最近用C#写一个简单的浏览器，通过WebBrowser获取的页面源码：
方法一：
System.IO.StreamReader getReader = new
System.IO.StreamReader(this.webBrowser.DocumentStream,
System.Text.Encoding.GetEncoding("gb2312"));
string gethtml = getReader.ReadToEnd();
注意：我这儿使用的不是DocumentText属性获取的页面内容。
方法二：
private void button1_Click(object sender, EventArgs e)
{
WebBrowser webBrowser = new WebBrowser();
webBrowser.DocumentCompleted += new
WebBrowserDocumentCompletedEventHandler(webBrowser_DocumentCompleted);
webBrowser.Navigate("http://www.mzwu.com/");
}
private void webBrowser_DocumentCompleted(object sender,
WebBrowserDocumentCompletedEventArgs e)
{
WebBrowser webBrowser = (WebBrowser)sender;
//WebBrowserReadyState.Interactive 和
WebBrowserReadyState.Complete
时都会触发DocumentCompleted
if (webBrowser.ReadyState == WebBrowserReadyState.Complete)
{
//webBrowser1.DocumentText 获取的内容中文会乱码
//获取文档编码
Encoding encoding =
Encoding.GetEncoding(webBrowser.Document.Encoding);
StreamReader stream = new StreamReader(webBrowser.DocumentStream,
encoding);
File.WriteAllText(@"C:\mzwu.txt", stream.ReadToEnd(),
Encoding.Unicode);
MessageBox.Show(DateTime.Now.ToString() + ":
页面内容获取完成! ");
}
}
