Class HTMLDocument
Namespace: Aspose.Html
Assembly: Aspose.HTML.dll (25.2.0)
An HTMLDocument is the root of the HTML hierarchy and holds
the entire content. Besides providing access to the hierarchy, it also
provides some convenience methods for accessing certain sets of
information from the document.
The following properties have been deprecated in favor of the
corresponding ones for the BODY element.
In DOM Level 2, the method getElementById is inherited from the Document
interface where it was moved to.
See also the Document object Model (DOM) Level 2 HTML Specification.
[ComVisible(true)]
[DOMObject]
[DOMName("HTMLDocument")]
public class HTMLDocument : Document, INotifyPropertyChanged, IEventTarget, IDisposable, IXPathNSResolver, IDocumentTraversal, IXPathEvaluator, IDocumentEvent, IParentNode, IElementTraversal, INonElementParentNode, IGlobalEventHandlers, IDocumentCSS, IDocumentStyleInheritance
object ← DOMObject ← EventTarget ← Node ← Document ← HTMLDocument
Implements
INotifyPropertyChanged, IEventTarget, IDisposable, IXPathNSResolver, IDocumentTraversal, IXPathEvaluator, IDocumentEvent, IParentNode, IElementTraversal, INonElementParentNode, IGlobalEventHandlers, IDocumentCSS, IDocumentStyle
Inherited Members
Document.Navigate(string), Document.Navigate(Url), Document.Navigate(string, string), Document.Navigate(string, Url), Document.Navigate(Stream, string), Document.Navigate(Stream, Url), Document.Navigate(RequestMessage), Document.CreateElement(string), Document.CreateElementNS(string, string), Document.CreateDocumentFragment(), Document.CreateTextNode(string), Document.CreateComment(string), Document.CreateCDATASection(string), Document.CreateProcessingInstruction(string, string), Document.CreateAttribute(string), Document.CreateAttributeNS(string, string), Document.CreateEntityReference(string), Document.CreateDocumentType(string, string, string, string), Document.GetElementsByTagName(string), Document.GetElementsByTagNameNS(string, string), Document.GetElementById(string), Document.GetElementsByClassName(string), Document.CreateNodeIterator(Node), Document.CreateNodeIterator(Node, long), Document.CreateNodeIterator(Node, long, INodeFilter), Document.CreateTreeWalker(Node), Document.CreateTreeWalker(Node, long), Document.CreateTreeWalker(Node, long, INodeFilter), Document.QuerySelectorAll(string), Document.QuerySelector(string), Document.ImportNode(Node, bool), Document.CreateEvent(string), Document.Write(params string[]), Document.WriteLn(params string[]), Document.CreateExpression(string, IXPathNSResolver), Document.CreateNSResolver(Node), Document.Evaluate(string, Node, IXPathNSResolver, XPathResultType, object), Document.RenderTo(IDevice), Document.Dispose(bool), Document.OwnerDocument, Document.Context, Document.Implementation, Document.Location, Document.DocumentURI, Document.Origin, Document.BaseURI, Document.NodeName, Document.NodeType, Document.CharacterSet, Document.Charset, Document.InputEncoding, Document.ContentType, Document.ReadyState, Document.Doctype, Document.DocumentElement, Document.FirstElementChild, Document.LastElementChild, Document.PreviousElementSibling, Document.NextElementSibling, Document.ChildElementCount, Document.Children, Document.XmlStandalone, Document.XmlVersion, Document.StrictErrorChecking, Document.DefaultView, Document.StyleSheets, Document.OnReadyStateChange, Document.OnAbort, Document.OnBlur, Document.OnCancel, Document.OnCanplay, Document.OnCanPlayThrough, Document.OnChange, Document.OnClick, Document.OnCueChange, Document.OnDblClick, Document.OnDurationChange, Document.OnEmptied, Document.OnEnded, Document.OnError, Document.OnFocus, Document.OnInput, Document.OnInvalid, Document