首页 / C# / C#获取指定网页源码的几种方法
C#获取指定网页源码的几种方法
内容导读
互联网集市收集整理的这篇技术教程文章主要介绍了C#获取指定网页源码的几种方法，小编现在分享给大家，供广大互联网技能从业者学习和参考。文章包含2682字，纯文字阅读大概需要4分钟。
内容图文
// 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("gb2312"));
string strHTML = readerOfStream.ReadToEnd();
readerOfStream.Close();
receviceStream.Close();
result.Close();
return strHTML;
}
// HttpWebRequest
private string GetHttpWebRequest(string url)
{
try
{
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("gb2312"));
string strHTML = readerOfStream.ReadToEnd();
readerOfStream.Close();
receviceStream.Close();
result.Close();
return strHTML;
}
catch (Exception ex)
{
throw new Exception("采集指定网址异常，" + ex.Message);
}
}
// 获取网页源码，如果启用了gzip压缩后页面获取会产生乱码，采用此方法可解决gzip压缩而产生的乱码情况
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;
}
原文：http://www.cnblogs.com/q4002945/p/5934246.html
内容总结
以上是互联网集市为您收集整理的C#获取指定网页源码的几种方法全部内容，希望文章能够帮你解决C#获取指定网页源码的几种方法所遇到的程序开发问题。 如果觉得互联网集市技术教程内容还不错，欢迎将互联网集市网站推荐给程序员好友。
内容备注
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 gblab@vip.qq.com 举报，一经查实，本站将立刻删除。
内容手机端
扫描二维码推送至手机访问。
来源：【匿名】