using System;using System.Data;using System.Configuration;using System.Web;using System.Web.Security;using System.Web.UI;using System.Web.UI.WebControls;using System.Web.UI.WebControls.WebParts;using System.Web.UI.HtmlControls;using MSXML2;using System.Text.RegularExpressions; public class Search{ public Search() { } public void Dispose() { GC.SuppressFinalize(this); } #region 日期随机函数 public string DateRndName(Random ra) { DateTime d = DateTime.Now; string s = null, y, m, dd, h, mm, ss; y = d.Year.ToString(); m = d.Month.ToString(); if (m.Length < 2) m = "0" + m; dd = d.Day.ToString(); if (dd.Length < 2) dd = "0" + dd; h = d.Hour.ToString(); if (h.Length < 2) h = "0" + h; mm = d.Minute.ToString(); if (mm.Length < 2) mm = "0" + mm; ss = d.Second.ToString(); if (ss.Length < 2) ss = "0" + ss; s += y + m + dd + h + mm + ss; s += ra.Next(100, 999).ToString(); return s; } #endregion #region 取得文件后缀 public string GetFileExtends(string filename) { string ext = null; if (filename.IndexOf('.') > 0) { string[] fs = filename.Split('.'); ext = fs[fs.Length - 1]; } return ext; } #endregion #region 获取远程文件源代码 public string GetRemoteHtmlCode(string Url) { string s = ""; try { MSXML2.XMLHTTP _xmlhttp = new MSXML2.XMLHTTPClass(); _xmlhttp.open("GET", Url, false, null, null); _xmlhttp.send(""); if (_xmlhttp.readyState == 4) { s = System.Text.Encoding.Default.GetString((byte[])_xmlhttp.responseBody); } } catch (Exception ex) { s = ex.Message+"指定的地址不存在或地址错误"; } return s; } #endregion #region 保存远程文件 public string RemoteSave(string Url, string Path) { Random ra = new Random(); string StringFileName = DateRndName(ra) + "." + GetFileExtends(Url); string StringFilePath = Path + StringFileName; MSXML2.XMLHTTP _xmlhttp = new MSXML2.XMLHTTPClass(); _xmlhttp.open("GET", Url, false, null, null); _xmlhttp.send(""); if (_xmlhttp.readyState == 4) { if (System.IO.File.Exists(StringFilePath)) System.IO.File.Delete(StringFilePath); System.IO.FileStream fs = new System.IO.FileStream(StringFilePath, System.IO.FileMode.CreateNew); System.IO.BinaryWriter w = new System.IO.BinaryWriter(fs); w.Write((byte[])_xmlhttp.responseBody); w.Close(); fs.Close(); } else throw new Exception(_xmlhttp.statusText); return StringFileName; } #endregion #region 替换网页中的换行和引号 public string ReplaceEnter(string HtmlCode) { string s = ""; if (HtmlCode == null || HtmlCode == "") s = ""; else s = HtmlCode.Replace("\"", ""); s = s.Replace("\r\n", ""); return s; } #endregion #region 执行正则提取出值 public string GetRegValue(string RegexString, string RemoteStr) { string MatchVale = ""; Regex r = new Regex(RegexString); Match m = r.Match(RemoteStr); if (m.Success) { MatchVale = m.Value; } return MatchVale; } #endregion #region 替换HTML源代码 public string RemoveHTML(string HtmlCode) { string MatchVale = HtmlCode; foreach (Match s in Regex.Matches(HtmlCode, "<.+?>")) { MatchVale = MatchVale.Replace(s.Value, ""); } return MatchVale; } #endregion #region 匹配页面的链接 public string GetHref(string HtmlCode) { string MatchVale = ""; string Reg = @"(h|H)(r|R)(e|E)(f|F) *= *('|"")?((\w|\\|\/|\.|:|-|_)+)('|""| *|>)?"; foreach (Match m in Regex.Matches(HtmlCode, Reg)) { MatchVale += (m.Value).ToLower().Replace("href=", "").Trim() + "||"; } return MatchVale; } #endregion #region 匹配页面的图片地址 public string GetImgSrc(string HtmlCode, string imgHttp) { string MatchVale = ""; string Reg = @"<img.+?>"; foreach (Match m in Regex.Matches(HtmlCode, Reg)) { MatchVale += GetImg((m.Value).ToLower().Trim(), imgHttp) + "||"; } return MatchVale; } public string GetImg(string ImgString, string imgHttp) { string MatchVale = ""; string Reg = @"src=.+\.(bmp|jpg|gif|png|)"; foreach (Match m in Regex.Matches(ImgString.ToLower(), Reg)) { MatchVale += (m.Value).ToLower().Trim().Replace("src=", ""); } return (imgHttp + MatchVale); } #endregion #region 替换通过正则获取字符串所带的正则首尾匹配字符串 public string RegReplace(string RegValue, string regStart, string regEnd) { string s = RegValue; if (RegValue != "" && RegValue != null) { if (regStart != "" && regStart != null) { s = s.Replace(regStart, ""); } if (regEnd != "" && regEnd != null) { s = s.Replace(regEnd, ""); } } return s; } public string SniffwebCode(string code, string wordsBegin, string wordsEnd) { string NewsTitle = ""; Regex regex1 = new Regex("" + wordsBegin + @"(?<title>[\s\S]+?)" + wordsEnd + "", RegexOptions.Compiled | RegexOptions.IgnoreCase); for (Match match1 = regex1.Match(code); match1.Success; match1 = match1.NextMatch()) { NewsTitle = match1.Groups["title"].ToString(); } return NewsTitle; } public DataTable GetCodeHref(string HtmlCode) { string regex = @"\<a.*href\s*=\s*(?:""(?<url>[^""]*)""|'(?<url>[^']*)'|(?<url>[^\>^\s]+)).*\>(?<title>[^\<^\>]*)\<[^\</a\>]*/a\>"; Regex reg1 = new Regex(regex, RegexOptions.IgnoreCase); MatchCollection ms1 = reg1.Matches(HtmlCode); DataTable table = new DataTable(); table.Columns.Add("title"); table.Columns.Add("url"); foreach (Match m1 in ms1) { DataRow row = table.NewRow(); row["title"] = m1.Groups["title"].Value.ToString(); row["url"] = m1.Groups["url"].Value.ToString(); table.Rows.Add(row); } return table; } #endregion }