asp.net 动态抓取网站数据(方法二)

    技术2022-05-20  49

     

     

      1using System;  2using System.Data;  3using System.Configuration;  4using System.Web;  5using System.Web.Security;  6using System.Web.UI;  7using System.Web.UI.WebControls;  8using System.Web.UI.WebControls.WebParts;  9using System.Web.UI.HtmlControls; 10using MSXML2;  //这个需要添加引用MSXML2 11using System.Text.RegularExpressions; 12namespace EC 13{ 14    /** <summary> 15    /// 远程文件抓取类 16    /// </summary> 17    public class GetRemoteObj 18    { 19       20        构造与析构函数#region 构造与析构函数 21        public GetRemoteObj() 22        { 23            // 24            // TODO: 在此处添加构造函数逻辑 25            // 26        } 27        ~GetRemoteObj() 28        { 29            Dispose(); 30        } 31        #endregion 32 33        IDisposable 成员#region IDisposable 成员 34 35        public void Dispose() 36        {            37            GC.SuppressFinalize(this); 38        } 39 40        #endregion 41 42        日期随机函数#region 日期随机函数 43        /**//********************************** 44         * 函数名称:DateRndName 45         * 功能说明:日期随机函数 46         * 参    数:ra:随机数 47         * 调用示例: 48         *          GetRemoteObj o = new GetRemoteObj(); 49         *          Random ra = new Random(); 50         *          string s = o.DateRndName(ra); 51         *          Response.Write(s); 52         *          o.Dispose(); 53         * ********************************/ 54        /** <summary> 55        /// 日期随机函数 56        /// </summary> 57        /// <param name="ra">随机数</param> 58        /// <returns></returns> 59        public  string DateRndName(Random ra) 60        { 61            DateTime d = DateTime.Now; 62            string s = null, y, m, dd, h, mm, ss; 63            y = d.Year.ToString(); 64            m = d.Month.ToString(); 65            if (m.Length < 2) m = "0" + m; 66            dd = d.Day.ToString(); 67            if (dd.Length < 2) dd = "0" + dd; 68            h = d.Hour.ToString(); 69            if (h.Length < 2) h = "0" + h; 70            mm = d.Minute.ToString(); 71            if (mm.Length < 2) mm = "0" + mm; 72            ss = d.Second.ToString(); 73            if (ss.Length < 2) ss = "0" + ss; 74            s += y + m + dd + h + mm + ss; 75            s += ra.Next(100, 999).ToString(); 76            return s; 77        } 78        #endregion 79 80        取得文件后缀#region 取得文件后缀 81        /**//********************************** 82         * 函数名称:GetFileExtends 83         * 功能说明:取得文件后缀 84         * 参    数:filename:文件名称 85         * 调用示例: 86         *          GetRemoteObj o = new GetRemoteObj(); 87         *          string url = @"http://www.baidu.com/img/logo.gif"; 88         *          string s = o.GetFileExtends(url); 89         *          Response.Write(s); 90         *          o.Dispose(); 91         * ********************************/ 92        /** <summary> 93        /// 取得文件后缀 94        /// </summary> 95        /// <param name="filename">文件名称</param> 96        /// <returns></returns> 97        public string GetFileExtends(string filename) 98        { 99            string ext = null;100            if (filename.IndexOf('.') > 0)101            {102                string[] fs = filename.Split('.');103                ext = fs[fs.Length - 1];104            }105            return ext;106        }107        #endregion108109        获取远程文件源代码#region 获取远程文件源代码110        /**//**********************************111         * 函数名称:GetRemoteHtmlCode112         * 功能说明:获取远程文件源代码113         * 参    数:Url:远程url114         * 调用示例:115         *          GetRemoteObj o = new GetRemoteObj();116         *          string url = @"http://www.baidu.com/";117         *          string s = o.GetRemoteHtmlCode(url);118         *          Response.Write(s);119         *          o.Dispose();120         * ********************************/121        /** <summary>122        /// 获取远程文件源代码123        /// </summary>124        /// <param name="url">远程url</param>125        /// <returns></returns>126        public string GetRemoteHtmlCode(string Url)127        {128            string s = "";129            MSXML2.XMLHTTP _xmlhttp = new MSXML2.XMLHTTPClass();130            _xmlhttp.open("GET", Url, false, null, null);131            _xmlhttp.send("");132            if (_xmlhttp.readyState == 4)133            {134                s = System.Text.Encoding.Default.GetString((byte[])_xmlhttp.responseBody);135            }136            return s;137        }138139        #endregion140141        保存远程文件#region 保存远程文件142        /**//**********************************143         * 函数名称:RemoteSave144         * 功能说明:保存远程文件145         * 参    数:Url:远程url;Path:保存到的路径146         * 调用示例:147         *          GetRemoteObj o = new GetRemoteObj();148         *          string s = "";149         *          string url = @"http://www.baidu.com/img/logo.gif";150         *          string path =Server.MapPath("Html/");151         *          s = o.RemoteSave(url,path);152         *          Response.Write(s);153         *          o.Dispose();         154         * ******************************/155        /** <summary>156        /// 保存远程文件157        /// </summary>158        /// <param name="Url">远程url</param>159        /// <param name="Path">保存到的路径</param>160        /// <returns></returns>161        public string RemoteSave(string Url, string Path)162        {163            Random ra = new Random();164            string StringFileName = DateRndName(ra) + "." + GetFileExtends(Url);165            string StringFilePath = Path + StringFileName;166            MSXML2.XMLHTTP _xmlhttp = new MSXML2.XMLHTTPClass();167            _xmlhttp.open("GET", Url, false, null, null);168            _xmlhttp.send("");169            if (_xmlhttp.readyState == 4)170            {171                if (System.IO.File.Exists(StringFilePath))172                    System.IO.File.Delete(StringFilePath);173                System.IO.FileStream fs = new System.IO.FileStream(StringFilePath, System.IO.FileMode.CreateNew);174                System.IO.BinaryWriter w = new System.IO.BinaryWriter(fs);175                w.Write((byte[])_xmlhttp.responseBody);176                w.Close();177                fs.Close();178            }179            else180                throw new Exception(_xmlhttp.statusText);181            return StringFileName;182        }183        #endregion184185        替换网页中的换行和引号#region 替换网页中的换行和引号186        /**//**********************************187         * 函数名称:ReplaceEnter188         * 功能说明:替换网页中的换行和引号189         * 参    数:HtmlCode:html源代码190         * 调用示例:191         *          GetRemoteObj o = new GetRemoteObj();192         *          string Url = @"http://www.baidu.com/";193         *          strion HtmlCode = o.GetRemoteHtmlCode(Url);194         *          string s = o.ReplaceEnter(HtmlCode);195         *          Response.Write(s);196         *          o.Dispose();197         * ********************************/198        /** <summary>199        /// 替换网页中的换行和引号200        /// </summary>201        /// <param name="HtmlCode">HTML源代码</param>202        /// <returns></returns>203        public string ReplaceEnter(string HtmlCode)204        {205            string s = "";206            if (HtmlCode == null || HtmlCode == "")207                s = "";208            else209                s = HtmlCode.Replace("/"", "");210            s = s.Replace("/r/n", "");211            return s;212        }213214        #endregion               215216        执行正则提取出值#region 执行正则提取出值217        /**//**********************************218         * 函数名称:GetRegValue219         * 功能说明:执行正则提取出值220         * 参    数:HtmlCode:html源代码221         * 调用示例:222         *          GetRemoteObj o = new GetRemoteObj();223         *          string Url = @"http://www.baidu.com/";224         *          strion HtmlCode = o.GetRemoteHtmlCode(Url);225         *          string s = o.ReplaceEnter(HtmlCode);226         *          string Reg="<title>.+?</title>";227         *          string GetValue=o.GetRegValue(Reg,HtmlCode)228         *          Response.Write(GetValue);229         *          o.Dispose();230         * ********************************/231        /** <summary>232        /// 执行正则提取出值233        /// </summary>234        /// <param name="RegexString">正则表达式</param>235        /// <param name="RemoteStr">HtmlCode源代码</param>236        /// <returns></returns>237        public string  GetRegValue(string RegexString, string RemoteStr)238        {239            string MatchVale = "";240            Regex r = new Regex(RegexString);241            Match m = r.Match(RemoteStr);242            if (m.Success)243            {244                MatchVale = m.Value;245            }246            return MatchVale;247        }248        #endregion        249250        替换HTML源代码#region 替换HTML源代码251        /**//**********************************252         * 函数名称:RemoveHTML253         * 功能说明:替换HTML源代码254         * 参    数:HtmlCode:html源代码255         * 调用示例:256         *          GetRemoteObj o = new GetRemoteObj();257         *          string Url = @"http://www.baidu.com/";258         *          strion HtmlCode = o.GetRemoteHtmlCode(Url);259         *          string s = o.ReplaceEnter(HtmlCode);260         *          string Reg="<title>.+?</title>";261         *          string GetValue=o.GetRegValue(Reg,HtmlCode)262         *          Response.Write(GetValue);263         *          o.Dispose();264         * ********************************/265        /** <summary>266        /// 替换HTML源代码267        /// </summary>268        /// <param name="HtmlCode">html源代码</param>269        /// <returns></returns>270        public string RemoveHTML(string HtmlCode)271        {272            string MatchVale = HtmlCode;          273            foreach (Match s in Regex.Matches(HtmlCode, "<.