这已在此处和其他站点及其工作中多次出现，但我想以其他方式提出想法：
使用导航或发布后获取 ReadyState = Complete，而不使用 DoEvents，因为它的所有缺点。
我还要注意，在这里使用 DocumentComplete 事件无济于事，因为我不会只在一个页面上导航，而是像这样一个接一个地导航。
wb.navigate("www.microsoft.com")
//dont use DoEvents loop here
wb.Document.Body.SetAttribute(textbox1, "login")
//dont use DoEvents loop here
if (wb.documenttext.contais("text"))
//do something
它今天的工作方式是使用 DoEvents。我想知道是否有人有适当的方法来等待浏览器方法的异步调用，然后才能继续执行其余的逻辑。只是为了它。
提前致谢。
DocumentCompleted下面是一个基本的 WinForms 应用程序代码，说明了如何异步等待事件，使用async/await. 它一个接一个地导航到多个页面。一切都发生在主 UI 线程上。
this.webBrowser.Navigate(url)它可能不是调用，而是模拟表单按钮单击，以触发 POST 样式的导航。
异步循环逻辑是可选的webBrowser.IsBusy，其目的是（非确定性地）考虑可能在事件之后window.onload发生的页面的动态 AJAX 代码。
using System;
using System.Diagnostics;
using System.Threading;
using System.Threading.Tasks;
using System.Windows.Forms;
namespace WebBrowserApp
{
public partial class MainForm : Form
{
WebBrowser webBrowser;
public MainForm()
{
InitializeComponent();
// create a WebBrowser
this.webBrowser = new WebBrowser();
this.webBrowser.Dock = DockStyle.Fill;
this.Controls.Add(this.webBrowser);
this.Load += MainForm_Load;
}
// Form Load event handler
async void MainForm_Load(object sender, EventArgs e)
{
// cancel the whole operation in 30 sec
var cts = new CancellationTokenSource(30000);
var urls = new String[] {
"http://www.example.com",
"http://www.gnu.org",
"http://www.debian.org" };
await NavigateInLoopAsync(urls, cts.Token);
}
// navigate to each URL in a loop
async Task NavigateInLoopAsync(string[] urls, CancellationToken ct)
{
foreach (var url in urls)
{
ct.ThrowIfCancellationRequested();
var html = await NavigateAsync(ct, () =>
this.webBrowser.Navigate(url));
Debug.Print("url: {0}, html: \n{1}", url, html);
}
}
// asynchronous navigation
async Task<string> NavigateAsync(CancellationToken ct, Action startNavigation)
{
var onloadTcs = new TaskCompletionSource<bool>();
EventHandler onloadEventHandler = null;
WebBrowserDocumentCompletedEventHandler documentCompletedHandler = delegate
{
// DocumentCompleted may be called several time for the same page,
// if the page has frames
if (onloadEventHandler != null)
return;
// so, observe DOM onload event to make sure the document is fully loaded
onloadEventHandler = (s, e) =>
onloadTcs.TrySetResult(true);
this.webBrowser.Document.Window.AttachEventHandler("onload", onloadEventHandler);
};
this.webBrowser.DocumentCompleted += documentCompletedHandler;
try
{
using (ct.Register(() => onloadTcs.TrySetCanceled(), useSynchronizationContext: true))
{
startNavigation();
// wait for DOM onload event, throw if cancelled
await onloadTcs.Task;
}
}
finally
{
this.webBrowser.DocumentCompleted -= documentCompletedHandler;
if (onloadEventHandler != null)
this.webBrowser.Document.Window.DetachEventHandler("onload", onloadEventHandler);
}
// the page has fully loaded by now
// optional: let the page run its dynamic AJAX code,
// we might add another timeout for this loop
do { await Task.Delay(500, ct); }
while (this.webBrowser.IsBusy);
// return the page's HTML content
return this.webBrowser.Document.GetElementsByTagName("html")[0].OuterHtml;
}
}
}
如果您希望从控制台应用程序中执行类似的操作，这里是一个示例。
解决方案很简单：
// MAKE SURE ReadyState = Complete
while (WebBrowser1.ReadyState.ToString() != "Complete") {
Application.DoEvents();
}
// 继续你的子序列代码...
