Regular expression to filter html in c#

The example of this article describes the C# method of downloading the HTML source code of a web page. Share it with everyone for your reference. The specific method is as follows:

public static class DownLoad_HTML
{
private static int FailCount = 0; //记录下载失败的次数
 
public static string GetHtml(string url) //传入要下载的网址
{
string str = string.Empty;
try
{
System.Net.WebRequest request = System.Net.WebRequest.Create(url);
request.Timeout = 10000; //下载超时时间
request.Headers.Set("Pragma", "no-cache");
System.Net.WebResponse response = request.GetResponse();
System.IO.Stream streamReceive = response.GetResponseStream();
Encoding encoding = Encoding.GetEncoding("gb2312");//utf-8 网页文字编码
System.IO.StreamReader streamReader = new System.IO.StreamReader(streamReceive, encoding);
str = streamReader.ReadToEnd();
streamReader.Close();
}
catch (Exception ex)
{
FailCount++;
 
if (FailCount > 5)
{
var result = System.Windows.Forms.MessageBox.Show("已下载失败" + FailCount + "次，是否要继续尝试？" + Environment.NewLine + ex.ToString(), "数据下载异常", System.Windows.Forms.MessageBoxButtons.YesNo, System.Windows.Forms.MessageBoxIcon.Error);
if (result == System.Windows.Forms.DialogResult.Yes)
{
str = GetHtml(url);
}
else
{
System.Windows.Forms.MessageBox.Show("下载HTML失败" + Environment.NewLine + ex.ToString(), "下载HTML失败", System.Windows.Forms.MessageBoxButtons.OK, System.Windows.Forms.MessageBoxIcon.Error);
throw ex;
}
}
else
{
str = GetHtml(url);
}
}
 
FailCount = 0; //如果能执行到这一步就表示下载终于成功了
return str;
}

I hope this article will be helpful to everyone’s C# programming

For more articles related to regular expressions for filtering HTML in C#, please pay attention to the PHP Chinese website!