feat(monitor): 抖音 Web 接口客户端 —— 绕开爬虫子进程,直接发 HTTP
Deploy VitePress site to Pages / build (push) Canceled after 0s
Deploy VitePress site to Pages / Deploy (push) Canceled after 0s

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)。
This commit is contained in:
2026-10-10 17:12:25 +08:00
parent 21ff01b894
commit 2112c1a870
1601 changed files with 367425 additions and 0 deletions
@@ -0,0 +1,40 @@
"""MC 平台插件 — 自动发现与注册"""
import importlib
import pkgutil
from pathlib import Path
_registry = {}
def discover_platforms():
"""自动扫描 platforms/ 目录下的所有插件"""
global _registry
_registry = {}
here = Path(__file__).parent
for entry in here.iterdir():
if not entry.is_dir() or entry.name.startswith("__"):
continue
init_file = entry / "__init__.py"
if not init_file.exists():
continue
try:
mod = importlib.import_module(f"platforms.{entry.name}")
if hasattr(mod, "register_platform"):
name, instance = mod.register_platform()
_registry[name] = instance
except Exception as e:
print(f" ⚠️ 插件 {entry.name} 加载失败: {e}")
return _registry
def get_platform(name):
if not _registry:
discover_platforms()
return _registry.get(name)
def list_platforms():
if not _registry:
discover_platforms()
return dict(_registry)
@@ -0,0 +1,53 @@
"""MC 平台插件基类"""
from typing import Optional
class BasePlatform:
"""平台插件基类
所有平台插件继承此类, 实现标准接口。
未实现的接口返回 {"status": "error", "message": "暂不支持"}。
"""
name: str = "" # 平台标识: 'douyin'
display_name: str = "" # 显示名: '抖音'
version: str = "1.0.0"
description: str = ""
# ── 登录 ──
def login(self, account_name: str, headless: bool = False) -> dict:
return {"status": "error", "message": "暂不支持"}
def logout(self, account_name: str) -> dict:
return {"status": "error", "message": "暂不支持"}
def status(self, account_name: str) -> dict:
return {"status": "error", "message": "暂不支持"}
# ── 采集 ──
def collect(self, account_name: str) -> dict:
return {"status": "error", "message": "暂不支持"}
# ── 发布 ──
def publish(self, account_name: str, file_path: str = "",
title: str = "", desc: str = "") -> dict:
return {"status": "error", "message": "暂不支持"}
# ── 养号 ──
def nurture(self, account_name: str, blueprint: str = "daily") -> dict:
return {"status": "error", "message": "暂不支持"}
# ── 互动 ──
def interact(self, account_name: str, action: str = "like",
target: str = "") -> dict:
return {"status": "error", "message": "暂不支持"}
# ── 搜索 ──
def search(self, keyword: str, limit: int = 10) -> dict:
return {"status": "error", "message": "暂不支持"}
def not_implemented(msg="暂不支持"):
"""返回标准未实现响应"""
return {"status": "error", "message": msg}
@@ -0,0 +1,19 @@
# 抖音平台插件
## 能力
| 接口 | 状态 | 说明 |
|------|:----:|------|
| login | ✅ | 打开浏览器扫码登录 |
| collect | ✅ | 采集抖音主页信息 |
| status | ✅ | 检查登录状态 |
| publish | 📋 | 计划中 (集成 social-auto-upload) |
| nurture | ✅ | 执行养号蓝图 |
## 用法
```bash
mc douyin collect --account 手机号
mc douyin login --account 手机号
mc douyin status --account 手机号
```
@@ -0,0 +1,7 @@
"""抖音平台插件"""
from .plugin import DouyinPlatform
def register_platform():
return "douyin", DouyinPlatform()
@@ -0,0 +1,103 @@
"""抖音插件实现 — 当前包装现有脚本
⚠️ DEPRECATED: 本插件层的功能已被 CommandBus + mc 引擎取代。
所有执行操作请走:
- 看板: POST /api/ops/run {type:'collect'|'nurture'|'login'|'comment', accounts, params}
- CLI: mc run / mc collect / mc smart-login
platforms/ 层将在后续清理中移除。
"""
import json
import subprocess
import sys
from pathlib import Path
from platforms.base import BasePlatform
SCRIPTS_DIR = Path(__file__).resolve().parent.parent.parent / "scripts"
AGENT_LOCAL = Path.home() / "workbuddy-agent-os" / "agent-local"
class DouyinPlatform(BasePlatform):
name = "douyin"
display_name = "抖音"
