c#获取网页源文件代码的六种方法

发布时间:2020-01-30编辑:脚本学堂
c#如何获取网页源文件代码,这里分享六种c#实现的网页文件源码获取方法,由简单到复杂,用于根据访问请求的url地址得到网页文件源码。

一、c#获取网页源文件的方法一

复制代码 代码示例:
using System.Text;
using System.Net;
private string getHtml(string url)
{
WebClient myWebClient = new WebClient();
byte[] myDataBuffer = myWebClient.DownloadData (url);
return Encoding.Default.GetString(myDataBuffer);
}

二、c#获取网页源文件的方法二
 

复制代码 代码示例:
public string getHttp(string HttpUrl,string RefererUrl)
{
string html = "";
try
{
MSXML2.XMLHTTP Http = new MSXML2.XMLHTTPClass();
xmlhttp.open("GET", Url, false, null, null);
Http.open("GET",HttpUrl,false,null,null);
Http.setRequestHeader("Referer",RefererUrl);
//Http.setRequestHeader("Referer",RefererUrl);
Http.setRequestHeader("Content-Type", "text/html;charset=gb2312");
Http.send("");
html = Encoding.Default.GetString((byte[])Http.responseBody);
Http = null;
}
catch
{
}
return html;
}
public bool getweb(string strURL,out string buf)
{
 buf="";
 try
 {
//Uri url=new Uri(strURL,false);
HttpWebRequest request;
request = (HttpWebRequest)WebRequest.Create(strURL);
request.Method="POST"; //Post请求方式
request.ContentType="text/html;charset=gb2312"; //内容类型
string paraUrlCoded = System.Web.HttpUtility.UrlEncode(""); //参数经过url编码
byte[] payload;
payload = System.Text.Encoding.GetEncoding("GB2312").GetBytes(paraUrlCoded); //将URL编码后的字符串转化为字节
request.ContentLength = payload.Length; //设置请求的ContentLength
Stream writer = request.GetRequestStream(); //获得请求流
writer.Write(payload,0,payload.Length); //将请求参数写入流
writer.Close(); //关闭请求流
HttpWebResponse response;
response = (HttpWebResponse)request.GetResponse(); //获得响应流
Stream s;
s = response.GetResponseStream();
StreamReader objReader = new StreamReader(s,System.Text.Encoding.GetEncoding("GB2312"));
string HTML = "";
string sLine ="";
int i = 0;
while (sLine!=null)
{
 i++;
 sLine = objReader.ReadLine();
 if (sLine!=null)
HTML += sLine;
}
//HTML = HTML.Replace("<","<");
//HTML = HTML.Replace(">",">");
buf=HTML;
return true;
 }
 catch (Exception x)
 {
buf=x.Message.ToString();
return false;
 }
}

带Cookie的情况:
 

复制代码 代码示例:
CookieContainer cc = new CookieContainer();
public bool getweb(string strURL,out string buf)
{
 buf="";
 try
 {
HttpWebRequest request;
request = (HttpWebRequest)WebRequest.Create(strURL);
request.Method="POST"; //Post请求方式
request.ContentType="text/html;charset=gb2312"; //内容类型
string paraUrlCoded = System.Web.HttpUtility.UrlEncode(""); //参数经过URL编码
byte[] payload;
payload = System.Text.Encoding.GetEncoding("GB2312").GetBytes(paraUrlCoded); //将URL编码后的字符串转化为字节
request.ContentLength = payload.Length; //设置请求的ContentLength
Stream writer = request.GetRequestStream(); //获得请求流
writer.Write(payload,0,payload.Length); //将请求参数写入流
writer.Close(); //关闭请求流
HttpWebResponse response;
response = (HttpWebResponse)request.GetResponse(); //获得响应流
Stream s;
s = response.GetResponseStream();
StreamReader objReader = new StreamReader(s,System.Text.Encoding.GetEncoding("GB2312"));
string HTML = "";
string sLine ="";
int i = 0;
while (sLine!=null)
{
 i++;
 sLine = objReader.ReadLine();
 if (sLine!=null)
HTML += sLine;
}
buf=HTML;
return true;
 }
 catch (Exception x)
 {
buf=x.Message.ToString();
return false;
 }
}
public bool getweb(string strURL,out string buf,string postData)
{
 buf="";
 try
 {
ASCIIEncoding encoding = new ASCIIEncoding();
byte[] data = encoding.GetBytes(postData);
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(strURL);
request.Method = "POST";
request.ContentType = "application/x-www-form-urlencoded";
request.ContentLength = data.Length;
Stream newStream = request.GetRequestStream();
newStream.Write(data, 0, data.Length);
newStream.Close();
request.CookieContainer = cc;
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
cc.Add(response.Cookies);
Stream stream = response.GetResponseStream();
string sHtml = new StreamReader(stream, System.Text.Encoding.Default).ReadToEnd();
buf=sHtml;
return true;
 }
 catch (Exception x)
 {
buf=x.Message.ToString();
return false;
 }
}
private string getWebresourceFile1(string url)
{
WebClient myWebClient = new WebClient();
byte[] myDataBuffer = myWebClient.DownloadData(url);
string SourceCode = Encoding.Default.GetString(myDataBuffer);
saveSourceCode(SourceCode);
return SourceCode;
}

三、c#获取网页源文件的方法三
 

复制代码 代码示例:
private string getWebresourceFile2(string url)
{
HttpWebRequest request=(HttpWebRequest)WebRequest.Create(url);
HttpWebResponse response=(HttpWebResponse)request.GetResponse();
request.Method = "GET ";
Stream receiveStream=response.GetResponseStream();
StreamReader readStream=new StreamReader(receiveStream,Encoding.Default);
string SourceCode=readStream.ReadToEnd();
saveSourceCode(SourceCode);
response.Close();
readStream.Close();
return SourceCode;
}

四、c#获取网页源文件的方法四
 

复制代码 代码示例:
private string getWebresourceFile3(string url)
{
WebClient wc = new WebClient();
wc.Credentials = CredentialCache.DefaultCredentials;
Byte[] pageData = wc.DownloadData(url);
string SourceCode = Encoding.Default.GetString(pageData);
saveSourceCode(SourceCode);
wc.Dispose();
return SourceCode;
}

五、c#获取网页源文件的方法五

复制代码 代码示例:
private string getWebresourceFile4(string url)
{
WebClient wc = new WebClient();
wc.Credentials = CredentialCache.DefaultCredentials;
Stream resStream = wc.OpenRead(url);
StreamReader sr = new StreamReader(resStream,System.Text.Encoding.Default);
string SourceCode = sr.ReadToEnd();
saveSourceCode(SourceCode);
resStream.Close();
wc.Dispose();
return SourceCode;
}

六、c#获取网页源文件的方法六
 

复制代码 代码示例:
private string getWebresourceFile5(string url)
{
WebRequest request = WebRequest.Create(url);
WebResponse response = request.GetResponse();
Stream resStream = response.GetResponseStream();
StreamReader sr = new StreamReader(resStream, System.Text.Encoding.Default);
string SourceCode = sr.ReadToEnd();
saveSourceCode(SourceCode);
resStream.Close();
sr.Close();
return SourceCode;
}