我正在使用此方法以编程方式实例化Web浏览器,导航到url并在文档完成后返回结果。
如果文档加载时间超过5秒,我如何能够停止Task
并GetFinalUrl()
返回null
?
我已经看到许多使用a的示例,TaskFactory
但是我无法将其应用于此代码。
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
}
已更新:WebBrowser
可以在Github上找到基于的控制台Web scraper的最新版本。
已更新:添加WebBrowser
对象池以进行多个并行下载。
您是否有机会在控制台应用程序中执行此操作的示例?另外,我也不认为webBrowser可以是一个类变量,因为我要为每个变量并行运行整个过程,从而迭代成千上万个URL
以下是或多或少WebBrowser
基于通用Web的scraper的实现,可作为控制台应用程序使用。这是我以前WebBrowser
相关工作的合并,包括问题中引用的代码:
几点:
可重用的MessageLoopApartment
类用于启动和运行带有自己的消息泵的WinForms STA线程。可以从控制台应用程序使用它,如下所示。此类公开了TPL任务计划程序(FromCurrentSynchronizationContext
)和一组Task.Factory.StartNew
包装程序以使用此任务计划程序。
这是在单独的STA线程上async/await
运行WebBrowser
导航任务的绝佳工具。这样,WebBrowser
就可以在该线程上创建,导航和销毁对象。虽然,MessageLoopApartment
不是WebBrowser
专门捆绑的。
使用浏览器功能控件启用HTML5渲染很重要,否则WebBrowser
默认情况下,对象将以IE7仿真模式运行。这就是SetFeatureBrowserEmulation
下面的内容。
不一定总是可以确定网页何时以100%的概率完成渲染。一些页面非常复杂,并使用连续的AJAX更新。但是,通过DocumentCompleted
首先处理事件,然后轮询页面的当前HTML快照以查找更改并检查WebBrowser.IsBusy
属性,我们可以得出非常接近的结论。这就是NavigateAsync
下面的内容。
如果页面渲染永无休止(请注意CancellationTokenSource
和CreateLinkedTokenSource
),则上述内容中会出现超时逻辑。
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 ScrapSitesAsync(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 = ScrapSitesAsync(
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();
}
}
}
本文收集自互联网,转载请注明来源。
如有侵权,请联系[email protected] 删除。
我来说两句