AngleSharp by AngleSharp

<PackageReference Include="AngleSharp" Version="1.3.1" />

 HtmlTokenizer

public sealed class HtmlTokenizer : BaseTokenizer
Performs the tokenization of the source code. Follows the tokenization algorithm at: http://www.w3.org/html/wg/drafts/html/master/syntax.html
public bool IsAcceptingCharacterData { get; set; }

Gets or sets if CDATA sections are accepted.

public bool IsNotConsumingCharacterReferences { get; set; }

Gets or sets if character references should be avoided.

public bool IsPreservingAttributeNames { get; set; }

Gets or sets if attribute names should be taken as is.

public bool IsStrictMode { get; set; }

Gets or sets if strict mode is used.

public bool IsSupportingProcessingInstructions { get; set; }

Gets or sets if XML processing instructions should be parsed into DOM nodes.

public Action<HtmlToken, TextRange> OnToken { get; set; }

Gets or sets the callback once a new token is read.

Gets or sets delegate to determine if the attribute should be emitted.

public bool SkipCDATA { get; set; }

Gets or sets if the tokenizer should skip CDATA text.

public bool SkipComments { get; set; }

Gets or sets if the tokenizer should skip comments.

public bool SkipDataText { get; set; }

Gets or sets if the tokenizer should skip data text.

public bool SkipPlaintext { get; set; }

Gets or sets if the tokenizer should skip plaintext.

public bool SkipProcessingInstructions { get; set; }

Gets or sets if the tokenizer should skip processing instructions.

public bool SkipRawText { get; set; }

Gets or sets if the tokenizer should skip raw text.

public bool SkipRCDataText { get; set; }

Gets or sets if the tokenizer should skip RCDATA text.

public bool SkipScriptText { get; set; }

Gets or sets if the tokenizer should skip script text.

public HtmlParseMode State { get; set; }

Gets or sets the current parse mode.

Fired in case of a parse error.

public HtmlTokenizer(TextSource source, IEntityProvider resolver)

See 8.2.4 Tokenization

See 8.2.4 Tokenization

public HtmlToken Get()

Gets the next available token.

Gets the next available token as a struct