+?>"))274            {275                MatchVale = MatchVale.Replace(s.Value, "");276            }277            return MatchVale;        278        }279280        #endregion281282        匹配页面的链接#region 匹配页面的链接283        /**//**********************************284         * 函数名称:GetHref285         * 功能说明:匹配页面的链接286         * 参    数:HtmlCode:html源代码287         * 调用示例:288         *          GetRemoteObj o = new GetRemoteObj();289         *          string Url = @"http://www.baidu.com/";290         *          strion HtmlCode = o.GetRemoteHtmlCode(Url);291         *          string s = o.GetHref(HtmlCode);292         *          Response.Write(s);293         *          o.Dispose();294         * ********************************/295        /** <summary>296        /// 获取页面的链接正则297        /// </summary>298        /// <param name="HtmlCode"></param>299        /// <returns></returns>300        public string GetHref(string HtmlCode)301        {302            string MatchVale = "";303            string Reg = @"(h|H)(r|R)(e|E)(f|F) *= *('|"")?((/w|//|//|/.|:|-|_)+)('|""| *|>)?";           304            foreach(Match m in Regex.Matches(HtmlCode,Reg))305            {306                MatchVale += (m.Value).ToLower().Replace("href=", "").Trim() + "||";307            }308            return MatchVale;         309        }310        #endregion311312        匹配页面的图片地址#region 匹配页面的图片地址313        /**//**********************************314         * 函数名称:GetImgSrc315         * 功能说明:匹配页面的图片地址316         * 参    数:HtmlCode:html源代码;imgHttp:要补充的http.当比如:<img src="bb/x.gif">则要补充http://www.baidu.com/,当包含http信息时,则可以为空317         * 调用示例:318         *          GetRemoteObj o = new GetRemoteObj();319         *          string Url = @"http://www.baidu.com/";320         *          strion HtmlCode = o.GetRemoteHtmlCode(Url);321         *          string s = o.GetImgSrc(HtmlCode,"http://www.baidu.com/");322         *          Response.Write(s);323         *          o.Dispose();324         * ********************************/325        /** <summary>326        /// 匹配页面的图片地址327        /// </summary>328        /// <param name="HtmlCode"></param>329        /// <param name="imgHttp">要补充的http://路径信息</param>330        /// <returns></returns>331        public string GetImgSrc(string HtmlCode, string imgHttp)332        {333            string MatchVale = "";334            string Reg = @"<img.+?>";335            foreach (Match m in Regex.Matches(HtmlCode, Reg))336            {337                MatchVale += GetImg((m.Value).ToLower().Trim(), imgHttp) + "||";338            }339            return MatchVale;340        }341        /** <summary>342        /// 匹配<img src="" />中的图片路径实际链接343        /// </summary>344        /// <param name="ImgString"><img src="" />字符串</param>345        /// <returns></returns>346        public string GetImg(string ImgString, string imgHttp)347        {348            string MatchVale = "";349            string Reg = @"src=.+/.(bmp|jpg|gif|png|)";350            foreach (Match m in Regex.Matches(ImgString.ToLower(), Reg))351            {352                MatchVale += (m.Value).ToLower().Trim().Replace("src=","");353            }354            return (imgHttp+MatchVale);355        }356357        #endregion358359        替换通过正则获取字符串所带的正则首尾匹配字符串#region 替换通过正则获取字符串所带的正则首尾匹配字符串360        /**//**********************************361         * 函数名称:GetHref362         * 功能说明:匹配页面的链接363         * 参    数:HtmlCode:html源代码364         * 调用示例:365         *          GetRemoteObj o = new GetRemoteObj();366         *          string Url = @"http://www.baidu.com/";367         *          strion HtmlCode = o.GetRemoteHtmlCode(Url);368         *          string s = o.RegReplace(HtmlCode,"<title>","</title>");369         *          Response.Write(s);370         *          o.Dispose();371         * ********************************/372        /** <summary>373        /// 替换通过正则获取字符串所带的正则首尾匹配字符串374        /// </summary>375        /// <param name="RegValue">要替换的值</param>376        /// <param name="regStart">正则匹配的首字符串</param>377        /// <param name="regEnd">正则匹配的尾字符串</param>378        /// <returns></returns>379        public string RegReplace(string RegValue, string regStart,string regEnd)380        {381            string s = RegValue;382            if (RegValue != "" && RegValue != null)383            {384                if (regStart != "" && regStart != null)385                {386                    s = s.Replace(regStart, "");387                }388                if (regEnd != "" && regEnd != null)389                {390                    s = s.Replace(regEnd, "");391                }392            }393            return s;394        }395        #endregion396397398    }399}400


    最新回复(0)