Class HtmlNode

The HtmlNode class represents a single DOM element in a HTML or XML document.

Inheritance

System.Object

HtmlNode

Inherited Members

System.Object.Equals(System.Object)

System.Object.Equals(System.Object, System.Object)

System.Object.GetHashCode()

System.Object.GetType()

System.Object.MemberwiseClone()

System.Object.ToString()

System.Object.ReferenceEquals(System.Object, System.Object)

Namespace: IronWebScraper

Assembly: IronWebScraper.dll

Syntax

public class HtmlNode

Properties

Attributes

Gets the attributes of the HTML node (such ash href, class, style etc).

Declaration

public Dictionary<string, string> Attributes { get; }

Property Value

Type	Description
System.Collections.Generic.Dictionary<System.String, System.String>	The attributes as a Dictionary<string, string>

ChildNodes

An array of nodes nested within the HtmlNode.

Declaration

public HtmlNode[] ChildNodes { get; }

Property Value

Type	Description
HtmlNode[]

InnerHtml

Gets the HtmlNode's inner Html as a string. OuterHTML will not include the current tag's own html markup, only that nested inside it.

Declaration

public string InnerHtml { get; }

Property Value

Type	Description
System.String

InnerText

Gets the text content of the HtmlNode as might be shown to a user. Text will be trimmed, with all groups of whitespace turned into a single space character.

Declaration

public string InnerText { get; }

Property Value

Type	Description
System.String

InnerTextClean

Gets the text content of the HtmlNode as might be shown to a user.

Declaration

public string InnerTextClean { get; }

Property Value

Type	Description
System.String

NodeName

Name of the HtmlNode such as "div" "p" or "#text"

Declaration

public string NodeName { get; }

Property Value

Type	Description
System.String

NodeType

Type of the HtmlNode

Possible values are: "ELEMENT_NODE", "TEXT_NODE" ,"CDATA_SECTION_NODE" ,"COMMENT_NODE", "DOCUMENT_NODE","DOCUMENT_TYPE_NODE","DOCUMENT_FRAGMENT_NODE"

Declaration

public string NodeType { get; }

Property Value

Type	Description
System.String

OuterHtml

Gets the HtmlNode's outer Html as a string. OuterHTML will include the tag's own html markup.

Declaration

public string OuterHtml { get; }

Property Value

Type	Description
System.String

ParentNode

Gets the Parent (enclosing) tag for this HtmlNode.

Declaration

public HtmlNode ParentNode { get; }

Property Value

Type	Description
HtmlNode	The parent node as an HtmlNode.

TextContent

Gets the text content of the HtmlNode and all of its descendants.

Declaration

public string TextContent { get; }

Property Value

Type	Description
System.String

TextContentClean

Gets the text content of the HtmlNode, Trimmed, with all groups of whitespace turned into a single space character. TextContent will include the content of non-printable elements just as style and script nodes.

Declaration

public string TextContentClean { get; }

Property Value

Type	Description
System.String

Methods

Css(String)

Uses CSS selectors to find all child nodes matching selector. This works in the same way as $('.ClassName') in jQuery or querySelectorAll() in JavaScript.

Declaration

public HtmlNode[] Css(string selector)

Parameters

Type	Name	Description
System.String	selector

Returns

Type	Description
HtmlNode[]

CssExists(String)

Uses CSS selectors to find if there are any matching nodes within the Response Document. This works in the same way as $('.ClassName').length > 0 in jQuery or querySelectorAll().length >0 in JavaScript.

Declaration

public bool CssExists(string selector)

Parameters

Type	Name	Description
System.String	selector

Returns

Type	Description
System.Boolean

GetAttribute(String)

Gets a single attribute vale from the HtmlNode. Returns null if that attribute is not present.

Declaration

public string GetAttribute(string Attribute)

Parameters

Type	Name	Description
System.String	Attribute

Returns

Type	Description
System.String

GetElementById(String)

Synonym of JavaScript's getElementById function. Searches inside the current HtmlNode.

Declaration

public HtmlNode GetElementById(string id)

Parameters

Type	Name	Description
System.String	id

Returns

Type	Description
HtmlNode

GetElementsByTagName(String)

Synonym of JavaScript's getElementsByTagName function. Searches inside the current HtmlNode.

Declaration

public HtmlNode[] GetElementsByTagName(string tagName)

Parameters

Type	Name	Description
System.String	tagName

Returns

Type	Description
HtmlNode[]

HasAtribute(String)

Tests if the HtmlNode has a given attribute such as "class" or "href"

Declaration

public bool HasAtribute(string Attribute)

Parameters

Type	Name	Description
System.String	Attribute

Returns

Type	Description
System.Boolean

QuerySelector(String)

Synonym of JavaScript's querySelector function. Searches inside the current HtmlNode.

Declaration

public HtmlNode QuerySelector(string selector)

Parameters

Type	Name	Description
System.String	selector

Returns

Type	Description
HtmlNode

QuerySelectorAll(String)

Synonym of JavaScript's querySelectorAll function. Searches inside the current HtmlNode.

Declaration

public HtmlNode[] QuerySelectorAll(string selector)

Parameters

Type	Name	Description
System.String	selector

Returns

Type	Description
HtmlNode[]

XPath(String)

Queries the HtmlNode to return all descendant nodes matching an XPath expression.

Declaration

public HtmlNode[] XPath(string expression)

Parameters

Type	Name	Description
System.String	expression

Returns

Type	Description
HtmlNode[]