Files
MediaCrawler/mac-agent-os-main/05_tools/07_matrix/scripts/page_state.py
T
butubb 2112c1a870
Deploy VitePress site to Pages / build (push) Canceled after 0s
Deploy VitePress site to Pages / Deploy (push) Canceled after 0s
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

198 lines
6.3 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python3
"""
PageState — 页面状态管理 (v1.0.0)
功能:
- 检测当前页面模式 (grid/player/search/unknown)
- 验证登录态 (Cookie + DOM + 标题多维检测)
- 提供状态切换建议 (下一步该做什么)
用法:
state = PageState(page)
mode = await state.detect() # → "grid" | "player" | "search"
ok = await state.check_login()
next = await state.suggest() # → 建议下一步操作
"""
import asyncio
from typing import Optional
__version__ = "1.0.0"
# 各模式的特征元素
MODE_SIGNATURES = {
"grid": {
"name": "首页卡片列表",
"anchors": ['[data-e2e="alink-item"]'],
"description": "显示视频卡片的推荐/精选页",
},
"player": {
"name": "视频播放器",
"anchors": ['[data-e2e="video-player-digg"]', '[data-e2e="video-player-collect"]'],
"description": "单个视频播放页,有点赞/收藏按钮",
},
"search": {
"name": "搜索结果",
"anchors": ['[data-e2e="searchbar-input"]', '.search-container'],
"description": "搜索结果页,显示视频列表",
},
}
class PageState:
"""页面状态管理器"""
def __init__(self, page):
self.page = page
self._mode = "unknown"
self._last_check = 0
async def detect(self) -> str:
"""检测当前页面模式"""
for mode, sig in MODE_SIGNATURES.items():
for anchor in sig["anchors"]:
try:
el = await self.page.query_selector(anchor)
if el:
self._mode = mode
self._last_check = asyncio.get_event_loop().time()
return mode
except Exception:
pass
# Fallback: 通过 URL 判断
url = self.page.url
if "/video/" in url:
self._mode = "player"
elif "/search/" in url:
self._mode = "search"
elif "/jingxuan" in url or url.endswith("/douyin.com/"):
self._mode = "grid"
else:
self._mode = "unknown"
self._last_check = asyncio.get_event_loop().time()
return self._mode
@property
def mode(self) -> str:
"""当前模式(可能过期,建议先调用 detect())"""
return self._mode
@property
def description(self) -> str:
"""当前模式的中文描述"""
sig = MODE_SIGNATURES.get(self._mode)
return sig["description"] if sig else "未知页面"
async def check_login(self) -> dict:
"""多维登录验证
返回:
{"logged_in": bool, "method": str, "detail": str}
"""
results = []
# 1. Cookie 检查
try:
cookies = await self.page.context.cookies()
dy = [c for c in cookies if "douyin" in c.get("domain", "")]
has_session = any(c["name"] == "sessionid" for c in dy)
has_sid = any(c["name"] == "sid_guard" for c in dy)
if has_session:
results.append(("cookie", True, "sessionid 存在"))
elif has_sid:
results.append(("cookie", True, "sid_guard 存在"))
else:
results.append(("cookie", False, "无登录态 Cookie"))
except Exception:
results.append(("cookie", False, "读取失败"))
# 2. DOM 检查
try:
avatar = await self.page.query_selector('[data-e2e="user-avatar"]')
detail = await self.page.query_selector('[data-e2e="user-detail"]')
if avatar or detail:
results.append(("dom", True, "用户头像可见"))
else:
results.append(("dom", False, "无头像元素"))
except Exception:
results.append(("dom", False, "检查失败"))
# 3. 标题检查
try:
title = await self.page.title()
if "登录" in title:
results.append(("title", False, "标题含登录字样"))
else:
results.append(("title", True, f"标题:{title[:30]}"))
except Exception:
results.append(("title", False, "读取失败"))
# 综合判断: 任意一个方法确认即可
positive = [r for r in results if r[1]]
logged_in = len(positive) >= 1
return {
"logged_in": logged_in,
"detail": results,
"methods_checked": len(results),
"methods_passed": len(positive),
}
async def suggest(self) -> list:
"""根据当前状态建议下一步操作"""
mode = await self.detect()
login_info = await self.check_login()
suggestions = []
if mode == "unknown":
suggestions.append({
"action": "goto_home",
"reason": "无法识别当前页面,跳转首页",
})
elif mode == "grid":
suggestions.append({
"action": "open_video",
"reason": "在首页,可以打开一个视频",
})
suggestions.append({
"action": "scroll_feed",
"reason": "浏览推荐内容",
})
# 如果未登录
if not login_info["logged_in"]:
decisions = "、".join(
[f"{r[0]}:{'✅' if r[1] else '❌'}" for r in login_info.get("detail", [])]
)
suggestions.append({
"action": "notify_login",
"reason": f"可能未登录 ({decisions})",
})
elif mode == "player":
suggestions.append({
"action": "like",
"reason": "在播放器,可以点赞",
})
suggestions.append({
"action": "collect",
"reason": "可以收藏",
})
suggestions.append({
"action": "next_video",
"reason": "可以看下一条",
})
suggestions.append({
"action": "wait_watch",
"reason": "观看一段时间",
})
elif mode == "search":
suggestions.append({
"action": "open_video",
"reason": "在搜索结果页,打开视频",
})
return suggestions