Skip to main content

HtmlParser

content_extractor_rl::html_parser

Struct HtmlParser

pub struct HtmlParser;

Implementations§

impl HtmlParser

pub fn parse(html: &str) -> Result<Html>

Parse HTML string into document

pub fn extract_text(element: ElementRef<'_>) -> String

Extract text content from element

pub fn get_element_path(element: ElementRef<'_>) -> String

Get XPath-like selector for element

pub fn clean_html(html: &str) -> Result<Html>

Clean HTML by removing script, style, comments, etc.

pub fn get_candidate_nodes(document: &Html, top_k: usize) -> Vec<ElementRef<'_>>

Get candidate article nodes from document

pub fn extract_paragraphs(element: ElementRef<'_>) -> Vec<String>

Extract paragraphs from element

pub fn get_parent(element: ElementRef<'_>) -> Option<ElementRef<'_>>

Get parent element

pub fn get_prev_sibling(element: ElementRef<'_>) -> Option<ElementRef<'_>>

Get previous sibling element

pub fn get_next_sibling(element: ElementRef<'_>) -> Option<ElementRef<'_>>

Get next sibling element

pub fn count_children(element: ElementRef<'_>) -> usize

Count child elements

pub fn get_tree_depth(document: &Html) -> usize

Get tree depth

pub fn get_node_depth(element: ElementRef<'_>) -> usize

Get node depth in tree

Auto Trait Implementations§

impl Freeze for HtmlParser

impl RefUnwindSafe for HtmlParser

impl Send for HtmlParser

impl Sync for HtmlParser

impl Unpin for HtmlParser

impl UnsafeUnpin for HtmlParser

impl UnwindSafe for HtmlParser

Blanket Implementations§

impl<T> Any for T
where T: 'static + ?Sized,

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more

impl<T> Borrow<T> for T
where T: ?Sized,

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more

impl<T> BorrowMut<T> for T
where T: ?Sized,

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more

impl<T> From<T> for T

fn from(t: T) -> T

Returns the argument unchanged.

impl<T> Instrument for T

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more

impl<T, U> Into<U> for T
where U: From<T>,

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

impl<T> IntoEither for T

fn into_either(self, into_left: bool) -> Either<Self, Self>

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

impl<T> Pointable for T

const ALIGN: usize

The alignment of pointer.

type Init = T

The type for initializers.

unsafe fn init(init: <T as Pointable>::Init) -> usize

Initializes a with the given initializer. Read more

unsafe fn deref<'a>(ptr: usize) -> &'a T

Dereferences the given pointer. Read more

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

Mutably dereferences the given pointer. Read more

unsafe fn drop(ptr: usize)

Drops the object pointed to by the given pointer. Read more

impl<T> Same for T

type Output = T

Should always be Self

impl<T, U> TryFrom<U> for T
where U: Into<T>,

type Error = Infallible

The type returned in the event of a conversion error.

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

fn vzip(self) -> V

impl<T> WithSubscriber for T

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a WithDispatch wrapper. Read more

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a WithDispatch wrapper. Read more

impl<T> ErasedDestructor for T
where T: 'static,