下面是我提取整个页面的所以文字功能,但如果我想要提取某一页面的文章,我又要怎样做??
static string GetPageSource(string URL)
{
Uri uri=new Uri(URL);
HttpWebRequest req=(HttpWebRequest)WebRequest.Create(uri);
HttpWebResponse res=(HttpWebResponse)req.GetResponse();
req.Method="Get";
req.KeepAlive=false;
StreamReader str=new StreamReader(res.GetResponseStream(),System.Text.Encoding.GetEncoding("GB2312"));
return str.ReadToEnd();
}

static string StripHTML(string strHtml)
{
string [] aryReg ={
@"<script[^>]*?>.*?</script>",

@"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\[""'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>",
@"([\r\n])[\s]+",
@"&(quot|#34);",
@"&(amp|#38);",
@"&(lt|#60);",
@"&(gt|#62);",
@"&(nbsp|#160);",
@"&(iexcl|#161);",
@"&(cent|#162);",
@"&(pound|#163);",
@"&(copy|#169);",
@"&#(\d+);",
@"-->",
@"<!--.*\n"

};

string [] aryRep = {
"",
"",
"",
"\"",
"&",
"<",
">",
" ",
"\xa1",//chr(161),
"\xa2",//chr(162),
"\xa3",//chr(163),
"\xa9",//chr(169),
"",
"\r\n",
""
};

string newReg =aryReg[0];
string strOutput=strHtml;
for(int i = 0;i<aryReg.Length;i++)
{
Regex regex = new Regex(aryReg[i],RegexOptions.IgnoreCase );
strOutput = regex.Replace(strOutput,aryRep[i]);
}

strOutput.Replace("<","");
strOutput.Replace(">","");
strOutput.Replace("\r\n","");

return strOutput;
}

private void Button1_ServerClick(object sender, System.EventArgs e)
{
string i=GetPageSource(Text1.Value);
DIV1.InnerText=StripHTML(i);
}