html

type Document ¶

type Document struct {
	Root *xhtml.Node
}

Document represents a parsed HTML document.

Root is the root node returned by the underlying HTML parser.

func ParseDocument(data []byte) (*Document, error)

type Heading ¶

type Heading struct {
	Level int
	Text  string
}

Heading represents a heading element (h1–h6).

func ExtractHeadings(doc *Document) []Heading

type Link ¶

type Link struct {
	Href string
	Text string
	Rel  string
}

Link represents a hyperlink in the document.

func ExtractLinks(doc *Document) []Link

type Meta ¶

type Meta struct {
	Name  string
	Value string
}

Meta represents a simple key/value metadata entry.

type Paragraph ¶

type Paragraph struct {
	Text string
}

Paragraph represents a paragraph of text.

func ExtractParagraphs(doc *Document) []Paragraph