我正在使用此方法以编程方式实例化网络浏览器，导航到 url 并在文档完成时返回结果。
如果文档加载时间超过 5 秒，我将如何停止 Task 并让 GetFinalUrl() 返回 null ？
我见过许多使用 TaskFactory 的示例，但我无法将其应用到这段代码中。
private Uri GetFinalUrl(PortalMerchant portalMerchant)
{
SetBrowserFeatureControl();
Uri finalUri = null;
if (string.IsNullOrEmpty(portalMerchant.Url))
{
return null;
}
Uri trackingUrl = new Uri(portalMerchant.Url);
var task = MessageLoopWorker.Run(DoWorkAsync, trackingUrl);
task.Wait();
if (!String.IsNullOrEmpty(task.Result.ToString()))
{
return new Uri(task.Result.ToString());
}
else
{
throw new Exception("Parsing Failed");
}
}
// by Noseratio - http://stackoverflow.com/users/1768303/noseratio
static async Task<object> DoWorkAsync(object[] args)
{
_threadCount++;
Console.WriteLine("Thread count:" + _threadCount);
Uri retVal = null;
var wb = new WebBrowser();
wb.ScriptErrorsSuppressed = true;
TaskCompletionSource<bool> tcs = null;
WebBrowserDocumentCompletedEventHandler documentCompletedHandler = (s, e) => tcs.TrySetResult(true);
foreach (var url in args)
{
tcs = new TaskCompletionSource<bool>();
wb.DocumentCompleted += documentCompletedHandler;
try
{
wb.Navigate(url.ToString());
await tcs.Task;
}
finally
{
wb.DocumentCompleted -= documentCompletedHandler;
}
retVal = wb.Url;
wb.Dispose();
return retVal;
}
return null;
}
public static class MessageLoopWorker
{
#region Public static methods
public static async Task<object> Run(Func<object[], Task<object>> worker, params object[] args)
{
var tcs = new TaskCompletionSource<object>();
var thread = new Thread(() =>
{
EventHandler idleHandler = null;
idleHandler = async (s, e) =>
{
// handle Application.Idle just once
Application.Idle -= idleHandler;
// return to the message loop
await Task.Yield();
// and continue asynchronously
// propogate the result or exception
try
{
var result = await worker(args);
tcs.SetResult(result);
}
catch (Exception ex)
{
tcs.SetException(ex);
}
// signal to exit the message loop
// Application.Run will exit at this point
Application.ExitThread();
};
// handle Application.Idle just once
// to make sure we're inside the message loop
// and SynchronizationContext has been correctly installed
Application.Idle += idleHandler;
Application.Run();
});
// set STA model for the new thread
thread.SetApartmentState(ApartmentState.STA);
// start the thread and await for the task
thread.Start();
try
{
return await tcs.Task;
}
finally
{
thread.Join();
}
}
#endregion
}
最佳答案
已更新:最新版本的基于WebBrowser的控制台网络scraper可以是found on Github .
