c#获取网页源代码（可解决某些页面乱码的问题）

OStack程序员社区-中国程序员成长平台 › 门户 › 编程› Node.js›Node.js教程

原作者: [db:作者] 来自: [db:来源] 收藏邀请

private string GetHtmlCode(string url)
{
string htmlCode;
HttpWebRequest webRequest = (System.Net.HttpWebRequest)System.Net.WebRequest.Create(url);
webRequest.Timeout = 30000;
webRequest.Method = "GET";
webRequest.UserAgent = "Mozilla/4.0";
webRequest.Headers.Add("Accept-Encoding", "gzip, deflate");
HttpWebResponse webResponse = (System.Net.HttpWebResponse)webRequest.GetResponse();
if (webResponse.ContentEncoding.ToLower() == "gzip")//如果使用了GZip则先解压
{
using (System.IO.Stream streamReceive = webResponse.GetResponseStream())
{
using (var zipStream =
new System.IO.Compression.GZipStream(streamReceive, System.IO.Compression.CompressionMode.Decompress))
{
using (StreamReader sr = new System.IO.StreamReader(zipStream, Encoding.Default))
{
htmlCode = sr.ReadToEnd();
}
}
}
}
else
{
using (System.IO.Stream streamReceive = webResponse.GetResponseStream())
{
using (System.IO.StreamReader sr = new System.IO.StreamReader(streamReceive, Encoding.Default))
{
htmlCode = sr.ReadToEnd();
}
}
}

return htmlCode;
}