WCF（.NET 4.0）是否提供了檢索網頁HTML的功能？

Question

WCF（.NET 4.0）提供了檢索網頁HTML的能力嗎？如果不是，.NET 4.0中最好的方法是什麼？

Answer 1

您可以使用WebClient檢索Web paqe

using (WebClient web = new WebClient()) 
{ 
    var data = web.DownloadData(myURL); 
}  

WebClient的一些侷限性遭受的HTML如無法設置下載時間和不一致的進度事件。我寫了自己的子類，改進了它。這是代碼，以防萬一它有用。請注意，我正在處理的代碼中存在一個錯誤（請參閱WebClient Subclass Disposed During Event Handler, Result is ObjectDisposedException）。解決這個問題的一個簡單方法就是在我的問題中提到的一條線上放一個try/catch，但我試圖理解這個問題中的核心問題。

public class MyWebClient : WebClient, IDisposable 
{ 
    public int Timeout { get; set; } 
    public int TimeUntilFirstByte { get; set; } 
    public int TimeBetweenProgressChanges { get; set; } 

    public long PreviousBytesReceived { get; private set; } 
    public long BytesNotNotified { get; private set; } 

    public string Error { get; private set; } 
    public bool HasError { get { return Error != null; } } 

    private bool firstByteReceived = false; 
    private bool success = true; 
    private bool cancelDueToError = false; 

    private EventWaitHandle asyncWait = new ManualResetEvent(false); 
    private Timer abortTimer = null; 
    private bool isDisposed = false; 

    const long ONE_MB = 1024 * 1024; 

    public delegate void PerMbHandler(long totalMb); 

    public event PerMbHandler NotifyMegabyteIncrement; 

    public MyWebClient(int timeout = 60000, int timeUntilFirstByte = 30000, int timeBetweenProgressChanges = 15000) 
    { 
     this.Timeout = timeout; 
     this.TimeUntilFirstByte = timeUntilFirstByte; 
     this.TimeBetweenProgressChanges = timeBetweenProgressChanges; 

     this.DownloadFileCompleted += new System.ComponentModel.AsyncCompletedEventHandler(MyWebClient_DownloadFileCompleted); 
     this.DownloadProgressChanged += new DownloadProgressChangedEventHandler(MyWebClient_DownloadProgressChanged); 

     abortTimer = new Timer(AbortDownload, null, TimeUntilFirstByte, System.Threading.Timeout.Infinite); 
    } 

    protected void OnNotifyMegabyteIncrement(long totalMb) 
    { 
     if (NotifyMegabyteIncrement != null) NotifyMegabyteIncrement(totalMb); 
    } 

    void AbortDownload(object state) 
    { 
     cancelDueToError = true; 
     this.CancelAsync(); 
     success = false; 
     Error = firstByteReceived ? "Download aborted due to >" + TimeBetweenProgressChanges + "ms between progress change updates." : "No data was received in " + TimeUntilFirstByte + "ms"; 
     asyncWait.Set(); 
    } 

    void MyWebClient_DownloadProgressChanged(object sender, DownloadProgressChangedEventArgs e) 
    { 
     if (cancelDueToError || isDisposed) return; 

     long additionalBytesReceived = e.BytesReceived - PreviousBytesReceived; 
     PreviousBytesReceived = e.BytesReceived; 
     BytesNotNotified += additionalBytesReceived; 

     if (BytesNotNotified > ONE_MB) 
     { 
      OnNotifyMegabyteIncrement(e.BytesReceived); 
      BytesNotNotified = 0; 
     } 
     firstByteReceived = true; 
     if (!isDisposed) abortTimer.Change(TimeBetweenProgressChanges, System.Threading.Timeout.Infinite); 
    } 

    public bool DownloadFileWithEvents(string url, string outputPath) 
    { 
     asyncWait.Reset(); 
     Uri uri = new Uri(url); 
     this.DownloadFileAsync(uri, outputPath); 
     asyncWait.WaitOne(); 

     return success; 
    } 

    void MyWebClient_DownloadFileCompleted(object sender, System.ComponentModel.AsyncCompletedEventArgs e) 
    { 
     if (cancelDueToError || isDisposed) return; 
     asyncWait.Set(); 
    } 

    protected override WebRequest GetWebRequest(Uri address) 
    {    
     var result = base.GetWebRequest(address); 
     result.Timeout = this.Timeout; 
     return result; 
    } 

    void IDisposable.Dispose() 
    { 
     isDisposed = true; 

     if (asyncWait != null) asyncWait.Dispose(); 
     if (abortTimer != null) abortTimer.Dispose(); 

     base.Dispose(); 
    } 
} 

Answer 2

如果您試圖抓取HTML內容（用於緩存等），那麼Eric J是對的。如果您打算將網頁的一部分作爲數據提取，您可能需要查看HTML Agility Pack。 http://htmlagilitypack.codeplex.com/wikipage?title=Examples