package html

import "git.sr.ht/~shulhan/pakakeh.go/lib/html"

Package html extends the golang.org/x/net/html by providing simplified methods to Node.

The x/net/html package currently only provide bare raw functionalities to iterate tree, there is no check for empty node, and no function to get attribute by name without looping it manually.

This package extends the parent package by adding methods to get node's attribute by name, get the first non-empty child, get the next non-empty sibling, and method to iterate the tree.

Index

Examples

Functions

func NormalizeForID 

func NormalizeForID(in string) (out string)

NormalizeForID given an input string normalize it to HTML ID. The normalization follow Mozilla specification rules,

This function,

Example

Code: 

{
	fmt.Println(NormalizeForID(""))
	fmt.Println(NormalizeForID(" id "))
	fmt.Println(NormalizeForID(" ID "))
	fmt.Println(NormalizeForID("_id.1"))
	fmt.Println(NormalizeForID("1-d"))
	fmt.Println(NormalizeForID(".123 ABC def"))
	fmt.Println(NormalizeForID("test 123"))
	fmt.Println(NormalizeForID("⌘"))
	// Output:
	// _
	// _id_
	// _id_
	// _id_1
	// _1-d
	// _123_abc_def
	// test_123
	// ___
}

Output:

_
_id_
_id_
_id_1
_1-d
_123_abc_def
test_123
___

func Sanitize 

func Sanitize(in []byte) (plain []byte)

Sanitize the content of HTML into plain text.

Example

Code: 

{
	input := `
<html>
	<title>Test</title>
	<head>
	</head>
	<body>
		This
		<p> is </p>
		a
		<a href="/">link</a>.
		An another
		<a href="/">link</a>.
	</body>
</html>
`

	out := Sanitize([]byte(input))
	fmt.Printf("%s", out)

	// Output:
	// This is a link. An another link.
}

Output:

This is a link. An another link.

Types

type Node 

type Node struct {
	*html.Node
}

Node extends the html.Node.

func NewNode 

func NewNode(el *html.Node) *Node

NewNode create new node by embedding html.Node "el".

func (*Node) GetAttrValue 

func (node *Node) GetAttrValue(key string) string

GetAttrValue get the value of node's attribute with specific key or empty if key not found.

func (*Node) GetFirstChild 

func (node *Node) GetFirstChild() *Node

GetFirstChild get the first non-empty child of node or nil if no child left.

func (*Node) GetNextSibling 

func (node *Node) GetNextSibling() *Node

GetNextSibling get the next non-empty sibling of node or nil if no more sibling left.

func (*Node) IsElement 

func (node *Node) IsElement() bool

IsElement will return true if node type is html.ElementNode.

type NodeIterator 

type NodeIterator struct {
	// contains filtered or unexported fields
}

NodeIterator simplify iterating each node from top to bottom.

func Parse 

func Parse(r io.Reader) (iter *NodeIterator, err error)

Parse returns the NodeIterator to iterate through HTML tree.

Example

Code: 

{
	rawHTML := `
<ul>
	<li>
		<b>item</b>
		<span>one</span>
	</li>
</ul>
`

	r := strings.NewReader(rawHTML)

	iter, err := Parse(r)
	if err != nil {
		log.Fatal(err)
	}

	for node := iter.Next(); node != nil; node = iter.Next() {
		if node.IsElement() {
			fmt.Printf("%s\n", node.Data)
		} else {
			fmt.Printf("\t%s\n", node.Data)
		}
	}

	// Output:
	// html
	// head
	// body
	// ul
	// li
	// b
	// 	item
	// b
	// span
	// 	one
	// span
	// li
	// ul
	// body
	// html
}

Output:

html
head
body
ul
li
b
	item
b
span
	one
span
li
ul
body
html

func (*NodeIterator) Next 

func (iter *NodeIterator) Next() *Node

Next return the first child or the next sibling of current node. If no more node in the tree, it will return nil.

func (*NodeIterator) SetNext 

func (iter *NodeIterator) SetNext(el *Node)

SetNext set the node for iteration to Node "el" only if its not nil.

Example

Code: 

{
	rawHTML := `
<ul>
	<li>
		<b>item</b>
		<span>one</span>
	</li>
</ul>
<h2>Jump here</h2>
`

	r := strings.NewReader(rawHTML)

	iter, err := Parse(r)
	if err != nil {
		log.Fatal(err)
	}

	for node := iter.Next(); node != nil; node = iter.Next() {
		if node.IsElement() {
			if node.Data == "ul" {
				// Skip iterating the "ul" element.
				iter.SetNext(node.GetNextSibling())
				continue
			}
			fmt.Printf("%s\n", node.Data)
		} else {
			fmt.Printf("\t%s\n", node.Data)
		}
	}

	// Output:
	// html
	// head
	// body
	// h2
	// 	Jump here
	// h2
	// body
	// html
}

Output:

html
head
body
h2
	Jump here
h2
body
html

func (*NodeIterator) SetNextNode 

func (iter *NodeIterator) SetNextNode(el *html.Node)

SetNextNode set the next iteration node to html.Node "el" only if its not nil.

Source Files

html.go node.go node_iterator.go

Version
v0.60.0 (latest)
Published
Feb 1, 2025
Platform
linux/amd64
Imports
5 packages
Last checked
4 minutes ago –

Tools for package owners.