获取网页源码

最新推荐文章于 2024-03-31 00:01:28 发布

转载最新推荐文章于 2024-03-31 00:01:28 发布 · 59 阅读

0 ·

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/ahghy/p/3504182.html

文章标签：

#c#

本文详细介绍了使用C#的WebClient、WebRequest和HttpWebRequest三种方式获取指定网页HTML原代码的方法，并讨论了不同方式在实际应用中的优缺点。通过实例代码演示，帮助开发者在遇到不同网站时灵活选择合适的获取策略。

C#获取指定网页HTML原代码可使用 WebClient WebRequest HttpWebRequest 三种方式来实现。

当然也可使用webBrowse！在此就不研究webBrowse如何获取了。

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;
}

注意“utf-8”应与指定网页的编码对应。