将html格式的内容转换成纯文本格式

时间:2023-02-10 22:09:24

 

1、[用正则表达式来提取html中的文本]

需要引用的命名空间是System.Text.RegularExpressions

using System.Text.RegularExpressions;

思路:

a、先将html文本中的所有空格、换行符去掉(因为html中的空格和换行是被忽略的)
b、将<head>标记中的所有内容去掉
c、将<script>标记中的所有内容去掉
d、将<style>标记中的所有内容去掉
e、将td换成空格,tr,li,br,p 等标记换成换行符
f、去掉所有以“<>”符号为头尾的标记去掉。
g、转换&,&nbps;等转义字符换成相应的符号
h、去掉多余的空格和空行

 方法如下:       

 

/// <summary>
        /// 将HTML内容转换成纯文本形式,即去除HTML格式
        /// </summary>
        /// <param name="source"></param>
        /// <returns></returns>
        public static string ConvertToText(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");

            //remove blank
            result = Regex.Replace(result, @"/s", "");

            return result;
        }

2、[取出文本中的图片地址]

public static string GetImgUrl(string HTMLStr)

        {

            string str = string.Empty;

            string sPattern = @"^<img/s+[^>]*>";

            Regex r = new Regex(@"<img/s+[^>]*/s*src/s*=/s*([']?)(?<url>/S+)'?[^>]*>",

                RegexOptions.Compiled);

            Match m = r.Match(HTMLStr.ToLower());

            if (m.Success)

                str = m.Result("${url}");

            return str;

        }