sso.douyin.com 有 JS 反爬,纯 HTTP 无法通过。 改用 Microsoft.Playwright 驱动 Headless Chromium 打开 creator.douyin.com 登录页,直接提取 QR 码 base64 和登录后 Cookie。 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
+30
-19
@@ -1,14 +1,11 @@
|
|||||||
# 多阶段构建 Dockerfile
|
# 多阶段构建 Dockerfile
|
||||||
# 第一阶段:构建前端
|
# 第一阶段:构建前端
|
||||||
# 使用官方 Docker Hub(mcr 能访问的环境一般也能访问 docker.io)
|
|
||||||
FROM node:18-alpine AS frontend-builder
|
FROM node:18-alpine AS frontend-builder
|
||||||
|
|
||||||
WORKDIR /app/frontend
|
WORKDIR /app/frontend
|
||||||
|
|
||||||
# 复制前端依赖文件
|
|
||||||
COPY app/package.json app/pnpm-lock.yaml* ./
|
COPY app/package.json app/pnpm-lock.yaml* ./
|
||||||
|
|
||||||
# 配置 npm 和 pnpm 使用国内镜像源
|
|
||||||
RUN npm config set registry https://registry.npmmirror.com && \
|
RUN npm config set registry https://registry.npmmirror.com && \
|
||||||
npm install -g pnpm && \
|
npm install -g pnpm && \
|
||||||
pnpm config set registry https://registry.npmmirror.com && \
|
pnpm config set registry https://registry.npmmirror.com && \
|
||||||
@@ -18,33 +15,30 @@ RUN npm config set registry https://registry.npmmirror.com && \
|
|||||||
npm install; \
|
npm install; \
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# 复制前端源码
|
|
||||||
COPY app/ ./
|
COPY app/ ./
|
||||||
|
|
||||||
# 构建前端
|
|
||||||
RUN pnpm build || npm run build
|
RUN pnpm build || npm run build
|
||||||
|
|
||||||
# 第二阶段:构建后端
|
# 第二阶段:构建后端 + 下载 Playwright Chromium
|
||||||
FROM mcr.microsoft.com/dotnet/sdk:6.0 AS backend-builder
|
FROM mcr.microsoft.com/dotnet/sdk:6.0 AS backend-builder
|
||||||
|
|
||||||
WORKDIR /src
|
WORKDIR /src
|
||||||
|
|
||||||
# 复制项目文件
|
|
||||||
COPY *.csproj ./
|
COPY *.csproj ./
|
||||||
RUN dotnet restore dy.net.csproj
|
RUN dotnet restore dy.net.csproj
|
||||||
|
|
||||||
# 复制所有文件
|
|
||||||
COPY . .
|
COPY . .
|
||||||
|
|
||||||
# 删除 macOS 资源分叉文件(._* 文件)
|
|
||||||
RUN find . -name "._*" -type f -delete
|
RUN find . -name "._*" -type f -delete
|
||||||
|
|
||||||
# 复制前端构建产物
|
|
||||||
COPY --from=frontend-builder /app/frontend/dist ./app/dist
|
COPY --from=frontend-builder /app/frontend/dist ./app/dist
|
||||||
|
|
||||||
# 发布后端
|
|
||||||
RUN dotnet publish dy.net.csproj -c Release -o /app/publish
|
RUN dotnet publish dy.net.csproj -c Release -o /app/publish
|
||||||
|
|
||||||
|
# 安装 Playwright CLI 并下载 Chromium 浏览器到固定路径
|
||||||
|
ENV PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
|
||||||
|
RUN dotnet tool install --global Microsoft.Playwright.CLI --version 1.44.0 2>/dev/null || true && \
|
||||||
|
/root/.dotnet/tools/playwright install chromium --with-deps 2>/dev/null || \
|
||||||
|
dotnet /app/publish/playwright.ps1 install chromium 2>/dev/null || true
|
||||||
|
|
||||||
# 第三阶段:运行镜像
|
# 第三阶段:运行镜像
|
||||||
FROM mcr.microsoft.com/dotnet/aspnet:6.0 AS final
|
FROM mcr.microsoft.com/dotnet/aspnet:6.0 AS final
|
||||||
|
|
||||||
@@ -54,16 +48,33 @@ WORKDIR /app
|
|||||||
ENV TZ=Asia/Shanghai
|
ENV TZ=Asia/Shanghai
|
||||||
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
|
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
|
||||||
|
|
||||||
# 从构建阶段复制发布文件
|
# 安装 Chromium 运行时依赖(Debian Bullseye)
|
||||||
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||||
|
libnss3 \
|
||||||
|
libatk1.0-0 \
|
||||||
|
libatk-bridge2.0-0 \
|
||||||
|
libcups2 \
|
||||||
|
libdrm2 \
|
||||||
|
libxkbcommon0 \
|
||||||
|
libxcomposite1 \
|
||||||
|
libxdamage1 \
|
||||||
|
libxfixes3 \
|
||||||
|
libxrandr2 \
|
||||||
|
libgbm1 \
|
||||||
|
libasound2 \
|
||||||
|
libpango-1.0-0 \
|
||||||
|
libpangocairo-1.0-0 \
|
||||||
|
libgtk-3-0 \
|
||||||
|
fonts-liberation \
|
||||||
|
&& rm -rf /var/lib/apt/lists/*
|
||||||
|
|
||||||
|
# 从构建阶段复制应用和浏览器
|
||||||
COPY --from=backend-builder /app/publish .
|
COPY --from=backend-builder /app/publish .
|
||||||
|
COPY --from=backend-builder /ms-playwright /ms-playwright
|
||||||
|
|
||||||
# 暴露端口
|
ENV PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
|
||||||
EXPOSE 10101
|
EXPOSE 10101
|
||||||
|
|
||||||
# 设置环境变量
|
|
||||||
ENV ASPNETCORE_URLS=http://*:10101
|
ENV ASPNETCORE_URLS=http://*:10101
|
||||||
ENV ASPNETCORE_ENVIRONMENT=Production
|
ENV ASPNETCORE_ENVIRONMENT=Production
|
||||||
|
|
||||||
# 启动应用
|
|
||||||
ENTRYPOINT ["dotnet", "dy.net.dll"]
|
ENTRYPOINT ["dotnet", "dy.net.dll"]
|
||||||
|
|
||||||
|
|||||||
@@ -57,6 +57,7 @@
|
|||||||
<PackageReference Include="System.Net.Http" Version="4.3.4" />
|
<PackageReference Include="System.Net.Http" Version="4.3.4" />
|
||||||
<PackageReference Include="System.Text.RegularExpressions" Version="4.3.1" />
|
<PackageReference Include="System.Text.RegularExpressions" Version="4.3.1" />
|
||||||
<PackageReference Include="BouncyCastle.NetCore" Version="2.2.1" />
|
<PackageReference Include="BouncyCastle.NetCore" Version="2.2.1" />
|
||||||
|
<PackageReference Include="Microsoft.Playwright" Version="1.44.0" />
|
||||||
</ItemGroup>
|
</ItemGroup>
|
||||||
|
|
||||||
<ItemGroup>
|
<ItemGroup>
|
||||||
|
|||||||
+91
-92
@@ -1,6 +1,5 @@
|
|||||||
using System.Collections.Concurrent;
|
using System.Collections.Concurrent;
|
||||||
using System.Net;
|
using Microsoft.Playwright;
|
||||||
using Newtonsoft.Json.Linq;
|
|
||||||
|
|
||||||
namespace dy.net.service
|
namespace dy.net.service
|
||||||
{
|
{
|
||||||
@@ -10,83 +9,100 @@ namespace dy.net.service
|
|||||||
|
|
||||||
private class QrSession
|
private class QrSession
|
||||||
{
|
{
|
||||||
public CookieContainer CookieJar { get; set; } = new();
|
public IPlaywright Playwright { get; set; }
|
||||||
|
public IBrowser Browser { get; set; }
|
||||||
|
public IBrowserContext Context { get; set; }
|
||||||
|
public IPage Page { get; set; }
|
||||||
public DateTime CreatedAt { get; set; } = DateTime.Now;
|
public DateTime CreatedAt { get; set; } = DateTime.Now;
|
||||||
public string? FinalCookies { get; set; }
|
public string FinalCookies { get; set; }
|
||||||
public string? SecUserId { get; set; }
|
public string SecUserId { get; set; }
|
||||||
}
|
}
|
||||||
|
|
||||||
private const string Fp = "kj5j6uhv_tvKYUFA0_qzgZ_4l9c_9Amt_DCywEfwbVFCJ";
|
private const string LoginUrl = "https://creator.douyin.com/creator-micro/login";
|
||||||
private const string NextUrl = "https://creator.douyin.com/content/manage";
|
// QR 码图片的 class 名含 qrcode_img(后缀随版本变化,用属性选择器匹配)
|
||||||
private const string Service = "https://creator.douyin.com";
|
private const string QrSelector = "img[class*='qrcode_img']";
|
||||||
private const string Aid = "2906";
|
|
||||||
private const string Ua = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36";
|
|
||||||
private const string Referer = "https://creator.douyin.com/";
|
|
||||||
|
|
||||||
public async Task<(string token, string qrBase64)> GetQrCodeAsync()
|
public async Task<(string token, string qrBase64)> GetQrCodeAsync()
|
||||||
{
|
{
|
||||||
var jar = new CookieContainer();
|
|
||||||
using var client = BuildClient(jar, autoRedirect: true);
|
|
||||||
|
|
||||||
var url = $"https://sso.douyin.com/get_qrcode/?next={Uri.EscapeDataString(NextUrl)}&aid={Aid}&service={Uri.EscapeDataString(Service)}&is_vcd=1&fp={Fp}";
|
|
||||||
var response = await client.GetStringAsync(url);
|
|
||||||
var json = JObject.Parse(response);
|
|
||||||
|
|
||||||
var token = json["data"]?["token"]?.ToString()
|
|
||||||
?? throw new Exception("获取二维码失败:响应中无 token");
|
|
||||||
var qrBase64 = json["data"]?["qrcode"]?.ToString()
|
|
||||||
?? throw new Exception("获取二维码失败:响应中无图片");
|
|
||||||
|
|
||||||
_sessions[token] = new QrSession { CookieJar = jar };
|
|
||||||
CleanExpiredSessions();
|
CleanExpiredSessions();
|
||||||
|
|
||||||
|
var playwright = await Playwright.CreateAsync();
|
||||||
|
var browser = await playwright.Chromium.LaunchAsync(new BrowserTypeLaunchOptions
|
||||||
|
{
|
||||||
|
Headless = true,
|
||||||
|
Args = new[] { "--no-sandbox", "--disable-setuid-sandbox", "--disable-dev-shm-usage" }
|
||||||
|
});
|
||||||
|
var context = await browser.NewContextAsync(new BrowserNewContextOptions
|
||||||
|
{
|
||||||
|
UserAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36"
|
||||||
|
});
|
||||||
|
var page = await context.NewPageAsync();
|
||||||
|
|
||||||
|
await page.GotoAsync(LoginUrl, new PageGotoOptions { Timeout = 15000 });
|
||||||
|
await page.WaitForSelectorAsync(QrSelector, new PageWaitForSelectorOptions { Timeout = 10000 });
|
||||||
|
|
||||||
|
// img.src 已经是 data:image/png;base64,... 直接取用
|
||||||
|
var src = await page.EvaluateAsync<string>($"() => document.querySelector(\"{QrSelector}\").src");
|
||||||
|
var qrBase64 = src.Replace("data:image/png;base64,", "");
|
||||||
|
|
||||||
|
var token = Guid.NewGuid().ToString("N");
|
||||||
|
_sessions[token] = new QrSession
|
||||||
|
{
|
||||||
|
Playwright = playwright,
|
||||||
|
Browser = browser,
|
||||||
|
Context = context,
|
||||||
|
Page = page
|
||||||
|
};
|
||||||
|
|
||||||
return (token, qrBase64);
|
return (token, qrBase64);
|
||||||
}
|
}
|
||||||
|
|
||||||
public async Task<(int status, string? cookies, string? secUserId)> CheckStatusAsync(string token)
|
public async Task<(int status, string cookies, string secUserId)> CheckStatusAsync(string token)
|
||||||
{
|
{
|
||||||
if (!_sessions.TryGetValue(token, out var session))
|
if (!_sessions.TryGetValue(token, out var session))
|
||||||
return (-1, null, null);
|
return (-1, null, null);
|
||||||
|
|
||||||
if (DateTime.Now - session.CreatedAt > TimeSpan.FromMinutes(10))
|
if (DateTime.Now - session.CreatedAt > TimeSpan.FromMinutes(5))
|
||||||
{
|
{
|
||||||
_sessions.TryRemove(token, out _);
|
await CloseSessionAsync(token, session);
