扒取网站内容(后台方法和前台方法的两种实现)

一.通过javascript可获取某个网站的HTML，不过只在IE下有效

function getHTTPPage(jnkcUrl) {
    var objxml = new ActiveXObject("Microsoft.XMLHTTP");
    objxml.open("GET", jnkcUrl, false);
    objxml.send();
    var sResult = objxml.responseText;
    return sResult;
}

 

二.通过C#获取

/// <summary>
/// 获取网页内容
/// </summary>
/// <param name="url">网址</param>
/// <returns>网站内容</returns>
public string GetWebSiteContent(string url)
{
    System.Net.WebClient web = new System.Net.WebClient();
    System.IO.Stream stream = web.OpenRead(url);
    System.IO.StreamReader sr = new System.IO.StreamReader(stream, System.Text.Encoding.Default);
    return sr.ReadToEnd();
}