又脏又快..我是一个 VBA 家伙，这个逻辑一直在工作，只是花了我几天的时间并没有找到 C#，但我只是自己想通了。
以下是我的完整功能，目的是从网页中获取一段信息：
private int maxReloadAttempt = 3;
private int currentAttempt = 1;
private string GetCarrier(string webAddress)
{
WebBrowser WebBrowser_4MobileCarrier = new WebBrowser();
string innerHtml;
string strStartSearchFor = "subtitle block pull-left\">";
string strEndSearchFor = "<";
try
{
WebBrowser_4MobileCarrier.ScriptErrorsSuppressed = true;
WebBrowser_4MobileCarrier.Navigate(webAddress);
// MAKE SURE ReadyState = Complete
while (WebBrowser_4MobileCarrier.ReadyState.ToString() != "Complete") {
Application.DoEvents();
}
// LOAD HTML
innerHtml = WebBrowser_4MobileCarrier.Document.Body.InnerHtml;
// ATTEMPT (x3) TO EXTRACT CARRIER STRING
while (currentAttempt <= maxReloadAttempt) {
if (innerHtml.IndexOf(strStartSearchFor) >= 0)
{
currentAttempt = 1; // Reset attempt counter
return Sub_String(innerHtml, strStartSearchFor, strEndSearchFor, "0"); // Method: "Sub_String" is my custom function
}
else
{
currentAttempt += 1; // Increment attempt counter
GetCarrier(webAddress); // Recursive method call
} // End if
} // End while
} // End Try
catch //(Exception ex)
{
}
return "Unavailable";
}
这是一个“快速而肮脏”的解决方案。它不是 100% 万无一失的，但它不会阻塞 UI 线程，它应该可以满足 WebBrowser 控件自动化程序的原型：
private async void testButton_Click(object sender, EventArgs e)
{
await Task.Factory.StartNew(
() =>
{
stepTheWeb(() => wb.Navigate("www.yahoo.com"));
stepTheWeb(() => wb.Navigate("www.microsoft.com"));
stepTheWeb(() => wb.Navigate("asp.net"));
stepTheWeb(() => wb.Document.InvokeScript("eval", new[] { "$('p').css('background-color','yellow')" }));
bool testFlag = false;
stepTheWeb(() => testFlag = wb.DocumentText.Contains("Get Started"));
if (testFlag) { /* TODO */ }
// ...
}
);
}
private void stepTheWeb(Action task)
{
this.Invoke(new Action(task));
WebBrowserReadyState rs = WebBrowserReadyState.Interactive;
while (rs != WebBrowserReadyState.Complete)
{
this.Invoke(new Action(() => rs = wb.ReadyState));
System.Threading.Thread.Sleep(300);
}
}
这是一个更通用的testButton_Click方法版本：
private async void testButton_Click(object sender, EventArgs e)
{
var actions = new List<Action>()
{
() => wb.Navigate("www.yahoo.com"),
() => wb.Navigate("www.microsoft.com"),
() => wb.Navigate("asp.net"),
() => wb.Document.InvokeScript("eval", new[] { "$('p').css('background-color','yellow')" }),
() => {
bool testFlag = false;
testFlag = wb.DocumentText.Contains("Get Started");
if (testFlag) { /* TODO */ }
}
//...