version = "1.0.0"
description = "抖音账号管理: 登录/采集/养号"
def _resolve_account(self, account_name: str) -> str:
"""通过手机号或账号ID找到 identity_dir"""
try:
sys.path.insert(0, str(SCRIPTS_DIR))
from matrix_mgmt import MatrixManager
mgr = MatrixManager()
for a in mgr.list_accounts():
if a.get("phone") == account_name or a["id"] == account_name:
if a.get("platform") == "douyin":
return a.get("identity_dir", a["id"]).replace("identities/", "")
except: pass
return account_name
def collect(self, account_name: str) -> dict:
"""采集主页信息(建议通过 mc run --blueprints=douyin_read_profile 执行)"""
# 旧路径:引用已归档的 collect_homepage_info.py(不存在)
# 改为通过 CommandBus 分发 mc run 采集蓝图
try:
sys.path.insert(0, str(SCRIPTS_DIR.parent.parent / "10_dashboard"))
from services.command_bus import CommandBus
result = CommandBus.dispatch("collect", [account_name], {"rounds": 1})
status = "ok" if result.get("status") in ("accepted", "completed") else "error"
return {"status": status, "message": f"已通过 CommandBus 分发: {result.get('status', '?')}"}
except Exception as e:
return {"status": "error", "message": f"CommandBus 分发失败: {e}"}
def login(self, account_name: str, headless: bool = False) -> dict:
"""打开浏览器登录"""
login_script = SCRIPTS_DIR / "login_identity.py"
identity = self._resolve_account(account_name)
cmd = [sys.executable, str(login_script), identity, "--platform", "douyin"]
try:
subprocess.Popen(cmd, cwd=str(SCRIPTS_DIR))
return {"status": "ok", "message": f"浏览器已打开, 请扫码登录 {account_name}"}
except Exception as e:
return {"status": "error", "message": str(e)}
def status(self, account_name: str) -> dict:
"""检查登录状态"""
try:
sys.path.insert(0, str(SCRIPTS_DIR))
from auth_manager import check_login_by_cookie_sync, get_session_id
from matrix_mgmt import MatrixManager
mgr = MatrixManager()
for a in mgr.list_accounts():
if (a.get("phone") == account_name or a["id"] == account_name) and a.get("platform") == "douyin":
# 检查 Cookie
cookies_path = AGENT_LOCAL / "identities" / (a.get("identity_dir", a["id"]).replace("identities/", "")) / "user_data" / "cookies.sqlite"
if cookies_path.exists():
return {"status": "logged_in", "account": a["id"]}
return {"status": "no_cookie", "account": a["id"]}
return {"status": "not_found"}
except Exception as e:
return {"status": "error", "message": str(e)}
def publish(self, account_name: str, file_path: str = "", title: str = "", desc: str = "") -> dict:
"""发布视频到抖音"""
identity = self._resolve_account(account_name)
publish_script = SCRIPTS_DIR / "publish_video.py"
if not Path(file_path).exists():
return {"status": "error", "message": f"文件不存在: {file_path}"}
cmd = [sys.executable, str(publish_script), "douyin",
"--account", identity, "--file", str(Path(file_path).resolve())]
if title:
cmd += ["--title", title]
if desc:
cmd += ["--desc", desc]
try:
p = subprocess.run(cmd, cwd=str(SCRIPTS_DIR), capture_output=True, text=True, timeout=300)
return {"status": "ok" if p.returncode == 0 else "error", "output": p.stdout[-500:]}
except subprocess.TimeoutExpired:
return {"status": "error", "message": "发布超时 (300s)"}
except Exception as e:
return {"status": "error", "message": str(e)}
Douyin = DouyinPlatform
@@ -0,0 +1,18 @@
# 小红书平台插件
## 能力
| 接口 | 状态 | 说明 |
|------|:----:|------|
| login | ✅ | 打开浏览器扫码登录 |
| collect | ✅ | 采集小红书主页信息 |
| status | ✅ | 检查登录状态 |
| publish | 📋 | 计划中 (集成 social-auto-upload) |
## 用法
```bash
mc xiaohongshu collect --account 手机号
mc xiaohongshu login --account 手机号
mc xiaohongshu status --account 手机号
```
@@ -0,0 +1,7 @@
"""小红书平台插件"""
from .plugin import XiaohongshuPlatform
def register_platform():
return "xiaohongshu", XiaohongshuPlatform()
