    if full_dump:
+        print(f"\n{'='*60}")
+        print(f"   📸 完整 DOM 快照")
+        print(f"   {'='*60}")
+        print(f"   正在保存到文件...")
+
+        # 获取关键区域的 HTML
+        dom_snapshot = await conn.page.evaluate("""
+        () => {
+            const areas = {};
+
+            // #app 容器
+            const app = document.querySelector('#app');
+            if (app) areas.app = app.outerHTML.substring(0, 5000);
+
+            // 瀑布流区域
+            const layout = document.querySelector('.layout, [class*=layout]');
+            if (layout) areas.layout = layout.outerHTML.substring(0, 3000);
+
+            // 检查是否有详情页（如果有多个 section.note-item 说明在首页）
+            const notes = document.querySelectorAll('section.note-item');
+            if (notes.length > 0) {
+                areas.note_first = notes[0].outerHTML.substring(0, 2000);
+                areas.note_count = notes.length;
+            }
+
+            // 记录当前页面上的所有 class 名（去重）
+            const allClasses = new Set();
+            document.querySelectorAll('*').forEach(el => {
+                if (el.className && typeof el.className === 'string') {
+                    el.className.split(/\\s+/).forEach(c => {
+                        if (c && c.length > 1) allClasses.add(c);
+                    });
+                }
+            });
+            areas.all_classes = [...allClasses].sort();
+
+            // 关键 URL 和 meta
+            areas.meta = {
+                url: location.href,
+                title: document.title,
+                links_count: document.querySelectorAll('a').length,
+                buttons_count: document.querySelectorAll('button').length,
+                img_count: document.querySelectorAll('img').length,
+                video_count: document.querySelectorAll('video').length,
+            };
+
+            return areas;
+        }
+        """)
+
+        timestamp = time.strftime("%Y%m%d_%H%M%S")
+        dump_path = SCRIPTS_DIR / "data" / f"xhs_dom_dump_{timestamp}.json"
+        dump_path.parent.mkdir(parents=True, exist_ok=True)
+
+        # 简化输出：移除过长内容
+        output = {}
+        for k, v in dom_snapshot.items():
+            if isinstance(v, str) and len(v) > 500:
+                output[k] = v[:500] + f"\n... [截断, 全文 {len(v)} 字符]"
+            else:
+                output[k] = v
+
+        with open(dump_path, "w", encoding="utf-8") as f:
+            json.dump(output, f, indent=2, ensure_ascii=False)
+
+        print(f"      📁 已保存: {dump_path}")
+        print(f"      页面元素: links={dom_snapshot.get('meta', {}).get('links_count','?')}, "
+              f"buttons={dom_snapshot.get('meta', {}).get('buttons_count','?')}, "
+              f"img={dom_snapshot.get('meta', {}).get('img_count','?')}")
+        if dom_snapshot.get('note_count'):
+            print(f"      笔记卡片数: {dom_snapshot.get('note_count')}")
+        print(f"      页面 class 数: {len(dom_snapshot.get('all_classes', []))}")
+
+    # ── 9. 截图 ──
+    print(f"\n   📸 截图")
+    screenshot_path = SCRIPTS_DIR / "data" / f"xhs_reanalyze_{time.strftime('%Y%m%d_%H%M%S')}.png"
+    try:
+        await conn.page.screenshot(path=str(screenshot_path))
+        print(f"      ✅ 截图: {screenshot_path}")
+    except:
+        print(f"      ⚠️ 截图失败")
+
+    # ── 10. 总结 ──
+    print(f"\n{'='*60}")
+    print(f"   📊 分析总结")
+    print(f"   {'='*60}")
+    if all_ok:
+        print(f"      ✅ 所有选择器均匹配当前 DOM")
+        print(f"      → 当前 selectors.py 无需更新")
+    else:
+        print(f"      ⚠️ 部分选择器未匹配到元素")
+        print(f"      → 建议更新 selectors.py 中的不匹配选择器")
+        print(f"      → 参考完整 DOM 快照了解最新结构")
+    print(f"\n   💡 提示: 如果是登录后分析，对比登录前后的选择器差异")
+    print(f"         尝试在探索页和笔记详情页分别运行此工具")
+    print(f"{'='*60}")
+
+    # 保持浏览器运行供检查
+    print(f"\n   🔄 浏览器保持运行，关闭终端即退出")
+    try:
+        while True:
+            await asyncio.sleep(30)
+    except (KeyboardInterrupt, asyncio.CancelledError):
+        pass
+    finally:
+        try:
+            await conn.close()
+        except:
+            pass
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="小红书登录后 DOM 重分析工具"
+    )
+    parser.add_argument("identity_name", help="身份名称 (如 xhs_01)")
+    parser.add_argument("--full-dump", "-f", action="store_true",
+                        help="输出完整 DOM 快照到 JSON 文件")
+    parser.add_argument("--explore-url", "-u", default=None,
+                        help="自定义分析 URL (默认: /explore)")
+    args = parser.parse_args()
+
+    asyncio.run(analyze(args.identity_name, args.full_dump, args.explore_url))
+
+
+if __name__ == "__main__":
+    main()