文本到 HTML 的转换
本文关键字：转换 HTML 文本 | 更新日期: 2023-09-27 18:31:22
我正在做的是从数据库加载一些字符串，我做得很好。我阅读了它并将其转换为 HTML ...有点..使用此代码：
private string StripHTML(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;
}
}
问题是，一些字符串包含HTML颜色，例如： <#D80000>StackOverFlow是一个很好的论坛
我想做的是将该HTML颜色转换为HTML颜色之后的文本的颜色，这意味着"StackOverFlow是一个很好的论坛成为红色或任何颜色（颜色总是X）
PS ：它在工具提示上...从数据库加载后我在做什么：
string XZ = StripHTML(XZSecond);
Invoke(new MethodInvoker(delegate { tp.SetToolTip(OMG[i], Name + "'r" + XZ.Replace("Text", "").Replace("Text", "")); }));
据我了解您的问题，您只想将代码 #D80000 例如转换为Color。获取此链接中的答案可能会为您提供答案。
using System.Windows.Media;
Color color = (Color)ColorConverter.ConvertFromString("#FFDFD991");
作为索拉林的回答
或
System.Drawing.Color col = System.Drawing.ColorTranslator.FromHtml("#FFCC66");
Color col = ColorConverter.ConvertFromString("#FFDFD991") as Color;
作为奥德的回答
您可以使用 System.Windows.Media.ColorConverter 方法来尝试将字符串转换为 Color。
参考示例帖子
将颜色作为字符串（如 #XXXXXX）转换为System.Windows.Media.Brush的最简单方法
将字符串转换为 HTML 参考帖子
http://www.blackbeltcoder.com/Articles/strings/converting-text-to-html
查看它有助于更多
http://htmlagilitypack.codeplex.com/