.OnKeyDown, Document.OnKeyPress, Document.OnKeyUp, Document.OnLoad, Document.OnLoadedData, Document.OnLoadedMetadata, Document.OnLoadStart, Document.OnMouseDown, Document.OnMouseEnter, Document.OnMouseLeave, Document.OnMouseMove, Document.OnMouseOut, Document.OnMouseOver, Document.OnMouseUp, Document.OnMouseWheel, Document.OnPause, Document.OnPlay, Document.OnPlaying, Document.OnProgress, Document.OnRateChange, Document.OnReset, Document.OnResize, Document.OnScroll, Document.OnSeeked, Document.OnSeeking, Document.OnSelect, Document.OnShow, Document.OnStalled, Document.OnSubmit, Document.OnSuspend, Document.OnTimeUpdate, Document.OnToggle, Document.OnVolumeChange, Document.OnWaiting, Node.ELEMENT_NODE, Node.ATTRIBUTE_NODE, Node.TEXT_NODE, Node.CDATA_SECTION_NODE, Node.ENTITY_REFERENCE_NODE, Node.ENTITY_NODE, Node.PROCESSING_INSTRUCTION_NODE, Node.COMMENT_NODE, Node.DOCUMENT_NODE, Node.DOCUMENT_TYPE_NODE, Node.DOCUMENT_FRAGMENT_NODE, Node.NOTATION_NODE, Node.HasChildNodes(), Node.Normalize(), Node.CloneNode(), Node.CloneNode(bool), Node.IsEqualNode(Node), Node.IsSameNode(Node), Node.LookupPrefix(string), Node.LookupNamespaceURI(string), Node.IsDefaultNamespace(string), Node.InsertBefore(Node, Node), Node.ReplaceChild(Node, Node), Node.RemoveChild(Node), Node.AppendChild(Node), Node.Dispose(bool), Node.ToString(), Node.NodeType, Node.LocalName, Node.NamespaceURI, Node.Prefix, Node.NodeName, Node.BaseURI, Node.OwnerDocument, Node.ParentNode, Node.ParentElement, Node.ChildNodes, Node.FirstChild, Node.LastChild, Node.PreviousSibling, Node.NextSibling, Node.NodeValue, Node.TextContent, EventTarget.AddEventListener(string, DOMEventHandler, bool), EventTarget.AddEventListener(string, IEventListener), EventTarget.AddEventListener(string, IEventListener, bool), EventTarget.RemoveEventListener(string, DOMEventHandler, bool), EventTarget.RemoveEventListener(string, IEventListener), EventTarget.RemoveEventListener(string, IEventListener, bool), EventTarget.DispatchEvent(Event), EventTarget.Dispose(), EventTarget.Dispose(bool), DOMObject.GetPlatformType(), object.GetType(), object.MemberwiseClone(), object.ToString(), object.Equals(object?), object.Equals(object?, object?), object.ReferenceEquals(object?, object?), object.GetHashCode()
Constructors
HTMLDocument()
Initializes a new instance of the Aspose.Html.HTMLDocument class.
public HTMLDocument()HTMLDocument(Configuration)
Initializes a new instance of the Aspose.Html.HTMLDocument class.
public HTMLDocument(Configuration configuration)Parameters
configuration Configuration
The environment configuration.
HTMLDocument(Url)
Initializes a new instance of the Aspose.Html.HTMLDocument class. Constructor works synchronously, it waits for loading of all the external resources (images, scripts, etc.). To load document asynchronously use method Aspose.Html.Dom.Document.Navigate(Aspose.Html.Url) or its overloads. Or you can disable loading of some external resources by setting appropriate flags in Aspose.Html.Dom.IBrowsingContext.Security.
public HTMLDocument(Url url)Parameters
url Url
The document URL.
HTMLDocument(Url, Configuration)
Initializes a new instance of the Aspose.Html.HTMLDocument class. Constructor works synchronously, it waits for loading of all the external resources (images, scripts, etc.). To load document asynchronously use method Aspose.Html.Dom.Document.Navigate(Aspose.Html.Url) or its overloads. Or you can disable loading of some external resources by setting appropriate flags in Aspose.Html.Dom.IBrowsingContext.Security.
public HTMLDocument(Url url, Configuration configuration)Parameters
url Url
The document URL.
configuration Configuration
The environment configuration.
