C#网页信息采集方法汇总
本文实例总结了三种常用的C#网页信息采集方法。分享给大家供大家参考。具体实现方法如下：
一、通过HttpWebResponse来获取
publicstaticstringCheckTeamSiteUrl(stringurl)
{
stringresponse="";
HttpWebResponsehttpResponse=null;
//assert:userhaveaccesstoURL
try
{
HttpWebRequesthttpRequest=(HttpWebRequest)WebRequest.Create(url);
httpRequest.Headers.Set("Pragma","no-cache");
//request.Headers.Set("KeepAlive","true");
httpRequest.CookieContainer=newCookieContainer();
httpRequest.Referer=url;
httpRequest.UserAgent="Mozilla/4.0(compatible;MSIE6.0;WindowsNT5.0;.NETCLR1.1.4322;.NETCLR2.0.50727)";
httpRequest.Credentials=System.Net.CredentialCache.DefaultCredentials;
httpResponse=(HttpWebResponse)httpRequest.GetResponse();
}
catch(Exceptionex)
{
thrownewApplicationException("HTTP403Accessdenied,URL:"+url,ex);
}
//ifhere,theURLiscorrectandtheuserhasaccess
try
{
stringstrEncod=httpResponse.ContentType;
StreamReaderstream;
if(strEncod.ToLower().IndexOf("utf")!=-1)
{
stream=newStreamReader(httpResponse.GetResponseStream(),System.Text.Encoding.UTF8);
}
else
{
stream=newStreamReader(httpResponse.GetResponseStream(),System.Text.Encoding.Default);
}
char[]buff=newchar[4000];
stream.ReadBlock(buff,0,4000);
response=newstring(buff);
stream.Close();
httpResponse.Close();
}
catch(Exceptionex)
{
thrownewApplicationException("HTTP404Pagenotfound,URL:"+url,ex);
}
returnresponse;
}二、通过WebResponse来获取
publicstaticstringgetPage(Stringurl)
{
WebResponseresult=null;
stringresultstring="";
try
{
WebRequestreq=WebRequest.Create(url);
req.Timeout=30000;
result=req.GetResponse();
StreamReceiveStream=result.GetResponseStream();
//readthestreamintoastring
//StreamReadersr=newStreamReader(ReceiveStream,System.Text.Encoding.UTF8);
stringstrEncod=result.ContentType;
StreamReadersr;
if(strEncod.ToLower().IndexOf("utf")!=-1)
{
sr=newStreamReader(ReceiveStream,System.Text.Encoding.UTF8);
}
else
{
sr=newStreamReader(ReceiveStream,System.Text.Encoding.Default);
}
resultstring=sr.ReadToEnd();
js.alert(resultstring);
//Console.WriteLine(resultstring);
}
catch
{
thrownewException();
}
finally
{
if(result!=null)
{
result.Close();
}
}
returnresultstring;
}三、通过WebClient来获取
publicstringget(intlength)
{
try
{
getEncodeing();
WebClientwb=newWebClient();
Streamresponse=wb.OpenRead(url);
StreamReaderreader=newStreamReader(response,this.encoding,true,256000);
char[]a=newchar[length];
inti =reader.Read(a,0,length);
reader.Close();
returnnewstring(a);
}
catch(Exceptione)
{
returne.Message;
//returnnull;
}
}
privatevoidgetEncodeing()
{
switch(this.encode)
{
case"UTF-8":encoding=Encoding.UTF8;break;
case"GB2312":encoding=Encoding.GetEncoding("GB2312");break;
case"ASCII":encoding=Encoding.ASCII;break;
default:encoding=Encoding.GetEncoding(encode);break;
}
}
希望本文所述对大家的C#程序设计有所帮助。