搜索之路 c#从html中提取文本
直接封装成一个类的,用起来还挺方便的
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 System.Text.RegularExpressions;
/// <summary>
/// HtmlExtract 抽取html里面的文本信息
/// </summary>
public class HtmlExtract
{
#region private attributes
private string _strHtml;
#endregion
#region public mehtods
public HtmlExtract(string inStrHtml)
{ _strHtml = inStrHtml;}
public string ExtractText()
{
string result = _strHtml;
result = RemoveComment(result);
result = RemoveScript(result);
result = RemoveStyle(result);
result = RemoveTags(result);
return result.Trim();
}
#endregion
#region private methods
private string RemoveComment(string input)
{
string result = input;
//remove comment
result = Regex.Replace(result, @"<!--[^-]*-->", string.Empty, RegexOptions.IgnoreCase);
return result;
}
相关文档:
新建一个专门用来创建验证码图片的页面ValidateCode.aspx
它的后台cs文件代码如下:
PageLoad
复制代码 代码如下:
private void Page_Load(object sender, System.EventArgs e)
{
string checkCode = CreateRandomCode(4);
Session["CheckCode"] = checkCode;
CreateImage(checkCode);
}
其中CreateRand ......
一种:
<html>
<head>
<meta content="text/html; charset=utf-8" http-equiv="Content-Type" />
<title>兼容FireFox的当前时间的JS脚本</title>
</head>
<body>
<DIV id=time>当前时间
<SCRIPT>document.getElementById('time').innerHTML=new Date().toLo ......
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="Content-Type" content="text/html; char ......
第一种:
<script language="javascript" type="text/javascript">
window.location.href="login.jsp?backurl="+window.location.href;
</script>
第二种:
<script language="javascript">
alert("返回");
window.history.back ......