HTMLDocument(string)
Initializes a new instance of the Aspose.Html.HTMLDocument class. Constructor works synchronously, it waits for loading of all the external resources (images, scripts, etc.). To load document asynchronously use method Aspose.Html.Dom.Document.Navigate(System.String) or its overloads. Or you can disable loading of some external resources by setting appropriate flags in Aspose.Html.Dom.IBrowsingContext.Security.
public HTMLDocument(string address)Parameters
address string
The document address. It will be combined with the current directory path to form an absolute URL.
HTMLDocument(string, Configuration)
Initializes a new instance of the Aspose.Html.HTMLDocument class. Constructor works synchronously, it waits for loading of all the external resources (images, scripts, etc.). To load document asynchronously use method Aspose.Html.Dom.Document.Navigate(System.String) or its overloads. Or you can disable loading of some external resources by setting appropriate flags in Aspose.Html.Dom.IBrowsingContext.Security.
public HTMLDocument(string address, Configuration configuration)Parameters
address string
The document address. It will be combined with the current directory path to form an absolute URL.
configuration Configuration
The environment configuration.
HTMLDocument(string, string)
Initializes a new instance of the Aspose.Html.HTMLDocument class. Constructor works synchronously, it waits for loading of all the external resources (images, scripts, etc.). To load document asynchronously use method Aspose.Html.Dom.Document.Navigate(System.String,System.String) or its overloads. Or you can disable loading of some external resources by setting appropriate flags in Aspose.Html.Dom.IBrowsingContext.Security.
public HTMLDocument(string content, string baseUri)Parameters
content string
The document content.
baseUri string
The base URI of the document. It will be combined with the current directory path to form an absolute URL.
Exceptions
baseUri is null.
HTMLDocument(string, string, Configuration)
Initializes a new instance of the Aspose.Html.HTMLDocument class. Constructor works synchronously, it waits for loading of all the external resources (images, scripts, etc.). To load document asynchronously use method Aspose.Html.Dom.Document.Navigate(System.String,System.String) or its overloads. Or you can disable loading of some external resources by setting appropriate flags in Aspose.Html.Dom.IBrowsingContext.Security.
public HTMLDocument(string content, string baseUri, Configuration configuration)Parameters
content string
The document content.
baseUri string
The base URI of the document. It will be combined with the current directory path to form an absolute URL.
configuration Configuration
The environment configuration.
Exceptions
baseUri is null.
HTMLDocument(string, Url)
Initializes a new instance of the Aspose.Html.HTMLDocument class. Constructor works synchronously, it waits for loading of all the external resources (images, scripts, etc.). To load document asynchronously use method Aspose.Html.Dom.Document.Navigate(System.String,Aspose.Html.Url) or its overloads. Or you can disable loading of some external resources by setting appropriate flags in Aspose.Html.Dom.IBrowsingContext.Security.
public HTMLDocument(string content, Url baseUri)Parameters
content string
The document content.
baseUri Url
The base URI of the document.
Exceptions
baseUri is null.
HTMLDocument(string, Url, Configuration)
Initializes a new instance of the Aspose.Html.HTMLDocument class. Constructor works synchronously, it waits for loading of all the external resources (images, scripts, etc.). To load document asynchronously use method Aspose.Html.Dom.Document.Navigate(System.String,Aspose.Html.Url) or its overloads. Or you can disable loading of some external resources by setting appropriate flags in Aspose.Html.Dom.IBrowsingContext.Security.
public HTMLDocument(string content, Url baseUri, Configuration configuration)Parameters
content string
The document content.
baseUri Url
The base URI of the document.
configuration Configuration
The environment configuration.
Exceptions
baseUri is null.
HTMLDocument(Stream, string)
Initializes a new instance of the Aspose.Html.HTMLDocument class. Constructor works synchronously, it waits for loading of all the external resources (images, scripts, etc.). To load document asynchronously use method Aspose.Html.Dom.Document.Navigate(System.IO.Stream,System.String) or its overloads. Or you can disable loading of some external resources by setting appropriate flags in Aspose.Html.Dom.IBrowsingContext.Security. Document loading starts from the current position in the stream.
public HTMLDocument(Stream content, string baseUri)Parameters
content Stream
The document content.
baseUri string
The base URI of the document. It will be combined with the current directory path to form an absolute URL.
