asp.net中将HTML转化成xml文件

于 2011-04-11 22:36:00 发布 · 95 阅读

本文介绍了一个实用的.NET程序，该程序可以将HTML文档转换为XHTML格式。通过使用SgmlReader和XmlTextWriter等类，该工具能够清理并格式化HTML源代码，使其符合XHTML规范。

publicstaticstringConvert(stringhtml)
{
if(string.IsNullOrEmpty(html.Trim()))
{
returnstring.Empty;
}
using(SgmlReaderreader=newSgmlReader())
{
reader.DocType="HTML";
reader.InputStream=newStringReader(html);
using(StringWriterstringWriter=newStringWriter())
{
using(XmlTextWriterwriter=newXmlTextWriter(stringWriter))
{
reader.WhitespaceHandling=WhitespaceHandling.None;
writer.Formatting=Formatting.Indented;
XmlDocumentdoc=newXmlDocument();
doc.Load(reader);
if(doc.DocumentElement==null)
{
returnstring.Empty;
}
else
{
doc.DocumentElement.WriteContentTo(writer);
}
writer.Close();
stringxhtml=stringWriter.ToString();
returnxhtml;
}
}
}
}