我遇到过类似的问题并找到了最佳解决方案。下面的代码非常适合我。
private string ConvertHtml_Totext(string source)
{
try
{
string result;
// Remove HTML Development formatting
// Replace line breaks with space
// because browsers inserts space
result = source.Replace("\r", " ");
// Replace line breaks with space
// because browsers inserts space
result = result.Replace("\n", " ");
// Remove step-formatting
result = result.Replace("\t", string.Empty);
// Remove repeating spaces because browsers ignore them
result = System.Text.RegularExpressions.Regex.Replace(result,
@"( )+", " ");
// 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 that's 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);
// Remove all others. More can be added, see
// http://hotwired.lycos.com/webmonkey/reference/special_characters/
result = System.Text.RegularExpressions.Regex.Replace(result,
@"&(.{2,6});", string.Empty,
System.Text.RegularExpressions.RegexOptions.IgnoreCase);
// for testing
//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 in between
// the escaped characters and remove redundant tabs in between line breaks
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);
// Remove redundant tabs
result = System.Text.RegularExpressions.Regex.Replace(result,
"(\r)(\t)+(\r)","\r\r",
System.Text.RegularExpressions.RegexOptions.IgnoreCase);
// Remove multiple tabs following a line break with just one tab
result = System.Text.RegularExpressions.Regex.Replace(result,
"(\r)(\t)+","\r\t",
System.Text.RegularExpressions.RegexOptions.IgnoreCase);
// Initial replacement target string for line breaks
string breaks = "\r\r\r";
// Initial replacement target string for tabs
string tabs = "\t\t\t\t\t";
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";
}
// That's it.
return result;
}
catch
{
MessageBox.Show("Error");
return source;
}
}
必须首先删除转义字符，例如 \n 和 \r，因为它们会导致正则表达式按预期停止工作。
此外，为了使结果字符串在文本框中正确显示，可能需要将其拆分并设置文本框的 Lines 属性，而不是分配给 Text 属性。
this.txtResult.Lines =
StripHTML(this.txtSource.Text).Split("\r".ToCharArray());
来源：https://www.codeproject.com/Articles/11902/Convert-HTML-to-Plain-Text-2