使用C#將HTML文本轉換為普通文本，去掉所有的Html標記

2019-11-14 09:24:53

字體：大中小

來源：轉載

供稿：網友

using System;using System.Collections.Generic;using System.Linq;

using System.Text;

//首先需要導入命名空間using System.Text.RegularExPRessions;namespace WindowsFormsapplication1{ public class Class1 { /// <summary> /// 將html文本轉化為文本內容方法NoHTML /// </summary> /// <param name="Htmlstring">HTML文本值</param> /// <returns></returns> public string NoHTML(string Htmlstring) { //刪除腳本 Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase); //刪除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); //替換掉 < 和 > 標記 Htmlstring.Replace("<", ""); Htmlstring.Replace(">", ""); Htmlstring.Replace("/r/n", ""); //返回去掉html標記的字符串 return Htmlstring; } }}

上一篇：ssh 常見面試題

下一篇：LeetCode | GrayCode