clean_html

Documentation

Index

• func ExtractClass(n *html.Node) string
• func ExtractIFrames(startTag string, n *html.Node, uri string) string
• func ExtractImages(startTag string, n *html.Node, uri string, imageList []models.Upload) (string, []models.Upload, string, int)
• func GenerateImagePath(href string, uri string) (string, models.Upload)
• type Config
• type HtmlCleaner
  • func (c HtmlCleaner) CleanHTML(uri string, body *html.Node) (string, []models.Entity, []models.Upload, string)

Functions

func ExtractClass

func ExtractClass(n *html.Node) string

ExtractClass - return class attribute values of a html element

func ExtractIFrames

func ExtractIFrames(startTag string, n *html.Node, uri string) string

func ExtractImages

func ExtractImages(startTag string, n *html.Node, uri string, imageList []models.Upload) (string, []models.Upload, string, int)

func GenerateImagePath

func GenerateImagePath(href string, uri string) (string, models.Upload)

Types

type Config

type Config struct {
	LineBreakers   []string
	IgnoreElements []string
	IgnoreStrings  []string
	IgnoreTitles   []string
	IgnoreClasses  []string
}

type HtmlCleaner

type HtmlCleaner struct {
	Config Config
}

func (HtmlCleaner) CleanHTML

func (c HtmlCleaner) CleanHTML(uri string, body *html.Node) (string, []models.Entity, []models.Upload, string)