更新:Adding a pool of WebBrowser objects用于多个并行下载。
Do you have an example of how to do this in a console app by any chance? Also I don't think webBrowser can be a class variable because I am running the whole thing in a parallell for each, iterating thousands of URLs
下面是或多或少通用的 **WebBrowser-based web scraper ** 的实现，它作为控制台应用程序工作。它整合了我之前与 WebBrowser 相关的一些工作，包括问题中引用的代码:
几点:
可重用
MessageLoopApartment类用于启动和运行带有自己的消息泵的 WinForms STA 线程。它可以从控制台应用程序中使用，如下所示。此类公开 TPL 任务计划程序 (FromCurrentSynchronizationContext) 和一组Task.Factory.StartNew包装器以使用此任务计划程序。这使得
async/await成为在单独的 STA 线程上运行WebBrowser导航任务的绝佳工具。这样，一个WebBrowser对象就在该线程上被创建、导航和销毁。虽然，MessageLoopApartment并未专门绑定(bind)到WebBrowser。使用 Browser Feature Control 启用 HTML5 渲染很重要，否则
WebBrowser对象默认在 IE7 仿真模式下运行。 这就是SetFeatureBrowserEmulation下面所做的。可能无法始终以 100% 的概率确定网页何时完成呈现。一些页面非常复杂并且使用连续的 AJAX 更新。然而我们 通过首先处理
DocumentCompleted事件，然后轮询页面的当前 HTML 快照以了解更改并检查WebBrowser.IsBusy属性，可以非常接近。这就是NavigateAsync下面所做的。超时逻辑存在于上述之上，以防页面呈现永无止境(注意
CancellationTokenSource和CreateLinkedTokenSource)。
using Microsoft.Win32;
using System;
using System.Threading;
using System.Threading.Tasks;
using System.Windows.Forms;
namespace Console_22239357
{
class Program
{
// by Noseratio - https://stackoverflow.com/a/22262976/1768303
// main logic
static async Task ScrapeSitesAsync(string[] urls, CancellationToken token)
{
using (var apartment = new MessageLoopApartment())
{
// create WebBrowser inside MessageLoopApartment
var webBrowser = apartment.Invoke(() => new WebBrowser());
try
{
foreach (var url in urls)
{
Console.WriteLine("URL:\n" + url);
// cancel in 30s or when the main token is signalled
var navigationCts = CancellationTokenSource.CreateLinkedTokenSource(token);
navigationCts.CancelAfter((int)TimeSpan.FromSeconds(30).TotalMilliseconds);
var navigationToken = navigationCts.Token;
// run the navigation task inside MessageLoopApartment
string html = await apartment.Run(() =>
webBrowser.NavigateAsync(url, navigationToken), navigationToken);
Console.WriteLine("HTML:\n" + html);
}
}
finally
{
// dispose of WebBrowser inside MessageLoopApartment
apartment.Invoke(() => webBrowser.Dispose());
}
}
}
// entry point
static void Main(string[] args)
{
try
{
WebBrowserExt.SetFeatureBrowserEmulation(); // enable HTML5
var cts = new CancellationTokenSource((int)TimeSpan.FromMinutes(3).TotalMilliseconds);
var task = ScrapeSitesAsync(
new[] { "http://example.com", "http://example.org", "http://example.net" },
cts.Token);
task.Wait();
Console.WriteLine("Press Enter to exit...");
Console.ReadLine();
}
catch (Exception ex)
{
while (ex is AggregateException && ex.InnerException != null)
ex = ex.InnerException;
Console.WriteLine(ex.Message);
Environment.Exit(-1);
}
}
}
/// <summary>
/// WebBrowserExt - WebBrowser extensions
/// by Noseratio - https://stackoverflow.com/a/22262976/1768303
/// </summary>
public static class WebBrowserExt
{
const int POLL_DELAY = 500;
// navigate and download
public static async Task<string> NavigateAsync(this WebBrowser webBrowser, string url, CancellationToken token)
{
// navigate and await DocumentCompleted
var tcs = new TaskCompletionSource<bool>();
WebBrowserDocumentCompletedEventHandler handler = (s, arg) =>
tcs.TrySetResult(true);
using (token.Register(() => tcs.TrySetCanceled(), useSynchronizationContext: true))
{
webBrowser.DocumentCompleted += handler;
try
{
webBrowser.Navigate(url);
await tcs.Task; // wait for DocumentCompleted
}
finally
{
webBrowser.DocumentCompleted -= handler;
}
}
// get the root element
var documentElement = webBrowser.Document.GetElementsByTagName("html")[0];
// poll the current HTML for changes asynchronosly
var html = documentElement.OuterHtml;
