Html2Text
from：http://www.cnblogs.com/rookieport/articles/272825.html
private static string StripHTML(string source)
{
try
{
string result;
// Remove HTML Development formatting
result = source.Replace("\r", " "); // Replace line breaks with space because browsers inserts space
result = result.Replace("\n", " "); // Replace line breaks with space because browsers inserts space
result = result.Replace("\t", string.Empty); // Remove step-formatting
result = System.Text.RegularExpressions.Regex.Replace(result, @"( )+", " "); // Remove repeating speces becuase browsers ignore them
// Remove the header (prepare first by clearing attributes)
result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*head([^>])*>", "<head>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"(<( )*(/)( )*head( )*>)", "</head>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, "(<head>).*(</head>)", string.Empty, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
// remove all scripts (prepare first by clearing attributes)
result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*script([^>])*>", "<script>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"(<( )*(/)( )*script( )*>)", "</script>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
//result = System.Text.RegularExpressions.Regex.Replace(result, @"(<script>)([^(<script>\.</script>)])*(</script>)",string.Empty, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"(<script>).*(</script>)", string.Empty, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
// remove all styles (prepare first by clearing attributes)
result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*style([^>])*>", "<style>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"(<( )*(/)( )*style( )*>)", "</style>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, "(<style>).*(</style>)", string.Empty, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
// insert tabs in spaces of <td> tags
result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*td([^>])*>", "\t", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
// insert line breaks in places of <BR> and <LI> tags
result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*br( )*>", "\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*li( )*>", "\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
// insert line paragraphs (double line breaks) in place if <P>, <DIV> and <TR> tags
result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*div([^>])*>", "\r\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*tr([^>])*>", "\r\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"<( )*p([^>])*>", "\r\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
// Remove remaining tags like <a>, links, images, comments etc - anything thats enclosed inside < >
result = System.Text.RegularExpressions.Regex.Replace(result, @"<[^>]*>", string.Empty, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
// replace special characters:
result = System.Text.RegularExpressions.Regex.Replace(result, @" ", " ", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"•", " * ", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"‹", "<", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"›", ">", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"™", "(tm)", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"⁄", "/", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"<", "<", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @">", ">", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"©", "(c)", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"®", "(r)", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, @"&(.{2,6});", string.Empty, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
// for testng
//System.Text.RegularExpressions.Regex.Replace(result, this.txtRegex.Text,string.Empty, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
// make line breaking consistent
result = result.Replace("\n", "\r");
// Remove extra line breaks and tabs: replace over 2 breaks with 2 and over 4 tabs with 4.
// Prepare first to remove any whitespaces inbetween the escaped characters and remove redundant tabs inbetween linebreaks
result = System.Text.RegularExpressions.Regex.Replace(result, "(\r)( )+(\r)", "\r\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, "(\t)( )+(\t)", "\t\t", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, "(\t)( )+(\r)", "\t\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, "(\r)( )+(\t)", "\r\t", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, "(\r)(\t)+(\r)", "\r\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase); // Remove redundant tabs
result = System.Text.RegularExpressions.Regex.Replace(result, "(\r)(\t)+", "\r\t", System.Text.RegularExpressions.RegexOptions.IgnoreCase); // Remove multible tabs followind a linebreak with just one tab
//string breaks = "\r\r\r"; // Initial replacement target string for linebreaks
//string tabs = "\t\t\t\t\t"; // Initial replacement target string for tabs
//for (int index = 0; index < result.Length; index++)
//{
// result = result.Replace(breaks, "\r\r");
// result = result.Replace(tabs, "\t\t\t\t");
// breaks = breaks + "\r";
// tabs = tabs + "\t";
//}
result = System.Text.RegularExpressions.Regex.Replace(result, "\r{2,}", "\r", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
result = System.Text.RegularExpressions.Regex.Replace(result, "\t{2,}", "\t", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
return result;
}
catch
{
}
return source;
}
【推荐】国内首个AI IDE，深度理解中文开发场景，立即下载体验Trae
【推荐】编程新体验，更懂你的AI，立即体验豆包MarsCode编程助手
【推荐】抖音旗下AI助手豆包，你的智能百科全书，全免费不限次数
【推荐】轻量又高性能的 SSH 工具 IShell：AI 加持，快人一步
· Linux系列：如何用heaptrack跟踪.NET程序的非托管内存泄露
· 开发者必知的日志记录最佳实践
· SQL Server 2025 AI相关能力初探
· Linux系列：如何用 C#调用 C方法造成内存泄露
· AI与.NET技术实操系列（二）：开始使用ML.NET
· 无需6万激活码！GitHub神秘组织3小时极速复刻Manus，手把手教你使用OpenManus搭建本
· C#/.NET/.NET Core优秀项目和框架2025年2月简报
· Manus爆火，是硬核还是营销？
· 终于写完轮子一部分：tcp代理 了，记录一下
· 【杭电多校比赛记录】2025“钉耙编程”中国大学生算法设计春季联赛（1）