将HTML转成XHTML并清除一些无用的标签和属性

介绍

　　这是一个能帮你从HTML生成有效XHTML的经典库。它还提供对标签以及属性过滤的支持。你可以指定允许哪些标签和属性可在出现在输出中，而其他的标签过滤掉。你也可以使用这个库清理Microsoft Word文档转化成HTML时生成的臃肿的HTML。你也在将HTML发布到博客网站前清理一下，否则像WordPress、b2evolution等博客引擎会拒绝的。

　它是如何工作的

　　里面有两个类：HtmlReader和HtmlWriter

　　HtmlReader拓展了著名的由Chris Clovett开发的SgmlReader。当它读取HTML时，它跳过所有有前缀的节点。其中，所有像<o:p>、<o:Document>、<st1:personname>等上百的无用标签被滤除了。这样你读取的HTML就剩下核心的HTML标签了。

　　HtmlWriter拓展了常规的XmlWriter，XmlWriter生成XML。XHTML本质上是XML格式的HTML。所有你熟悉使用的标签——比如<img>、<br>和<hr>，都不是闭合的标签——在XHTML中必需是空元素形式，像<img .. />、<br/>和<hr/>。由于XHTML是常见的XML格式，你可以方便的使用XML解析器读取XHTML文档。这使得有了应用XPath搜索的机会。

　HtmlReader

　　HtmlReader很简单，下面是完整的类：

////// This class skips all nodes which has some

/// kind of prefix. This trick does the job

/// to clean up MS Word/Outlook HTML markups.

///public class HtmlReader : Sgml.SgmlReader

{

public HtmlReader( TextReader reader ) : base( )

{

base.InputStream = reader;

base.DocType = "HTML";

}

public HtmlReader( string content ) : base( )

{

base.InputStream = new StringReader( content );

base.DocType = "HTML";

}

public override bool Read()

{

bool status = base.Read();

if( status )

{

if( base.NodeType == XmlNodeType.Element )

{

// Got a node with prefix. This must be one

// of those "" or something else.

// Skip this node entirely. We want prefix

// less nodes so that the resultant XML

// requires not namespace.

if( base.Name.IndexOf(':') > 0 )

base.Skip();

}

return status;

}

　HtmlWriter

　　这个类是有点麻烦。下面是使用技巧：

重写WriteString方法并避免使用常规的XML编码。对HTML文件手动更改编码。
重写WriteStartElementis以避免不被允许的标签写到输出中。
重写WriteAttributesis以避免不需求的属性。

　　让我们分部分来看下整个类：

　　可配置性

　　你可以通过修改下面的部分配置HtmlWriter：

public class HtmlWriter : XmlTextWriter

{

////// If set to true, it will filter the output

/// by using tag and attribute filtering,

/// space reduce etc

///public bool FilterOutput = false;

////// If true, it will reduce consecutive with one instance

///public bool ReduceConsecutiveSpace = true;

////// Set the tag names in lower case which are allowed to go to output

///public string [] AllowedTags =

new string[] { "p", "b", "i", "u", "em", "big", "small",

"div", "img", "span", "blockquote", "code", "pre", "br", "hr",

"ul", "ol", "li", "del", "ins", "strong", "a", "font", "dd", "dt"};

////// If any tag found which is not allowed, it is replaced by this tag.

/// Specify a tag which has least impact on output

///public string ReplacementTag = "dd";

////// New lines \r\n are replaced with space

/// which saves space and makes the

/// output compact

///public bool RemoveNewlines = true;

////// Specify which attributes are allowed.

/// Any other attribute will be discarded

///public string [] AllowedAttributes = new string[]

{

"class", "href", "target", "border", "src",

"align", "width", "height", "color", "size"

};

}

　　WriteString方法

////// The reason why we are overriding

/// this method is, we do not want the output to be

/// encoded for texts inside attribute

/// and inside node elements. For example, all the

/// gets converted to &nbsp in output. But this does not

/// apply to HTML. In HTML, we need to have as it is.

//////public override void WriteString(string text)

{

// Change all non-breaking space to normal space

text = text.Replace( " ", " " );

/// When you are reading RSS feed and writing Html,

/// this line helps remove those CDATA tags

text = text.Replace("", "");

// Do some encoding of our own because

// we are going to use WriteRaw which won't

// do any of the necessary encoding

text = text.Replace( "<", "<" );

text = text.Replace( ">", ">" );

text = text.Replace( "'", "'" );

text = text.Replace( "\"", ""e;" );

if( this.FilterOutput )

{

text = text.Trim();

// We want to replace consecutive spaces

// to one space in order to save horizontal width

if( this.ReduceConsecutiveSpace )

text = text.Replace(" ", " ");

if( this.RemoveNewlines )

text = text.Replace(Environment.NewLine, " ");

base.WriteRaw( text );

}

else

{

base.WriteRaw( text );

}

　　WriteStartElement: 应用标签过滤

public override void WriteStartElement(string prefix,

string localName, string ns)

{

if( this.FilterOutput )

{

bool canWrite = false;

string tagLocalName = localName.ToLower();

foreach( string name in this.AllowedTags )

{

if( name == tagLocalName )

{

canWrite = true;

break;

}

if( !canWrite )

localName = "dd";

}

base.WriteStartElement(prefix, localName, ns);

}

　　WriteAttributes方法: 应用属性过滤

bool canWrite = false;

string attributeLocalName = reader.LocalName.ToLower();

foreach( string name in this.AllowedAttributes )

{

if( name == attributeLocalName )

{

canWrite = true;

break;

}

// If allowed, write the attribute

if( canWrite )

this.WriteStartAttribute(reader.Prefix,

attributeLocalName, reader.NamespaceURI);

while (reader.ReadAttributeValue())

{

if (reader.NodeType == XmlNodeType.EntityReference)

{

if( canWrite ) this.WriteEntityRef(reader.Name);

continue;

}

if( canWrite )this.WriteString(reader.Value);

}

if( canWrite ) this.WriteEndAttribute();

　结论

　　示例应用是一个你可以立即用来清理HTML文件的实用工具。你可以将这个类应用在像博客等需要发布一些HTML到Web服务的工具中。

　　原文地址：http://www.codeproject.com/Articles/10792/Convert-HTML-to-XHTML-and-Clean-Unnecessary-Tags-a