|
||||||
return (-1, null, null);
|
return (-1, null, null);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// 已经登录过,直接返回缓存
|
||||||
if (session.FinalCookies != null)
|
if (session.FinalCookies != null)
|
||||||
return (3, session.FinalCookies, session.SecUserId);
|
return (3, session.FinalCookies, session.SecUserId);
|
||||||
|
|
||||||
using var client = BuildClient(session.CookieJar, autoRedirect: false);
|
var url = session.Page.Url;
|
||||||
|
|
||||||
var serviceParam = Uri.EscapeDataString($"{Service}/?logintype=user&loginapp=douyin&jump={NextUrl}");
|
// 还在登录页
|
||||||
var url = $"https://sso.douyin.com/check_qrconnect/?next={Uri.EscapeDataString(NextUrl)}&token={token}&service={serviceParam}&loginapp=douyin&jump={Uri.EscapeDataString(NextUrl)}&correct_service={serviceParam}&aid={Aid}&is_vcd=1&fp={Fp}";
|
if (url.Contains("/creator-micro/login") || url.Contains("sso.douyin.com"))
|
||||||
var response = await client.GetStringAsync(url);
|
|
||||||
var json = JObject.Parse(response);
|
|
||||||
|
|
||||||
var statusStr = json["data"]?["status"]?.ToString() ?? "1";
|
|
||||||
int.TryParse(statusStr, out int statusCode);
|
|
||||||
|
|
||||||
if (statusCode == 3)
|
|
||||||
{
|
{
|
||||||
var redirectUrl = json["data"]?["redirect_url"]?.ToString();
|
// 判断是否已扫码(页面出现"确认"或"已扫码"文字)
|
||||||
if (!string.IsNullOrEmpty(redirectUrl))
|
var scanned = await session.Page.EvaluateAsync<bool>(
|
||||||
{
|
"() => { const t = document.body.innerText; return t.includes('已扫码') || t.includes('确认登录'); }"
|
||||||
try
|
);
|
||||||
{
|
return (scanned ? 2 : 1, null, null);
|
||||||
using var followClient = BuildClient(session.CookieJar, autoRedirect: true);
|
|
||||||
await followClient.GetAsync(redirectUrl);
|
|
||||||
session.FinalCookies = ExtractCookieString(session.CookieJar);
|
|
||||||
session.SecUserId = await GetSecUserIdAsync(session.CookieJar);
|
|
||||||
}
|
|
||||||
catch (Exception ex)
|
|
||||||
{
|
|
||||||
Serilog.Log.Error($"跟进登录重定向失败: {ex.Message}");
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
return (statusCode, session.FinalCookies, session.SecUserId);
|
// URL 已离开登录页,说明登录成功
|
||||||
|
var browserCookies = await session.Context.CookiesAsync(new[]
|
||||||
|
{
|
||||||
|
"https://creator.douyin.com",
|
||||||
|
"https://www.douyin.com",
|
||||||
|
"https://sso.douyin.com"
|
||||||
|
});
|
||||||
|
var cookieStr = string.Join("; ", browserCookies.Select(c => $"{c.Name}={c.Value}"));
|
||||||
|
|
||||||
|
// 尝试从页面获取 sec_user_id
|
||||||
|
var secUserId = await GetSecUserIdAsync(session.Page);
|
||||||
|
|
||||||
|
session.FinalCookies = cookieStr;
|
||||||
|
session.SecUserId = secUserId;
|
||||||
|
|
||||||
|
// 登录完成后关闭浏览器释放资源
|
||||||
|
_ = Task.Run(async () => await CloseSessionAsync(token, session));
|
||||||
|
|
||||||
|
return (3, cookieStr, secUserId);
|
||||||
}
|
}
|
||||||
|
|
||||||
public (string cookies, string secUserId) GetSessionResult(string token)
|
public (string cookies, string secUserId) GetSessionResult(string token)
|
||||||
@@ -96,59 +112,42 @@ namespace dy.net.service
|
|||||||
return ("", "");
|
return ("", "");
|
||||||
}
|
}
|
||||||
|
|
||||||
