Enum Html

Source

pub enum Html {
    Comment(String),
    Doctype {
        name: String,
        attr: Option<String>,
    },
    Empty,
    Tag {
        tag: Tag,
        child: Box<Self>,
    },
    Text(String),
    Vec(Box<[Self]>),
}

Expand description

Dom tree structure to represent the parsed html.

This tree represents the whole parsed HTML. To create an Html from a string, use the Html::parse function.

§Examples

use html_filter::*;

let _html: Html = Html::parse(
    r#"<nav>
    <!-- Navigation menu -->
    <ul>
        <li href="first">First link</li>
        <li href="second">Second link</li>
        <li href="third">Third link</li>
    </ul>
</nav>"#,
)
.unwrap();

Variants§

§

Comment(String)

Comment block

§Example

§

Doctype

Document tag.

These are tags with exclamation marks

§Examples

<!doctype html>

Fields

§name: String

Name of the tag

§Examples

In the previous example, the name is doctype.

§attr: Option<String>

Attribute of the tag

§Examples

In the previous example, the attribute is html.

§

Empty

Empty html tree

Corresponds to an empty string

§

Tag

§Examples

<div id="blob">content</div>
<div attr />
</>

Fields

§tag: Tag

Opening tag

Contains the name of the tag and its attributes.

§child: Box<Self>

Child of the tag

Everything between the opening and the closing tag.

§Note

This is always empty if the tag is self-closing.

§

Text(String)

Raw text

Text outside of a tag.

§Examples

In a<strong>b, a and b are Html::Text elements

§

Vec(Box<[Self]>)

List of nodes

§Examples

In a<strong>b, the node is a vector, with Html::Text a, Html::Tag strong Html::Text b.

Implementations§

Source §

impl Html

Source

pub fn filter(self, filter: &Filter) -> Self

Filters html based on a defined filter.

See Filter to learn how to create filters.

Filters allow you to select the portions of the html code you want to keep or remove.

§Returns

The html tree obtains by keeping only the nodes that fulfil the filter.

Source

pub fn find(self, filter: &Filter) -> Self

Finds an html node based on a defined filter.

See Filter to know how to define a filter.

Filters allow you to select the portions of the html code you want to keep or remove.

§Returns

The first node that fulfils the filter.

Source

pub fn to_filtered(&self, filter: &Filter) -> Self

Filters html based on a defined filter.

Equivalent of Html::filter when data is not owned.

Source

pub fn to_found(&self, filter: &Filter) -> Self

Finds an html node based on a defined filter.

Equivalent of Html::find when data is not owned.

Source §

impl Html

Source

pub fn parse(html: &str) -> Result<Self, String>

Parses an HTML string into a Dom tree.

§Errors

This function returns an error when the input HTML’s syntax is invalid.

§Examples

use html_filter::*;

let html: &str = r#"
<!DOCTYPE html>
<html lang="en">
    <head>
        <title>Html sample</title>
    </head>
    <body>
        <p>This is an html sample.</p>
    </body>
</html>
"#;
let tree: Html = Html::parse(html).expect("Invalid HTML");
assert_eq!(format!("{tree}"), html);

Source §

impl Html

Source

pub const fn as_comment(&self) -> Option<&str>

Returns the text of the comment, if this node is a comment.

§Examples

use html_filter::*;

assert_eq!(Html::parse("<!-- some comment -->").unwrap().as_comment(), Some(" some comment "));
assert_eq!(Html::parse("<div>a</div>").unwrap().as_comment(), None);
assert_eq!(Html::parse("not <!-- at --> top-level").unwrap().as_comment(), None);

Source

pub const fn as_doctype(&self) -> Option<(&str, Option<&str>)>

Returns the text of the doctype, if this node is a doctype.

§Examples

use html_filter::*;

assert_eq!(
    Html::parse("<!doctype html>").unwrap().as_doctype(),
    Some(("doctype", Some("html")))
);
assert_eq!(Html::parse("<!xml>").unwrap().as_doctype(), Some(("xml", None)));
assert_eq!(Html::parse("<div>a</div>").unwrap().as_doctype(), None);
assert_eq!(Html::parse("<!not at> top-level").unwrap().as_doctype(), None);

Source

pub const fn as_tag(&self) -> Option<(&Tag, &Self)>

Returns the tag, if this node is a tag.

§Examples

use html_filter::*;

let div = Html::parse(r#"<div href="/">a</div>"#).unwrap();
assert_eq!(div.as_tag().unwrap().0.as_name(), "div");
assert_eq!(div.as_tag().unwrap().0.find_attr_value("href"), Some(&"/".to_owned()));

assert_eq!(Html::parse("<div>a</div>").unwrap().as_tag().unwrap().1.as_text(), Some("a"));
assert_eq!(Html::parse("<p>a</p><p>b</p>").unwrap().as_tag(), None);

Source

pub const fn as_text(&self) -> Option<&str>

Returns the text, if this node is a text.

§Examples

use html_filter::*;

assert_eq!(Html::parse("text").unwrap().as_text(), Some("text"));
assert_eq!(Html::parse("<div>a</div>").unwrap().as_text(), None);
assert_eq!(Html::parse("<div>a</div>").unwrap().as_tag().unwrap().1.as_text(), Some("a"));
assert_eq!(Html::parse("<p>a</p><p>b</p>").unwrap().as_text(), None);

Source

pub const fn as_vec(&self) -> Option<&[Self]>

Returns the vec, if this isn’t a node but a list of nodes.

§Examples

use html_filter::*;

assert_eq!(Html::parse("<div>a</div>").unwrap().as_vec(), None);
let html = Html::parse("<p>a</p>text<!-- comment-->").unwrap();
let vec = html.as_vec().unwrap();
assert_eq!(vec[0].as_tag().unwrap().0.as_name(), "p");
assert_eq!(vec[0].as_tag().unwrap().1.as_text(), Some("a"));
assert_eq!(vec[1].as_text(), Some("text"));
assert_eq!(vec[2].as_comment(), Some(" comment"));