html代码转换成为纯文本
先解码。接着转换为纯文本,用这段代码:
public static string HtmlToText(string source)
{
string result;
//remove line breaks,tabs
result = source.Replace("\r", " ");
result = result.Replace("\n", " ");
result = result.Replace("\t", " ");
//remove the header
result = Regex.Replace(result, "(<head>).*(</head>)", string.Empty, RegexOptions.IgnoreCase);
result = Regex.Replace(result, @"<( )*script([^>])*>", "<script>", RegexOptions.IgnoreCase);
result = Regex.Replace(result, @"(<script>).*(</script>)", string.Empty, RegexOptions.IgnoreCase);
//remove all styles
result = Regex.Replace(result, @"<( )*style([^>])*>", "<style>", RegexOptions.IgnoreCase); //clearing attributes
result = Regex.Replace(result, "(<style>).*(</style>)", string.Empty, RegexOptions.IgnoreCase);
//insert tabs in spaces of <td> tags
result = Regex.Replace(result, @"<( )*td([^>])*>", " ", RegexOptions.IgnoreCase);
//insert line breaks in places of <br> and <li> tags
result = Regex.Replace(result, @"<( )*br( )*>", "\r", RegexOptions.IgnoreCase);
result = Regex.Replace(result, @"<( )*li( )*>", "\r", RegexOptions.IgnoreCase);
//insert line paragraphs in places of <tr> and <p> tags
result = Regex.Replace(result, @"<( )*tr([^>])*>", "\r\r", RegexOptions.IgnoreCase);
result = Regex.Replace(result, @"<( )*p([^>])*>", "\r\r", RegexOptions.IgnoreCase);
//remove anything thats enclosed inside < >
result = Regex.Replace(result, @"<[^>]*>", string.Empty, RegexOptions.IgnoreCase);
//replace special characters:
result = Regex.Replace(result, @"&", "&", RegexOptions.IgnoreCase);
result = Regex.Replace(result, @" ", " ", RegexOptions.IgnoreCase);
result = Regex.Replace(result, @"<", "<", RegexOptions.IgnoreCase);
result = Regex.Replace(result, @">", ">", RegexOptions.IgnoreCase);
result = Regex.Replace(result, @"&(.{2,6});", string.Empty, RegexOptions.IgnoreCase);
//remove extra line breaks and tabs
result = Regex.Replace(result, @" ( )+", " ");
result = Regex.Replace(result, "(\r)( )+(\r)", "\r\r");
result = Regex.Replace(result, @"(\r\r)+", "\r\n");
return result;
}
【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
· 如何编写易于单元测试的代码
· 10年+ .NET Coder 心语,封装的思维:从隐藏、稳定开始理解其本质意义
· .NET Core 中如何实现缓存的预热?
· 从 HTTP 原因短语缺失研究 HTTP/2 和 HTTP/3 的设计差异
· AI与.NET技术实操系列:向量存储与相似性搜索在 .NET 中的实现
· 10年+ .NET Coder 心语 ── 封装的思维:从隐藏、稳定开始理解其本质意义
· 地球OL攻略 —— 某应届生求职总结
· 提示词工程——AI应用必不可少的技术
· Open-Sora 2.0 重磅开源!
· 周边上新:园子的第一款马克杯温暖上架