Exceptions
baseUri is null.
HTMLDocument(Stream, string, Configuration)
Initializes a new instance of the Aspose.Html.HTMLDocument class. Constructor works synchronously, it waits for loading of all the external resources (images, scripts, etc.). To load document asynchronously use method Aspose.Html.Dom.Document.Navigate(System.IO.Stream,System.String) or its overloads. Or you can disable loading of some external resources by setting appropriate flags in Aspose.Html.Dom.IBrowsingContext.Security. Document loading starts from the current position in the stream.
public HTMLDocument(Stream content, string baseUri, Configuration configuration)Parameters
content Stream
The document content.
baseUri string
The base URI of the document. It will be combined with the current directory path to form an absolute URL.
configuration Configuration
The environment configuration.
Exceptions
baseUri is null.
HTMLDocument(Stream, Url)
Initializes a new instance of the Aspose.Html.HTMLDocument class. Constructor works synchronously, it waits for loading of all the external resources (images, scripts, etc.). To load document asynchronously use method Aspose.Html.Dom.Document.Navigate(System.IO.Stream,Aspose.Html.Url) or its overloads. Or you can disable loading of some external resources by setting appropriate flags in Aspose.Html.Dom.IBrowsingContext.Security. Document loading starts from the current position in the stream.
public HTMLDocument(Stream content, Url baseUri)Parameters
content Stream
The document content.
baseUri Url
The base URI of the document.
Exceptions
baseUri is null.
HTMLDocument(Stream, Url, Configuration)
Initializes a new instance of the Aspose.Html.HTMLDocument class. Constructor works synchronously, it waits for loading of all the external resources (images, scripts, etc.). To load document asynchronously use method Aspose.Html.Dom.Document.Navigate(System.IO.Stream,Aspose.Html.Url) or its overloads. Or you can disable loading of some external resources by setting appropriate flags in Aspose.Html.Dom.IBrowsingContext.Security. Document loading starts from the current position in the stream.
public HTMLDocument(Stream content, Url baseUri, Configuration configuration)Parameters
content Stream
The document content.
baseUri Url
The base URI of the document.
configuration Configuration
The environment configuration.
Exceptions
baseUri is null.
HTMLDocument(RequestMessage)
Initializes a new instance of the Aspose.Html.HTMLDocument class. Constructor works synchronously, it waits for loading of all the external resources (images, scripts, etc.). To load document asynchronously use method Aspose.Html.Dom.Document.Navigate(Aspose.Html.Net.RequestMessage) or its overloads. Or you can disable loading of some external resources by setting appropriate flags in Aspose.Html.Dom.IBrowsingContext.Security.
public HTMLDocument(RequestMessage request)Parameters
request RequestMessage
The request message.
HTMLDocument(RequestMessage, Configuration)
Initializes a new instance of the Aspose.Html.HTMLDocument class. Constructor works synchronously, it waits for loading of all the external resources (images, scripts, etc.). To load document asynchronously use method Aspose.Html.Dom.Document.Navigate(Aspose.Html.Net.RequestMessage) or its overloads. Or you can disable loading of some external resources by setting appropriate flags in Aspose.Html.Dom.IBrowsingContext.Security.
public HTMLDocument(RequestMessage request, Configuration configuration)Parameters
request RequestMessage
The request message.
configuration Configuration
The environment configuration.
Properties
Anchors
A collection of all the anchor (A) elements in a document
with a value for the name attribute. For reasons of
backward compatibility, the returned set of anchors only contains
those anchors created with the name attribute, not those
created with the id attribute. Note that in [XHTML 1.0], the
name attribute (see section 4.10) has no semantics and
is only present for legacy user agents: the id attribute
is used instead. Users should prefer the iterator mechanisms provided
by [DOM Level 2 Traversal] instead.
[DOMName("anchors")]
public HTMLCollection Anchors { get; }Property Value
Applets
A collection of all the OBJECT elements that include
applets and APPLET (deprecated) elements in a document.