public void RemoveSession(string token) => _sessions.TryRemove(token, out _);
|
public void RemoveSession(string token)
|
||||||
|
|
||||||
private static HttpClient BuildClient(CookieContainer jar, bool autoRedirect)
|
|
||||||
{
|
{
|
||||||
var handler = new HttpClientHandler
|
if (_sessions.TryRemove(token, out var session))
|
||||||
{
|
_ = Task.Run(async () => await CloseSessionAsync(token, session));
|
||||||
CookieContainer = jar,
|
|
||||||
AllowAutoRedirect = autoRedirect,
|
|
||||||
UseCookies = true
|
|
||||||
};
|
|
||||||
var client = new HttpClient(handler);
|
|
||||||
client.DefaultRequestHeaders.Add("User-Agent", Ua);
|
|
||||||
client.DefaultRequestHeaders.Add("Referer", Referer);
|
|
||||||
return client;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
private static string ExtractCookieString(CookieContainer jar)
|
private static async Task<string> GetSecUserIdAsync(IPage page)
|
||||||
{
|
|
||||||
var domains = new[] { "https://www.douyin.com", "https://creator.douyin.com", "https://sso.douyin.com" };
|
|
||||||
var all = new Dictionary<string, string>();
|
|
||||||
foreach (var domain in domains)
|
|
||||||
{
|
|
||||||
foreach (Cookie c in jar.GetCookies(new Uri(domain)))
|
|
||||||
all[c.Name] = c.Value;
|
|
||||||
}
|
|
||||||
return string.Join("; ", all.Select(kv => $"{kv.Key}={kv.Value}"));
|
|
||||||
}
|
|
||||||
|
|
||||||
private static async Task<string?> GetSecUserIdAsync(CookieContainer jar)
|
|
||||||
{
|
{
|
||||||
try
|
try
|
||||||
{
|
{
|
||||||
using var client = BuildClient(jar, autoRedirect: true);
|
// 从页面 URL 或 API 提取 sec_user_id
|
||||||
var resp = await client.GetStringAsync("https://creator.douyin.com/web/api/userinfo/");
|
var resp = await page.EvaluateAsync<string>(
|
||||||
var json = JObject.Parse(resp);
|
"async () => { const r = await fetch('/web/api/userinfo/'); const j = await r.json(); return j?.data?.sec_uid || j?.sec_uid || ''; }"
|
||||||
return json["data"]?["sec_uid"]?.ToString()
|
);
|
||||||
?? json["data"]?["sec_user_id"]?.ToString()
|
return resp ?? "";
|
||||||
?? json["sec_uid"]?.ToString();
|
|
||||||
}
|
}
|
||||||
catch (Exception ex)
|
catch
|
||||||
{
|
{
|
||||||
Serilog.Log.Error($"获取 sec_user_id 失败: {ex.Message}");
|
return "";
|
||||||
return null;
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
private static async Task CloseSessionAsync(string token, QrSession session)
|
||||||
|
{
|
||||||
|
_sessions.TryRemove(token, out _);
|
||||||
|
try { await session.Browser?.CloseAsync(); } catch { }
|
||||||
|
try { session.Playwright?.Dispose(); } catch { }
|
||||||
|
}
|
||||||
|
|
||||||
private static void CleanExpiredSessions()
|
private static void CleanExpiredSessions()
|
||||||
{
|
{
|
||||||
var expired = _sessions
|
var expired = _sessions
|
||||||
.Where(kv => DateTime.Now - kv.Value.CreatedAt > TimeSpan.FromMinutes(10))
|
.Where(kv => DateTime.Now - kv.Value.CreatedAt > TimeSpan.FromMinutes(6))
|
||||||
.Select(kv => kv.Key).ToList();
|
.ToList();
|
||||||
foreach (var key in expired)
|
foreach (var kv in expired)
|
||||||
_sessions.TryRemove(key, out _);
|
_ = Task.Run(async () => await CloseSessionAsync(kv.Key, kv.Value));
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user