htmlutil

README

htmlutil

A collection of helper methods for go.net/html. The document is available at godoc.

This work was mainly done while I was employed by Hohoyi.com and was part of the Sight app.

Documentation

Index

• Variables
• func Children(n *html.Node) (ns []*html.Node)
• func Create(tag string) *html.Node
• func DelAttr(n *html.Node, name string)
• func Drop(n *html.Node) *html.Node
• func FindAllFunc(n *html.Node, f func(*html.Node) bool) (nodes []*html.Node)
• func FindId(n *html.Node, id string) *html.Node
• func FindOne(n *html.Node, a atom.Atom) *html.Node
• func FindOneFunc(n *html.Node, f func(*html.Node) bool) *html.Node
• func FindTags(n *html.Node, f func(*html.Node), atoms ...atom.Atom)
• func GetAttr(n *html.Node, name string) string
• func GetText(n *html.Node) string
• func GetValue(n *html.Node) string
• func Lift(n *html.Node)
• func ParseClean(r io.Reader) (*html.Node, error)
• func Replace(original, repl *html.Node)
• func SetAttr(n *html.Node, name, val string)
• func Walk(n *html.Node, before, after func(*html.Node))
• type AtomSet
  • func NewAtomSet(atoms []atom.Atom) AtomSet
  • func NewAtomSetFromString(s string) AtomSet
  • func (s AtomSet) Has(a atom.Atom) bool
  • func (s AtomSet) HasName(name []byte) bool

Variables

var (
	Codes      = NewAtomSetFromString("style script link")
	Blocks     = NewAtomSetFromString("address article aside audio blockquote canvas dd div dl fieldset figcaption figure figcaption footer form h1 h2 h3 h4 h5 h6 header hgroup hr noscript ol output p pre section table tfoot ul video")
	Containers = NewAtomSetFromString("article aside div footer header hgroup section")
	Headers    = NewAtomSetFromString("h1 h2 h3 h4 h5 h6 h7")
	Voids      = NewAtomSetFromString("area base br col embed hr img input keygen link meta param source track wbr")
)

var BodyContext *html.Node

BodyContext can be used as the context when parsing fragments.

Functions

func Children

func Children(n *html.Node) (ns []*html.Node)

func Create

func Create(tag string) *html.Node

func DelAttr

func DelAttr(n *html.Node, name string)

func Drop

func Drop(n *html.Node) *html.Node

func FindAllFunc

func FindAllFunc(n *html.Node, f func(*html.Node) bool) (nodes []*html.Node)

func FindId

func FindId(n *html.Node, id string) *html.Node

func FindOne

func FindOne(n *html.Node, a atom.Atom) *html.Node

func FindOneFunc

func FindOneFunc(n *html.Node, f func(*html.Node) bool) *html.Node

func FindTags

func FindTags(n *html.Node, f func(*html.Node), atoms ...atom.Atom)

func GetAttr

func GetAttr(n *html.Node, name string) string

func GetText

func GetText(n *html.Node) string

func GetValue

func GetValue(n *html.Node) string

func Lift

func Lift(n *html.Node)

func ParseClean

func ParseClean(r io.Reader) (*html.Node, error)

Clean and parse the HTML, so that: 0. Encoding converted to UTF8 if not already. 1. Comment and DOCTYPE removed. 2. Code blocks (script, style, link) removed.

func Replace

func Replace(original, repl *html.Node)

func SetAttr

func SetAttr(n *html.Node, name, val string)

func Walk

func Walk(n *html.Node, before, after func(*html.Node))

Types

type AtomSet

type AtomSet map[atom.Atom]struct{}

func NewAtomSet

func NewAtomSet(atoms []atom.Atom) AtomSet

func NewAtomSetFromString

func NewAtomSetFromString(s string) AtomSet

func (AtomSet) Has

func (s AtomSet) Has(a atom.Atom) bool

func (AtomSet) HasName

func (s AtomSet) HasName(name []byte) bool