[DOMName("applets")]
public HTMLCollection Applets { get; }Property Value
Body
The element that contains the content for the document. In documents
with BODY contents, returns the BODY
element. In frameset documents, this returns the outermost
FRAMESET element.
[DOMName("body")]
public HTMLElement Body { get; set; }Property Value
Domain
The domain name of the server that served the document, or
null if the server cannot be identified by a domain
name.
[DOMNullable]
[DOMName("domain")]
public string Domain { get; }Property Value
Forms
A collection of all the forms of a document.
[DOMName("forms")]
public HTMLCollection Forms { get; }Property Value
Images
A collection of all the IMG elements in a document. The
behavior is limited to IMG elements for backwards
compatibility. As suggested by [HTML 4.01], to include images, authors may use
the OBJECT element or the IMG element.
Therefore, it is recommended not to use this attribute to find the
images in the document but getElementsByTagName with
HTML 4.01 or getElementsByTagNameNS with XHTML 1.0.
[DOMName("images")]
public HTMLCollection Images { get; }Property Value
Links
A collection of all AREA elements and anchor (
A) elements in a document with a value for the
href attribute.
[DOMName("links")]
public HTMLCollection Links { get; }Property Value
Referrer
Returns the URI [IETF RFC 2396] of the page that linked to this page. The value is an empty string if the user navigated to the page directly (not through a link, but, for example, via a bookmark).
[DOMName("referrer")]
public string Referrer { get; }Property Value
Title
The title of a document as specified by the TITLE element
in the head of the document.
[DOMName("title")]
public string Title { get; set; }Property Value
Methods
GetOverrideStyle(Element, string)
This method is used to retrieve the override style declaration for a specified element and a specified pseudo-element.
public ICSSStyleDeclaration GetOverrideStyle(Element elt, string pseudoElt)Parameters
elt Element
The element whose style is to be modified. This parameter cannot be null.
pseudoElt string
The pseudo-element or null if none.
Returns
The override style declaration
RenderTo(IDevice)
This method is used to print the contents of the current document to the specified device.
public override void RenderTo(IDevice device)Parameters
device IDevice
The user device.
Save(Url)
Saves the document to local file specified by url. All resources used in this document will be saved in
to adjacent folder, whose name will be constructed as: output_file_name + “_files”.
public void Save(Url url)Parameters
url Url
Local URL to output file.
Exceptions
Raised if the specified url is not a valid local file URL.
Save(ResourceHandler)
Saves the document content and resources using the Aspose.Html.Saving.ResourceHandlers.ResourceHandler.
public void Save(ResourceHandler resourceHandler)Parameters
resourceHandler ResourceHandler
The resource handler Aspose.Html.Saving.ResourceHandlers.ResourceHandler.
Save(string)
Saves the document to local file specified by path. All resources used in this document will be saved in
to adjacent folder, whose name will be constructed as: output_file_name + “_files”.
public void Save(string path)Parameters
path string
Local path to output file.
Exceptions
Raised if the specified path is not a valid local file path.
Save(string, HTMLSaveFormat)
Saves the document to local file specified by path. All resources used in this document will be saved in
to adjacent folder, whose name will be constructed as: output_file_name + “_files”.
public void Save(string path, HTMLSaveFormat saveFormat)Parameters
path string
Local path to output file.
saveFormat HTMLSaveFormat
Format in which document is saved.
Exceptions
Raised if the specified path is not a valid local file path.
Save(Url, HTMLSaveFormat)
Saves the document to local file specified by url. All resources used in this document will be saved in
to adjacent folder, whose name will be constructed as: output_file_name + “_files”.
public void Save(Url url, HTMLSaveFormat saveFormat)Parameters
url Url
Local URL to output file.
saveFormat HTMLSaveFormat
Format in which document is saved.
Exceptions
Raised if the specified url is not a valid local file URL.
