开通博客赚积分
发布资源赚积分
分类

源码开发语言/平台
当前位置：首页 > 源码/资料 > 编辑器/阅读器 > 查看源码
CollectionSystem.cs
资源名称：DotNetTextBox.rar　[点击查看]
上传用户：lanchensha
上传日期：2022-02-27
资源大小：7530k
文件大小：11k
源码类别：

编辑器/阅读器

开发平台：

C#

CollectionSystem.cs：源码内容
  1. //------------------------------------------------------------------------------
  2. //                                  版权声明
  3. //DotNetTextBox免费版源码版权由小宝.NET及Aspxcn中华网工作室所有!
  4. //非盈利性个人网站可免费使用本控件，商业及盈利性网站请购买功能更强大的商业版本授
  5. //权或开发版，如发现任何个人或机构违反本声明，本站将对其追究法律责任！
  6. //商业授权及开发版购买地址:http://www.aspxcn.com.cn/dotnettextbox/default.htm
  7. //联系email:webmaster@aspxcn.com.cn
  8. //------------------------------------------------------------------------------
  9. using System;
  10. using System.Net;
  11. using System.Text;
  12. using System.Text.RegularExpressions;
  13. using System.Web;
  14. using System.Web.UI;
  15. using System.Web.UI.WebControls;
  17. namespace DotNetTextBox
  18. {
  19.     #region 自定义控件的页面采集功能
  20.     public partial class PageCollection : System.Web.UI.Page
  21.     {
  22.         protected System.Web.UI.WebControls.Button btnReturn;
  23.         protected System.Web.UI.WebControls.Button canceloading;
  24.         protected System.Web.UI.WebControls.TextBox txtUrl;
  25.         protected System.Web.UI.WebControls.DropDownList seltype;
  26.         protected System.Web.UI.WebControls.HiddenField tempcontent;
  28.         protected void Page_Load(object sender, EventArgs e)
  29.         {
  30.             if (!IsPostBack)
  31.             {
  32.                 btnReturn.Text = ResourceManager.GetString("insertpage");
  33.                 seltype.Items.Add(new ListItem(ResourceManager.GetString("getallcontent"), "1"));
  34.                 seltype.Items.Add(new ListItem(ResourceManager.GetString("getnoscriptcontent"), "2"));
  35.                 seltype.Items.Add(new ListItem(ResourceManager.GetString("getalltext"), "3"));
  36.                 seltype.Items.Add(new ListItem(ResourceManager.GetString("getallimg"), "4"));
  37.                 seltype.Items.Add(new ListItem(ResourceManager.GetString("getalllink"), "5"));
  38.                 canceloading.Text = ResourceManager.GetString("canceloading");
  39.                 if (Request.Cookies["languages"] != null)
  40.                 {
  41.                     ResourceManager.SiteLanguageKey = Request.Cookies["languages"].Value;
  42.                 }
  43.                 else
  44.                 {
  45.                     ResourceManager.SiteLanguageKey = HttpContext.Current.Request.ServerVariables["HTTP_ACCEPT_LANGUAGE"].ToLower().Split(',')[0];
  46.                 }
  47.             }
  48.         }
  50.         public void btnReturn_Click(object sender, System.EventArgs e)
  51.         {
  52.             string url = txtUrl.Text.Trim();
  54.             WebClient wb = new WebClient();
  55.             try
  56.             {
  57.                 byte[] pagedata = wb.DownloadData(@url);
  58.                 string result = Encoding.Default.GetString(pagedata);
  59.                 string returnvalue = "";
  60.                 switch (seltype.SelectedValue)
  61.                 {
  62.                     case "1":
  63.                         returnvalue = result;
  64.                         break;
  65.                     case "2":
  66.                         returnvalue = wipeScript(result);
  67.                         break;
  68.                     case "3":
  69.                         returnvalue = NoHTML(result);
  70.                         break;
  71.                     case "4":
  72.                         returnvalue = getImages(result);
  73.                         break;
  74.                     case "5":
  75.                         returnvalue = getLink(result);
  76.                         break;
  77.                     default:
  78.                         break;
  79.                 }
  81.                 tempcontent.Value = returnvalue;
  82.                 ClientScript.RegisterStartupScript(typeof(Page), "Key", "addeditor();", true);
  83.             }
  84.             catch
  85.             {
  86.                 ClientScript.RegisterStartupScript(typeof(Page), "Key", "alert('" + ResourceManager.GetString("getpageerror") + "')", true);
  87.                 
  88.             }
  90.         }
  92.         public static string NoHTML(string Htmlstring)
  93.         {
  94.             //删除脚本
  95.             Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>","",RegexOptions.IgnoreCase);
  96.             //Htmlstring = Regex.Replace(Htmlstring, @"<script[sS]+</script *>", "", RegexOptions.IgnoreCase);
  97.             Htmlstring = Regex.Replace(Htmlstring, @"<style[sS]+</style *>","",RegexOptions.IgnoreCase);
  98.             //删除HTML
  99.             Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "", RegexOptions.IgnoreCase);
  100.             Htmlstring = Regex.Replace(Htmlstring, @"([rn])[s]+", "", RegexOptions.IgnoreCase);
  101.             Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase);
  102.             Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "", RegexOptions.IgnoreCase);
  103.             Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", """, RegexOptions.IgnoreCase);
  104.             Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&", RegexOptions.IgnoreCase);
  105.             Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<", RegexOptions.IgnoreCase);
  106.             Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">", RegexOptions.IgnoreCase);
  107.             Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", " ", RegexOptions.IgnoreCase);
  108.             Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "xa1", RegexOptions.IgnoreCase);
  109.             Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "xa2", RegexOptions.IgnoreCase);
  110.             Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "xa3", RegexOptions.IgnoreCase);
  111.             Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "xa9", RegexOptions.IgnoreCase);
