C#抓取网页HTML内容

using System;

using System.Collections.Generic;

using System.Linq;

using System.Web;

using ;

using System.Text;

using System.IO;

using System.Text.RegularExpressions;

namespace Web

{

/// <summary>

/// 公共方法类

/// </summary>

public class WebHandler

{

/// <summary>

/// 获取网页的HTML码

/// </summary>

/// <param name="url">链接地址</param>

/// <param name="encoding">编码类型</param>

/// <returns></returns>

public static string GetHtmlStr(string url, string encoding)

{

string htmlStr = "";

try

{

if (!String.IsNullOrEmpty(url))

{

WebRequest request = WebRequest.Create(url);//实例化WebRequest对象

WebResponse response = request.GetResponse();//创建WebResponse对象

Stream datastream = response.GetResponseStream(); //创建流对象

Encoding ec = Encoding.Default;

if (encoding == "UTF8")

{

ec = Encoding.UTF8;

}

else if (encoding == "Default")

{

ec = Encoding.Default;

}

StreamReader reader = new StreamReader(datastream, ec);

htmlStr = reader.ReadToEnd(); //读取网页内容

reader.Close();

datastream.Close();

response.Close();

}

}

catch { }

return htmlStr;

}

}

}