Struct Html

Source

pub struct Html {
    pub errors: Vec<Cow<'static, str>>,
    pub quirks_mode: QuirksMode,
    pub tree: Tree<Node>,
}

Expand description

An HTML tree.

Parsing does not fail hard. Instead, the quirks_mode is set and errors are added to the errors field. The tree will still be populated as best as possible.

Implements the TreeSink trait from the html5ever crate, which allows HTML to be parsed.

Fields§

§errors: Vec<Cow<'static, str>>

Parse errors.

§quirks_mode: QuirksMode

The quirks mode.

§tree: Tree<Node>

The node tree.

Implementations§

Source §

impl Html

Source

pub fn new_document() -> Self

Creates an empty HTML document.

Source

pub fn new_fragment() -> Self

Creates an empty HTML fragment.

Source

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, HtmlTreeSink};
use tendril::TendrilSink;

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

Examples found in repository ?

examples/document.rs (line 21)

7fn main() {
8    let mut input = String::new();
9    let mut stdout = io::stdout();
10    let mut stdin = io::stdin();
11
12    write!(stdout, "CSS selector: ").unwrap();
13    stdout.flush().unwrap();
14    stdin.read_line(&mut input).unwrap();
15    let selector = Selector::parse(&input).unwrap();
16
17    writeln!(stdout, "HTML document:").unwrap();
18    stdout.flush().unwrap();
19    input.clear();
20    stdin.read_to_string(&mut input).unwrap();
21    let document = Html::parse_document(&input);
22
23    println!("{:#?}", document);
24
25    for node in document.select(&selector) {
26        println!("{:?}", node.value());
27    }
28}

Source

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

Parses a string of HTML as a fragment.

Examples found in repository ?

examples/fragment.rs (line 21)

7fn main() {
8    let mut input = String::new();
9    let mut stdout = io::stdout();
10    let mut stdin = io::stdin();
11
12    write!(stdout, "CSS selector: ").unwrap();
13    stdout.flush().unwrap();
14    stdin.read_line(&mut input).unwrap();
15    let selector = Selector::parse(&input).unwrap();
16
17    writeln!(stdout, "HTML fragment:").unwrap();
18    stdout.flush().unwrap();
19    input.clear();
20    stdin.read_to_string(&mut input).unwrap();
21    let fragment = Html::parse_fragment(&input);
22
23    println!("{:#?}", fragment);
24
25    for node in fragment.select(&selector) {
26        println!("{:?}", node.value());
27    }
28}

Source

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)

7fn main() {
8    let mut input = String::new();
9    let mut stdout = io::stdout();
10    let mut stdin = io::stdin();
11
12    write!(stdout, "CSS selector: ").unwrap();
13    stdout.flush().unwrap();
14    stdin.read_line(&mut input).unwrap();
15    let selector = Selector::parse(&input).unwrap();
16
17    writeln!(stdout, "HTML document:").unwrap();
18    stdout.flush().unwrap();
19    input.clear();
20    stdin.read_to_string(&mut input).unwrap();
21    let document = Html::parse_document(&input);
22
23    println!("{:#?}", document);
24
25    for node in document.select(&selector) {
26        println!("{:?}", node.value());
27    }
28}

More examples

Hide additional examples

examples/fragment.rs (line 25)

7fn main() {
8    let mut input = String::new();
9    let mut stdout = io::stdout();
10    let mut stdin = io::stdin();
11
12    write!(stdout, "CSS selector: ").unwrap();
13    stdout.flush().unwrap();
14    stdin.read_line(&mut input).unwrap();
15    let selector = Selector::parse(&input).unwrap();
16
17    writeln!(stdout, "HTML fragment:").unwrap();
18    stdout.flush().unwrap();
19    input.clear();
20    stdin.read_to_string(&mut input).unwrap();
21    let fragment = Html::parse_fragment(&input);
22
23    println!("{:#?}", fragment);
24
25    for node in fragment.select(&selector) {
26        println!("{:?}", node.value());
27    }
28}