};
await Task.Factory.StartNew(() => actions.ForEach((x)=> stepTheWeb (x)));
}
[更新]
我通过从这个主题中借用和轻微重构@Noseratio 的NavigateAsync方法来调整我的“快速和肮脏”示例。新的代码版本将在 UI 线程上下文中异步自动/执行，不仅是导航操作，还有 Javascript/AJAX 调用——任何“lamdas”/一个自动化步骤任务实现方法。
非常欢迎所有和每一个代码审查/评论。特别是，从@Noseratio. 我们将一起让这个世界变得更美好；）
public enum ActionTypeEnumeration
{
Navigation = 1,
Javascript = 2,
UIThreadDependent = 3,
UNDEFINED = 99
}
public class ActionDescriptor
{
public Action Action { get; set; }
public ActionTypeEnumeration ActionType { get; set; }
}
/// <summary>
/// Executes a set of WebBrowser control's Automation actions
/// </summary>
/// <remarks>
/// Test form shoudl ahve the following controls:
/// webBrowser1 - WebBrowser,
/// testbutton - Button,
/// testCheckBox - CheckBox,
/// totalHtmlLengthTextBox - TextBox
/// </remarks>
private async void testButton_Click(object sender, EventArgs e)
{
try
{
var cts = new CancellationTokenSource(60000);
var actions = new List<ActionDescriptor>()
{
new ActionDescriptor() { Action = ()=> wb.Navigate("www.yahoo.com"), ActionType = ActionTypeEnumeration.Navigation} ,
new ActionDescriptor() { Action = () => wb.Navigate("www.microsoft.com"), ActionType = ActionTypeEnumeration.Navigation} ,
new ActionDescriptor() { Action = () => wb.Navigate("asp.net"), ActionType = ActionTypeEnumeration.Navigation} ,
new ActionDescriptor() { Action = () => wb.Document.InvokeScript("eval", new[] { "$('p').css('background-color','yellow')" }), ActionType = ActionTypeEnumeration.Javascript},
new ActionDescriptor() { Action =
() => {
testCheckBox.Checked = wb.DocumentText.Contains("Get Started");
},
ActionType = ActionTypeEnumeration.UIThreadDependent}
//...
};
foreach (var action in actions)
{
string html = await ExecuteWebBrowserAutomationAction(cts.Token, action.Action, action.ActionType);
// count HTML web page stats - just for fun
int totalLength = 0;
Int32.TryParse(totalHtmlLengthTextBox.Text, out totalLength);
totalLength += !string.IsNullOrWhiteSpace(html) ? html.Length : 0;
totalHtmlLengthTextBox.Text = totalLength.ToString();
}
}
catch (Exception ex)
{
MessageBox.Show(ex.Message, "Error");
}
}
// asynchronous WebBroswer control Automation
async Task<string> ExecuteWebBrowserAutomationAction(
CancellationToken ct,
Action runWebBrowserAutomationAction,
ActionTypeEnumeration actionType = ActionTypeEnumeration.UNDEFINED)
{
var onloadTcs = new TaskCompletionSource<bool>();
EventHandler onloadEventHandler = null;
WebBrowserDocumentCompletedEventHandler documentCompletedHandler = delegate
{
// DocumentCompleted may be called several times for the same page,
// if the page has frames
if (onloadEventHandler != null)
return;
// so, observe DOM onload event to make sure the document is fully loaded
onloadEventHandler = (s, e) =>
onloadTcs.TrySetResult(true);
this.wb.Document.Window.AttachEventHandler("onload", onloadEventHandler);
};
this.wb.DocumentCompleted += documentCompletedHandler;
try
{
using (ct.Register(() => onloadTcs.TrySetCanceled(), useSynchronizationContext: true))
{
runWebBrowserAutomationAction();
if (actionType == ActionTypeEnumeration.Navigation)
{
// wait for DOM onload event, throw if cancelled
await onloadTcs.Task;
}
}
}
finally
{
this.wb.DocumentCompleted -= documentCompletedHandler;
if (onloadEventHandler != null)
this.wb.Document.Window.DetachEventHandler("onload", onloadEventHandler);
}
// the page has fully loaded by now
// optional: let the page run its dynamic AJAX code,
// we might add another timeout for this loop
do { await Task.Delay(500, ct); }
while (this.wb.IsBusy);
// return the page's HTML content
return this.wb.Document.GetElementsByTagName("html")[0].OuterHtml;
}