HtmlParser

halldyll_parser::parser

Struct HtmlParser

pub struct HtmlParser { /* private fields */ }

Expand description

Main HTML parser

§Example

use halldyll_parser::HtmlParser;
 
let html = r#"
    <html>
    <head><title>Test</title></head>
    <body><p>Hello world</p></body>
    </html>
"#;
 
let parser = HtmlParser::new();
let result = parser.parse(html).unwrap();
 
println!("Title: {:?}", result.metadata.title);

Implementations§

impl HtmlParser

pub fn new() -> Self

Create a new parser with default configuration

pub fn with_config(config: ParserConfig) -> Self

Create a parser with custom configuration

pub fn with_base_url(url: &str) -> ParserResult<Self>

Create a parser with a base URL

pub fn set_base_url(&mut self, url: &str) -> ParserResult<()>

Set the base URL for resolving relative URLs

pub fn config(&self) -> &ParserConfig

Get the current configuration

pub fn config_mut(&mut self) -> &mut ParserConfig

Get mutable configuration

pub fn parse(&self, html: &str) -> ParserResult<ParsedContent>

Parse HTML and extract all content

pub fn parse_fragment(&self, html: &str) -> ParserResult<ParsedContent>

Parse HTML fragment (not a full document)

pub fn extract_metadata(&self, html: &str) -> ParserResult<PageMetadata>

Extract only metadata

pub fn extract_text(&self, html: &str) -> ParserResult<TextContent>

Extract only text content

pub fn extract_headings(&self, html: &str) -> ParserResult<Vec<Heading>>

Extract only headings

pub fn extract_links(&self, html: &str) -> ParserResult<Vec<Link>>

Extract only links

pub fn extract_images(&self, html: &str) -> ParserResult<Vec<Image>>

Extract only images

pub fn extract_lists(&self, html: &str) -> ParserResult<Vec<ListContent>>

Extract only lists

pub fn extract_tables(&self, html: &str) -> ParserResult<Vec<TableContent>>

Extract only tables

pub fn extract_code_blocks(&self, html: &str) -> ParserResult<Vec<CodeBlock>>

Extract only code blocks

pub fn extract_quotes(&self, html: &str) -> ParserResult<Vec<Quote>>

Extract only quotes

pub fn extract_structured_data(&self, html: &str) -> Vec<StructuredData>

Extract only structured data

pub fn resolve_url(&self, href: &str) -> Option<String>

Resolve a relative URL to absolute using the parser’s base URL

pub fn has_base_url(&self) -> bool

Check if the parser has a base URL configured

pub fn base_url(&self) -> Option<&Url>

Get the base URL if configured

Trait Implementations§

impl Clone for HtmlParser

fn clone(&self) -> HtmlParser

Returns a duplicate 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 HtmlParser

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

Formats the value using the given formatter. Read more

impl Default for HtmlParser

fn default() -> Self

Returns the “default value” for a type. Read more

Auto Trait Implementations§

impl Freeze for HtmlParser

impl RefUnwindSafe for HtmlParser

impl Send for HtmlParser

impl Sync for HtmlParser

impl Unpin 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> CloneToUninit for T
where T: Clone,

unsafe fn clone_to_uninit(&self, dest: *mut u8)

🔬This is a nightly-only experimental API. (clone_to_uninit)

Performs copy-assignment from self to dest. Read more

impl<T> From<T> for T

fn from(t: T) -> T

Returns the argument unchanged.

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> ToOwned for T
where T: Clone,

type Owned = T

The resulting type after obtaining ownership.

fn to_owned(&self) -> T

Creates owned data from borrowed data, usually by cloning. Read more

fn clone_into(&self, target: &mut T)

Uses borrowed data to replace owned data, usually by cloning. Read more

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.