去除html标记，以及文件的读写
今天在去字段的时候 把标记取出来了没有办法 只能去除下面引用别人的文章
http://www.cnblogs.com/zoupeiyang/archive/2009/06/22/1508039.html
/// <summary>
/// 去除HTML标记
/// </summary>
/// <param name="Htmlstring">包括HTML的源码 </param>
/// <returns>已经去除后的文字</returns>
public string NoHTML(string Htmlstring)
{
//删除脚本
Htmlstring = Htmlstring.Replace("\r\n","");
Htmlstring = Regex.Replace(Htmlstring,@"<script.*?</script>","",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"<style.*?</style>","",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"<.*?>","",RegexOptions.IgnoreCase);
//删除HTML
Htmlstring = Regex.Replace(Htmlstring,@"<(.[^>]*)>","",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"([\r\n])[\s]+","",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"-->","",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"<!--.*","",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"&(quot|#34);","\"",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"&(amp|#38);","&",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"&(lt|#60);","<",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"&(gt|#62);",">",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"&(nbsp|#160);","",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"&(iexcl|#161);","\xa1",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"&(cent|#162);","\xa2",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"&(pound|#163);","\xa3",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"&(copy|#169);","\xa9",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"&#(\d+);","",RegexOptions.IgnoreCase);
Htmlstring = Htmlstring.Replace("<","");
Htmlstring = Htmlstring.Replace(">","");
Htmlstring = Htmlstring.Replace("\r\n","");
Htmlstring=HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
return Htmlstring;
}
http://www.cnblogs.com/happyday56/archive/2009/04/25/1443526.html 这篇也不错
http://www.cnblogs.com/yjwgood/articles/756717.html 这篇如下：
使用 axWebBrowser 控件
引用 mshtml
[1)去掉HTML标记及其标记中的属性
[2)axWebBrower 打开某个页面
[3)取出HTML源代码
1)去掉HTML标记及其标记中的属性
private string getOneValue(string TempStr)
{
if(TempStr.Length >0)
{
TempStr = regularExpressionsOfHTML(TempStr);
TempStr = TempStr.Substring(0,TempStr.Length-1);
}
return TempStr;
}
public static string regularExpressionsOfHTML(string TempContent)
{
//TempContent = System.Text.RegularExpressions.Regex.Replace(TempContent,"<[^>]+>",""); //任意多个
TempContent = System.Text.RegularExpressions.Regex.Replace(TempContent,"<[^>]*>",""); //匹配一个
return TempContent;
}
2)axWebBrower 打开某个页面
string Url = "**********";
object Zero = 0;
object EmptyString = "";
axWebBrowser.Navigate(Url ,ref Zero, ref EmptyString, ref EmptyString, ref EmptyString);
3)取出HTML源代码
在axWebBrower_DocumentComplete事件中比较好
引用:using mshtml;
IHTMLDocument2 HTMLDocument =(IHTMLDocument2) axWebBrowser1.Document;
string strHtml = HTMLDocument.body.innerHTML.ToString(); //Get HTML
string[] arHtml = strHtml.Split('\n');
此时arHtml中保存了所有的HTML source．
我把我自己做的调试程序上传了，这样的文章不能算原创也不算自己的 还是写转载吧
代码可是我的啊里面有测试字符串的 还有测试文件的用到了文件的读和写。
页:
[1]