C# to get the source code of the web page

admin · Posted on 2/15/2015 2:35:51 PM

C# can be obtained in three ways: WebClient, WebRequest, and HttpWebRequest.

Of course, you can also use webBrowse! I won't look at how webBrowse gets here.

WebClient

private string GetWebClient(string url)
{
string strHTML = "";
WebClient myWebClient = new WebClient();
Stream myStream = myWebClient.OpenRead(url);
StreamReader sr = new StreamReader(myStream, System.Text.Encoding.GetEncoding("utf-8"));
strHTML = sr. ReadToEnd();
myStream.Close();
return strHTML;
}
WebRequest

private string GetWebRequest(string url)
{
Uri uri = new Uri(url);
WebRequest myReq = WebRequest.Create(uri);
WebResponse result = myReq.GetResponse();
Stream receviceStream = result. GetResponseStream();
StreamReader readerOfStream = new StreamReader(receviceStream, System.Text.Encoding.GetEncoding("utf-8"));
string strHTML = readerOfStream.ReadToEnd();
readerOfStream.Close();
receviceStream.Close();
result. Close();
return strHTML;
}
HttpWebRequest

private string GetHttpWebRequest(string url)
{
Uri uri = new Uri(url);
HttpWebRequest myReq = (HttpWebRequest)WebRequest.Create(uri);
myReq.UserAgent = "User-Agent:Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.0.3705";
myReq.Accept = "*/*";
myReq.KeepAlive = true;
myReq.Headers.Add("Accept-Language", "zh-cn,en-us; q=0.5");
HttpWebResponse result = (HttpWebResponse)myReq.GetResponse();
Stream receviceStream = result. GetResponseStream();
StreamReader readerOfStream = new StreamReader(receviceStream, System.Text.Encoding.GetEncoding("utf-8"));
string strHTML = readerOfStream.ReadToEnd();
readerOfStream.Close();
receviceStream.Close();
result. Close();
return strHTML;
}
Note that "UTF-8" should correspond to the encoding of the specified web page.

summary

You can see that the HttpWebRequest method is the most complex, but it does offer more choice.

[Communication] C# to get the source code of the web page

Related Posts