Save(ResourceHandler, HTMLSaveFormat)
Saves the document content and resources using the Aspose.Html.Saving.ResourceHandlers.ResourceHandler.
public void Save(ResourceHandler resourceHandler, HTMLSaveFormat saveFormat)Parameters
resourceHandler ResourceHandler
The resource handler Aspose.Html.Saving.ResourceHandlers.ResourceHandler.
saveFormat HTMLSaveFormat
Format in which document is saved.
Save(string, HTMLSaveOptions)
Saves the document to local file specified by path. All resources used in this document will be saved in
to adjacent folder, whose name will be constructed as: output_file_name + “_files”.
public void Save(string path, HTMLSaveOptions saveOptions)Parameters
path string
Local path to output file.
saveOptions HTMLSaveOptions
HTML save options.
Exceptions
Raised if the specified path is not a valid local file path.
Save(Url, HTMLSaveOptions)
Saves the document to local file specified by url. All resources used in this document will be saved in
to adjacent folder, whose name will be constructed as: output_file_name + “_files”.
public void Save(Url url, HTMLSaveOptions saveOptions)Parameters
url Url
Local URL to output file.
saveOptions HTMLSaveOptions
HTML save options.
Exceptions
Raised if the specified url is not a valid local file URL.
Save(ResourceHandler, HTMLSaveOptions)
Saves the document content and resources using the Aspose.Html.Saving.ResourceHandlers.ResourceHandler.
public void Save(ResourceHandler resourceHandler, HTMLSaveOptions saveOptions)Parameters
resourceHandler ResourceHandler
The resource handler Aspose.Html.Saving.ResourceHandlers.ResourceHandler.
saveOptions HTMLSaveOptions
HTML save options.
Save(string, MarkdownSaveOptions)
Saves the document to local file specified by path. All resources used in this document will be saved in
to adjacent folder, whose name will be constructed as: output_file_name + “_files”.
public void Save(string path, MarkdownSaveOptions saveOptions)Parameters
path string
Local path to output file.
saveOptions MarkdownSaveOptions
Markdown save options.
Exceptions
Raised if the specified path is not a valid local file path.
Save(Url, MarkdownSaveOptions)
Saves the document to local file specified by url. All resources used in this document will be saved in
to adjacent folder, whose name will be constructed as: output_file_name + “_files”.
public void Save(Url url, MarkdownSaveOptions saveOptions)Parameters
url Url
Local URL to output file.
saveOptions MarkdownSaveOptions
Markdown save options.
Exceptions
Raised if the specified url is not a valid local file URL.
Save(ResourceHandler, MarkdownSaveOptions)
Saves the document content and resources using the Aspose.Html.Saving.ResourceHandlers.ResourceHandler.
public void Save(ResourceHandler resourceHandler, MarkdownSaveOptions saveOptions)Parameters
resourceHandler ResourceHandler
The resource handler Aspose.Html.Saving.ResourceHandlers.ResourceHandler.
saveOptions MarkdownSaveOptions
Markdown save options.
Save(string, MHTMLSaveOptions)
Saves the document to local file specified by path. All resources used in this document will be saved in
to adjacent folder, whose name will be constructed as: output_file_name + “_files”.
public void Save(string path, MHTMLSaveOptions saveOptions)Parameters
path string
Local path to output file.
saveOptions MHTMLSaveOptions
MHTML save options.
Exceptions
Raised if the specified path is not a valid local file path.
Save(Url, MHTMLSaveOptions)
Saves the document to local file specified by url. All resources used in this document will be saved in
to adjacent folder, whose name will be constructed as: output_file_name + “_files”.
public void Save(Url url, MHTMLSaveOptions saveOptions)Parameters
url Url
Local URL to output file.
saveOptions MHTMLSaveOptions
MHTML save options.
Exceptions
Raised if the specified url is not a valid local file URL.
Save(ResourceHandler, MHTMLSaveOptions)
Saves the document content and resources using the Aspose.Html.Saving.ResourceHandlers.ResourceHandler.
public void Save(ResourceHandler resourceHandler, MHTMLSaveOptions saveOptions)Parameters
resourceHandler ResourceHandler
The resource handler Aspose.Html.Saving.ResourceHandlers.ResourceHandler.
saveOptions MHTMLSaveOptions
MHTML save options.