while (true)
{
// wait asynchronously, this will throw if cancellation requested
await Task.Delay(POLL_DELAY, token);
// continue polling if the WebBrowser is still busy
if (webBrowser.IsBusy)
continue;
var htmlNow = documentElement.OuterHtml;
if (html == htmlNow)
break; // no changes detected, end the poll loop
html = htmlNow;
}
// consider the page fully rendered
token.ThrowIfCancellationRequested();
return html;
}
// enable HTML5 (assuming we're running IE10+)
// more info: https://stackoverflow.com/a/18333982/1768303
public static void SetFeatureBrowserEmulation()
{
if (System.ComponentModel.LicenseManager.UsageMode != System.ComponentModel.LicenseUsageMode.Runtime)
return;
var appName = System.IO.Path.GetFileName(System.Diagnostics.Process.GetCurrentProcess().MainModule.FileName);
Registry.SetValue(@"HKEY_CURRENT_USER\Software\Microsoft\Internet Explorer\Main\FeatureControl\FEATURE_BROWSER_EMULATION",
appName, 10000, RegistryValueKind.DWord);
}
}
/// <summary>
/// MessageLoopApartment
/// STA thread with message pump for serial execution of tasks
/// by Noseratio - https://stackoverflow.com/a/22262976/1768303
/// </summary>
public class MessageLoopApartment : IDisposable
{
Thread _thread; // the STA thread
TaskScheduler _taskScheduler; // the STA thread's task scheduler
public TaskScheduler TaskScheduler { get { return _taskScheduler; } }
/// <summary>MessageLoopApartment constructor</summary>
public MessageLoopApartment()
{
var tcs = new TaskCompletionSource<TaskScheduler>();
// start an STA thread and gets a task scheduler
_thread = new Thread(startArg =>
{
EventHandler idleHandler = null;
idleHandler = (s, e) =>
{
// handle Application.Idle just once
Application.Idle -= idleHandler;
// return the task scheduler
tcs.SetResult(TaskScheduler.FromCurrentSynchronizationContext());
};
// handle Application.Idle just once
// to make sure we're inside the message loop
// and SynchronizationContext has been correctly installed
Application.Idle += idleHandler;
Application.Run();
});
_thread.SetApartmentState(ApartmentState.STA);
_thread.IsBackground = true;
_thread.Start();
_taskScheduler = tcs.Task.Result;
}
/// <summary>shutdown the STA thread</summary>
public void Dispose()
{
if (_taskScheduler != null)
{
var taskScheduler = _taskScheduler;
_taskScheduler = null;
// execute Application.ExitThread() on the STA thread
Task.Factory.StartNew(
() => Application.ExitThread(),
CancellationToken.None,
TaskCreationOptions.None,
taskScheduler).Wait();
_thread.Join();
_thread = null;
}
}
/// <summary>Task.Factory.StartNew wrappers</summary>
public void Invoke(Action action)
{
Task.Factory.StartNew(action,
CancellationToken.None, TaskCreationOptions.None, _taskScheduler).Wait();
}
public TResult Invoke<TResult>(Func<TResult> action)
{
return Task.Factory.StartNew(action,
CancellationToken.None, TaskCreationOptions.None, _taskScheduler).Result;
}
public Task Run(Action action, CancellationToken token)
{
return Task.Factory.StartNew(action, token, TaskCreationOptions.None, _taskScheduler);
}
public Task<TResult> Run<TResult>(Func<TResult> action, CancellationToken token)
{
return Task.Factory.StartNew(action, token, TaskCreationOptions.None, _taskScheduler);
}
public Task Run(Func<Task> action, CancellationToken token)
{
return Task.Factory.StartNew(action, token, TaskCreationOptions.None, _taskScheduler).Unwrap();
}
public Task<TResult> Run<TResult>(Func<Task<TResult>> action, CancellationToken token)
{
return Task.Factory.StartNew(action, token, TaskCreationOptions.None, _taskScheduler).Unwrap();
}
}
}
关于c# - 如何在超时后取消任务等待，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/22239357/