Question

如何剥离此文本

<html>

<body>      

<h1>My First Heading</h1>

<p>My first paragraph.</p>
<test@test.com>
</body>
</html>

看起来像

My First Heading
My first paragraph.
<test@test.com>

使用功能

public static string StripHTML(this string htmlText)
    {
        var reg = new Regex("<(.|\n)*?>", RegexOptions.IgnoreCase);
        return reg.Replace(htmlText, "");
    }

我得到了

我的第一个标题我的第一段。

Answer 1

使用Html Agility Pack进行此类操作。它比任何正则表达式都快，并且支持LINQ。

Answer 2

static void Main(string[] args)
    {


      string modified_html =  emas(input);

        HtmlDocument doc = new HtmlDocument();

        doc.LoadHtml(modified_html);

        string test1 = doc.DocumentNode.InnerText;


        Console.WriteLine();


        var reg = new Regex("<(.|\n)*?>", RegexOptions.IgnoreCase);

        Console.WriteLine(reg.Replace(modified_html , ""));

        Console.Read();
    }


    public static string emas(string text)
    {

        string stripped = text;

        const string MatchEmailPattern =
       @"(([\w-]+\.)+[\w-]+|([a-zA-Z]{1}|[\w-]{2,}))@"
       + @"((([0-1]?[0-9]{1,2}|25[0-5]|2[0-4][0-9])\.([0-1]?[0-9]{1,2}|25[0-5]|2[0-4][0-9])\."
         + @"([0-1]?[0-9]{1,2}|25[0-5]|2[0-4][0-9])\.([0-1]?[0-9]{1,2}|25[0-5]|2[0-4][0-9])){1}|"
       + @"([a-zA-Z]+[\w-]+\.)+[a-zA-Z]{2,4})";
        Regex rx = new Regex(MatchEmailPattern, RegexOptions.Compiled | RegexOptions.IgnoreCase);
        // Find matches.
        MatchCollection matches = rx.Matches(text);
        // Report the number of matches found.
        int noOfMatches = matches.Count;
        // Report on each match.
        foreach (Match match in matches)
        {

            stripped = stripped.Replace("<"+ match.Value + ">" , match.Value);

        }


        return stripped;


    }



   static string input = " Your html goes here  ";

剥离HTML标签？

2 个答案: