博客园  :: 首页  :: 新随笔  :: 订阅 订阅  :: 管理

c# 获取网页源码

Posted on 2011-03-10 23:51  PHP-张工  阅读(25775)  评论(3编辑  收藏  举报

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。

总结

可以看到HttpWebRequest 方式最复杂,但确提供了更多的选择性。

有的网站检测客户端的UserAgent!如163.com,你如果使用WebClient WebRequest方式获取时,将获取到的是错误提示页面内容。

而通过HttpWebRequest 就没问题。

源码下载:https://files.cnblogs.com/zjfree/GetHTML.rar

测试环境:WIN2003 + VS2005 + C# + winForm