@@ -0,0 +1,97 @@
"""小红书插件实现
⚠️ DEPRECATED: 本插件层的功能已被 CommandBus + mc 引擎取代。
所有执行操作请走:
- 看板: POST /api/ops/run {type:'collect'|'nurture'|'login', accounts, params}
- CLI: mc run / mc collect / mc smart-login
platforms/ 层将在后续清理中移除。
"""
import json
import subprocess
import sys
from pathlib import Path
from platforms.base import BasePlatform
SCRIPTS_DIR = Path(__file__).resolve().parent.parent.parent / "scripts"
AGENT_LOCAL = Path.home() / "workbuddy-agent-os" / "agent-local"
class XiaohongshuPlatform(BasePlatform):
name = "xiaohongshu"
display_name = "小红书"
version = "1.0.0"
description = "小红书账号管理: 登录/采集"
def _resolve_account(self, account_name: str) -> str:
try:
sys.path.insert(0, str(SCRIPTS_DIR))
from matrix_mgmt import MatrixManager
mgr = MatrixManager()
for a in mgr.list_accounts():
if a.get("phone") == account_name or a["id"] == account_name:
if a.get("platform") == "xiaohongshu":
return a.get("identity_dir", a["id"]).replace("identities/", "")
except: pass
return account_name
def collect(self, account_name: str) -> dict:
"""采集主页信息(建议通过 mc run --blueprints=xiaohongshu_read_profile 执行)"""
# 旧路径:引用已归档的 collect_homepage_info.py(不存在)
# 改为通过 CommandBus 分发 mc run 采集蓝图
try:
sys.path.insert(0, str(SCRIPTS_DIR.parent.parent / "10_dashboard"))
from services.command_bus import CommandBus
result = CommandBus.dispatch("collect", [account_name], {"rounds": 1})
status = "ok" if result.get("status") in ("accepted", "completed") else "error"
return {"status": status, "message": f"已通过 CommandBus 分发: {result.get('status', '?')}"}
except Exception as e:
return {"status": "error", "message": f"CommandBus 分发失败: {e}"}
def login(self, account_name: str, headless: bool = False) -> dict:
login_script = SCRIPTS_DIR / "login_identity.py"
identity = self._resolve_account(account_name)
cmd = [sys.executable, str(login_script), identity, "--platform", "xiaohongshu"]
try:
subprocess.Popen(cmd, cwd=str(SCRIPTS_DIR))
return {"status": "ok", "message": f"浏览器已打开, 请扫码登录 {account_name}"}
except Exception as e:
return {"status": "error", "message": str(e)}
def status(self, account_name: str) -> dict:
try:
from matrix_mgmt import MatrixManager
mgr = MatrixManager()
for a in mgr.list_accounts():
if (a.get("phone") == account_name or a["id"] == account_name) and a.get("platform") == "xiaohongshu":
cookies_path = AGENT_LOCAL / "identities" / (a.get("identity_dir", a["id"]).replace("identities/", "")) / "user_data" / "cookies.sqlite"
if cookies_path.exists():
return {"status": "logged_in", "account": a["id"]}
return {"status": "no_cookie", "account": a["id"]}
return {"status": "not_found"}
except Exception as e:
return {"status": "error", "message": str(e)}
def publish(self, account_name: str, file_path: str = "", title: str = "", desc: str = "") -> dict:
"""发布笔记到小红书"""
identity = self._resolve_account(account_name)
publish_script = SCRIPTS_DIR / "publish_video.py"
if not Path(file_path).exists():
return {"status": "error", "message": f"文件不存在: {file_path}"}
cmd = [sys.executable, str(publish_script), "xiaohongshu",
"--account", identity, "--file", str(Path(file_path).resolve())]
if title:
cmd += ["--title", title]
if desc:
cmd += ["--desc", desc]
try:
p = subprocess.run(cmd, cwd=str(SCRIPTS_DIR), capture_output=True, text=True, timeout=300)
return {"status": "ok" if p.returncode == 0 else "error", "output": p.stdout[-500:]}
except subprocess.TimeoutExpired:
return {"status": "error", "message": "发布超时 (300s)"}
except Exception as e:
return {"status": "error", "message": str(e)}
Xiaohongshu = XiaohongshuPlatform