根据URL取页面内容

各位高手门!还望不吝赐教啊!~
就是一个方法参数是URL地址返回的是string返回内容是URL对应的网页静态内容,不需要取图片什么的只需要文字就可以,
所有在<html></html>标记里的字符这个方法该怎么写啊!
谢谢了啊!~
问题解决马上就给分了!~
JAVA里用的是HttpUnit框架
ASP.NET应该怎么写啊

解决方案 »

免费领取超大流量手机卡，每月29元包185G流量+100分钟通话, 中国电信官方发货

Function getContent() As String
        Dim request As System.Net.HttpWebRequest
        request = System.Net.WebRequest.Create(url)
        request.UserAgent = "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.1) Web-Sniffer/1.0.24"        Dim response As System.Net.WebResponse
        response = request.GetResponse        Dim resStream As System.IO.Stream
        resStream = response.GetResponseStream        Dim sr As System.IO.StreamReader
        sr = New System.IO.StreamReader(resStream, System.Text.UTF8Encoding.Default)        Dim htmlCode As String = sr.ReadToEnd()
        resStream.Close()
        sr.Close()
        Return htmlCode    End Function
HttpWebRequest
http://support.microsoft.com/kb/303436
下班回家了，丢给你，自已参考，删减using System;
using System.Text;
using System.Net;
using System.IO;
using System.Text.RegularExpressions;namespace XXXXXXXXXX.XXXXXXXX
{
    public class BLL_UrlContent
    {
        private string _filteredContent = "";
        private string _pageContent = "";
        private Encoding encoding;
        private string _Url = "";
        private string _DataCode = "";        public BLL_UrlContent(string Url, string DataCode)
        {            _Url = Url;
            _DataCode = DataCode;            _pageContent = GetPage(_Url);
        }        public string pageContent
        {
            get
            {
                return _pageContent;
            }
        }        public string filteredContent
        {
            get
            {
                if (_filteredContent != "")
                {
                    return _filteredContent;
                }
                else
                {
                    _filteredContent = FilterScript(FilterNewLine(FilterEnter(FilterAllHTML(getBodyContent(pageContent)))));
                    return _filteredContent;
                }
           }
        }        private string GetPage(string m_uri)
        {
            #region            WebResponse response = null;
            Stream stream = null;
            StreamReader reader = null;            try
            {
                HttpWebRequest request = (HttpWebRequest)WebRequest.Create(m_uri);
                request.Timeout = 3000;
                response = request.GetResponse();
                if (!request.HaveResponse)
                {
                    response.Close();
                    return null;
                }
                stream = response.GetResponseStream();                if (!response.ContentType.ToLower().StartsWith("text/"))
                {
                    return null;
                }                string strEncoding = _DataCode.ToLower();
                if (strEncoding == "utf-8")
                    encoding = Encoding.UTF8;
                else if (strEncoding == "utf-7")
                    encoding = Encoding.UTF7;
                else if (strEncoding == "unicode")
                    encoding = Encoding.Unicode;
                else
                    encoding = Encoding.Default;                reader = new StreamReader(stream, encoding);
                return reader.ReadToEnd();
                //string buffer = "";// = reader.ReadToEnd();//,line;
                //string line;
                //while ((line = reader.ReadLine()) != null)
                //{
                //    buffer += line + "\r\n";
                //}
                //return buffer;
            }
            catch
            {
                return "";
            }
            finally
            {
                if (reader != null) reader.Close();
                if (stream != null) stream.Close();
                if (response != null) response.Close();
            }
            #endregion
        }
        private string FilterAllHTML(string input)
        {
            string pattern = @"<.*?>";
            return Regex.Replace(input, pattern, "", RegexOptions.Singleline | RegexOptions.Compiled | RegexOptions.IgnoreCase);        }
        private static string FilterScript(string input)
        {
            string pattern = "<script.*?</script>";
            return Regex.Replace(input, pattern, "", RegexOptions.Singleline | RegexOptions.Compiled | RegexOptions.IgnoreCase);
        }
        private static string FilterLink(string input)
        {
            string pattern = @"<a.*?</a>";
            string result = Regex.Replace(input, pattern, "", RegexOptions.Singleline | RegexOptions.Compiled | RegexOptions.IgnoreCase);
            return result;
        }
        private string getBodyContent(string input)
        {
            string pattern = @"<body.*?</body>";
            Regex reg = new Regex(pattern, RegexOptions.Singleline | RegexOptions.Compiled | RegexOptions.IgnoreCase);
            Match mc = reg.Match(input);
            string bodyContent = "";
            if (mc.Success)
            {
                bodyContent = mc.Value;
            }
            return bodyContent;        }
        private string FilterNewLine(string input)
        {
            string pattern = "\r";
            return Regex.Replace(input, pattern, "", RegexOptions.Singleline | RegexOptions.Compiled | RegexOptions.IgnoreCase);
        }
        private string FilterEnter(string input)
        {
            string pattern = "\n";
            return Regex.Replace(input, pattern, "", RegexOptions.Singleline | RegexOptions.Compiled | RegexOptions.IgnoreCase);
        }
    }
}
WebRequest request = WebRequest.Create(页面url);
WebResponse response = request.GetResponse();
Stream resStream = response.GetResponseStream();
StreamReader sr = new StreamReader(resStream, System.Text.Encoding.Default);
页面内容 = sr.ReadToEnd(); 在页面内容中取<html></html>部分就是文本操作了
http://blog.csdn.net/jiang_jiajia10/archive/2008/11/18/3325407.aspx