  112.             Htmlstring = Regex.Replace(Htmlstring, @"&#(d+);", "", RegexOptions.IgnoreCase);
  113.             Htmlstring.Replace("<", "");
  114.             Htmlstring.Replace(">", "");
  115.             Htmlstring.Replace("rn", "");
  116.             Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
  118.             return Htmlstring;
  119.         }
  122.         public static string wipeScript(string html)
  123.         {
  124.             System.Text.RegularExpressions.Regex regex1 = new System.Text.RegularExpressions.Regex(@"<script[sS]+</script *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
  125.             System.Text.RegularExpressions.Regex regex2 = new System.Text.RegularExpressions.Regex(@" href *= *[sS]*script *:", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
  126.             System.Text.RegularExpressions.Regex regex3 = new System.Text.RegularExpressions.Regex(@" on[sS]*=", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
  127.             System.Text.RegularExpressions.Regex regex4 = new System.Text.RegularExpressions.Regex(@"<iframe[sS]+</iframe *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
  128.             System.Text.RegularExpressions.Regex regex5 = new System.Text.RegularExpressions.Regex(@"<frameset[sS]+</frameset *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
  129.             html = regex1.Replace(html, ""); //过滤<script></script>标记
  130.             html = regex2.Replace(html, ""); //过滤href=javascript: (<A>) 属性
  131.             html = regex3.Replace(html, " _disibledevent="); //过滤其它控件的on...事件
  132.             html = regex4.Replace(html, ""); //过滤iframe
  133.             html = regex5.Replace(html, ""); //过滤frameset
  134.             return html;
  135.         }
  137.         public string getImages(string html)
  138.         {
  139.             string resultStr = "";
  140.             string temp = "";
  141.             string url = "";
  142.             string[] url2;
  143.             Match m;
  144.             Regex r = new Regex(@"<IMG[^>]+src=s*(?:'(?<src>[^']+)'|""(?<src>[^""]+)""|(?<src>[^>s]+))s*[^>]*>", RegexOptions.IgnoreCase);
  145.             for (m = r.Match(html); m.Success; m = m.NextMatch())
  146.             {
  147.                 temp=m.Groups["src"].Value.ToLower();
  148.                 if (temp.IndexOf("http")==0)
  149.                 {
  150.                     resultStr += m.Value + "<br />";
  151.                 }
  152.                 else
  153.                 {
  154.                     url2 = txtUrl.Text.Trim().Split('/');
  155.                     
  156.                     try
  157.                     {
  158.                         if (url2.Length > 3)
  159.                         {
  160.                             url = txtUrl.Text.Trim().Replace(url2[url2.Length - 1], "");
  161.                         }
  162.                         else
  163.                         {
  164.                             url = txtUrl.Text.Trim();
  165.                         }
  166.                     }
  167.                     catch
  168.                     {
  169.                         url = txtUrl.Text.Trim();
  170.                     }
  172.                     if (temp.IndexOf("/") == 0)
  173.                     {
  175.                         resultStr += m.Value.Replace(m.Groups["src"].Value,"http://"+url2[2] + m.Groups["src"].Value) + "<br/>";
  176.                     }
  177.                     else
  178.                     {
  179.                         resultStr += m.Value.Replace(m.Groups["src"].Value,url + m.Groups["src"].Value) + "<br/>";
  180.                     } 
  181.                 }
  182.             }
  183.             return resultStr;
  184.         }
  186.         public string getLink(string html)
  187.         {
  188.             string resultStr = "";
  189.             string temp = "";
  190.             string url = "";
  191.             string[] url2;
  192.             Regex re = new Regex(@"<a[^>]+href=s*(?:'(?<href>[^']+)'|""(?<href>[^""]+)""|(?<href>[^>s]+))s*[^>]*>(?<text>.*?)</a>", RegexOptions.IgnoreCase);
  194.             MatchCollection mc = re.Matches(html);
  195.             foreach (Match m in mc)
  196.             {
  197.                 temp=m.Groups["href"].Value.ToLower();
  198.                 if (temp.IndexOf("http")==0)
  199.                 {
  200.                     resultStr += m.Value + "<br/>";
  201.                 }
  202.                 else
  203.                 {
  204.                     url2 = txtUrl.Text.Trim().Split('/');
  205.                     try
  206.                     {
  207.                         if (url2.Length > 1)
  208.                         {
  209.                             url = txtUrl.Text.Trim().Replace(url2[url2.Length - 1], "");
  210.                         }
  211.                         else
  212.                         {
  213.                             url = txtUrl.Text.Trim();
  214.                         }
  215.                     }
  216.                     catch
  217.                     {
  218.                         url = txtUrl.Text.Trim();
  219.                     }
  221.                     if (temp.IndexOf("/")==0)
  222.                     {
  223.                         resultStr += m.Value.Replace(m.Groups["href"].Value,"http://" + url2[2] + m.Groups["href"].Value) + "<br/>";
  224.                     }
  225.                     else if (temp.IndexOf("mailto") == 0)
  226.                     {
  227.                         resultStr += m.Value + "<br/>";
  228.                     }
  229.                     else
  230.                     {
  231.                         resultStr += m.Value.Replace(m.Groups["href"].Value, url + m.Groups["href"].Value) + "<br/>";
  232.                     }
  233.                 }
  234.             }
  235.             
  236.             return resultStr;
  237.         }
  238.     }
  239.     #endregion
  240. }