Struct scraper::html::Html

impl Html

pub fn new_document() -> Self

Creates an empty HTML document.

pub fn new_fragment() -> Self

Creates an empty HTML fragment.

pub fn parse_document(document: &str) -> Self

Parses a string of HTML as a document.

This is a convenience method for the following:

use html5ever::driver::{self, ParseOpts};
use scraper::Html;
use tendril::TendrilSink;

let parser = driver::parse_document(Html::new_document(), ParseOpts::default());
let html = parser.one(document);

Examples found in repository ?

examples/document.rs (line 21)

fn main() {
    let mut input = String::new();
    let mut stdout = io::stdout();
    let mut stdin = io::stdin();

    write!(stdout, "CSS selector: ").unwrap();
    stdout.flush().unwrap();
    stdin.read_line(&mut input).unwrap();
    let selector = Selector::parse(&input).unwrap();

    writeln!(stdout, "HTML document:").unwrap();
    stdout.flush().unwrap();
    input.clear();
    stdin.read_to_string(&mut input).unwrap();
    let document = Html::parse_document(&input);

    println!("{:#?}", document);

    for node in document.select(&selector) {
        println!("{:?}", node.value());
    }
}

pub fn parse_fragment(fragment: &str) -> Self

Parses a string of HTML as a fragment.

Examples found in repository ?

examples/fragment.rs (line 21)

fn main() {
    let mut input = String::new();
    let mut stdout = io::stdout();
    let mut stdin = io::stdin();

    write!(stdout, "CSS selector: ").unwrap();
    stdout.flush().unwrap();
    stdin.read_line(&mut input).unwrap();
    let selector = Selector::parse(&input).unwrap();

    writeln!(stdout, "HTML fragment:").unwrap();
    stdout.flush().unwrap();
    input.clear();
    stdin.read_to_string(&mut input).unwrap();
    let fragment = Html::parse_fragment(&input);

    println!("{:#?}", fragment);

    for node in fragment.select(&selector) {
        println!("{:?}", node.value());
    }
}

pub fn select<'a, 'b>(&'a self, selector: &'b Selector) -> Select<'a, 'b> ⓘ

Returns an iterator over elements matching a selector.

Examples found in repository ?

examples/document.rs (line 25)

fn main() {
    let mut input = String::new();
    let mut stdout = io::stdout();
    let mut stdin = io::stdin();

    write!(stdout, "CSS selector: ").unwrap();
    stdout.flush().unwrap();
    stdin.read_line(&mut input).unwrap();
    let selector = Selector::parse(&input).unwrap();

    writeln!(stdout, "HTML document:").unwrap();
    stdout.flush().unwrap();
    input.clear();
    stdin.read_to_string(&mut input).unwrap();
    let document = Html::parse_document(&input);

    println!("{:#?}", document);

    for node in document.select(&selector) {
        println!("{:?}", node.value());
    }
}

More examples

Hide additional examples

examples/fragment.rs (line 25)

fn main() {
    let mut input = String::new();
    let mut stdout = io::stdout();
    let mut stdin = io::stdin();

    write!(stdout, "CSS selector: ").unwrap();
    stdout.flush().unwrap();
    stdin.read_line(&mut input).unwrap();
    let selector = Selector::parse(&input).unwrap();

    writeln!(stdout, "HTML fragment:").unwrap();
    stdout.flush().unwrap();
    input.clear();
    stdin.read_to_string(&mut input).unwrap();
    let fragment = Html::parse_fragment(&input);

    println!("{:#?}", fragment);

    for node in fragment.select(&selector) {
        println!("{:?}", node.value());
    }
}

pub fn root_element(&self) -> ElementRef<'_>

Returns the root <html> element.

pub fn html(&self) -> String

Serialize entire document into HTML.

Trait Implementations§

impl Clone for Html

fn clone(&self) -> Html

Returns a copy of the value. Read more

1.0.0 · source§

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source. Read more

impl Debug for Html

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter. Read more

impl PartialEq for Html

fn eq(&self, other: &Html) -> bool

This method tests for self and other values to be equal, and is used by ==.

1.0.0 · source§

fn ne(&self, other: &Rhs) -> bool

This method tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl<'a> Selectable<'a> for &'a Html

type Select<'b> = Select<'a, 'b>

Iterator over element references matching a [CSS selectorSelector

fn select(self, selector: &Selector) -> Self::Select<'_>

Applies the given selector to the collection of elements represented by self

impl Serialize for Html

fn serialize<S: Serializer>( &self, serializer: &mut S, traversal_scope: TraversalScope ) -> Result<(), Error>

Take the serializer and call its methods to serialize this type. The type will dictate which methods are called and with what parameters.

impl TreeSink for Html

Note: does not support the <template> element.

type Output = Html

The overall result of parsing. Read more

type Handle = NodeId

Handle is a reference to a DOM node. The tree builder requires that a Handle implements Clone to get another reference to the same node.

fn finish(self) -> Self

Consume this sink and return the overall result of parsing. Read more

fn parse_error(&mut self, msg: Cow<'static, str>)

Signal a parse error.

fn set_quirks_mode(&mut self, mode: QuirksMode)

Set the document’s quirks mode.

fn get_document(&mut self) -> Self::Handle

Get a handle to the Document node.

fn same_node(&self, x: &Self::Handle, y: &Self::Handle) -> bool

Do two handles refer to the same node?

fn elem_name(&self, target: &Self::Handle) -> ExpandedName<'_>

What is the name of this element? Read more

fn create_element( &mut self, name: QualName, attrs: Vec<Attribute>, _flags: ElementFlags ) -> Self::Handle

Create an element. Read more

fn create_comment(&mut self, text: StrTendril) -> Self::Handle

Create a comment node.

fn append_doctype_to_document( &mut self, name: StrTendril, public_id: StrTendril, system_id: StrTendril )

Append a DOCTYPE element to the Document node.

fn append(&mut self, parent: &Self::Handle, child: NodeOrText<Self::Handle>)

Append a node as the last child of the given node. If this would produce adjacent sibling text nodes, it should concatenate the text instead. Read more

fn append_before_sibling( &mut self, sibling: &Self::Handle, new_node: NodeOrText<Self::Handle> )

Append a node as the sibling immediately before the given node. Read more

fn remove_from_parent(&mut self, target: &Self::Handle)

Detach the given node from its parent.

fn reparent_children(&mut self, node: &Self::Handle, new_parent: &Self::Handle)

Remove all the children from node and append them to new_parent.

fn add_attrs_if_missing(&mut self, target: &Self::Handle, attrs: Vec<Attribute>)

Add each attribute to the given element, if no attribute with that name already exists. The tree builder promises this will never be called with something else than an element.

fn get_template_contents(&mut self, target: &Self::Handle) -> Self::Handle

Get a handle to a template’s template contents. The tree builder promises this will never be called with something else than a template element.

fn mark_script_already_started(&mut self, _node: &Self::Handle)

Mark a HTML <script> as “already started”.

fn create_pi(&mut self, target: StrTendril, data: StrTendril) -> Self::Handle

Create a Processing Instruction node.

fn append_based_on_parent_node( &mut self, element: &Self::Handle, prev_element: &Self::Handle, child: NodeOrText<Self::Handle> )

When the insertion point is decided by the existence of a parent node of the element, we consider both possibilities and send the element which will be used if a parent node exists, along with the element to be used if there isn’t one.